{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5H7ZPBG7OWQCBEA6IKC6UK53EH","short_pith_number":"pith:5H7ZPBG7","schema_version":"1.0","canonical_sha256":"e9ff9784df75a020901e4285ea2bbb21caccff3b22e4c808a494062493088e70","source":{"kind":"arxiv","id":"2606.05161","version":1},"attestation_state":"computed","paper":{"title":"Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Daling Wang, Heng Guo, Shi Feng, Xiaocui Yang, Xi Wu, Yichen Gao, Yifei Zhang, Yiqun Zhang, Yujia Li, Zijing Wang","submitted_at":"2026-06-03T17:57:51Z","abstract_excerpt":"Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We examine this question using a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text, and measures the resulting shift in model preference. Across five ALMs and four conflict tasks, 64.1% of conflict samples show a sign flip: the same-audio branch prefers the audio-supported answer, whereas the joint branch prefers "},"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":"2606.05161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T17:57:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0cf2c8c7dc1ff38aaabbc06d40a853607775740285d4dbcb2ae150d21c7450db","abstract_canon_sha256":"2cc33cbdeb9a4bc371e8088bc4c03fce98d6d472c71150c18e8f62e208e202bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T02:07:54.520703Z","signature_b64":"ApcJCWjAlj2a7PCo2po4C1wuEUn9ukmuoRR4P1aTIG86AYG/qgSexrCqLdjR1dqRw8gQgx2XsTwuP2sFYPeVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ff9784df75a020901e4285ea2bbb21caccff3b22e4c808a494062493088e70","last_reissued_at":"2026-06-04T02:07:54.520069Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T02:07:54.520069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Daling Wang, Heng Guo, Shi Feng, Xiaocui Yang, Xi Wu, Yichen Gao, Yifei Zhang, Yiqun Zhang, Yujia Li, Zijing Wang","submitted_at":"2026-06-03T17:57:51Z","abstract_excerpt":"Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We examine this question using a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text, and measures the resulting shift in model preference. Across five ALMs and four conflict tasks, 64.1% of conflict samples show a sign flip: the same-audio branch prefers the audio-supported answer, whereas the joint branch prefers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05161","kind":"arxiv","version":1},"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/2606.05161/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":"2606.05161","created_at":"2026-06-04T02:07:54.520134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05161v1","created_at":"2026-06-04T02:07:54.520134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05161","created_at":"2026-06-04T02:07:54.520134+00:00"},{"alias_kind":"pith_short_12","alias_value":"5H7ZPBG7OWQC","created_at":"2026-06-04T02:07:54.520134+00:00"},{"alias_kind":"pith_short_16","alias_value":"5H7ZPBG7OWQCBEA6","created_at":"2026-06-04T02:07:54.520134+00:00"},{"alias_kind":"pith_short_8","alias_value":"5H7ZPBG7","created_at":"2026-06-04T02:07:54.520134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH","json":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH.json","graph_json":"https://pith.science/api/pith-number/5H7ZPBG7OWQCBEA6IKC6UK53EH/graph.json","events_json":"https://pith.science/api/pith-number/5H7ZPBG7OWQCBEA6IKC6UK53EH/events.json","paper":"https://pith.science/paper/5H7ZPBG7"},"agent_actions":{"view_html":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH","download_json":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH.json","view_paper":"https://pith.science/paper/5H7ZPBG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05161&json=true","fetch_graph":"https://pith.science/api/pith-number/5H7ZPBG7OWQCBEA6IKC6UK53EH/graph.json","fetch_events":"https://pith.science/api/pith-number/5H7ZPBG7OWQCBEA6IKC6UK53EH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH/action/storage_attestation","attest_author":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH/action/author_attestation","sign_citation":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH/action/citation_signature","submit_replication":"https://pith.science/pith/5H7ZPBG7OWQCBEA6IKC6UK53EH/action/replication_record"}},"created_at":"2026-06-04T02:07:54.520134+00:00","updated_at":"2026-06-04T02:07:54.520134+00:00"}