{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2JPMMZB45P2RPTO3YBL24CA64V","short_pith_number":"pith:2JPMMZB4","schema_version":"1.0","canonical_sha256":"d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4","source":{"kind":"arxiv","id":"2605.07061","version":2},"attestation_state":"computed","paper":{"title":"Do Joint Audio-Video Generation Models Understand Physics?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions.","cross_cats":["cs.AI","cs.CV","cs.MM"],"primary_cat":"cs.SD","authors_text":"Chenming Ge, Feiyu Du, Hao Fang, Jiageng Liu, Mingwei Xu, Shijian Deng, Weiguo Pian, Xiulong Liu, Yapeng Tian, Zexin Xu, Zijun Cui","submitted_at":"2026-05-08T00:14:07Z","abstract_excerpt":"Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency? We introduce AV-Phys Bench, a benchmark for evaluating physical commonsense in joint audio-video generation. AV-Phys Bench tests models across three scene categories: Steady State, Event Transition, and Environment Transition. It covers physics-grounded subcategories drawn from real-world scenes, plus Anti-AV-Physics prompts that deliberately request p"},"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":true},"canonical_record":{"source":{"id":"2605.07061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-08T00:14:07Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"title_canon_sha256":"4a7c2f2bf6b98b0011dcc95f1171af3a36e8b98077585534e5620b173448414d","abstract_canon_sha256":"05ade6be67c87e0afbc5def52126333fe90c0039e9d11a349f293546fa122a73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:48.229916Z","signature_b64":"TBY73r9PQx3IH5ZW35om0ub4jNreDkWLrNx+hPcsNRgok/GrLA+6bI1Q7ofZ35YjC0SLuz/Y+rUG1z4oDWZWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4","last_reissued_at":"2026-06-02T01:03:48.229439Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:48.229439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Joint Audio-Video Generation Models Understand Physics?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions.","cross_cats":["cs.AI","cs.CV","cs.MM"],"primary_cat":"cs.SD","authors_text":"Chenming Ge, Feiyu Du, Hao Fang, Jiageng Liu, Mingwei Xu, Shijian Deng, Weiguo Pian, Xiulong Liu, Yapeng Tian, Zexin Xu, Zijun Cui","submitted_at":"2026-05-08T00:14:07Z","abstract_excerpt":"Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency? We introduce AV-Phys Bench, a benchmark for evaluating physical commonsense in joint audio-video generation. AV-Phys Bench tests models across three scene categories: Steady State, Event Transition, and Environment Transition. It covers physics-grounded subcategories drawn from real-world scenes, plus Anti-AV-Physics prompts that deliberately request p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across three proprietary and four open-source models, we find that Seedance 2.0 performs best overall, but all models remain far from robust physical understanding. Performance drops sharply on event-driven and environment-driven transitions, and even strong proprietary systems collapse on Anti-AV-Physics prompts.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the five evaluation dimensions (visual/audio semantic adherence, visual/audio physical commonsense, cross-modal physical commonsense) together constitute a sufficient and unbiased measure of physical understanding without requiring additional human validation or external physics simulators.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Current joint audio-video generation models lack robust physical commonsense, especially during transitions and when prompted for impossible behaviors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ebe658fec31ff2c781ebf50f368fecf2e6b4c2d60806ef4cc6f38a5f4d4e24af"},"source":{"id":"2605.07061","kind":"arxiv","version":2},"verdict":{"id":"d561db9a-627d-436a-b72e-fabf49a89dbc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T02:08:27.608016Z","strongest_claim":"Across three proprietary and four open-source models, we find that Seedance 2.0 performs best overall, but all models remain far from robust physical understanding. Performance drops sharply on event-driven and environment-driven transitions, and even strong proprietary systems collapse on Anti-AV-Physics prompts.","one_line_summary":"Current joint audio-video generation models lack robust physical commonsense, especially during transitions and when prompted for impossible behaviors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the five evaluation dimensions (visual/audio semantic adherence, visual/audio physical commonsense, cross-modal physical commonsense) together constitute a sufficient and unbiased measure of physical understanding without requiring additional human validation or external physics simulators.","pith_extraction_headline":"Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07061/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T11:42:03.394008Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T06:37:10.217339Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.744647Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:09:37.526702Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"26745d2109c6111bbf6a833bb8e0c1fb2184db7465cb7d2301cff55b0503fe36"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4ee6fccf7e2543a11a4bd827a3535e436fdc46489d7d94694c2a61f634f88688"},"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":"2605.07061","created_at":"2026-06-02T01:03:48.229514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.07061v2","created_at":"2026-06-02T01:03:48.229514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07061","created_at":"2026-06-02T01:03:48.229514+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JPMMZB45P2R","created_at":"2026-06-02T01:03:48.229514+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JPMMZB45P2RPTO3","created_at":"2026-06-02T01:03:48.229514+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JPMMZB4","created_at":"2026-06-02T01:03:48.229514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V","json":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V.json","graph_json":"https://pith.science/api/pith-number/2JPMMZB45P2RPTO3YBL24CA64V/graph.json","events_json":"https://pith.science/api/pith-number/2JPMMZB45P2RPTO3YBL24CA64V/events.json","paper":"https://pith.science/paper/2JPMMZB4"},"agent_actions":{"view_html":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V","download_json":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V.json","view_paper":"https://pith.science/paper/2JPMMZB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.07061&json=true","fetch_graph":"https://pith.science/api/pith-number/2JPMMZB45P2RPTO3YBL24CA64V/graph.json","fetch_events":"https://pith.science/api/pith-number/2JPMMZB45P2RPTO3YBL24CA64V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/action/storage_attestation","attest_author":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/action/author_attestation","sign_citation":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/action/citation_signature","submit_replication":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/action/replication_record"}},"created_at":"2026-06-02T01:03:48.229514+00:00","updated_at":"2026-06-02T01:03:48.229514+00:00"}