{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CRW75HZRZFE262S4FAMM6E4K4Y","short_pith_number":"pith:CRW75HZR","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"},"canonical_sha256":"146dfe9f31c949af6a5c2818cf138ae635c727e7a65ae7d5e16baa7453d0e54f","source":{"kind":"arxiv","id":"2605.15199","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15199","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15199v1","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"CRW75HZRZFE2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CRW75HZRZFE262S4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CRW75HZR","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CRW75HZRZFE262S4FAMM6E4K4Y","target":"record","payload":{"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"},"canonical_sha256":"146dfe9f31c949af6a5c2818cf138ae635c727e7a65ae7d5e16baa7453d0e54f","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"},"source_kind":"arxiv","source_id":"2605.15199","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:18:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYXtNvI+I+AgChfXsbO6QIp/g54U+fYQNW7mUJQ2dfj8Z+4Wffv44w49f4vQ8O0QzOjuYQ6ZAewL+Yc0mp09CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T00:44:21.786528Z"},"content_sha256":"11fddb68ac3795ada108f97da1d0c6e56a9733543852a24fe28dd56e7c341df5","schema_version":"1.0","event_id":"sha256:11fddb68ac3795ada108f97da1d0c6e56a9733543852a24fe28dd56e7c341df5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CRW75HZRZFE262S4FAMM6E4K4Y","target":"graph","payload":{"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"},"verdict_id":"e0c0b10c-aa4b-4654-a2a7-fea1ceb01554"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zZCmG05qZIe8/CJ119MsZ+vkug5j80gX9wSBEXXjpoZdZYlOfBibAIxq0C/j+EbAvsJk3uQEIB7CHqTAJKwTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T00:44:21.787075Z"},"content_sha256":"18354780e70f1cb4fdc321634c1ea29b7d89f3cf6e3d2bb6d32835f83376c22f","schema_version":"1.0","event_id":"sha256:18354780e70f1cb4fdc321634c1ea29b7d89f3cf6e3d2bb6d32835f83376c22f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/bundle.json","state_url":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRW75HZRZFE262S4FAMM6E4K4Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T00:44:21Z","links":{"resolver":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y","bundle":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/bundle.json","state":"https://pith.science/pith/CRW75HZRZFE262S4FAMM6E4K4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRW75HZRZFE262S4FAMM6E4K4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CRW75HZRZFE262S4FAMM6E4K4Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4c96a559abd3ffc6454d3041f0dfedd22d0bdd44731caf3124aa9ab26cba1c57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:59:55Z","title_canon_sha256":"11d992f42dc4675222b71a4aea55c171ea04bf8e28a4ea7ab891a585ae23f18a"},"schema_version":"1.0","source":{"id":"2605.15199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15199","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15199v1","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"CRW75HZRZFE2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CRW75HZRZFE262S4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CRW75HZR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:18354780e70f1cb4fdc321634c1ea29b7d89f3cf6e3d2bb6d32835f83376c22f","target":"graph","created_at":"2026-05-17T21:57:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Explicit per-entity memory maintains character consistency across long gaps in multi-shot video generation where existing methods fail."}],"snapshot_sha256":"35bb8b75321305d5184577536cc9736b67cb7b05fe9916729bd8e6d449408a62"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0b4ee4d44b3050f2a38465a68565b01c84409343b3d73d9f4762f016ad8284e4"},"paper":{"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","authors_text":"Meng Wei, Ruozhen He, Vicente Ordonez, Ziyan Yang","cross_cats":["cs.AI"],"headline":"Explicit per-entity memory maintains character consistency across long gaps in multi-shot video generation where existing methods fail.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:59:55Z","title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation"},"references":{"count":34,"internal_anchors":9,"resolved_work":34,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Mixture of contexts for long video generation","work_id":"b800ec2a-ab41-48e3-a98d-a26b4942bb2a","year":null},{"cited_arxiv_id":"2504.13074","doi":"","is_internal_anchor":true,"ref_index":2,"title":"SkyReels-V2: Infinite-length Film Generative Model","work_id":"2ce11350-273e-4f0d-ae78-292aa3151060","year":null},{"cited_arxiv_id":"2507.06261","doi":"","is_internal_anchor":true,"ref_index":3,"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","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Narrlv: Towards a comprehensive narrative-centric evaluation for long video generation.arXiv preprint arXiv:2507.11245,","work_id":"b79202ec-ba64-4d4f-b95e-af6e30e82a4a","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Longvie: Multimodal-guided controllable ultra-long video generation","work_id":"3f0217fc-ba5b-4c51-a512-eb2300699c36","year":null}],"snapshot_sha256":"d0d450de56368ede9848d269eaf894c7eff4050e0b1218171f67832999c978cf"},"source":{"id":"2605.15199","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:10:57.117220Z","id":"e0c0b10c-aa4b-4654-a2a7-fea1ceb01554","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Explicit per-entity memory maintains character consistency across long gaps in multi-shot video generation where existing methods fail.","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.","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."}},"verdict_id":"e0c0b10c-aa4b-4654-a2a7-fea1ceb01554"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11fddb68ac3795ada108f97da1d0c6e56a9733543852a24fe28dd56e7c341df5","target":"record","created_at":"2026-05-17T21:18:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4c96a559abd3ffc6454d3041f0dfedd22d0bdd44731caf3124aa9ab26cba1c57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:59:55Z","title_canon_sha256":"11d992f42dc4675222b71a4aea55c171ea04bf8e28a4ea7ab891a585ae23f18a"},"schema_version":"1.0","source":{"id":"2605.15199","kind":"arxiv","version":1}},"canonical_sha256":"146dfe9f31c949af6a5c2818cf138ae635c727e7a65ae7d5e16baa7453d0e54f","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"146dfe9f31c949af6a5c2818cf138ae635c727e7a65ae7d5e16baa7453d0e54f","first_computed_at":"2026-05-17T21:40:24.971979Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:18.363405Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11fddb68ac3795ada108f97da1d0c6e56a9733543852a24fe28dd56e7c341df5","sha256:18354780e70f1cb4fdc321634c1ea29b7d89f3cf6e3d2bb6d32835f83376c22f"],"state_sha256":"fb0756abe988b41d39b77f1f4aa672da49d6645df5bed574c6132b832898634e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yw4zfEdMsuCS6i9DOlvwf8r558QjaRq/xXlOFD0VEfoanuiIUJnLYkiTWFO71KAcd5AMhLNDeGmJkM2/8n33Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T00:44:21.789856Z","bundle_sha256":"c8251db25833b380444dfa98afe01eb5dd9d604677c33b8e29610a4dc3617fa7"}}