{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2DB2NHLMTVFSJTTDB4LN6UGISH","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":"e80f400cffa3467fb98e39335d4f948e952c8f7f22dc1114921a0c66c1156b6d","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T16:51:54Z","title_canon_sha256":"c440a51f1df740ef21fb14557b61df99fda4e07328bd883a62dc1d2b964467a2"},"schema_version":"1.0","source":{"id":"2406.08402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08402","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08402v1","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08402","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"2DB2NHLMTVFS","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"2DB2NHLMTVFSJTTD","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"2DB2NHLM","created_at":"2026-07-05T08:30:59Z"}],"graph_snapshots":[{"event_id":"sha256:ec52fa7200a4027ed160a46ba8d2bfe0f35da637edd6f1590981edeb941b766a","target":"graph","created_at":"2026-07-05T08:30:59Z","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/2406.08402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large audio-language models (LALMs) enhance traditional large language models by integrating audio perception capabilities, allowing them to tackle audio-related tasks. Previous research has primarily focused on assessing the performance of LALMs across various tasks, yet overlooking their reliability, particularly concerning issues like object hallucination. In our study, we introduce methods to assess the extent of object hallucination of publicly available LALMs. Our findings reveal that LALMs are comparable to specialized audio captioning models in their understanding of audio content, but","authors_text":"Chun-Yi Kuan, Hung-yi Lee, Wei-Ping Huang","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T16:51:54Z","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08402","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":"sha256:0f74f5bad530e145db61a8c11794670edf4c44907d48a119cfd54ba4c88d0505","target":"record","created_at":"2026-07-05T08:30:59Z","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":"e80f400cffa3467fb98e39335d4f948e952c8f7f22dc1114921a0c66c1156b6d","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T16:51:54Z","title_canon_sha256":"c440a51f1df740ef21fb14557b61df99fda4e07328bd883a62dc1d2b964467a2"},"schema_version":"1.0","source":{"id":"2406.08402","kind":"arxiv","version":1}},"canonical_sha256":"d0c3a69d6c9d4b24ce630f16df50c891e95c5e33988a0fd8ef4dc8d1d9364008","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0c3a69d6c9d4b24ce630f16df50c891e95c5e33988a0fd8ef4dc8d1d9364008","first_computed_at":"2026-07-05T08:30:59.262645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:59.262645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nT6GpfAm2TUKAQfhh3ZBITtHJq0PEjwg9ZnNzrEGujS0cKf2EJ7fOIDG+GgmIFrBV0zzm6LJtRCOKTRyeuwfCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:59.263042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f74f5bad530e145db61a8c11794670edf4c44907d48a119cfd54ba4c88d0505","sha256:ec52fa7200a4027ed160a46ba8d2bfe0f35da637edd6f1590981edeb941b766a"],"state_sha256":"adf0ddcf496cb017ae3915694cb69e0ddd8db58d655709f48ed439706c07edf9"}