{"as_of":"2026-07-19T11:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d7348569b74ef74acacb1f4b565aaea68e448a790af33cc0e8fc272712007550","coverage":[{"denominator":83,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":83,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-17T02:06:54.730272Z","state":"measured"},{"denominator":91,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":91,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":null,"state":"measured"},{"denominator":8,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":8,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T23:07:50.491677Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-02T07:46:45.723756Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2604.08456","last_updated":"2026-04-09T16:51:42Z","snapshot_observed_at":"2026-05-10T17:14:11.348131Z","submitted_at":"2026-04-09T16:51:42Z","title":"Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T17:14:11.941977Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2604.08456"},"observation_digest":"sha256:d6766f0d637403d88554ac1fbada96c41d3c3bfd572ef8dcead625ac35f13ac6","observation_id":"91920249-d5c9-4d24-8d92-382e763ebd76","resolution":{"observed_at":"2026-05-11T07:16:11.325152Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2604.15284","last_updated":"2026-04-17T07:38:26Z","snapshot_observed_at":"2026-05-10T10:53:50.331173Z","submitted_at":"2026-04-16T17:52:06Z","title":"GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T10:53:50.950739Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2604.15284"},"observation_digest":"sha256:3d7d1697f007101221b31ed56f24c55e05b0d2e6ff9dbdccf3e40947a0555503","observation_id":"1cff2833-f9ca-42c9-970a-e88ac744a268","resolution":{"observed_at":"2026-05-10T10:55:03.922850Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2605.07287","last_updated":"2026-05-21T06:22:28Z","snapshot_observed_at":"2026-05-24T23:01:12.361007Z","submitted_at":"2026-05-08T05:51:34Z","title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-11T01:14:57.486828Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2605.07287"},"observation_digest":"sha256:e07b646a73db49bc727e4ac30f1eb13346b8059535fc9b50e83b0aaa4e7f66d1","observation_id":"f9e03970-0188-4b5f-9f80-1cf586c10ba6","resolution":{"observed_at":"2026-05-11T04:35:57.951784Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2605.07287","last_updated":"2026-05-21T06:22:28Z","snapshot_observed_at":"2026-05-24T23:01:12.361007Z","submitted_at":"2026-05-08T05:51:34Z","title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-22T10:44:18.694076Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2605.07287"},"observation_digest":"sha256:4120504fec4dcf7aca623741d36ccb1eefb2dbf8033eddb37a22e270d0c62679","observation_id":"3a7e72fa-0f6e-473b-862e-a4cbc8d2de1c","resolution":{"observed_at":"2026-05-22T10:44:47.310192Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2605.11594","last_updated":"2026-05-12T06:20:59Z","snapshot_observed_at":"2026-05-15T19:34:50.214311Z","submitted_at":"2026-05-12T06:20:59Z","title":"PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-13T01:22:05.111224Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2605.11594"},"observation_digest":"sha256:c3c8387f85bd2746c08f4516b847fa794621bb7c125b6cd87dd8500d7a4f6446","observation_id":"ab7dbd1d-f83d-4d97-af6c-aa10d4151d61","resolution":{"observed_at":"2026-05-13T01:27:02.656833Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2605.22190","last_updated":"2026-05-21T08:57:21Z","snapshot_observed_at":"2026-05-24T23:01:37.584733Z","submitted_at":"2026-05-21T08:57:21Z","title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-22T06:27:21.559658Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2605.22190"},"observation_digest":"sha256:883c32cc1d7ef3882dd8d67c0ff454ff898f570231ea0febe1e689308f70f7ab","observation_id":"2449f73f-22bd-4339-8e90-a21d9bcfee81","resolution":{"observed_at":"2026-05-22T06:31:10.201291Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2605.31595","last_updated":"2026-05-29T17:57:41Z","snapshot_observed_at":"2026-06-28T23:07:49.843170Z","submitted_at":"2026-05-29T17:57:41Z","title":"Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T23:07:50.491677Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2605.31595"},"observation_digest":"sha256:ae3c99e421554176a73b2fb76ab5854d9dbe3cf4667e2b9d6f0844c114475bdc","observation_id":"bb3658ba-0d11-441c-8a4d-05292fe2997f","resolution":{"observed_at":"2026-06-28T23:12:47.208780Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"cited_work":{"arxiv_id":"2512.04021","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04021","snapshot_observed_at":"2026-07-02T07:46:45.723756Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","venue":"cs.CV","work_id":"3bb6dcb4-1989-41d0-a68c-07d88069fc54","year":2025},"citing_paper":{"arxiv_id":"2606.05102","last_updated":"2026-06-03T17:04:30Z","snapshot_observed_at":"2026-06-28T06:47:09.425332Z","submitted_at":"2026-06-03T17:04:30Z","title":"ZipSplat: Fewer Gaussians, Better Splats","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T06:47:10.385182Z"},"links":{"cited_paper":"/paper/2512.04021","citing_paper":"/paper/2606.05102"},"observation_digest":"sha256:a9890aa448ae4ea2eeba5d38f5e10d780fab1c84b2812d93e44bb0e0b2afb7c4","observation_id":"246f86a3-f2fd-42e0-98c0-60a3d03733b8","resolution":{"observed_at":"2026-07-02T07:46:45.724896Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2512.04021/citation-record","integrity":"/paper/2512.04021/integrity","json":"/paper/2512.04021/citation-record.json","paper":"/paper/2512.04021"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cross-view completion models are zero-shot correspondence