{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U53XFOSQRAKKUD7Y4QLYNE4FBB","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":"67b677307285d2821e404243c3164c5b0c81ee4beefc0309545aad7ecf6fda4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-01T02:34:19Z","title_canon_sha256":"9da7080edd88062f561402164d7ec1baaf65fd436096dfd63afad93885d2baad"},"schema_version":"1.0","source":{"id":"2504.00369","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00369","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00369v2","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00369","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"U53XFOSQRAKK","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"U53XFOSQRAKKUD7Y","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"U53XFOSQ","created_at":"2026-07-05T11:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:75f601e600b85d7ed92efbe7756ab0aa81041085882a46ecbe1e36ea12bbda54","target":"graph","created_at":"2026-07-05T11:18:42Z","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/2504.00369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio Language Models (LALMs), where pretrained text LLMs are finetuned with audio input, have made remarkable progress in music understanding. However, current evaluation methodologies exhibit critical limitations: on the leading Music Question Answering benchmark, MuchoMusic, text-only LLMs without audio perception capabilities achieve surprisingly high accuracy of up to 56.4%, on par or above most LALMs. Furthermore, when presented with random Gaussian noise instead of actual audio, LALMs still perform significantly above chance. These findings suggest existing benchmarks predominantl","authors_text":"Julian McAuley, Sean O'Brien, Taylor Berg-Kirkpatrick, Yongyi Zang, Zachary Novack","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-01T02:34:19Z","title":"Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00369","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":"sha256:58d4b20c9879c89179c24ec7306a008e112daa0b8badfe7a7d8519a643aa26c3","target":"record","created_at":"2026-07-05T11:18:42Z","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":"67b677307285d2821e404243c3164c5b0c81ee4beefc0309545aad7ecf6fda4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-01T02:34:19Z","title_canon_sha256":"9da7080edd88062f561402164d7ec1baaf65fd436096dfd63afad93885d2baad"},"schema_version":"1.0","source":{"id":"2504.00369","kind":"arxiv","version":2}},"canonical_sha256":"a77772ba508814aa0ff8e4178693850843fde168ccfcc6574443876f4fbed5f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a77772ba508814aa0ff8e4178693850843fde168ccfcc6574443876f4fbed5f4","first_computed_at":"2026-07-05T11:18:42.546456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:42.546456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+b3QaOvM/H0YasOQSbh2Y/hsFNZUN+Oo06AdbxCUdE448IN+f85vQy/7CMlyoPbGr+piwAOFks3drFSkxbqwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:42.546874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00369","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58d4b20c9879c89179c24ec7306a008e112daa0b8badfe7a7d8519a643aa26c3","sha256:75f601e600b85d7ed92efbe7756ab0aa81041085882a46ecbe1e36ea12bbda54"],"state_sha256":"025c13fc8587b75004218f2975a2a24aee2c928a9f1081d81afa9704d59a6f1f"}