{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EO4ULENEFI5AB5TLTB47A3YXTI","short_pith_number":"pith:EO4ULENE","schema_version":"1.0","canonical_sha256":"23b94591a42a3a00f66b9879f06f179a34338035bbf0638d72e196f2b3b12ac2","source":{"kind":"arxiv","id":"2511.22973","version":2},"attestation_state":"computed","paper":{"title":"BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Fan Wang, Jiasheng Tang, Jinyuan Mao, Shuning Chang, Yizeng Han, Yuanyu He, Zeyu Zhang","submitted_at":"2025-11-28T08:25:59Z","abstract_excerpt":"Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction consistency. Recent autoregressive diffusion models enable long-horizon generation through KV cache reuse, yet suffer from two fundamental challenges: failure to preserve long-range interactions due to sliding-window KV cache and error accumulation that progressively degrades generation quality over time. To address these issues, we propose BIFE, a framework that introduces a semantic sparse KV cache for retrieval-based long-range conditioning and a Bl"},"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":"2511.22973","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-28T08:25:59Z","cross_cats_sorted":[],"title_canon_sha256":"6f0186eefc35a3c17da3ebc15265d18b425996c84d1e9abdba668256b034da8d","abstract_canon_sha256":"c2c6f00f50993e6e9fdaa47bf6f84de11f2d918f485f66860341a6b0e0ec565d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:51.962878Z","signature_b64":"upJk0Wc44f51DHQCwn9zKtAO9f/+XwO2LmVcneiXSp2+VavILAYKNVhrwnxhSf/+it3AuAnYzf0gm80aSifUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23b94591a42a3a00f66b9879f06f179a34338035bbf0638d72e196f2b3b12ac2","last_reissued_at":"2026-06-23T03:13:51.962439Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:51.962439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Fan Wang, Jiasheng Tang, Jinyuan Mao, Shuning Chang, Yizeng Han, Yuanyu He, Zeyu Zhang","submitted_at":"2025-11-28T08:25:59Z","abstract_excerpt":"Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction consistency. Recent autoregressive diffusion models enable long-horizon generation through KV cache reuse, yet suffer from two fundamental challenges: failure to preserve long-range interactions due to sliding-window KV cache and error accumulation that progressively degrades generation quality over time. To address these issues, we propose BIFE, a framework that introduces a semantic sparse KV cache for retrieval-based long-range conditioning and a Bl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.22973","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/2511.22973/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":"2511.22973","created_at":"2026-06-23T03:13:51.962494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.22973v2","created_at":"2026-06-23T03:13:51.962494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.22973","created_at":"2026-06-23T03:13:51.962494+00:00"},{"alias_kind":"pith_short_12","alias_value":"EO4ULENEFI5A","created_at":"2026-06-23T03:13:51.962494+00:00"},{"alias_kind":"pith_short_16","alias_value":"EO4ULENEFI5AB5TL","created_at":"2026-06-23T03:13:51.962494+00:00"},{"alias_kind":"pith_short_8","alias_value":"EO4ULENE","created_at":"2026-06-23T03:13:51.962494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.30519","citing_title":"OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18733","citing_title":"Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI","json":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI.json","graph_json":"https://pith.science/api/pith-number/EO4ULENEFI5AB5TLTB47A3YXTI/graph.json","events_json":"https://pith.science/api/pith-number/EO4ULENEFI5AB5TLTB47A3YXTI/events.json","paper":"https://pith.science/paper/EO4ULENE"},"agent_actions":{"view_html":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI","download_json":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI.json","view_paper":"https://pith.science/paper/EO4ULENE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.22973&json=true","fetch_graph":"https://pith.science/api/pith-number/EO4ULENEFI5AB5TLTB47A3YXTI/graph.json","fetch_events":"https://pith.science/api/pith-number/EO4ULENEFI5AB5TLTB47A3YXTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI/action/storage_attestation","attest_author":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI/action/author_attestation","sign_citation":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI/action/citation_signature","submit_replication":"https://pith.science/pith/EO4ULENEFI5AB5TLTB47A3YXTI/action/replication_record"}},"created_at":"2026-06-23T03:13:51.962494+00:00","updated_at":"2026-06-23T03:13:51.962494+00:00"}