estimators","venue":null,"work_id":"024d3367-3130-4a40-bbcd-54c241d8066f","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:909cee633b5eea4b5601d14cbdce7492f607d6f57e2a375407f56c46876548ef","observation_id":"44a3305a-f0ab-46a7-aa5f-372208527c44","resolution":{"observed_at":"2026-05-17T02:08:51.975229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-07-04T21:08:49.691596Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":"1607.06450","doi":null,"metadata_source":"pith","pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-07-05T05:30:43.180275Z","title":"Layer Normalization","venue":"stat.ML","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","year":2016},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:fcb14c473b6b718ac19339e9c6f39517d310f1ffcb651e9fc3352fe60ad9edaf","observation_id":"c3431690-7bf9-41b9-bf16-ec56fc638c4b","resolution":{"observed_at":"2026-05-17T02:08:51.396013Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Spatial memory: how egocentric and allocen- tric combine.Trends in cognitive sciences, 10(12):551–557","venue":null,"work_id":"071a0fd0-dba9-4d83-bdfe-0621bbe51a06","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:9ab70fc0afad6a6947043a88164ddacc0e44f24ee348cc397505e56d698e06d2","observation_id":"b31eb964-58b3-4e6c-b28b-e7c4694586e3","resolution":{"observed_at":"2026-05-17T02:08:51.970470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"pixelsplat: 3d gaussian splats from image pairs for scalable generalizable 3d reconstruction","venue":null,"work_id":"d66df34d-4167-45af-823c-466566cf85e0","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:96e6e1c563f4e8b4093013f96bfee43d47225ae14cb950cd6d4b6007b32c4a38","observation_id":"56e13757-b024-4021-a6ec-b3610d5bbbb6","resolution":{"observed_at":"2026-05-17T02:08:51.967572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images","venue":null,"work_id":"3000cd2f-99d7-42e4-af29-a5a3e4460686","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:6ac74ddcf6fe29f7ba6ebb3203ee806e145ccfc75f47358ce3e1375e38c7c13b","observation_id":"eb338efa-8e2b-4aaf-afb2-bab49c78545e","resolution":{"observed_at":"2026-05-17T02:08:51.972830Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2412.01807","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T13:36:58.496192Z","title":"Occam’s lgs: An efficient approach for language gaussian splatting","venue":null,"work_id":"ad3ed31c-7feb-4d82-b3fd-099f9732aac9","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:c56c2db3e50badd4fdf1f179f1e8245935624205992077671cff03c90eff70ed","observation_id":"052f9c08-03fb-4b02-8b1c-b4f39578705b","resolution":{"observed_at":"2026-05-17T02:08:51.315856Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cats: Cost ag- gregation transformers for visual correspondence.Advances in Neural Information Processing Systems, 34:9011–9023","venue":null,"work_id":"24bbf92c-a3c5-4221-9a18-ed97dfecc989","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:2bbda3391711854e94a60c1879ac2ab4f77419246c0845719fc8feddc3b6036e","observation_id":"3e594e1d-feb2-445f-8c9f-f6ea0116fa8b","resolution":{"observed_at":"2026-05-17T02:08:51.895381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cats++: Boosting cost aggregation with convolutions and transformers.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(6):7174–7194","venue":null,"work_id":"9297127f-1991-405e-9a15-17f21004aa34","year":2022},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:67f2077b698a2ba70a8bf161eb866963048eb8aa15a70d839590784928f9461f","observation_id":"c21df4db-9bd6-4815-a26a-aa294a2b5366","resolution":{"observed_at":"2026-05-17T02:08:51.890109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cat- seg: Cost aggregation for open-vocabulary semantic seg- mentation","venue":null,"work_id":"4f060dff-0920-4cba-b425-0a4bbfe0bee4","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:2c5c642d4d66ce8d914307dfcf3eb62ac361ba158e961e1db490ad0c8fd88936","observation_id":"9be9152a-8818-48f2-9d8b-2ad6e87ef851","resolution":{"observed_at":"2026-05-17T02:08:51.892364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scannet: Richly-annotated 3d reconstructions of indoor scenes","venue":null,"work_id":"0fde06e2-28e0-48e4-a044-0d3429170419","year":2017},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:3e68afd95c1012b8c9e146dd805298f92f78cfa18e3aec81b8e2d4fca0437f14","observation_id":"bd0380d3-0bdc-4942-b8c8-be261fe3018b","resolution":{"observed_at":"2026-05-17T02:08:51.887546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to render novel views from wide-baseline stereo pairs","venue":null,"work_id":"7a75ec57-21bc-4ba2-9a4b-b2cda93d16ae","year":2023},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:30ec129dbb33478db152ca5eec1a480fb20a4c8dc4b03b26c2a7f488dd49884c","observation_id":"f024b4b2-4754-4553-bd35-22911426e7c7","resolution":{"observed_at":"2026-05-17T02:08:51.897778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Roma: Robust dense fea- ture matching","venue":null,"work_id":"8bfa3995-aeb3-48af-98c4-acddaffa6cca","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:2d568f6dfa9af2bd87a4feaa7b0aa5138716e3f74e704bc112e0749bcc9f3cd0","observation_id":"02e1a222-c728-4513-9989-4c8502b3cf05","resolution":{"observed_at":"2026-05-17T02:08:51.900191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Prob- ing the 3d awareness of visual foundation models","venue":null,"work_id":"a607a0b6-f51b-4663-8386-56a790ed1646","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:4fb4194b73fa6b7af18e88aa839c1a8d21d536fef764a03acc3fb751b4d66ff1","observation_id":"af7718f0-c299-451a-b6eb-303758d5063f","resolution":{"observed_at":"2026-05-17T02:08:51.914658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Large spatial model: End-to-end unposed