{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BTNKSU7F3WJ2NMDXOXSOXQC37C","short_pith_number":"pith:BTNKSU7F","schema_version":"1.0","canonical_sha256":"0cdaa953e5dd93a6b07775e4ebc05bf89c0e7b5e34a405778c035c859b8fb088","source":{"kind":"arxiv","id":"2401.09774","version":1},"attestation_state":"computed","paper":{"title":"On the Audio Hallucinations in Large Audio-Video Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Masayoshi Kondo, Shota Nakada, Taichi Nishimura","submitted_at":"2024-01-18T07:50:07Z","abstract_excerpt":"Large audio-video language models can generate descriptions for both video and audio. However, they sometimes ignore audio content, producing audio descriptions solely reliant on visual information. This paper refers to this as audio hallucinations and analyzes them in large audio-video language models. We gather 1,000 sentences by inquiring about audio information and annotate them whether they contain hallucinations. If a sentence is hallucinated, we also categorize the type of hallucination. The results reveal that 332 sentences are hallucinated with distinct trends observed in nouns and ve"},"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":"2401.09774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-18T07:50:07Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"ec8a08fa162f9dd864fdafad8e86be3cc1c026ae7ad60ddf44e0cb7513127009","abstract_canon_sha256":"85935c5ec11fcab79c13cd8b4c08e71cbde40ae0eb668f4f792354f496c332ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:02.117465Z","signature_b64":"/i8f+n8XRYhRlbRtxoaS5tQmJg8xIZx+rtI8z2nFOpMCMLLa90ALUM6IRGL9lBF8yHAHidLCdu2CTdv3v7tsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cdaa953e5dd93a6b07775e4ebc05bf89c0e7b5e34a405778c035c859b8fb088","last_reissued_at":"2026-07-05T07:35:02.116967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:02.116967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Audio Hallucinations in Large Audio-Video Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Masayoshi Kondo, Shota Nakada, Taichi Nishimura","submitted_at":"2024-01-18T07:50:07Z","abstract_excerpt":"Large audio-video language models can generate descriptions for both video and audio. However, they sometimes ignore audio content, producing audio descriptions solely reliant on visual information. This paper refers to this as audio hallucinations and analyzes them in large audio-video language models. We gather 1,000 sentences by inquiring about audio information and annotate them whether they contain hallucinations. If a sentence is hallucinated, we also categorize the type of hallucination. The results reveal that 332 sentences are hallucinated with distinct trends observed in nouns and ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09774","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/2401.09774/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":"2401.09774","created_at":"2026-07-05T07:35:02.117025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09774v1","created_at":"2026-07-05T07:35:02.117025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09774","created_at":"2026-07-05T07:35:02.117025+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTNKSU7F3WJ2","created_at":"2026-07-05T07:35:02.117025+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTNKSU7F3WJ2NMDX","created_at":"2026-07-05T07:35:02.117025+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTNKSU7F","created_at":"2026-07-05T07:35:02.117025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10815","citing_title":"Probing Cross-modal Information Hubs in Audio-Visual LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10815","citing_title":"Probing Cross-modal Information Hubs in Audio-Visual LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14129","citing_title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C","json":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C.json","graph_json":"https://pith.science/api/pith-number/BTNKSU7F3WJ2NMDXOXSOXQC37C/graph.json","events_json":"https://pith.science/api/pith-number/BTNKSU7F3WJ2NMDXOXSOXQC37C/events.json","paper":"https://pith.science/paper/BTNKSU7F"},"agent_actions":{"view_html":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C","download_json":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C.json","view_paper":"https://pith.science/paper/BTNKSU7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09774&json=true","fetch_graph":"https://pith.science/api/pith-number/BTNKSU7F3WJ2NMDXOXSOXQC37C/graph.json","fetch_events":"https://pith.science/api/pith-number/BTNKSU7F3WJ2NMDXOXSOXQC37C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/action/storage_attestation","attest_author":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/action/author_attestation","sign_citation":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/action/citation_signature","submit_replication":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/action/replication_record"}},"created_at":"2026-07-05T07:35:02.117025+00:00","updated_at":"2026-07-05T07:35:02.117025+00:00"}