{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HN3GWO7XATOIA36BHDWSAVDZXJ","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":"1fd692a43af4dbfe265c9f71763f446d16ca4de7cc5a489ad4b044c6d1037f02","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:00:19Z","title_canon_sha256":"52acd4cd7a1b8f90645672ba808d208d4cafa2473b1e943468196073837e18b4"},"schema_version":"1.0","source":{"id":"2605.16403","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16403","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16403v1","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16403","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"HN3GWO7XATOI","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"HN3GWO7XATOIA36B","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"HN3GWO7X","created_at":"2026-05-20T00:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:f6acd36c934c24d23ed9d1fc61dedcc33a43cbb627ac6d7ed53260d82ff22a4d","target":"graph","created_at":"2026-05-20T00:02:20Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T20:21:57.657330Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.601172Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16403/integrity.json","findings":[],"snapshot_sha256":"8dee41cc6b0bc83d045b13995bb79afab260e5582bc1bebc4978ac5f3c12001b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate acoustic information, rather than verifying the audio stream. This issue appears across both state-of-the-art open-source omni models and leading closed-source models from providers such as Google and OpenAI. We characterize this failure mode as an audio-visual Clever Hans effect, in which models appear (falsely) audio-grounded, but actually exploit visual-acoustic correlations without verifying whether the audio and","authors_text":"Muhao Chen, Peng Qi, Rui Cai, Tinghui Zhu, Wendi Li, Wenjie Jacky Mo, Xiaofei Wen, Xingyu Fu, Yanan Xie","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:00:19Z","title":"When Vision Speaks for Sound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16403","kind":"arxiv","version":1},"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":"sha256:1c7d4ba99bbb59fbb6247d1643ca787fb4f37fa433460f7e5e6bdd80f0732792","target":"record","created_at":"2026-05-20T00:02:20Z","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":"1fd692a43af4dbfe265c9f71763f446d16ca4de7cc5a489ad4b044c6d1037f02","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:00:19Z","title_canon_sha256":"52acd4cd7a1b8f90645672ba808d208d4cafa2473b1e943468196073837e18b4"},"schema_version":"1.0","source":{"id":"2605.16403","kind":"arxiv","version":1}},"canonical_sha256":"3b766b3bf704dc806fc138ed205479ba7e5b053fb469b4612ae46c7d6d59a249","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b766b3bf704dc806fc138ed205479ba7e5b053fb469b4612ae46c7d6d59a249","first_computed_at":"2026-05-20T00:02:20.585408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:20.585408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y5UwVa7Q4Ctnv/hsnkKBHLV9tNP7dAtCWWGqE+qNUjzn0BMdoti+M60OsmMXeZHLvLxkHVuEFXyen/T+9mnWDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:20.586169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16403","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c7d4ba99bbb59fbb6247d1643ca787fb4f37fa433460f7e5e6bdd80f0732792","sha256:f6acd36c934c24d23ed9d1fc61dedcc33a43cbb627ac6d7ed53260d82ff22a4d"],"state_sha256":"978ac39f23e244f7030e5ade3d3bc12fb656f788949ec97bf0f99bcc14ca66cf"}