images to semantic 3d.Advances in neural information processing systems, 37:40212–40229","venue":null,"work_id":"a6592a76-0077-45cb-8415-69ea289b3a89","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:81b3d6fcab4529c27431ab06688079611a2e42796aa4dcf0a56713f8427f45ec","observation_id":"6254453f-030d-4b2a-aa0e-fa757f51c3d4","resolution":{"observed_at":"2026-05-17T02:08:51.906139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"4175d0fe-aa0f-4667-9269-2c977254afe4","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:90cc65f7a9b688c497f9ab28020c0d719e0c47c3c4f24b4f81fd136e1f418900","observation_id":"c73b0039-4857-4208-91e7-b6dd1b5beb88","resolution":{"observed_at":"2026-05-17T02:08:51.882996Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.00992","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T00:17:29.253334Z","title":"arXiv preprint arXiv:2504.00992 , year=","venue":null,"work_id":"9873fc55-9652-4e40-83eb-474c5f23f3e2","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:62bf46f054c1fa7013731f7998375f0b1f2e98bde5b9f6a3fec7a1e2a6bf67ac","observation_id":"22f6a565-20ed-44e9-8081-0fa14dd433d5","resolution":{"observed_at":"2026-05-17T02:08:51.364293Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.06264","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-30T20:35:02.587289Z","title":"D^2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes, April 2025","venue":null,"work_id":"a44ca4d3-c07d-4d64-97d7-3323bee0797b","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:e8d28b064dc22dd1628e02d6ef328ac1e8fe870551fbfa9eaa49184542f2b20b","observation_id":"6b637e54-a3e8-484b-9059-73a1db13424f","resolution":{"observed_at":"2026-05-17T02:08:51.371451Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep matching prior: Test-time optimization for dense correspondence","venue":null,"work_id":"6f4a9111-f954-444d-9340-e8262ce697ac","year":2021},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:2ec58bd24ac0a6215b20ee01759c5e1f28d00dc53310f9207ef82e1e38fc3d8b","observation_id":"7e0aa673-bed8-415e-a3b0-6ea18076e3c1","resolution":{"observed_at":"2026-05-17T02:08:51.880599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cost aggregation with 4d convolutional swin transformer for few-shot segmentation","venue":null,"work_id":"f3921264-08b4-4c44-b6dc-f510ad4053ff","year":2022},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:990d21fdb8fbdad8b6fe6a44af9437638d68d7f98579e5885a0d8942d74b93aa","observation_id":"43c6e3e5-17e6-4c12-be0b-f55de57c0f4a","resolution":{"observed_at":"2026-05-17T02:08:51.878161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Neural matching fields: Implicit representation of matching fields for visual correspondence.Advances in Neural Information Processing Systems, 35:13512–13526","venue":null,"work_id":"2400aa5c-5dcf-4f4e-b39f-746ac0a92d53","year":2022},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:05419daf8313b3c617c693684641e1b8f64a2afdcd55776d8a06766693c0317e","observation_id":"ac62c007-ec12-4cbf-bba2-59f7a8c5e2f4","resolution":{"observed_at":"2026-05-17T02:08:51.873679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2403.11120","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unifying feature and cost aggregation with transformers for semantic and visual correspondence","venue":null,"work_id":"4fe2a590-8890-4b30-a37b-d8d5ea4b2e47","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:2ea075bddda72cc81f41c82a7d8a5fee646ecd767aae894bf3d4db20ecd36113","observation_id":"2a23b26a-7fd9-4023-99b0-33a0a1a0d96e","resolution":{"observed_at":"2026-05-17T02:08:51.344210Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2410.22128","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T07:46:45.718660Z","title":"Pf3plat: Pose-free feed-forward 3d gaussian splatting","venue":null,"work_id":"b5826d37-8ba8-443a-899a-7734fc7cbab0","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:010d22330ba254aee56cacf98261a80fe3d3ee8d8bb12c98be498a06a4ba31cc","observation_id":"7e1d8d6c-8e9e-4aec-9287-7283f9252ee9","resolution":{"observed_at":"2026-05-17T02:08:51.307595Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unifying cor- respondence pose and nerf for generalized pose-free novel view synthesis","venue":null,"work_id":"bd88b316-a302-4638-a4dd-03930a13e795","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:c07aaf74c22958e348bdc37822977fa72571b4d9a89fd9ca0b1807121980e396","observation_id":"d5335d5b-b74f-41fe-8a88-5b2042ce3a1c","resolution":{"observed_at":"2026-05-17T02:08:51.871327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2507.16144","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T02:46:28.114023Z","title":"Longsplat: On- line generalizable 3d gaussian splatting from long sequence images","venue":null,"work_id":"3851bd0e-5722-4fa3-b9e8-5b7b93d4aa5a","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:583e4554eb1916f3ede8c2e2d54849c47ff9e058d4aa7cdb4cc64a5e1ca42d39","observation_id":"8e52bda5-f56c-47e8-9b6c-a24eae03e796","resolution":{"observed_at":"2026-05-17T02:08:51.378200Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"No pose at all: Self-supervised pose-free 3d gaussian splatting from sparse 21 views","venue":null,"work_id":"31a74c71-974f-4b79-8236-8d66c7fefb7b","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:a62e39d80433c70d4b5dedb46013304e5e3d1ffc075f3669ee814f26cc6f254d","observation_id":"5aba0de2-b4c8-45fa-ad3e-d7a0ab284e9a","resolution":{"observed_at":"2026-05-17T02:08:51.859682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.23716","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T09:59:45.446785Z","title":"Anysplat: Feed-forward 3d gaussian splatting from unconstrained