{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5ZKBXQEUPCYZKRZEKOPRMZSR4C","short_pith_number":"pith:5ZKBXQEU","schema_version":"1.0","canonical_sha256":"ee541bc09478b1954724539f166651e0856d6d7d6c3ff416a7daf72fe590fbaf","source":{"kind":"arxiv","id":"2605.23610","version":1},"attestation_state":"computed","paper":{"title":"EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun-Hao P. Huang, Hyeonho Jeong, Jente Vandersanden, Matheus Gadelha, Yulia Gryaditskaya","submitted_at":"2026-05-22T13:20:29Z","abstract_excerpt":"Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory. However, full-frame storage entangles persistent entity information with transient scene context, leading to irrelevant information leakage and high computational cost. We propose an entity-centric memory in the form of an entity-indexed bank of latent patches. We introduce sparse token conditioning compatible with pretrained models, restricting self-attentio"},"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":"2605.23610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T13:20:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55d0ddd9b015c6138a44cb6365b2ef5f8c9047dfa9008edb05326efa2e4feb67","abstract_canon_sha256":"9079a323056e21c9cbd20028ca7368be3727e76b67168fe9f436579ce3acb06c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:22.011762Z","signature_b64":"+mcuoHvH/wLack0yaFY6MGfU6NNUMlBN9efkHlOqjGWTH1IN4xoQ3CuLT5PPf/84mdMa8V4+V4Ysi4PckcR5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee541bc09478b1954724539f166651e0856d6d7d6c3ff416a7daf72fe590fbaf","last_reissued_at":"2026-05-25T02:02:22.011006Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:22.011006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun-Hao P. Huang, Hyeonho Jeong, Jente Vandersanden, Matheus Gadelha, Yulia Gryaditskaya","submitted_at":"2026-05-22T13:20:29Z","abstract_excerpt":"Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory. However, full-frame storage entangles persistent entity information with transient scene context, leading to irrelevant information leakage and high computational cost. We propose an entity-centric memory in the form of an entity-indexed bank of latent patches. We introduce sparse token conditioning compatible with pretrained models, restricting self-attentio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23610","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/2605.23610/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":"2605.23610","created_at":"2026-05-25T02:02:22.011118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23610v1","created_at":"2026-05-25T02:02:22.011118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23610","created_at":"2026-05-25T02:02:22.011118+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZKBXQEUPCYZ","created_at":"2026-05-25T02:02:22.011118+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZKBXQEUPCYZKRZE","created_at":"2026-05-25T02:02:22.011118+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZKBXQEU","created_at":"2026-05-25T02:02:22.011118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C","json":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C.json","graph_json":"https://pith.science/api/pith-number/5ZKBXQEUPCYZKRZEKOPRMZSR4C/graph.json","events_json":"https://pith.science/api/pith-number/5ZKBXQEUPCYZKRZEKOPRMZSR4C/events.json","paper":"https://pith.science/paper/5ZKBXQEU"},"agent_actions":{"view_html":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C","download_json":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C.json","view_paper":"https://pith.science/paper/5ZKBXQEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23610&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZKBXQEUPCYZKRZEKOPRMZSR4C/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZKBXQEUPCYZKRZEKOPRMZSR4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C/action/storage_attestation","attest_author":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C/action/author_attestation","sign_citation":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C/action/citation_signature","submit_replication":"https://pith.science/pith/5ZKBXQEUPCYZKRZEKOPRMZSR4C/action/replication_record"}},"created_at":"2026-05-25T02:02:22.011118+00:00","updated_at":"2026-05-25T02:02:22.011118+00:00"}