{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2AXBSXO2CMDYRA6H2P4GGKLYVH","short_pith_number":"pith:2AXBSXO2","schema_version":"1.0","canonical_sha256":"d02e195dda13078883c7d3f8632978a9d7fe414e09054599c6f5ac73da833a7d","source":{"kind":"arxiv","id":"2007.08509","version":1},"attestation_state":"computed","paper":{"title":"World-Consistent Video-to-Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Mallya, Karan Sapra, Ming-Yu Liu, Ting-Chun Wang","submitted_at":"2020-07-16T17:58:13Z","abstract_excerpt":"Video-to-video synthesis (vid2vid) aims for converting high-level semantic inputs to photorealistic videos. While existing vid2vid methods can achieve short-term temporal consistency, they fail to ensure the long-term one. This is because they lack knowledge of the 3D world being rendered and generate each frame only based on the past few frames. To address the limitation, we introduce a novel vid2vid framework that efficiently and effectively utilizes all past generated frames during rendering. This is achieved by condensing the 3D world rendered so far into a physically-grounded estimate of "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.08509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-16T17:58:13Z","cross_cats_sorted":[],"title_canon_sha256":"825b3834a997fe87a8ea78d0e14b43ef6e862a94975f6baed3e33ef26b00ad30","abstract_canon_sha256":"1a17c1c960d4dfe3b23229ff9f8b0a8947e33cba7465be97f3453ac0311727d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:48.323562Z","signature_b64":"A0APtHwjHFPUi1mV39ZHSq5g5y4moytIWfNnljA9zpVQVuM3pZDvhv3nRGK/Pt7YruG7oJdl6p20eXgeb6hUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d02e195dda13078883c7d3f8632978a9d7fe414e09054599c6f5ac73da833a7d","last_reissued_at":"2026-07-05T01:19:48.323081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:48.323081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"World-Consistent Video-to-Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Mallya, Karan Sapra, Ming-Yu Liu, Ting-Chun Wang","submitted_at":"2020-07-16T17:58:13Z","abstract_excerpt":"Video-to-video synthesis (vid2vid) aims for converting high-level semantic inputs to photorealistic videos. While existing vid2vid methods can achieve short-term temporal consistency, they fail to ensure the long-term one. This is because they lack knowledge of the 3D world being rendered and generate each frame only based on the past few frames. To address the limitation, we introduce a novel vid2vid framework that efficiently and effectively utilizes all past generated frames during rendering. This is achieved by condensing the 3D world rendered so far into a physically-grounded estimate of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08509","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.08509/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.08509","created_at":"2026-07-05T01:19:48.323136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08509v1","created_at":"2026-07-05T01:19:48.323136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08509","created_at":"2026-07-05T01:19:48.323136+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AXBSXO2CMDY","created_at":"2026-07-05T01:19:48.323136+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AXBSXO2CMDYRA6H","created_at":"2026-07-05T01:19:48.323136+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AXBSXO2","created_at":"2026-07-05T01:19:48.323136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11707","citing_title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH","json":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH.json","graph_json":"https://pith.science/api/pith-number/2AXBSXO2CMDYRA6H2P4GGKLYVH/graph.json","events_json":"https://pith.science/api/pith-number/2AXBSXO2CMDYRA6H2P4GGKLYVH/events.json","paper":"https://pith.science/paper/2AXBSXO2"},"agent_actions":{"view_html":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH","download_json":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH.json","view_paper":"https://pith.science/paper/2AXBSXO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08509&json=true","fetch_graph":"https://pith.science/api/pith-number/2AXBSXO2CMDYRA6H2P4GGKLYVH/graph.json","fetch_events":"https://pith.science/api/pith-number/2AXBSXO2CMDYRA6H2P4GGKLYVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH/action/storage_attestation","attest_author":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH/action/author_attestation","sign_citation":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH/action/citation_signature","submit_replication":"https://pith.science/pith/2AXBSXO2CMDYRA6H2P4GGKLYVH/action/replication_record"}},"created_at":"2026-07-05T01:19:48.323136+00:00","updated_at":"2026-07-05T01:19:48.323136+00:00"}