{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BTNKSU7F3WJ2NMDXOXSOXQC37C","short_pith_number":"pith:BTNKSU7F","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"},"canonical_sha256":"0cdaa953e5dd93a6b07775e4ebc05bf89c0e7b5e34a405778c035c859b8fb088","source":{"kind":"arxiv","id":"2401.09774","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09774","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09774v1","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09774","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"BTNKSU7F3WJ2","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"BTNKSU7F3WJ2NMDX","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"BTNKSU7F","created_at":"2026-07-05T07:35:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BTNKSU7F3WJ2NMDXOXSOXQC37C","target":"record","payload":{"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"},"canonical_sha256":"0cdaa953e5dd93a6b07775e4ebc05bf89c0e7b5e34a405778c035c859b8fb088","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"},"source_kind":"arxiv","source_id":"2401.09774","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+yLhJ9BSkmmeNrcGs7Rk5KeHX+YW5wlxhjiursDeB0qACdz9YMuxeKQII7WUtlt9l2ZDE2DYhg4WqgCBfvu6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:07:01.387578Z"},"content_sha256":"417dc5eb6c8da85cc4df123bd24eff632ad1c4aead3e3e61b459b17820955860","schema_version":"1.0","event_id":"sha256:417dc5eb6c8da85cc4df123bd24eff632ad1c4aead3e3e61b459b17820955860"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BTNKSU7F3WJ2NMDXOXSOXQC37C","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4RMASWPQ/rJ8lwr8WbEq9JhXmmVv3IxncH7kga+kZYsgNgodZe3gTkz8OGfiHiuyAZa4ZChJrB4OZ3OkSEZzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:07:01.387964Z"},"content_sha256":"48748197d5d4613a4b984b89725b9f37e59213750968c5644c5a48f26e9f4d9e","schema_version":"1.0","event_id":"sha256:48748197d5d4613a4b984b89725b9f37e59213750968c5644c5a48f26e9f4d9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/bundle.json","state_url":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/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":"2026-08-07T05:07:01Z","links":{"resolver":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C","bundle":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/bundle.json","state":"https://pith.science/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BTNKSU7F3WJ2NMDXOXSOXQC37C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BTNKSU7F3WJ2NMDXOXSOXQC37C","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":"85935c5ec11fcab79c13cd8b4c08e71cbde40ae0eb668f4f792354f496c332ca","cross_cats_sorted":["cs.CL","cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-18T07:50:07Z","title_canon_sha256":"ec8a08fa162f9dd864fdafad8e86be3cc1c026ae7ad60ddf44e0cb7513127009"},"schema_version":"1.0","source":{"id":"2401.09774","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09774","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09774v1","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09774","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"BTNKSU7F3WJ2","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"BTNKSU7F3WJ2NMDX","created_at":"2026-07-05T07:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"BTNKSU7F","created_at":"2026-07-05T07:35:02Z"}],"graph_snapshots":[{"event_id":"sha256:48748197d5d4613a4b984b89725b9f37e59213750968c5644c5a48f26e9f4d9e","target":"graph","created_at":"2026-07-05T07:35:02Z","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":[],"endpoint":"/pith/2401.09774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Masayoshi Kondo, Shota Nakada, Taichi Nishimura","cross_cats":["cs.CL","cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-18T07:50:07Z","title":"On the Audio Hallucinations in Large Audio-Video Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09774","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":"sha256:417dc5eb6c8da85cc4df123bd24eff632ad1c4aead3e3e61b459b17820955860","target":"record","created_at":"2026-07-05T07:35:02Z","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":"85935c5ec11fcab79c13cd8b4c08e71cbde40ae0eb668f4f792354f496c332ca","cross_cats_sorted":["cs.CL","cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-18T07:50:07Z","title_canon_sha256":"ec8a08fa162f9dd864fdafad8e86be3cc1c026ae7ad60ddf44e0cb7513127009"},"schema_version":"1.0","source":{"id":"2401.09774","kind":"arxiv","version":1}},"canonical_sha256":"0cdaa953e5dd93a6b07775e4ebc05bf89c0e7b5e34a405778c035c859b8fb088","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cdaa953e5dd93a6b07775e4ebc05bf89c0e7b5e34a405778c035c859b8fb088","first_computed_at":"2026-07-05T07:35:02.116967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:02.116967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/i8f+n8XRYhRlbRtxoaS5tQmJg8xIZx+rtI8z2nFOpMCMLLa90ALUM6IRGL9lBF8yHAHidLCdu2CTdv3v7tsBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:02.117465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09774","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:417dc5eb6c8da85cc4df123bd24eff632ad1c4aead3e3e61b459b17820955860","sha256:48748197d5d4613a4b984b89725b9f37e59213750968c5644c5a48f26e9f4d9e"],"state_sha256":"e5a843d0a8bc721c2d60b7029bd6859c4ac64dff8768437c9f81af717a2a14ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EcZ0wr6y1yesF86KDwoyRLZJJIANno/h0RXsgucR8s/g1t/oLGhbH1NckiSnMfgx3W3A/BVIfof0QVwPXe5uCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:07:01.390627Z","bundle_sha256":"1b677117900ebbb1755a5057f698173af9b1dfe89aad3049415419aae44a2c55"}}