{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NBVSX4Y2IZUKWATL6E7OMMDDJU","short_pith_number":"pith:NBVSX4Y2","schema_version":"1.0","canonical_sha256":"686b2bf31a4668ab026bf13ee630634d3f1ea9d809b0816d2eec690abd668dcb","source":{"kind":"arxiv","id":"2407.19402","version":1},"attestation_state":"computed","paper":{"title":"NVC-1B: A Large Neural Video Coding Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chuanbo Tang, Dong Liu, Feng Wu, Li Li, Xihua Sheng","submitted_at":"2024-07-28T05:12:22Z","abstract_excerpt":"The emerging large models have achieved notable progress in the fields of natural language processing and computer vision. However, large models for neural video coding are still unexplored. In this paper, we try to explore how to build a large neural video coding model. Based on a small baseline model, we gradually scale up the model sizes of its different coding parts, including the motion encoder-decoder, motion entropy model, contextual encoder-decoder, contextual entropy model, and temporal context mining module, and analyze the influence of model sizes on video compression performance. T"},"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":"2407.19402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-28T05:12:22Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"4f5d3fe72669ade86fb80549c01f077c42ba197ace4ac65cf5daab3f9fd794b2","abstract_canon_sha256":"d8f4ec09c7d356c7d65a40e7f57d6520e7cfd920a907bbb838fa68b46dda2a8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:39.507321Z","signature_b64":"gI476sec7WMG5KwJX40sf/wcUUy3W8x+mwupaw3tKN7dcBou771sPXKnf6pSSCf6bgHJXN0sDLG8MgQrD7naDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"686b2bf31a4668ab026bf13ee630634d3f1ea9d809b0816d2eec690abd668dcb","last_reissued_at":"2026-07-05T08:49:39.506871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:39.506871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NVC-1B: A Large Neural Video Coding Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chuanbo Tang, Dong Liu, Feng Wu, Li Li, Xihua Sheng","submitted_at":"2024-07-28T05:12:22Z","abstract_excerpt":"The emerging large models have achieved notable progress in the fields of natural language processing and computer vision. However, large models for neural video coding are still unexplored. In this paper, we try to explore how to build a large neural video coding model. Based on a small baseline model, we gradually scale up the model sizes of its different coding parts, including the motion encoder-decoder, motion entropy model, contextual encoder-decoder, contextual entropy model, and temporal context mining module, and analyze the influence of model sizes on video compression performance. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19402","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/2407.19402/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":"2407.19402","created_at":"2026-07-05T08:49:39.506935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19402v1","created_at":"2026-07-05T08:49:39.506935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19402","created_at":"2026-07-05T08:49:39.506935+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBVSX4Y2IZUK","created_at":"2026-07-05T08:49:39.506935+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBVSX4Y2IZUKWATL","created_at":"2026-07-05T08:49:39.506935+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBVSX4Y2","created_at":"2026-07-05T08:49:39.506935+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":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU","json":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU.json","graph_json":"https://pith.science/api/pith-number/NBVSX4Y2IZUKWATL6E7OMMDDJU/graph.json","events_json":"https://pith.science/api/pith-number/NBVSX4Y2IZUKWATL6E7OMMDDJU/events.json","paper":"https://pith.science/paper/NBVSX4Y2"},"agent_actions":{"view_html":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU","download_json":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU.json","view_paper":"https://pith.science/paper/NBVSX4Y2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19402&json=true","fetch_graph":"https://pith.science/api/pith-number/NBVSX4Y2IZUKWATL6E7OMMDDJU/graph.json","fetch_events":"https://pith.science/api/pith-number/NBVSX4Y2IZUKWATL6E7OMMDDJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU/action/storage_attestation","attest_author":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU/action/author_attestation","sign_citation":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU/action/citation_signature","submit_replication":"https://pith.science/pith/NBVSX4Y2IZUKWATL6E7OMMDDJU/action/replication_record"}},"created_at":"2026-07-05T08:49:39.506935+00:00","updated_at":"2026-07-05T08:49:39.506935+00:00"}