{"as_of":"2026-07-14T17:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a1895447de8c607f76c2ded01d8a6870e72d90fb6575b68df6ebba52d2205f62","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T11:51:01.769882Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":null,"state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.28421/citation-record","integrity":"/paper/2605.28421/integrity","json":"/paper/2605.28421/citation-record.json","paper":"/paper/2605.28421"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.14740","last_updated":"2024-02-26T18:26:25Z","snapshot_observed_at":"2026-05-13T01:36:26.180541Z","submitted_at":"2024-02-22T17:52:34Z","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","version":2},"cited_work":{"arxiv_id":"2402.14740","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.14740","snapshot_observed_at":"2026-07-04T13:29:51.706500Z","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","venue":"cs.LG","work_id":"7bb8f9ec-1241-4472-a4fa-c636c6d79892","year":2024},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2402.14740","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:5ee610961d6494fe9dca0cf62db6e484ff50cd5cbe9d15cb4cf306415b6026d2","observation_id":"37e14206-a075-475f-ae9a-460573103097","resolution":{"observed_at":"2026-06-29T11:53:23.681551Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:e7939cadcff501d7738cfb8551cb1309286434c22832452db1f83cfbe909e4d0","observation_id":"bec034d0-20ff-47f8-a0c3-62ebb9ab9c50","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:b37885e96c3ba838b5bdd91378f1c574a4df98af3541e6db77ee6d41e7f65c0e","observation_id":"f6b7c844-a0e7-4c8f-95e7-faa5ce9ee977","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2312.09390","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T09:59:44.739031Z","title":"Burns, P","venue":null,"work_id":"4a21c761-9a3d-4f84-a55d-5779da5da28f","year":2024},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:80bf93541d6f3a98e357bd095bbabd4a8226d323b6f10e8c5f1ab9a3cf58f1f9","observation_id":"a0e04240-5782-4147-90e3-08a2d48c1c32","resolution":{"observed_at":"2026-06-29T11:53:23.662416Z","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":"2510.08191","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T17:20:00.002556Z","title":"Training-free group relative policy optimization, October 2025","venue":null,"work_id":"e147d6d6-f3f4-44ff-94e9-78f84be63bdb","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:73c40d51ddb260412a52a45456f2448b24d320ba7601e626a9f096fb3f1d3fed","observation_id":"d092d25e-94da-4b7a-bcdd-e913d5d9d672","resolution":{"observed_at":"2026-06-29T11:53:23.684505Z","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":"2510.26277","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T10:19:47.411960Z","title":"Do LLMs signal when they’re right? evidence from neuron agreement, 2025","venue":null,"work_id":"c6738122-c6cc-4da9-b098-338e12efde09","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:a5341e2248bd1bc5d9a727bb09d55e46c157760c221cbdfaf763c96ae75409cb","observation_id":"617b1317-457d-444b-afd8-1775a422db2b","resolution":{"observed_at":"2026-06-29T11:53:23.669549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.05742","last_updated":"2026-05-07T06:33:25Z","snapshot_observed_at":"2026-05-10T23:42:58.834128Z","submitted_at":"2026-05-07T06:33:25Z","title":"Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)","version":1},"cited_work":{"arxiv_id":"2605.05742","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.05742","snapshot_observed_at":"2026-06-29T11:53:23.700060Z","title":"Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)","venue":"cs.LG","work_id":"1060ca8b-10d9-477c-88a4-e57b18922da4","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2605.05742","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:3419e82ea93cc873e6b1438cdf04db96852ee83d7d12891efc9f7a24cf8de0b6","observation_id":"c3af9b88-12f8-4561-a053-5c6a4dbb51d7","resolution":{"observed_at":"2026-06-29T11:53:23.701503Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-13T19:33:48.196325Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2501.12948","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-07-05T