{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QZHGDGY5MONL7W3QDRRPVKPCZF","short_pith_number":"pith:QZHGDGY5","schema_version":"1.0","canonical_sha256":"864e619b1d639abfdb701c62faa9e2c950004bc41a794f94cc86693d88222244","source":{"kind":"arxiv","id":"2406.03520","version":2},"attestation_state":"computed","paper":{"title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Chenfanfu Jiang, Hritik Bansal, Kai-Wei Chang, Michal Yarom, Tianyi Xie, Yizhou Sun, Yonatan Bitton, Zeshun Zong, Zongyu Lin","submitted_at":"2024-06-05T17:53:55Z","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"},"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":"2406.03520","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T17:53:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b4d4e607042f238c532416db55fe035258b10e6a1cbcb0f0ac330c9234df5dc9","abstract_canon_sha256":"83b04c297d02a76e69bbdd2fc8011e49da689e8baff5fb04888cbe4e8d83894e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T11:29:15.602621Z","signature_b64":"ioYsTgt5h8J/CHEYT3D5wWsqjqdzCCwvRWs8jk0WdSs9MN+dPYmUUYrzeLKJOomi3zBNm+FrFXOWnreBWRY+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"864e619b1d639abfdb701c62faa9e2c950004bc41a794f94cc86693d88222244","last_reissued_at":"2026-05-20T11:29:15.601937Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T11:29:15.601937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Chenfanfu Jiang, Hritik Bansal, Kai-Wei Chang, Michal Yarom, Tianyi Xie, Yizhou Sun, Yonatan Bitton, Zeshun Zong, Zongyu Lin","submitted_at":"2024-06-05T17:53:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03520","kind":"arxiv","version":2},"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/2406.03520/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":"2406.03520","created_at":"2026-05-20T11:29:15.602026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03520v2","created_at":"2026-05-20T11:29:15.602026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03520","created_at":"2026-05-20T11:29:15.602026+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZHGDGY5MONL","created_at":"2026-05-20T11:29:15.602026+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZHGDGY5MONL7W3Q","created_at":"2026-05-20T11:29:15.602026+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZHGDGY5","created_at":"2026-05-20T11:29:15.602026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2603.21002","citing_title":"SURF: Signature-Retained Fast Video Generation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01843","citing_title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18743","citing_title":"WorldString: Actionable World Representation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18233","citing_title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18396","citing_title":"NEWTON: Agentic Planning for Physically Grounded Video Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18743","citing_title":"WorldString: Actionable World Representation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15391","citing_title":"PanoWorld: Geometry-Consistent Panoramic Video World Modeling","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2410.05363","citing_title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2510.20206","citing_title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13281","citing_title":"VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09030","citing_title":"PlayWorld: Learning Robot World Models from Autonomous Play","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15185","citing_title":"Quantitative Video World Model Evaluation for Geometric-Consistency","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2505.13211","citing_title":"MAGI-1: Autoregressive Video Generation at Scale","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04029","citing_title":"ATSS: Detecting AI-Generated Videos via Anomalous Temporal Self-Similarity","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":212,"is_internal_anchor":true},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10806","citing_title":"PhyGround: Benchmarking Physical Reasoning in Generative World Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00630","citing_title":"CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07348","citing_title":"MoRight: Motion Control Done Right","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07061","citing_title":"Do Joint Audio-Video Generation Models Understand Physics?","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF","json":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF.json","graph_json":"https://pith.science/api/pith-number/QZHGDGY5MONL7W3QDRRPVKPCZF/graph.json","events_json":"https://pith.science/api/pith-number/QZHGDGY5MONL7W3QDRRPVKPCZF/events.json","paper":"https://pith.science/paper/QZHGDGY5"},"agent_actions":{"view_html":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF","download_json":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF.json","view_paper":"https://pith.science/paper/QZHGDGY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03520&json=true","fetch_graph":"https://pith.science/api/pith-number/QZHGDGY5MONL7W3QDRRPVKPCZF/graph.json","fetch_events":"https://pith.science/api/pith-number/QZHGDGY5MONL7W3QDRRPVKPCZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF/action/storage_attestation","attest_author":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF/action/author_attestation","sign_citation":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF/action/citation_signature","submit_replication":"https://pith.science/pith/QZHGDGY5MONL7W3QDRRPVKPCZF/action/replication_record"}},"created_at":"2026-05-20T11:29:15.602026+00:00","updated_at":"2026-05-20T11:29:15.602026+00:00"}