{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DBWNANPBERMIS3PZZFHPY7JOKY","short_pith_number":"pith:DBWNANPB","schema_version":"1.0","canonical_sha256":"186cd035e12458896df9c94efc7d2e560cdf8c3477541555872347153f7e37ca","source":{"kind":"arxiv","id":"2603.13402","version":3},"attestation_state":"computed","paper":{"title":"Event-Driven Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chika Maduabuchi, Jindong Wang","submitted_at":"2026-03-12T00:16:56Z","abstract_excerpt":"Current text-to-video models can make individual frames look convincing while still getting simple interactions wrong: objects move before contact, an intended action is skipped, a placed object keeps drifting, or a support relation breaks. Our starting point is that standard frame-first denoising updates every latent region at every step, even when the prompt implies that only a local interaction should be active. We introduce Event-Driven Video Generation (EVD), a small DiT-compatible intervention that gives the sampler an explicit event signal. A lightweight head predicts token-level event "},"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":"2603.13402","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T00:16:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88f85304bf2cfee29cd39edc1f00dbeb8e35de61329ba0f2e1bf2e577686308d","abstract_canon_sha256":"263ab275e4ef764d511a9fab5ea0f1aea91607d457d9adc7536d6bc0090df4f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:10.791620Z","signature_b64":"3HLCltnKFWCRPWkufI90cqOndgKbV3+BxPICefDfl9QNRm3A+hfmU/+imLw4GExB1u979WQbhQ2bPuntEv7DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"186cd035e12458896df9c94efc7d2e560cdf8c3477541555872347153f7e37ca","last_reissued_at":"2026-07-01T00:17:10.790987Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:10.790987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Event-Driven Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chika Maduabuchi, Jindong Wang","submitted_at":"2026-03-12T00:16:56Z","abstract_excerpt":"Current text-to-video models can make individual frames look convincing while still getting simple interactions wrong: objects move before contact, an intended action is skipped, a placed object keeps drifting, or a support relation breaks. Our starting point is that standard frame-first denoising updates every latent region at every step, even when the prompt implies that only a local interaction should be active. We introduce Event-Driven Video Generation (EVD), a small DiT-compatible intervention that gives the sampler an explicit event signal. A lightweight head predicts token-level event "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.13402","kind":"arxiv","version":3},"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/2603.13402/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":"2603.13402","created_at":"2026-07-01T00:17:10.791055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.13402v3","created_at":"2026-07-01T00:17:10.791055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.13402","created_at":"2026-07-01T00:17:10.791055+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBWNANPBERMI","created_at":"2026-07-01T00:17:10.791055+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBWNANPBERMIS3PZ","created_at":"2026-07-01T00:17:10.791055+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBWNANPB","created_at":"2026-07-01T00:17:10.791055+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/DBWNANPBERMIS3PZZFHPY7JOKY","json":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY.json","graph_json":"https://pith.science/api/pith-number/DBWNANPBERMIS3PZZFHPY7JOKY/graph.json","events_json":"https://pith.science/api/pith-number/DBWNANPBERMIS3PZZFHPY7JOKY/events.json","paper":"https://pith.science/paper/DBWNANPB"},"agent_actions":{"view_html":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY","download_json":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY.json","view_paper":"https://pith.science/paper/DBWNANPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.13402&json=true","fetch_graph":"https://pith.science/api/pith-number/DBWNANPBERMIS3PZZFHPY7JOKY/graph.json","fetch_events":"https://pith.science/api/pith-number/DBWNANPBERMIS3PZZFHPY7JOKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY/action/storage_attestation","attest_author":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY/action/author_attestation","sign_citation":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY/action/citation_signature","submit_replication":"https://pith.science/pith/DBWNANPBERMIS3PZZFHPY7JOKY/action/replication_record"}},"created_at":"2026-07-01T00:17:10.791055+00:00","updated_at":"2026-07-01T00:17:10.791055+00:00"}