04:40:40.671403Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","venue":"cs.CL","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:316f5493276d2eff94aee2859665dac680d81cc2c7e1e55c4676bc50553c178a","observation_id":"ee8bc249-2756-4881-9ac8-131095b16c32","resolution":{"observed_at":"2026-06-29T11:53:23.704929Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.11456","last_updated":"2025-05-22T19:12:14Z","snapshot_observed_at":"2026-05-16T10:29:22.168589Z","submitted_at":"2025-04-15T17:59:51Z","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","version":2},"cited_work":{"arxiv_id":"2504.11456","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.11456","snapshot_observed_at":"2026-07-04T16:29:56.820111Z","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","venue":"cs.CL","work_id":"3dea79f1-73da-4db2-8d7b-64013c3c5fa5","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2504.11456","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:53e3b574765cf6bbe69350ac36a9262c62212cd36055f8c9401c4a02a93e152e","observation_id":"9bee5b38-0f96-4678-a3e3-9faac621eb5c","resolution":{"observed_at":"2026-06-29T11:53:23.707364Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03874","last_updated":"2021-11-08T21:30:18Z","snapshot_observed_at":"2026-07-05T03:30:09.713662Z","submitted_at":"2021-03-05T18:59:39Z","title":"Measuring Mathematical Problem Solving With the MATH Dataset","version":2},"cited_work":{"arxiv_id":"2103.03874","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.03874","snapshot_observed_at":"2026-07-04T19:10:05.889865Z","title":"Measuring Mathematical Problem Solving With the MATH Dataset","venue":"cs.LG","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","year":2021},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2103.03874","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:c71b334f891798849295cb4a61b34857ad19b846ed75a01f2c63177b0e3fc0f8","observation_id":"2a5b6baa-ef87-4718-b6af-dd058bf0a6b3","resolution":{"observed_at":"2026-06-29T11:53:23.709943Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:7a26dfe762938c63bb3d6b5a976103264eec493ac3793799d401501655d6f4fc","observation_id":"02abb5a9-9cce-43d8-9681-20c7560d5002","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:e791695642ffeb0ab30404f83fc262293a7d4d674be05a3c53e5576178b7ab5e","observation_id":"4ee058bb-acd1-484c-a80e-5b5a31989c8c","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.16828","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T20:40:07.881388Z","title":"Process reward models that think","venue":null,"work_id":"5eb327be-4cef-462e-8ccc-1fafa6d30e28","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:1551d882b607e6f097afcf28e3bdd7b64051ac194407f4c41e61339adfe14c85","observation_id":"1993e84a-6c8b-4fca-9cc6-f0781a897f26","resolution":{"observed_at":"2026-06-29T11:53:23.715281Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.00705","last_updated":"2026-06-26T15:22:20Z","snapshot_observed_at":"2026-07-01T23:15:48.158119Z","submitted_at":"2025-10-01T09:20:51Z","title":"Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs","version":3},"cited_work":{"arxiv_id":"2510.00705","doi":null,"metadata_source":"pith","pith_arxiv_id":"2510.00705","snapshot_observed_at":"2026-06-29T11:53:23.711158Z","title":"Training-free uncertainty guidance for complex visual tasks with mllms.arXiv preprint arXiv:2510.00705","venue":"cs.CV","work_id":"27e7ae02-8293-4c18-a0bd-802824b7e5bf","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2510.00705","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:7a36f9b1c54321e63bdeb3c8f9df9d61534847b0206ce7dff8a45157957a8af2","observation_id":"d0ec393c-dffe-4757-af64-54b9d339b4d5","resolution":{"observed_at":"2026-06-29T11:53:23.712612Z","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":"2511.14166","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:53:23.688562Z","title":null,"venue":null,"work_id":"bf86aaf2-fdfc-4815-9ffd-01f85d9cdfdf","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:9dcbe02dbd270d2ed7273487ad4ede02cb086823ce83a5f24328a5d1e2e3fd3b","observation_id":"2d59e6bc-6b99-4350-8fdc-a5e4edce4d91","resolution":{"observed_at":"2026-06-29T11:53:23.689895Z","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":"2601.22718","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T04:47:37.872104Z","title":"arXiv