{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:EWGSUEHA3O7PLI23ZPAPQUIKKU","short_pith_number":"pith:EWGSUEHA","schema_version":"1.0","canonical_sha256":"258d2a10e0dbbef5a35bcbc0f8510a5511886d3a09fac0236ad7e29338e1608d","source":{"kind":"arxiv","id":"1306.1461","version":2},"attestation_state":"computed","paper":{"title":"The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bob L. Sturm","submitted_at":"2013-06-06T16:30:44Z","abstract_excerpt":"The GTZAN dataset appears in at least 100 published works, and is the most-used public dataset for evaluation in machine listening research for music genre recognition (MGR). Our recent work, however, shows GTZAN has several faults (repetitions, mislabelings, and distortions), which challenge the interpretability of any result derived using it. In this article, we disprove the claims that all MGR systems are affected in the same ways by these faults, and that the performances of MGR systems in GTZAN are still meaningfully comparable since they all face the same faults. We identify and analyze "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1306.1461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2013-06-06T16:30:44Z","cross_cats_sorted":[],"title_canon_sha256":"3830dabe5f5350dc11060f53bb7ae1e997bb61e9a0550fd9054c199dfbd0671c","abstract_canon_sha256":"a9d6c26288b25fc0a225dbc75bb4ba7949fded186848fcb68908a53fc93517c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:09:42.053700Z","signature_b64":"1vaFbi4ouGReHte6eO00zyfmGoCUkWWh+ho7E1yaaN3Pr9IiEDXZMAP7xKgwlru95EyOHoYbKJUtG7bK6s1MBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"258d2a10e0dbbef5a35bcbc0f8510a5511886d3a09fac0236ad7e29338e1608d","last_reissued_at":"2026-05-18T02:09:42.052967Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:09:42.052967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bob L. Sturm","submitted_at":"2013-06-06T16:30:44Z","abstract_excerpt":"The GTZAN dataset appears in at least 100 published works, and is the most-used public dataset for evaluation in machine listening research for music genre recognition (MGR). Our recent work, however, shows GTZAN has several faults (repetitions, mislabelings, and distortions), which challenge the interpretability of any result derived using it. In this article, we disprove the claims that all MGR systems are affected in the same ways by these faults, and that the performances of MGR systems in GTZAN are still meaningfully comparable since they all face the same faults. We identify and analyze "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.1461","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1306.1461","created_at":"2026-05-18T02:09:42.053076+00:00"},{"alias_kind":"arxiv_version","alias_value":"1306.1461v2","created_at":"2026-05-18T02:09:42.053076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.1461","created_at":"2026-05-18T02:09:42.053076+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWGSUEHA3O7P","created_at":"2026-05-18T12:27:43.054852+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWGSUEHA3O7PLI23","created_at":"2026-05-18T12:27:43.054852+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWGSUEHA","created_at":"2026-05-18T12:27:43.054852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.18273","citing_title":"Continuous Audio Thinking for Large Audio Language Models","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04040","citing_title":"Channel-Oriented Design for EEG-to-Music Reconstruction","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02937","citing_title":"If It's Good Enough for You, It's Good Enough for Me: Transferability of Audio Sufficiencies across Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU","json":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU.json","graph_json":"https://pith.science/api/pith-number/EWGSUEHA3O7PLI23ZPAPQUIKKU/graph.json","events_json":"https://pith.science/api/pith-number/EWGSUEHA3O7PLI23ZPAPQUIKKU/events.json","paper":"https://pith.science/paper/EWGSUEHA"},"agent_actions":{"view_html":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU","download_json":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU.json","view_paper":"https://pith.science/paper/EWGSUEHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1306.1461&json=true","fetch_graph":"https://pith.science/api/pith-number/EWGSUEHA3O7PLI23ZPAPQUIKKU/graph.json","fetch_events":"https://pith.science/api/pith-number/EWGSUEHA3O7PLI23ZPAPQUIKKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU/action/storage_attestation","attest_author":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU/action/author_attestation","sign_citation":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU/action/citation_signature","submit_replication":"https://pith.science/pith/EWGSUEHA3O7PLI23ZPAPQUIKKU/action/replication_record"}},"created_at":"2026-05-18T02:09:42.053076+00:00","updated_at":"2026-05-18T02:09:42.053076+00:00"}