views","venue":null,"work_id":"60813889-15bf-4c3b-b3a8-a141aab96316","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:e4ce90f84b9f605ecc45cd41c14f35566d1d54bea41361b25d20fab5a885a24e","observation_id":"61b557aa-0ab2-499e-a269-5b691f1cb53f","resolution":{"observed_at":"2026-05-17T02:08:51.356388Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Geonerf: Generalizing nerf with geometry priors","venue":null,"work_id":"18f779b9-ebfe-40bc-a09f-d1acb48a7826","year":2022},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:0ef48760335377b605c09a8a8d3c587f4e1e7357dc2ed80c070e94e0c0cdd7aa","observation_id":"baa3c3ee-d8a4-410f-849f-b07b0a0f856d","resolution":{"observed_at":"2026-05-17T02:08:51.946515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5d44b781-a671-40b2-abee-78a486963b04","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:dbf8a097c9cbea7ac2010b548660f12e0dc1bc38717931a2dd0cc1933069d6ba","observation_id":"87ae0b0b-892f-435c-8e79-9e2388e66a27","resolution":{"observed_at":"2026-05-17T02:08:51.846866Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Relaxing accurate initialization constraint for 3d gaussian splatting","venue":null,"work_id":"c420fb5f-0f17-4dd4-98b6-89373d061b2b","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:7f42333b8289b5dba21e0929e920f8262bbbb681b38a47bbfb2828b692cf52b7","observation_id":"de5e19ac-38f1-4f9e-9305-7b0b27ac90e5","resolution":{"observed_at":"2026-05-17T02:08:51.908934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3d gaussian splatting for real-time radiance field rendering.ACM Trans","venue":null,"work_id":"f02b3a8e-cb41-4f1f-ae1c-75b487ba20f9","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:d3e9f4e721c8a8c0245b26b56372aafb40355e2c383eab72288c01ba204ff9f0","observation_id":"e19ad191-7dbb-4caf-a0c7-4d662fb51b27","resolution":{"observed_at":"2026-05-17T02:08:51.869041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2509.18096","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Seg4diff: Unveiling open-vocabulary segmentation in text-to-image diffusion transformers","venue":null,"work_id":"1d9fc1c1-c3b4-45a1-8912-e8dc6c1279dd","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:3ae011a43390dd604cc530cbe153831e1b64e03cbf3c38936de3cd8b00a70f25","observation_id":"8172b036-c308-44e4-98cb-99c55d7dfce9","resolution":{"observed_at":"2026-05-17T02:08:51.299550Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-04T21:43:40.503445Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":"1412.6980","doi":null,"metadata_source":"pith","pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-07-05T02:20:36.803655Z","title":"Adam: A Method for Stochastic Optimization","venue":"cs.LG","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","year":2014},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:cebc60c92bfbddf0f1211b2421e4e64768561d4a1b2df95ff70cb7b4b063f455","observation_id":"034f2570-cec8-41d1-9ad5-03e69ba0b600","resolution":{"observed_at":"2026-05-17T02:08:51.303557Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Segment any- thing","venue":null,"work_id":"bb997e0a-87c8-44c9-959f-db5f8799350f","year":2023},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:8b4879673a007b9e6d4d43c8bda951105085a9c4195d69fea69727f4fb4ff568","observation_id":"76b8687c-80ea-4eea-b870-4a395688047d","resolution":{"observed_at":"2026-05-17T02:08:51.848886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2508.05254","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cf3: Compact and fast 3d feature fields.arXiv preprint arXiv:2508.05254","venue":null,"work_id":"7fc0b33b-5f35-4b25-a501-e571ed4526ec","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:b01cc515dd97204b9d402724d2b68d40586f8efd3053036abbebf7d6579f3b5b","observation_id":"c94c8aad-3c93-49aa-acf5-c151d02fda1c","resolution":{"observed_at":"2026-05-17T02:08:51.325339Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2fa79ca7-1487-4eef-be25-ca1e3397e88d","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:3f4e27c877e8591b390b0ce80f9b1b9edc94c092f02f6f734016b4ad4e8b7545","observation_id":"959e435e-5343-4da5-9f3f-6af7992bfd94","resolution":{"observed_at":"2026-05-17T02:08:51.902439Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ground- ing image matching in 3d with mast3r","venue":null,"work_id":"d6a816b0-1ea8-4361-89a6-0d8464e3f27b","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:bc8b8e9ffe260292963c9b79a36304448fa6ee79b09bad8d8959c29e6ad4bde0","observation_id":"b2327292-8183-4576-bf2c-516cb3d885a6","resolution":{"observed_at":"2026-05-17T02:08:51.866199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03546","last_updated":"2022-04-03T03:33:43Z","snapshot_observed_at":"2026-07-05T04:11:10.669285Z","submitted_at":"2022-01-10T18:59:10Z","title":"Language-driven Semantic Segmentation","version":2},"cited_work":{"arxiv_id":"2201.03546","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.03546","snapshot_observed_at":"2026-07-03T16:58:42.516083Z","title":"Language-driven Semantic Segmentation","venue":"cs.CV","work_id":"20f0fe18-203a-461e-b860-9b93636dd77b","year":2022},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/2201.03546","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:8dc11179ddce60cf407b0551a1799ca2942a7e73d7441cb60111347b88008df5","observation_id":"5b855589-ecfc-481c-81e4-a951d7ee05c4","resolution":{"observed_at":"2026-05-17T03:21:12.879668Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2507.07136","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Langsplatv2: High- dimensional 3d language gaussian splatting with 450+ fps","venue":null,"work_id":"fbb09bb9-f791-4116-9fd0-90016daaf779","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:5c1115772caea02424cf16b2547c531f91f6c7831459cb6a592165237d6d979b","observation_id":"6138bd08-0e78-40bf-8299-6890a28d44cc","resolution":{"observed_at":"2026-05-17T02:08:51.292291Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916","venue":null,"work_id":"ed95961f-bc02-46d4-8f4f-8c008db06739","year":2023},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:1cab5216be07b2e5e2a7551c32e20f6872f4467ee6c04588041ab6afff893ec6","observation_id":"892a3d7f-a4b5-46f2-892b-97bfb7bb0169","resolution":{"observed_at":"2026-05-17T02:08:51.861695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improved baselines with visual instruction tuning","venue":null,"work_id":"7013a6d0-f5d4-43ba-979e-524655dde7b1","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:42a493b94ad6b6466787b294fb39df49d4d850945a687aa86936bdf893792218","observation_id":"e59a33c1-f52f-4f58-8026-898c779ed363","resolution":{"observed_at":"2026-05-17T02:08:51.911707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-04T23:18:27.958871Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":"1711.05101","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-07-05T05:30:43.193164Z","title":"Decoupled Weight Decay Regularization","venue":"cs.LG","work_id":"07ef7360-d385-4033-83f7-8384a6325204","year":2017},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:77500776adbcf7c1fba9878031a574c5de38b6b4993dc85f844b9603924a41e3","observation_id":"0d2c4f76-58e3-4769-95d7-7ef69a9e343a","resolution":{"observed_at":"2026-05-17T02:08:51.329421Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Distinctive image features from scale- invariant keypoints.International journal of computer vi- sion, 60(2):91–110","venue":null,"work_id":"08c49636-2c99-4027-b1f6-76e98ce9dda9","year":2004},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:c1ee2ffbc4362561533f2b1192ed9ac6e26638b0361884520e73be121b23fb59","observation_id":"6beb13b0-055d-483c-afbc-fab1b817e2f5","resolution":{"observed_at":"2026-05-17T02:08:51.864174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ludvig: Learning-free uplift- ing of 2d visual features to gaussian splatting scenes","venue":null,"work_id":"0da79895-42a6-4f4c-9fdb-089fbf3dcfb9","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:0b2ffeda4e2ac096f02ee5ca70f7200a3e2d3b1703d243bc5c8cffb59a70bd9a","observation_id":"6acbc162-3239-4556-8fbe-ead6d823f65f","resolution":{"observed_at":"2026-05-17T02:08:51.837327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Evolsplat: Efficient volume-based gaussian splatting for urban view synthesis","venue":null,"work_id":"26d0afed-9752-4fd4-9bfc-0d0c28688e84","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:d398c1031607e58ca863011eabda65600ac7a5d3bcf2e3f7795e2c9db3ad0417","observation_id":"fb007cee-f9ae-4e37-b9a0-69bb5e6c2cde","resolution":{"observed_at":"2026-05-17T02:08:51.835131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Differentiable blocks world: Qualitative 3d decomposition by rendering primitives.Advances in Neu- ral Information Processing Systems, 36:5791–5807","venue":null,"work_id":"014afa9f-697c-46fd-bd97-d4dc2faf38b3","year":2023},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:6a0b6f370fc29e470cba985882bbfccca78e4c6f6d27cc76c2ec8649078cef78","observation_id":"9cb68348-abb9-418a-abbd-b9be38e89f2d","resolution":{"observed_at":"2026-05-17T02:08:51.839295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Polyfit: Polygonal surface reconstruction from point clouds","venue":null,"work_id":"9e728ea6-b070-4dcd-809a-37516aabeea9","year":2017},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:d117c379d395015b289c48ddcad252cdae096b85981efecefe85c10dfc27e118","observation_id":"e4e8c9c4-9ccf-4f2f-9398-d4604c0c5b27","resolution":{"observed_at":"2026-05-17T02:08:51.919849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-05-09T02:06:29.184040Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":"2304.07193","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-07-04T21:10:09.658071Z","title":"DINOv2: Learning Robust Visual Features without Supervision","venue":"cs.CV","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","year":2023},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:a4d01e8cbca3ab9a77b652e80c732a3197ac204e49a07e7bae3560ab87b54683","observation_id":"dd47e3fe-0f94-49fe-a8a2-5605eaba7de9","resolution":{"observed_at":"2026-05-17T02:08:51.385780Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Superquadrics revisited: Learning 3d shape pars- ing beyond cuboids","venue":null,"work_id":"34eee206-6a58-4bdb-ac20-25c004f551b6","year":2019},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:8cd0ecfd9c0906256187c574325c63e47f72dad27b462b5c86be6cf1f1b43b9f","observation_id":"dfd6a254-d886-4f14-8be6-26df5ca5d236","resolution":{"observed_at":"2026-05-17T02:08:51.857612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning unsupervised hierarchical part decomposition of 3d objects from a single rgb image","venue":null,"work_id":"5e9c676d-42c7-40cc-89bf-b9079d604e8b","year":2020},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:f3eb5b077c68b30b460c664422d3b0ede9d38fef2ff089d01495d4b70da1c197","observation_id":"65a2cfe2-019b-43ed-9d49-98a4ca0a19e8","resolution":{"observed_at":"2026-05-17T02:08:51.855646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-05T06:50:49.755272Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"292e4202-5927-473f-b73e-1d6883498f14","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:7f6cc48c0808895af995999d8abb7edbce5c22e44e32c841c51c416dcdb6650e","observation_id":"2f680415-875b-4b35-ab83-6b3e0579c625","resolution":{"observed_at":"2026-05-17T02:08:51.935080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unidepth: Universal monocular metric depth