preprint arXiv:2601.22718 , year=","venue":null,"work_id":"c3544b5b-2386-42a5-ae9e-d86e155af07e","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:9f60314ddf7e27e8ccfe16b6d5e37d2116c1809ec4aec540859f63cf10dd848d","observation_id":"9149339f-63a5-4e9d-92b1-e79fcab7d694","resolution":{"observed_at":"2026-06-29T11:53:23.686496Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:cada8a6f424596547dc6ba1baff90d425fee06d5fa6b916b793f30e85d2e0e4b","observation_id":"fcdeebe8-0569-4bde-89ea-8cb96c50e3ea","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:2539ddee856e7375690d6b36a21d81a933e721576e139c6efa6b1deffa6730cc","observation_id":"cacb1f9c-d9b2-4846-8426-53f881f94825","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.07809","last_updated":"2026-04-20T09:03:51Z","snapshot_observed_at":"2026-05-18T23:56:46.653470Z","submitted_at":"2025-08-11T09:49:01Z","title":"EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning","version":5},"cited_work":{"arxiv_id":"2508.07809","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.07809","snapshot_observed_at":"2026-06-29T11:53:23.697384Z","title":"EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning","venue":"cs.LG","work_id":"878d25a1-8a74-4746-a55a-66d0645ce895","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2508.07809","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:eb8b82c61b6b230535f5a8eb67fda8adb75fa4822e006261ca5a84cdf23e2482","observation_id":"c682f812-c459-439d-8c41-b594f9ddd14a","resolution":{"observed_at":"2026-06-29T11:53:23.698614Z","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":"2505.19641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T22:17:25.603039Z","title":"Synlogic: Synthesizing verifiable reasoning data at scale for learning logical reasoning and beyond","venue":null,"work_id":"11a55d46-fb86-4226-b0f0-2144857aeb9c","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:4f915d1206b2be85d52e4140b1ea06f81bb1423c084e4f16697ff03bfe05547d","observation_id":"09397fe9-541f-4b71-a434-e42ba757d11a","resolution":{"observed_at":"2026-06-29T11:53:23.704451Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:a00faaa8e6d7a86430301ef8518e18a100072ced73968476d516ebe9ad1b4c13","observation_id":"802b7182-ffa2-446d-8122-166375d722d5","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:f8b8d922b50ad26573f71c725455354d2f9f58d6c2e762aed79d754745aa25b9","observation_id":"c0dd154d-c180-490e-8dfa-1389a00e51c1","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.18779","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T00:29:15.135959Z","title":"Pope: Learning to reason on hard problems via privileged on-policy exploration","venue":null,"work_id":"49d6a516-37ca-4bd7-8174-20b4b69db931","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:45e8f84a5d7c34f38bcedf5007c0c2818930a7a646d76447e1ccd315a30f5078","observation_id":"7c49f55d-bd89-413c-8cdb-09ad2e4a4af6","resolution":{"observed_at":"2026-06-29T11:53:23.698713Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-04T22:09:55.707882Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":"1707.06347","doi":null,"metadata_source":"pith","pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-07-05T06:00:43.850049Z","title":"Proximal Policy Optimization Algorithms","venue":"cs.LG","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","year":2017},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:7e7e4ec0fa856b19cf80a5673763c239bfde8a69ea26a0fa6223e662122e9c13","observation_id":"d918def2-29c6-4970-9c8b-d88b4fe8c921","resolution":{"observed_at":"2026-06-29T11:53:23.684012Z","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":"2601.18795","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T12:03:24.396698Z","title":"Reuse your flops: Scaling rl on hard problems by conditioning on very off-policy