{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N5A4EID6PZCXUMUUENVXNROFJW","short_pith_number":"pith:N5A4EID6","schema_version":"1.0","canonical_sha256":"6f41c2207e7e457a3294236b76c5c54db6cf8035701f0ca3131b9604707512a5","source":{"kind":"arxiv","id":"2605.30346","version":1},"attestation_state":"computed","paper":{"title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie-Ying Lee, Kaipeng Zhang, You-Zhe Xie, Yu-Hsuan Li, Yu-Lun Liu, Zhixiang Wang","submitted_at":"2026-05-28T17:59:51Z","abstract_excerpt":"As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistical temporal patterns? Existing benchmarks mostly rely on synthetic data, limiting real-world generalization due to the sim-to-real gap. We present YoCausal, a two-level benchmark inspired by the Violation of Expectation (VoE) paradigm from cognitive science. By temporally reversing real-world videos at zero cost as natural counterfactual samples, YoCausal establishes an arbitrarily extensible evaluation protocol. Level 1 introduces the Reverse S"},"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":"2605.30346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"d179a031dbea3dd4f7f514369af79cb69d1d6b7982566ecbcb45e7b5d92df652","abstract_canon_sha256":"ec3ba68f2522283e9bff39f0f455d7aa65e99e8dbe84eaa553fe7d3c7c837c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:17.205334Z","signature_b64":"2UTyKmyb1fkZEekILxYKDcYExAES4K+zRSImV0eNRoAJv6SkgKWShqmDxCjgSSzdwVEQXRaM8BDtOqb8JRplCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f41c2207e7e457a3294236b76c5c54db6cf8035701f0ca3131b9604707512a5","last_reissued_at":"2026-05-29T02:06:17.204886Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:17.204886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie-Ying Lee, Kaipeng Zhang, You-Zhe Xie, Yu-Hsuan Li, Yu-Lun Liu, Zhixiang Wang","submitted_at":"2026-05-28T17:59:51Z","abstract_excerpt":"As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistical temporal patterns? Existing benchmarks mostly rely on synthetic data, limiting real-world generalization due to the sim-to-real gap. We present YoCausal, a two-level benchmark inspired by the Violation of Expectation (VoE) paradigm from cognitive science. By temporally reversing real-world videos at zero cost as natural counterfactual samples, YoCausal establishes an arbitrarily extensible evaluation protocol. Level 1 introduces the Reverse S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30346","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/2605.30346/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":"2605.30346","created_at":"2026-05-29T02:06:17.204943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30346v1","created_at":"2026-05-29T02:06:17.204943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30346","created_at":"2026-05-29T02:06:17.204943+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5A4EID6PZCX","created_at":"2026-05-29T02:06:17.204943+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5A4EID6PZCXUMUU","created_at":"2026-05-29T02:06:17.204943+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5A4EID6","created_at":"2026-05-29T02:06:17.204943+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/N5A4EID6PZCXUMUUENVXNROFJW","json":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW.json","graph_json":"https://pith.science/api/pith-number/N5A4EID6PZCXUMUUENVXNROFJW/graph.json","events_json":"https://pith.science/api/pith-number/N5A4EID6PZCXUMUUENVXNROFJW/events.json","paper":"https://pith.science/paper/N5A4EID6"},"agent_actions":{"view_html":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW","download_json":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW.json","view_paper":"https://pith.science/paper/N5A4EID6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30346&json=true","fetch_graph":"https://pith.science/api/pith-number/N5A4EID6PZCXUMUUENVXNROFJW/graph.json","fetch_events":"https://pith.science/api/pith-number/N5A4EID6PZCXUMUUENVXNROFJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW/action/storage_attestation","attest_author":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW/action/author_attestation","sign_citation":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW/action/citation_signature","submit_replication":"https://pith.science/pith/N5A4EID6PZCXUMUUENVXNROFJW/action/replication_record"}},"created_at":"2026-05-29T02:06:17.204943+00:00","updated_at":"2026-05-29T02:06:17.204943+00:00"}