{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IXHMVBOZHE33WYTBR6EJ2XCTZW","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":"24c6b2642aa9e77681cdd87a9855d4e76edbf8b1fb1cda4553ab2ef52ff29021","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T08:39:56Z","title_canon_sha256":"d0f2ba9b4f7e960a9a4367e1386ca5d05d1031971b3561fa21236db530336e23"},"schema_version":"1.0","source":{"id":"2606.31338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31338","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31338v1","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31338","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"IXHMVBOZHE33","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"IXHMVBOZHE33WYTB","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"IXHMVBOZ","created_at":"2026-07-01T01:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:b04e175e3df397629b1808b3a59c78cbd47b9310c35c6ff57825ee450c203aab","target":"graph","created_at":"2026-07-01T01:17:59Z","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/2606.31338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent music audio-language models achieve high accuracy on instrument question-answering benchmarks, but it remains unclear whether this reflects robust audio grounding or benchmark-specific shortcuts. In this paper, we introduce an OpenMIC-derived diagnostic benchmark sequence for instrument grounding in music audio-language models, extending binary instrument-presence QA to genre-prior-reduced examples, confusable instrument discrimination, longer audio context, and temporal localization. Across these settings, high binary QA accuracy often fails to predict model behavior: models can exhibi","authors_text":"Hyoeun Kim, Joonhyeok Shin, Kyuhong Shim, Yujun Lee","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T08:39:56Z","title":"Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31338","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:c61e023c4e76721e21f32614ef6342854a959ebf05ec5db752b1ea7f581d2e48","target":"record","created_at":"2026-07-01T01:17:59Z","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":"24c6b2642aa9e77681cdd87a9855d4e76edbf8b1fb1cda4553ab2ef52ff29021","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T08:39:56Z","title_canon_sha256":"d0f2ba9b4f7e960a9a4367e1386ca5d05d1031971b3561fa21236db530336e23"},"schema_version":"1.0","source":{"id":"2606.31338","kind":"arxiv","version":1}},"canonical_sha256":"45ceca85d93937bb62618f889d5c53cdba684ab8acaa3cc164de1dd5efe49053","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45ceca85d93937bb62618f889d5c53cdba684ab8acaa3cc164de1dd5efe49053","first_computed_at":"2026-07-01T01:17:59.715277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:59.715277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"46CsXf3eXwm2v9rwneG5xhcxlHsbHaV8l4ZteeiSBlVbYRSBF24MAfnza6QrJkTwuG8IlRqgoepUXGLHyKLTDw==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:59.715743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c61e023c4e76721e21f32614ef6342854a959ebf05ec5db752b1ea7f581d2e48","sha256:b04e175e3df397629b1808b3a59c78cbd47b9310c35c6ff57825ee450c203aab"],"state_sha256":"12337cd969bf1233efba46c356180bce58f95e3a96c437508f8f71918ececc9e"}