estimation","venue":null,"work_id":"d411ea57-8db0-4c22-8032-c4cc5daf8725","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:baa65a58e90b3e06bf8716c0df5757da7918c117f7b6a4c8d436ccb927cfd545","observation_id":"799b3164-c2ff-4b68-b9b4-025eca0f18e6","resolution":{"observed_at":"2026-05-17T02:08:51.853550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Langsplat: 3d language gaussian splatting","venue":null,"work_id":"1dd7ca15-d5e0-459f-8814-2bc492193ab3","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:8a1f8bab21ca33ac06c78754c24ba602a7d488ba77b38dc992122aa800b7d5a7","observation_id":"11a0d46b-5c7d-4dff-83de-cb6193fe4279","resolution":{"observed_at":"2026-05-17T02:08:51.922981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"99947f77-48e9-47ab-b281-21f3d1e0aae0","year":2021},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:b434e66609a5dba42b50fcd597718a5cceba6f4caabb7f85e4edc979024d1a94","observation_id":"6a5393e6-5448-4287-861e-da08051105cd","resolution":{"observed_at":"2026-05-17T02:08:51.941029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Superglue: Learning feature matching with graph neural networks","venue":null,"work_id":"099ee38e-8f93-4f1c-80f2-c41911ba1e83","year":2020},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:2413553b065a4732de2f8d9d9242a859c43b654fdade6ccaceb55de1ae37a6e4","observation_id":"bf7570f1-91e5-462a-b928-5c5c6b0ede18","resolution":{"observed_at":"2026-05-17T02:08:51.851346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Structure- from-motion revisited","venue":null,"work_id":"73cf1d0c-10ca-455b-8caf-d80ef69c4828","year":2016},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:e16b6afbeb19b1d0e76b52bfd08356168346c3f7bb0c263e5cc40c4c26a612d2","observation_id":"e2cbfe3c-2f2d-485e-98d5-62f68f80e97e","resolution":{"observed_at":"2026-05-17T02:08:51.943530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2308.07931","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T23:27:27.410966Z","title":"Distilled feature fields en- able few-shot language-guided manipulation","venue":null,"work_id":"3afaaa4a-5f3e-4b7c-a353-1683de8ebe6b","year":2023},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:56b2a36bf121c755e16db54ff936d30a98400de7fb2f85c003f529de62bcb7de","observation_id":"eee8b240-46f4-4033-bd58-e086a5b4fd4e","resolution":{"observed_at":"2026-05-17T02:08:51.335099Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.23044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T16:58:42.439349Z","title":"Spatialsplat: Efficient semantic 3d from sparse unposed images","venue":null,"work_id":"79559077-1ad8-49db-8e0f-618d503b4d2d","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:11b509505cd1f6bbe4c918068c0745d1359f3956108dffd0db6521601bb9ba0a","observation_id":"f4070a49-d693-4bba-9ee8-8243ee68bb0d","resolution":{"observed_at":"2026-05-17T02:08:51.367943Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mental rotation of three-dimensional objects.Science, 171(3972):701–703","venue":null,"work_id":"06eab69b-dbca-480e-8154-5cf9f58b3072","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:9a1cc9228b70ef27ec599b9fb1445a9ee09005b26ecf7ee54a04ccb1e6303a83","observation_id":"edb3b764-c36b-460a-a082-e6a28109d843","resolution":{"observed_at":"2026-05-17T02:08:51.926331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards open-vocabulary semantic segmentation with- out semantic labels.Advances in Neural Information Pro- cessing Systems, 37:9153–9177","venue":null,"work_id":"c33ffa65-99a1-4119-bcc6-c5a31b0f072e","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:4df7e56f71600ddb787b88b57aa63372a43eacc3ed2858363cc1fef982fcb63c","observation_id":"de18fa8c-5525-483a-8186-f7a02e1b8252","resolution":{"observed_at":"2026-05-17T02:08:51.964925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10104","last_updated":"2025-08-13T18:00:55Z","snapshot_observed_at":"2026-05-18T22:37:00.541191Z","submitted_at":"2025-08-13T18:00:55Z","title":"DINOv3","version":1},"cited_work":{"arxiv_id":"2508.10104","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.10104","snapshot_observed_at":"2026-07-04T21:00:09.151549Z","title":"DINOv3","venue":"cs.CV","work_id":"c8b07deb-8fe7-4e18-9620-f3569d3529ce","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/2508.10104","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:838868e3e80253c29a4157db640295f3709968bf5c7e36a162574d9821df9ee4","observation_id":"0081e8c6-f88e-4cde-910e-c815499703f2","resolution":{"observed_at":"2026-05-17T02:08:51.295886Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13912","last_updated":"2024-08-27T19:06:57Z","snapshot_observed_at":"2026-05-17T01:11:25.135375Z","submitted_at":"2024-08-25T18:27:20Z","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","version":2},"cited_work":{"arxiv_id":"2408.13912","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.13912","snapshot_observed_at":"2026-07-04T13:49:51.641963Z","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","venue":"cs.CV","work_id":"3950c9e4-deb4-4280-ac8f-08754c3ccf34","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/2408.13912","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:729d29d0bf7b50bc50b3d85ad76641ad9f98c27932c8fb53f4f35c3830b0425f","observation_id":"236f1940-ea4a-4ad6-80c1-02e924a8b7d0","resolution":{"observed_at":"2026-05-17T02:08:51.350515Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.05797","last_updated":"2019-06-13T16:29:58Z","snapshot_observed_at":"2026-07-04T23:42:36.177304Z","submitted_at":"2019-06-13T16:29:58Z","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","version":1},"cited_work":{"arxiv_id":"1906.05797","doi":null,"metadata_source":"pith","pith_arxiv_id":"1906.05797","snapshot_observed_at":"2026-07-04T13:29:52.120545Z","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","venue":"cs.CV","work_id":"8145b3bf-a202-46d8-a3bc-fad366dd5d4a","year":2019},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/1906.05797","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:f250cfab9b3a3425051971c64c94007c20184ae55a55510a095920c66fc051a6","observation_id":"ba392089-027b-4f7a-b1f2-87020d8e9400","resolution":{"observed_at":"2026-05-17T02:08:51.339480Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning shape abstractions by as- sembling volumetric primitives","venue":null,"work_id":"81947a68-24f7-4773-a3be-aa208449283b","year":2017},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:0a3c5cf35dbd481404fa6ecf7b5231eb983783fff22bacf6b4c626bb768cb057","observation_id":"fb3d6370-2fd0-474a-a867-e3a51151b0ca","resolution":{"observed_at":"2026-05-17T02:08:51.845104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Attention is all you need.Advances in neural information processing systems, 30","venue":null,"work_id":"1d73cb8e-bd95-49eb-8d35-3338aa1c3043","year":2017},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:db2824e01107cc5c0012e3d306dc6473472303077e22e51e23ce6b13045c413e","observation_id":"e0ca8d4f-5289-43d8-a322-9512c4595114","resolution":{"observed_at":"2026-05-17T02:08:51.843152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vggt: Vi- sual geometry grounded transformer","venue":null,"work_id":"6a81648f-a6e1-431e-a9e8-21e19dd43145","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:41954707d67189f2624c032bf8ac542be5de60c03750d12acd869c4318ab0c2f","observation_id":"95888265-77aa-4bc9-aaae-d8c8076743ff","resolution":{"observed_at":"2026-05-17T02:08:51.841147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ibr- net: Learning multi-view image-based rendering","venue":null,"work_id":"d67dded7-1c55-4f0d-8be3-a600721603af","year":2021},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:81bf0df350ee72acd293f218a6e4b0b25ee93edb00610a7026568532a0f92a02","observation_id":"4cb581fb-c571-4293-9331-9fce49830097","resolution":{"observed_at":"2026-05-17T02:08:51.956019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dust3r: Geometric 3d vi- sion made easy","venue":null,"work_id":"19527a6e-a98f-48a1-a408-7a9c0bcfa7b5","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:4585a22026ea27e4deb0f86b003ba1f3553075bb0d729bfd4371d55450bafbb7","observation_id":"fa3a91e9-137b-4ed0-bc23-fdd131cf4273","resolution":{"observed_at":"2026-05-17T02:08:51.958921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.23734","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T09:59:45.438219Z","title":"Zpressor: Bottleneck-aware compression for scalable feed-forward 3dgs","venue":null,"work_id":"ad2b1f44-7afe-4ee0-b4cf-cf0e72e39f5c","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:3aeeee3049364a08c68ec213592d58519ffa659f6c9ac6b0039532ed127d0e6a","observation_id":"866fb9a5-1665-464f-9ce9-d4104423a77c","resolution":{"observed_at":"2026-05-17T02:08:51.374844Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.19297","last_updated":"2026-06-24T10:16:56Z","snapshot_observed_at":"2026-06-27T23:13:47.136759Z","submitted_at":"2025-09-23T17:59:02Z","title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","version":3},"cited_work":{"arxiv_id":"2509.19297","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.19297","snapshot_observed_at":"2026-07-04T13:19:51.046437Z","title":"V olsplat: Rethinking feed-forward 3d gaussian splatting with voxel-aligned prediction","venue":"cs.CV","work_id":"a1117a19-eb44-4a5b-866c-4918d06fbdd5","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/2509.19297","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:ad15c39128d2871970adde6f5b97aebca868d059768e1c4db80d12952a0a9aa8","observation_id":"21e23298-cb7a-4cf1-9849-9a2f48e2bd7d","resolution":{"observed_at":"2026-06-25T02:17:30.860642Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Freesplat: Generalizable 3d gaussian splatting towards free view synthesis of indoor scenes.Advances in Neural Information Processing Systems, 37:107326–107349","venue":null,"work_id":"dd141a2d-3fff-433c-b08a-78e503bba33e","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:ce15dce2b76cb227b0ecfd95263a0122a537bb31bb341404909f011682c70762","observation_id":"6493e8d0-2b6e-491f-982e-fa4b57984a8e","resolution":{"observed_at":"2026-05-17T02:08:51.949693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.12764","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T10:19:47.768286Z","title":"Anyup: Universal feature upsampling","venue":null,"work_id":"6b22f24a-f58c-46c5-98a0-293acd8190a7","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:a74b6fcc43794665edb9b9f7d31ff49d02d71785bfbbf114121134871641441b","observation_id":"6a3513cc-d2f4-47a7-8f1c-4383e9653d09","resolution":{"observed_at":"2026-05-17T02:08:51.288151Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Murf: multi-baseline radiance fields","venue":null,"work_id":"06de45ad-718c-4d7f-b438-b4446b818011","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:96d18f9a93432dcaa571b057655cec505aa8fb98fc3cf37c9bcd15775972ab62","observation_id":"e6f0438b-5984-46b3-bcf8-f395b8a26ba9","resolution":{"observed_at":"2026-05-17T02:08:51.931679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2410.24207","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T13:49:51.630495Z","title":"No pose, no problem: Surprisingly simple 3d gaussian splats from sparse unposed images","venue":null,"work_id":"7827f7a7-41b8-4493-9d14-da77b48ea827","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:a37d8f1358f77a76a1727d84b2cd2ee79520d8eccf8362ddf7ee56ac3dbe0bc5","observation_id":"3cd4d0aa-57b1-417c-9575-12bdef679d90","resolution":{"observed_at":"2026-05-17T02:08:51.389458Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"pixelnerf: Neural radiance