{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZRIENHZE6F4UH6RJNMYPYNTGUA","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":"c4e363e7cece37326b7f1859c36cf32f1ee07cf9122ce8a7f7d6dd83b8071fb9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-08T17:36:50Z","title_canon_sha256":"24aacf5bdae78fb77b952cb666bc524978945c40c26cbfd5c75a44558c11d3ef"},"schema_version":"1.0","source":{"id":"2506.07233","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07233","created_at":"2026-07-05T12:11:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07233v2","created_at":"2026-07-05T12:11:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07233","created_at":"2026-07-05T12:11:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZRIENHZE6F4U","created_at":"2026-07-05T12:11:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZRIENHZE6F4UH6RJ","created_at":"2026-07-05T12:11:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZRIENHZE","created_at":"2026-07-05T12:11:18Z"}],"graph_snapshots":[{"event_id":"sha256:51e49431188e41273ad1073ccc3691c6626b3ebf935f306ff90e8e3ee881ac0c","target":"graph","created_at":"2026-07-05T12:11:18Z","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/2506.07233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio-Language Models (LALMs) can take audio and text as the inputs and answer questions about the audio. While prior LALMs have shown strong performance on standard benchmarks, there has been alarming evidence that LALMs can hallucinate what is presented in the audio. To mitigate the hallucination of LALMs, we introduce Audio-Aware Decoding (AAD), a lightweight inference-time strategy that uses contrastive decoding to compare the token prediction logits with and without the audio context. By contrastive decoding, AAD promotes the tokens whose probability increases when the audio is pres","authors_text":"Cheng-Han Chiang, Hung-yi Lee, Ke-Han Lu, Tzu-Wen Hsu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-08T17:36:50Z","title":"Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07233","kind":"arxiv","version":2},"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":"sha256:14a8191e2b2e4e3ce0311b2d6198fc8802c922589dc4caccc858d8523a23d79e","target":"record","created_at":"2026-07-05T12:11:18Z","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":"c4e363e7cece37326b7f1859c36cf32f1ee07cf9122ce8a7f7d6dd83b8071fb9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-08T17:36:50Z","title_canon_sha256":"24aacf5bdae78fb77b952cb666bc524978945c40c26cbfd5c75a44558c11d3ef"},"schema_version":"1.0","source":{"id":"2506.07233","kind":"arxiv","version":2}},"canonical_sha256":"cc50469f24f17943fa296b30fc3666a00e4516898b35ec6b8238a81848102c6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc50469f24f17943fa296b30fc3666a00e4516898b35ec6b8238a81848102c6a","first_computed_at":"2026-07-05T12:11:18.582294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:18.582294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BVDA1WRmaiLDXYKfJrv6WGOwi+8kl5Xrf5Ca3qHyqy1k+ixGfJjA0Z6xf2RREBHDHHL7+eLv/py2SjntCIJ9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:18.582860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07233","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14a8191e2b2e4e3ce0311b2d6198fc8802c922589dc4caccc858d8523a23d79e","sha256:51e49431188e41273ad1073ccc3691c6626b3ebf935f306ff90e8e3ee881ac0c"],"state_sha256":"a9797d009722c9061f8f656fe6423b7dbd944507570227b07b9b57859ab55469"}