{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2JPMMZB45P2RPTO3YBL24CA64V","short_pith_number":"pith:2JPMMZB4","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"},"canonical_sha256":"d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4","source":{"kind":"arxiv","id":"2605.07061","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07061","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07061v2","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07061","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"2JPMMZB45P2R","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"2JPMMZB45P2RPTO3","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"2JPMMZB4","created_at":"2026-06-02T01:03:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2JPMMZB45P2RPTO3YBL24CA64V","target":"record","payload":{"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"},"canonical_sha256":"d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4","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"},"source_kind":"arxiv","source_id":"2605.07061","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6f/jNEK9CeJXnKf+xwHLhlgRQS1e4R5EdwNRagoXTMliLd+0L97PittqSwOjs/sLpwLbUBar/UPfdYp4fzeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:05:42.796632Z"},"content_sha256":"cbc6d4fed15e2b345b58389c60a5c6a532988b654a59b8b6e65a644782fb9ee8","schema_version":"1.0","event_id":"sha256:cbc6d4fed15e2b345b58389c60a5c6a532988b654a59b8b6e65a644782fb9ee8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2JPMMZB45P2RPTO3YBL24CA64V","target":"graph","payload":{"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"},"verdict_id":"d561db9a-627d-436a-b72e-fabf49a89dbc"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKV8IwpwbWpqp/wv7VJM5+m7V4kue2pVzcX0B7+vy6GIyryPUcgUYpy4ihG+cInGGce0CCld9YtiKxyPSCiVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:05:42.797121Z"},"content_sha256":"cb2e6336c6b99fde3736cf5e6c8e1581ac6737c3ca2670edfd05723b0919fefd","schema_version":"1.0","event_id":"sha256:cb2e6336c6b99fde3736cf5e6c8e1581ac6737c3ca2670edfd05723b0919fefd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/bundle.json","state_url":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JPMMZB45P2RPTO3YBL24CA64V/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-12T18:05:42Z","links":{"resolver":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V","bundle":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/bundle.json","state":"https://pith.science/pith/2JPMMZB45P2RPTO3YBL24CA64V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JPMMZB45P2RPTO3YBL24CA64V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2JPMMZB45P2RPTO3YBL24CA64V","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":"05ade6be67c87e0afbc5def52126333fe90c0039e9d11a349f293546fa122a73","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-08T00:14:07Z","title_canon_sha256":"4a7c2f2bf6b98b0011dcc95f1171af3a36e8b98077585534e5620b173448414d"},"schema_version":"1.0","source":{"id":"2605.07061","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07061","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07061v2","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07061","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"2JPMMZB45P2R","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"2JPMMZB45P2RPTO3","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"2JPMMZB4","created_at":"2026-06-02T01:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:cb2e6336c6b99fde3736cf5e6c8e1581ac6737c3ca2670edfd05723b0919fefd","target":"graph","created_at":"2026-06-02T01:03:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Current joint audio-video generation models lack robust physical commonsense, especially during transitions and when prompted for impossible behaviors."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions."}],"snapshot_sha256":"ebe658fec31ff2c781ebf50f368fecf2e6b4c2d60806ef4cc6f38a5f4d4e24af"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4ee6fccf7e2543a11a4bd827a3535e436fdc46489d7d94694c2a61f634f88688"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.07061/integrity.json","findings":[],"snapshot_sha256":"26745d2109c6111bbf6a833bb8e0c1fb2184db7465cb7d2301cff55b0503fe36","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenming Ge, Feiyu Du, Hao Fang, Jiageng Liu, Mingwei Xu, Shijian Deng, Weiguo Pian, Xiulong Liu, Yapeng Tian, Zexin Xu, Zijun Cui","cross_cats":["cs.AI","cs.CV","cs.MM"],"headline":"Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-08T00:14:07Z","title":"Do Joint Audio-Video Generation Models Understand Physics?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07061","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T02:08:27.608016Z","id":"d561db9a-627d-436a-b72e-fabf49a89dbc","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions.","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.","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."}},"verdict_id":"d561db9a-627d-436a-b72e-fabf49a89dbc"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cbc6d4fed15e2b345b58389c60a5c6a532988b654a59b8b6e65a644782fb9ee8","target":"record","created_at":"2026-06-02T01:03:48Z","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":"05ade6be67c87e0afbc5def52126333fe90c0039e9d11a349f293546fa122a73","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-08T00:14:07Z","title_canon_sha256":"4a7c2f2bf6b98b0011dcc95f1171af3a36e8b98077585534e5620b173448414d"},"schema_version":"1.0","source":{"id":"2605.07061","kind":"arxiv","version":2}},"canonical_sha256":"d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4","first_computed_at":"2026-06-02T01:03:48.229439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:48.229439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TBY73r9PQx3IH5ZW35om0ub4jNreDkWLrNx+hPcsNRgok/GrLA+6bI1Q7ofZ35YjC0SLuz/Y+rUG1z4oDWZWDg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:48.229916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07061","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbc6d4fed15e2b345b58389c60a5c6a532988b654a59b8b6e65a644782fb9ee8","sha256:cb2e6336c6b99fde3736cf5e6c8e1581ac6737c3ca2670edfd05723b0919fefd"],"state_sha256":"11fea04129b16287b0c3cf44554b0904d0b32595c4df83d81b0b776493660bd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nCPYlrruCRkavZ9A5upxbjRbesOSPlLIxKCl+OrF+NM8us+ArfBeqspJO2DAkQ2l/2gB4jWMF4lbYrVTRNrnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T18:05:42.799445Z","bundle_sha256":"fbd71f191d0a6882a7a980e9a26086b7048d5b211e8bfbe56d16d938a14aba0f"}}