{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GS2EE6XU7XI5XMUVNMW4LZO5YU","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":"7700e21a1bb61236b9592ea8607358f1f2bad5b415889dbddb2a2e9f765ee7c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-15T17:00:14Z","title_canon_sha256":"a10312b468e591865a82c6fdb6fd1ead032aa69ea56807972b03792e35c78d8d"},"schema_version":"1.0","source":{"id":"2605.16181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16181","created_at":"2026-05-20T00:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16181v1","created_at":"2026-05-20T00:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16181","created_at":"2026-05-20T00:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"GS2EE6XU7XI5","created_at":"2026-05-20T00:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"GS2EE6XU7XI5XMUV","created_at":"2026-05-20T00:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"GS2EE6XU","created_at":"2026-05-20T00:01:56Z"}],"graph_snapshots":[{"event_id":"sha256:2203f1ba2bc0c6ea9e643ff27304685278ff41130326f59a61c2c65c896cf68e","target":"graph","created_at":"2026-05-20T00:01:56Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On a symbolic-music model where attribution ground truth is available through counterfactual retraining, the reliability diagnostics rank four attribution methods identically to that ground truth."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The chosen musical aspects (five for symbolic music, three for audio) and the reliability diagnostics (within-group similarity, SVD, column statistics) correctly capture the dimensions of influence relevant to copyright analysis and model behavior."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ARIA decomposes music training data attribution into musical aspects and supplies reliability diagnostics from similarity metrics and score matrix analysis, with validation on symbolic models using counterfactual retraining."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ARIA decomposes music training data attribution into specific musical aspects and validates methods using reliability diagnostics that match ground truth rankings."}],"snapshot_sha256":"68a1d2c97804292413ba1eb3c42edd4cdde1dc0fdfbf589bf341641ef8dd4b00"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6c986e4947b1c28e95f11576d45e3189e0a314914336b3fadafdaa2554dd6143"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:18.742143Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:31:09.096656Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T17:52:01.735861Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T17:49:47.146206Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:30.692590Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"external_links","ran_at":"2026-05-19T17:31:43.753042Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.420035Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16181/integrity.json","findings":[],"snapshot_sha256":"6406f629d87e42aebb0c9e019bb78ec7388858ea870320b4a7ccde3faf8076f4","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training data attribution (TDA) for music generation must answer two questions that copyright analysis requires, namely which training songs influence a generated output and along which musical aspects the influence operates. Existing methods reduce influence to a single scalar, without revealing which musical aspects are dominant in that influence. We propose ARIA, a framework that decomposes attribution along musical aspects (five for symbolic music, three for audio) and pairs the decomposition with reliability diagnostics computed from the segment-level score matrix. It measures within-grou","authors_text":"Ashkan Panahi, Changheon Han, K{\\i}van\\c{c} Tatar","cross_cats":[],"headline":"ARIA decomposes music training data attribution into specific musical aspects and validates methods using reliability diagnostics that match ground truth rankings.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-15T17:00:14Z","title":"ARIA: A Diagnostic Framework for Music Training Data Attribution"},"references":{"count":56,"internal_anchors":1,"resolved_work":56,"sample":[{"cited_arxiv_id":"2301.11325","doi":"","is_internal_anchor":true,"ref_index":1,"title":"MusicLM: Generating Music From Text","work_id":"15e6566e-1c36-468f-966e-823248cbf87f","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Towards tracing knowledge in language models back to the training data","work_id":"3af79ad8-541f-47aa-be07-87cb92830bc3","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Exploring musical roots: Applying audio embeddings to empower influence attribution for a generative music model","work_id":"2b642d65-2cef-444c-85e4-9dc5b7d0421b","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Bittner, Brian McFee, Justin Salamon, Peter Li, and Juan Pablo Bello","work_id":"c7e5b7d0-33eb-4eb4-af3d-4712aa338ddc","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"AudioLM: A language modeling approach to audio generation.IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2523–2533, 2023","work_id":"e2394a15-768a-4ce1-9425-f8c509945f7d","year":2023}],"snapshot_sha256":"e2077b611bb724af072468170333b8fdc67e699b8bf1357492c5d994fbc86e21"},"source":{"id":"2605.16181","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T18:20:24.981741Z","id":"caf50536-f47b-4df4-be11-51bb098d73cd","model_set":{"reader":"grok-4.3"},"one_line_summary":"ARIA decomposes music training data attribution into musical aspects and supplies reliability diagnostics from similarity metrics and score matrix analysis, with validation on symbolic models using counterfactual retraining.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ARIA decomposes music training data attribution into specific musical aspects and validates methods using reliability diagnostics that match ground truth rankings.","strongest_claim":"On a symbolic-music model where attribution ground truth is available through counterfactual retraining, the reliability diagnostics rank four attribution methods identically to that ground truth.","weakest_assumption":"The chosen musical aspects (five for symbolic music, three for audio) and the reliability diagnostics (within-group similarity, SVD, column statistics) correctly capture the dimensions of influence relevant to copyright analysis and model behavior."}},"verdict_id":"caf50536-f47b-4df4-be11-51bb098d73cd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d6cbe861569a014d80869fdb8b02c1f7ae5458ae9aaaa47545eebc3d3a271786","target":"record","created_at":"2026-05-20T00:01:56Z","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":"7700e21a1bb61236b9592ea8607358f1f2bad5b415889dbddb2a2e9f765ee7c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-15T17:00:14Z","title_canon_sha256":"a10312b468e591865a82c6fdb6fd1ead032aa69ea56807972b03792e35c78d8d"},"schema_version":"1.0","source":{"id":"2605.16181","kind":"arxiv","version":1}},"canonical_sha256":"34b4427af4fdd1dbb2956b2dc5e5ddc53cb40d7aeb9c8dcec88d5dbe25152c0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34b4427af4fdd1dbb2956b2dc5e5ddc53cb40d7aeb9c8dcec88d5dbe25152c0f","first_computed_at":"2026-05-20T00:01:56.512122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:56.512122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7njNyAfjaMykDmFcUQoPRVcoIRtYxDRKlR1XtgkY/5XYUfrKw6m8+Q8HokRdwhWJ+S+dL5VVDXTPc2l5H9OgBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:56.512914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6cbe861569a014d80869fdb8b02c1f7ae5458ae9aaaa47545eebc3d3a271786","sha256:2203f1ba2bc0c6ea9e643ff27304685278ff41130326f59a61c2c65c896cf68e"],"state_sha256":"9bd4361faab916c7c7ab79d3a8e89e4974f73d7f09ce66d0a0e4ee703e8651c5"}