{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XU3PX4EWCGKED4NBITIDFD232I","short_pith_number":"pith:XU3PX4EW","schema_version":"1.0","canonical_sha256":"bd36fbf096119441f1a144d0328f5bd20812035ca0ddf4d96f182f322a7084eb","source":{"kind":"arxiv","id":"2111.03386","version":2},"attestation_state":"computed","paper":{"title":"Versatile Learned Video Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Runsen Feng, Zhibo Chen, Zhizheng Zhang, Zongyu Guo","submitted_at":"2021-11-05T10:50:37Z","abstract_excerpt":"Learned video compression methods have demonstrated great promise in catching up with traditional video codecs in their rate-distortion (R-D) performance. However, existing learned video compression schemes are limited by the binding of the prediction mode and the fixed network framework. They are unable to support various inter prediction modes and thus inapplicable for various scenarios. In this paper, to break this limitation, we propose a versatile learned video compression (VLVC) framework that uses one model to support all possible prediction modes. Specifically, to realize versatile com"},"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":"2111.03386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-11-05T10:50:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1d871b84c15303a3d95f688a79abadb1f8b4789cbfba5ed29af127f0bfc32920","abstract_canon_sha256":"6bea644bc6a3dacbee164a6aa262185f19113e774dd336938c847886ed4ec014"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:03.594857Z","signature_b64":"3APt1LUlc6+5Az2MKTlBheeqk9CmyJD/mRybSFjGCNZQtyjdvM2B3A3U3a6JU6EW4/NG+zxuJTwzWAKImgC9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd36fbf096119441f1a144d0328f5bd20812035ca0ddf4d96f182f322a7084eb","last_reissued_at":"2026-07-05T03:46:03.594412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:03.594412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Versatile Learned Video Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Runsen Feng, Zhibo Chen, Zhizheng Zhang, Zongyu Guo","submitted_at":"2021-11-05T10:50:37Z","abstract_excerpt":"Learned video compression methods have demonstrated great promise in catching up with traditional video codecs in their rate-distortion (R-D) performance. However, existing learned video compression schemes are limited by the binding of the prediction mode and the fixed network framework. They are unable to support various inter prediction modes and thus inapplicable for various scenarios. In this paper, to break this limitation, we propose a versatile learned video compression (VLVC) framework that uses one model to support all possible prediction modes. Specifically, to realize versatile com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03386","kind":"arxiv","version":2},"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/2111.03386/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":"2111.03386","created_at":"2026-07-05T03:46:03.594474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03386v2","created_at":"2026-07-05T03:46:03.594474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03386","created_at":"2026-07-05T03:46:03.594474+00:00"},{"alias_kind":"pith_short_12","alias_value":"XU3PX4EWCGKE","created_at":"2026-07-05T03:46:03.594474+00:00"},{"alias_kind":"pith_short_16","alias_value":"XU3PX4EWCGKED4NB","created_at":"2026-07-05T03:46:03.594474+00:00"},{"alias_kind":"pith_short_8","alias_value":"XU3PX4EW","created_at":"2026-07-05T03:46:03.594474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01818","citing_title":"Conditional Residual Coding with Explicit-Implicit Temporal Buffering for Learned Video Compression","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I","json":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I.json","graph_json":"https://pith.science/api/pith-number/XU3PX4EWCGKED4NBITIDFD232I/graph.json","events_json":"https://pith.science/api/pith-number/XU3PX4EWCGKED4NBITIDFD232I/events.json","paper":"https://pith.science/paper/XU3PX4EW"},"agent_actions":{"view_html":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I","download_json":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I.json","view_paper":"https://pith.science/paper/XU3PX4EW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03386&json=true","fetch_graph":"https://pith.science/api/pith-number/XU3PX4EWCGKED4NBITIDFD232I/graph.json","fetch_events":"https://pith.science/api/pith-number/XU3PX4EWCGKED4NBITIDFD232I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I/action/storage_attestation","attest_author":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I/action/author_attestation","sign_citation":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I/action/citation_signature","submit_replication":"https://pith.science/pith/XU3PX4EWCGKED4NBITIDFD232I/action/replication_record"}},"created_at":"2026-07-05T03:46:03.594474+00:00","updated_at":"2026-07-05T03:46:03.594474+00:00"}