fields from one or few images","venue":null,"work_id":"fca446bc-eeab-4b4b-9ff9-95170e31082b","year":2021},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:95657ed229266d8f2c1a29dcdf2793e976b4bfad087727a0fea692a267ab2d6e","observation_id":"518ad503-d2b9-450c-895c-4077c5ef389f","resolution":{"observed_at":"2026-05-17T02:08:51.937798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving 2d feature representations by 3d-aware fine-tuning","venue":null,"work_id":"802ec623-4e69-4a88-8c7b-743ffb8c84b0","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:7698b6c28ccc1bcaf73f74e1f0bcd82c8e91747bd6519d0f6283928d46b1cf7a","observation_id":"5a8148a1-670d-4f9d-8593-ddd534a2d268","resolution":{"observed_at":"2026-05-17T02:08:51.929142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2503.18944","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T06:09:37.319147Z","title":"Knaebel, K","venue":null,"work_id":"a909a387-f093-4f34-a5f1-62f725ff89ed","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:90cd192689aafddce0142bb5ad787be97f9ffeb5e2c313a3c5ce76424cd3bf43","observation_id":"d62be158-25e1-459a-b4ba-e165c4fff99f","resolution":{"observed_at":"2026-05-17T02:08:51.392984Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Transplat: Generalizable 3d gaussian splatting from sparse multi-view images with transformers","venue":null,"work_id":"a0bac5f4-36cf-4095-af49-1874d8ccc949","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:977c9eb5b7f374ab7f78b1806a85c29d61f6d893e34bc5ac03e8cb9be4a4b7bb","observation_id":"81014a71-3f1e-4cbd-a6f2-83044bc37d05","resolution":{"observed_at":"2026-05-17T02:08:51.952803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c1bf51e2-595c-4ab8-b30e-643bdf52afcb","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:08a771549b3e649765b4fa16cf42f4b8c515a25705749bd69ea896a1a74f7dff","observation_id":"d988893a-6e41-45fd-b93f-f6e0b3bc31d9","resolution":{"observed_at":"2026-05-17T02:08:51.885242Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.11690","last_updated":"2025-10-13T17:51:39Z","snapshot_observed_at":"2026-05-11T22:28:33.046368Z","submitted_at":"2025-10-13T17:51:39Z","title":"Diffusion Transformers with Representation Autoencoders","version":1},"cited_work":{"arxiv_id":"2510.11690","doi":null,"metadata_source":"pith","pith_arxiv_id":"2510.11690","snapshot_observed_at":"2026-07-04T20:50:11.422290Z","title":"Diffusion Transformers with Representation Autoencoders","venue":"cs.CV","work_id":"c1a2d4de-4439-4005-8c56-e0124e4ed5fa","year":2025},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/2510.11690","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:f289884891e093ed0fc5b13425810316f3535385555693c0e2c722e499007767","observation_id":"d531d9ff-6ff3-4ffd-9661-613cac63be96","resolution":{"observed_at":"2026-05-17T02:08:51.360473Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Extract free dense labels from clip","venue":null,"work_id":"75449ce9-923e-43cf-af74-ba3d4ba31262","year":2022},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:1fde1ccc445649428836b4f3d5138076ba726f618062bc6ee1a6b3af1ae72fa8","observation_id":"854206c5-d154-43fd-b9d5-da7da733b661","resolution":{"observed_at":"2026-05-17T02:08:51.875904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Feature 3dgs: Supercharging 3d gaussian splatting to enable distilled feature fields","venue":null,"work_id":"d4d0755e-40dd-4b6b-9865-9b90451126dd","year":2024},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:f3eea82fa6bfd54fe02a7e424da619bdff6e60eef28f33659bbf821aa460a48d","observation_id":"140d8f8d-66a0-4a70-9fa4-26aaa4563187","resolution":{"observed_at":"2026-05-17T02:08:51.917126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.09817","last_updated":"2018-05-24T17:58:02Z","snapshot_observed_at":"2026-07-04T22:47:54.331237Z","submitted_at":"2018-05-24T17:58:02Z","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","version":1},"cited_work":{"arxiv_id":"1805.09817","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.09817","snapshot_observed_at":"2026-07-04T16:49:58.085080Z","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","venue":"cs.CV","work_id":"f6abb68f-df5c-4569-af1b-9ede43a44468","year":2018},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"cited_paper":"/paper/1805.09817","citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:25fb0f8285652501385bfe7ec55aedb22c835048228c263a8d0b89c133764e21","observation_id":"08c27cd2-2e9e-424f-81e8-6fed6d985cde","resolution":{"observed_at":"2026-05-17T02:08:51.382185Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Long-lrm: Long- sequence large reconstruction model for wide-coverage gaussian splats","venue":null,"work_id":"b0a8ede3-7394-4240-a823-482d07fc28a9","year":null},"citing_paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-05-17T02:06:54.730272Z"},"links":{"citing_paper":"/paper/2512.04021"},"observation_digest":"sha256:bc57691637f6dc326362faf9ce87be7dbde468dd57d83869eb6219430ad7b86d","observation_id":"383a47f4-23c4-4c6c-a416-3b43cda75b0e","resolution":{"observed_at":"2026-05-17T02:08:51.962123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.04021","last_updated":"2026-04-28T10:44:53Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-05-17T02:19:12.590071Z","submitted_at":"2025-12-03T17:59:05Z","title":"C3G: Learning Compact 3D Representations with 2K Gaussians"},"reference_resolution":{"displayed":83,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":4,"verified_exact":25,"verified_fuzzy":52},"total_outbound_references":83},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[],"thesis":"As of 19 July 2026, this Paper Citation Record lists 83 of 83 outbound references and 8 inbound Pith citation observations for arXiv:2512.04021."}