prefixes","venue":null,"work_id":"2be8a44f-c445-4fc6-9eec-82c26f802afc","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:dd49c1421079345a2d6f9c9d741ce3922745898b9f4ced8bb2ebe5992918f790","observation_id":"fb0250b3-8437-417d-ac4a-7d68a45c6eef","resolution":{"observed_at":"2026-06-29T11:53:23.689537Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-05-24T03:26:42.287120Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":"2402.03300","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-07-05T04:40:40.674631Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","venue":"cs.CL","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","year":2024},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:7a625a32450fc9387da2834f7fae63e3cc9668e56f94544ec46c1c35c2b96c18","observation_id":"0bab13af-6ac6-42bc-af36-8a382921f3b6","resolution":{"observed_at":"2026-06-29T11:53:23.652281Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:446084e052e05212c8b7086118685b313bf552f7108a9b6df3227cb2528c3256","observation_id":"049b37ea-e7c2-45e3-be6c-5938937028bb","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:e77aeb314e96fedf93011a542701ece8a7fa1bfa605ac55dbea945a74a76d7d0","observation_id":"cdc7c0b7-22be-446d-bcd0-3d83e69cbc0d","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:ac8c6406b05c94af040611402eef54a2cc91fb9f3ae42881d732f4d471c434ff","observation_id":"a1de8982-be7b-40bf-8bce-f93b70684c22","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-05-09T00:12:58.330394Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-05T04:50:41.673455Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:3e9d8f5862d35553e6eb9ee9783f97fd0c9ba7898ede5b2ab9bd4772b68a2334","observation_id":"60c4c9ce-e9fa-40da-a4af-6a89c7a9703a","resolution":{"observed_at":"2026-06-29T11:53:23.672403Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:fe7518b17c631f1b19664b3c95f62b2bd92b627f0355fcfb8e44b2dc5206db86","observation_id":"f46631b7-1aec-4f9d-aaec-10b5d9e639b6","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.00053","last_updated":"2022-10-31T18:09:51Z","snapshot_observed_at":"2026-07-05T05:12:17.804008Z","submitted_at":"2022-10-31T18:09:51Z","title":"Generating Sequences by Learning to Self-Correct","version":1},"cited_work":{"arxiv_id":"2211.00053","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.00053","snapshot_observed_at":"2026-07-02T20:57:23.932125Z","title":"Generating sequences by learning to self-correct","venue":null,"work_id":"ccd1e168-905a-48c2-a387-c43d5c25f8bc","year":2022},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2211.00053","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:1517c8359a3de488cbe9ace96b4f9960c242506df37789d5d29b712ceb436525","observation_id":"7d992c4d-6284-4b5b-b08d-3b4105e8a474","resolution":{"observed_at":"2026-06-29T11:53:23.676256Z","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":"2506.02864","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T08:09:40.713683Z","title":"arXiv preprint arXiv:2506.02864 , year=","venue":null,"work_id":"14ce32a8-5db9-49f8-b890-9695ba59f1ee","year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:8714bdadd1aa6e2d98ea8739a620fc5e0215f513c16d63879185535c3278cd84","observation_id":"64639df8-7838-4fb5-8962-e9ea3bb461ae","resolution":{"observed_at":"2026-06-29T11:53:23.678846Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.04809","last_updated":"2026-05-04T13:55:24Z","snapshot_observed_at":"2026-05-16T16:28:19.363865Z","submitted_at":"2026-01-08T10:42:04Z","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","version":5},"cited_work":{"arxiv_id":"2601.04809","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.04809","snapshot_observed_at":"2026-07-04T17:09:59.118536Z","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","venue":"cs.AI","work_id":"b64419eb-b675-430f-82c8-ba9b335004f6","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2601.04809","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:571b7ab05b94e6d5e59d13ac4d7b91bcd536ccc59a5e914b86e077bbd446155e","observation_id":"dd996933-3890-41ae-9507-12d77df4d16f","resolution":{"observed_at":"2026-06-29T11:53:23.667020Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:fc4bc0087ac6502b3b5ece6436c8d5082fdcfff8722d3e2d31727932423f52bf","observation_id":"0d33a8be-bd11-4930-a06d-c1b7dc0a01b1","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-05-10T14:02:05.423502Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":"2407.10671","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-07-05T04:50:41.670963Z","title":"Qwen2 