{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QZHGDGY5MONL7W3QDRRPVKPCZF","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":"83b04c297d02a76e69bbdd2fc8011e49da689e8baff5fb04888cbe4e8d83894e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T17:53:55Z","title_canon_sha256":"b4d4e607042f238c532416db55fe035258b10e6a1cbcb0f0ac330c9234df5dc9"},"schema_version":"1.0","source":{"id":"2406.03520","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03520","created_at":"2026-05-20T11:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03520v2","created_at":"2026-05-20T11:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03520","created_at":"2026-05-20T11:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"QZHGDGY5MONL","created_at":"2026-05-20T11:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"QZHGDGY5MONL7W3Q","created_at":"2026-05-20T11:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"QZHGDGY5","created_at":"2026-05-20T11:29:15Z"}],"graph_snapshots":[{"event_id":"sha256:72aeddbfc25bd5d45b22b7d5be01265de4a5cd98f19d8fccd69f8970d69869fc","target":"graph","created_at":"2026-05-20T11:29:15Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.03520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in internet-scale video data pretraining have led to the development of text-to-video generative models that can create high-quality videos across a broad range of visual concepts, synthesize realistic motions and render complex objects. Hence, these generative models have the potential to become general-purpose simulators of the physical world. However, it is unclear how far we are from this goal with the existing text-to-video generative models. To this end, we present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-w","authors_text":"Aditya Grover, Chenfanfu Jiang, Hritik Bansal, Kai-Wei Chang, Michal Yarom, Tianyi Xie, Yizhou Sun, Yonatan Bitton, Zeshun Zong, Zongyu Lin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T17:53:55Z","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03520","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:64befa55b25223a5a3fb736a8f596c63ac1476fdb381edd67ecb01898f864f4b","target":"record","created_at":"2026-05-20T11:29:15Z","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":"83b04c297d02a76e69bbdd2fc8011e49da689e8baff5fb04888cbe4e8d83894e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T17:53:55Z","title_canon_sha256":"b4d4e607042f238c532416db55fe035258b10e6a1cbcb0f0ac330c9234df5dc9"},"schema_version":"1.0","source":{"id":"2406.03520","kind":"arxiv","version":2}},"canonical_sha256":"864e619b1d639abfdb701c62faa9e2c950004bc41a794f94cc86693d88222244","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"864e619b1d639abfdb701c62faa9e2c950004bc41a794f94cc86693d88222244","first_computed_at":"2026-05-20T11:29:15.601937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T11:29:15.601937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ioYsTgt5h8J/CHEYT3D5wWsqjqdzCCwvRWs8jk0WdSs9MN+dPYmUUYrzeLKJOomi3zBNm+FrFXOWnreBWRY+Cg==","signature_status":"signed_v1","signed_at":"2026-05-20T11:29:15.602621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03520","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64befa55b25223a5a3fb736a8f596c63ac1476fdb381edd67ecb01898f864f4b","sha256:72aeddbfc25bd5d45b22b7d5be01265de4a5cd98f19d8fccd69f8970d69869fc"],"state_sha256":"3b56eda8a459b59a12dea68cc5b95b6342b70f2b523935a74c8c0bdaa8412227"}