{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CRW75HZRZFE262S4FAMM6E4K4Y","short_pith_number":"pith:CRW75HZR","schema_version":"1.0","canonical_sha256":"146dfe9f31c949af6a5c2818cf138ae635c727e7a65ae7d5e16baa7453d0e54f","source":{"kind":"arxiv","id":"2605.15199","version":1},"attestation_state":"computed","paper":{"title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Explicit per-entity memory maintains character consistency across long gaps in multi-shot video generation where existing methods fail.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Meng Wei, Ruozhen He, Vicente Ordonez, Ziyan Yang","submitted_at":"2026-05-14T17:59:55Z","abstract_excerpt":"Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and locations across shots remains a challenge over long sequences. Existing evaluations typically use independently generated prompt sets with limited entity coverage and simple consistency metrics, making standardized comparison difficult. We introduce EntityBench, a benchmark of 140 episodes (2,491 shots) derived from real narrative media, with explicit per-shot entity schedules tracking characters, objects, and locations simultaneously across easy / medi"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:59:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11d992f42dc4675222b71a4aea55c171ea04bf8e28a4ea7ab891a585ae23f18a","abstract_canon_sha256":"4c96a559abd3ffc6454d3041f0dfedd22d0bdd44731caf3124aa9ab26cba1c57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"146dfe9f31c949af6a5c2818cf138ae635c727e7a65ae7d5e16baa7453d0e54f","last_reissued_at":"2026-05-17T21:57:18.363405Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:24.971979Z"},"graph_snapshot":{"paper":{"title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Explicit per-entity memory maintains character consistency across long gaps in multi-shot video generation where existing methods fail.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Meng Wei, Ruozhen He, Vicente Ordonez, Ziyan Yang","submitted_at":"2026-05-14T17:59:55Z","abstract_excerpt":"Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and locations across shots remains a challenge over long sequences. Existing evaluations typically use independently generated prompt sets with limited entity coverage and simple consistency metrics, making standardized comparison difficult. We introduce EntityBench, a benchmark of 140 episodes (2,491 shots) derived from real narrative media, with explicit per-shot entity schedules tracking characters, objects, and locations simultaneously across easy / medi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments show that cross-shot entity consistency degrades sharply with recurrence distance in existing methods, and that explicit per-entity memory yields the highest character fidelity (Cohen's d = +2.33) and presence among methods evaluated.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The entity schedules extracted from real narrative media and the fidelity gate used for cross-shot scoring accurately reflect the consistency challenges faced by current video generation models.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EntityBench is a new benchmark with detailed per-shot entity schedules from real media, and the EntityMem baseline using persistent per-entity memory achieves the highest character fidelity with Cohen's d of +2.33.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Explicit per-entity memory maintains character consistency across long gaps in multi-shot video generation where existing methods fail.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"35bb8b75321305d5184577536cc9736b67cb7b05fe9916729bd8e6d449408a62"},"source":{"id":"2605.15199","kind":"arxiv","version":1},"verdict":{"id":"e0c0b10c-aa4b-4654-a2a7-fea1ceb01554","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:10:57.117220Z","strongest_claim":"Experiments show that cross-shot entity consistency degrades sharply with recurrence distance in existing methods, and that explicit per-entity memory yields the highest character fidelity (Cohen's d = +2.33) and presence among methods evaluated.","one_line_summary":"EntityBench is a new benchmark with detailed per-shot entity schedules from real media, and the EntityMem baseline using persistent per-entity memory achieves the highest character fidelity with Cohen's d of +2.33.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The entity schedules extracted from real narrative media and the fidelity gate used for cross-shot scoring accurately reflect the consistency challenges faced by current video generation models.","pith_extraction_headline":"Explicit per-entity memory maintains character consistency across long gaps in multi-shot video generation where existing methods fail."},"references":{"count":34,"sample":[{"doi":"","year":null,"title":"Mixture of contexts for long video generation","work_id":"b800ec2a-ab41-48e3-a98d-a26b4942bb2a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"SkyReels-V2: Infinite-length Film Generative Model","work_id":"2ce11350-273e-4f0d-ae78-292aa3151060","ref_index":2,"cited_arxiv_id":"2504.13074","is_internal_anchor":true},{"doi":"","year":null,"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","ref_index":3,"cited_arxiv_id":"2507.06261","is_internal_anchor":true},{"doi":"","year":null,"title":"Narrlv: Towards a comprehensive narrative-centric evaluation for long video generation.arXiv preprint arXiv:2507.11245,","work_id":"b79202ec-ba64-4d4f-b95e-af6e30e82a4a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Longvie: Multimodal-guided controllable ultra-long video generation","work_id":"3f0217fc-ba5b-4c51-a512-eb2300699c36","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":34,"snapshot_sha256":"d0d450de56368ede9848d269eaf894c7eff4050e0b1218171f67832999c978cf","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0b4ee4d44b3050f2a38465a68565b01c84409343b3d73d9f4762f016ad8284e4"},"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":"2605.15199","created_at":"2026-05-17T21:18:32.681023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15199v1","created_at":"2026-05-17T21:18:32.681023+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRW75HZRZFE2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRW75HZRZFE262S4","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRW75HZR","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y","json":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y.json","graph_json":"https://pith.science/api/pith-number/CRW75HZRZFE262S4FAMM6E4K4Y/graph.json","events_json":"https://pith.science/api/pith-number/CRW75HZRZFE262S4FAMM6E4K4Y/events.json","paper":"https://pith.science/paper/CRW75HZR"},"agent_actions":{"view_html":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y","download_json":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y.json","view_paper":"https://pith.science/paper/CRW75HZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15199&json=true","fetch_graph":"https://pith.science/api/pith-number/CRW75HZRZFE262S4FAMM6E4K4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/CRW75HZRZFE262S4FAMM6E4K4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/action/storage_attestation","attest_author":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/action/author_attestation","sign_citation":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/action/citation_signature","submit_replication":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/action/replication_record"}},"created_at":"2026-05-17T21:18:32.681023+00:00","updated_at":"2026-05-17T21:57:18.363516+00:00"}