Technical Report","venue":"cs.CL","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","year":2024},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:7a3688e5e5ba10d7462f34a04bdc01e7f688c5b711cb34e2fab125a1ce4e145a","observation_id":"34a259c7-bc2a-4585-8edb-a0efa7bb0702","resolution":{"observed_at":"2026-06-29T11:53:23.676192Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:cec1f1446acef4816b640a7d2103baec4f80ad04ad6c75498d0049e9510ed8b9","observation_id":"b351e235-5754-48d3-b6f4-adda2fbbee5a","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.12627","last_updated":"2026-04-14T11:53:23Z","snapshot_observed_at":"2026-05-10T15:00:26.883408Z","submitted_at":"2026-04-14T11:53:23Z","title":"KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance","version":1},"cited_work":{"arxiv_id":"2604.12627","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.12627","snapshot_observed_at":"2026-06-29T11:53:23.663504Z","title":"KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance","venue":"cs.AI","work_id":"16597dd3-6f3e-4c93-a68b-57af9f092bef","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2604.12627","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:44a8fcc824ab4ece0336c33e6d505aa55a4d3b057e823ea1f19152d143db064b","observation_id":"e0abe62f-3451-4811-b91e-5eb208bee888","resolution":{"observed_at":"2026-06-29T11:53:23.664636Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:51:01.769882Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:48d5976ef707088add4207770a60f683cbf0ddec9abd16f472f503c6a4ccadf9","observation_id":"e14d4db1-9649-4d22-a45d-e35d04018528","resolution":{"observed_at":"2026-06-29T11:51:01.769882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.20072","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:53:23.668265Z","title":null,"venue":null,"work_id":"e780f076-a52c-4c89-944a-16272b73ed95","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:95d46d5cc8b2315ff3e2313adf01704d7ab76185df38f2f29ead84f63019fb3c","observation_id":"5faf7014-cab4-4e1e-8d0c-92bbb22d437f","resolution":{"observed_at":"2026-06-29T11:53:23.669676Z","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":"2508.05592","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T11:53:23.677594Z","title":"Mathsmith: Towards extremely hard mathematical reasoning by forging synthetic problems with a reinforced policy","venue":null,"work_id":"413bcd50-7b9d-4ad9-be19-a66aa2cca9fb","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:20b4144ff50c1d9e06f53903c0e33d9aba56b8d46645f15e26512b67cc36c5a1","observation_id":"570f1cdf-1701-4847-b222-8dd6d85b8c23","resolution":{"observed_at":"2026-06-29T11:53:23.679110Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.22495","last_updated":"2026-06-17T23:32:06Z","snapshot_observed_at":"2026-06-21T23:11:29.736449Z","submitted_at":"2026-02-26T00:20:39Z","title":"Reinforcement-aware Knowledge Distillation for LLM Reasoning","version":3},"cited_work":{"arxiv_id":"2602.22495","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.22495","snapshot_observed_at":"2026-07-02T01:56:27.858327Z","title":"Reinforcement-aware Knowledge Distillation for LLM Reasoning","venue":"cs.LG","work_id":"e1b3cffd-f5ae-4eb9-abb7-6df5fa58497e","year":2026},"citing_paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-29T11:51:01.769882Z"},"links":{"cited_paper":"/paper/2602.22495","citing_paper":"/paper/2605.28421"},"observation_digest":"sha256:8d99675bc385ad5262189ab8fb698b6efc1b300c8a7e7fbbf45cfebeae2dafc9","observation_id":"a06f4f99-00cc-44dc-a733-1b7c78396f7c","resolution":{"observed_at":"2026-06-29T11:53:23.660779Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"reason":"named_source_frontier_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.28421","last_updated":"2026-05-27T12:52:58Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-06-29T11:51:01.311155Z","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":27,"verified_fuzzy":0},"total_outbound_references":42},"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 14 July 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2605.28421."}