{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GTDHTVB5BY4BIGE5RDPCVX3ESU","short_pith_number":"pith:GTDHTVB5","schema_version":"1.0","canonical_sha256":"34c679d43d0e3814189d88de2adf649529f1baa34166050023f9089b8f4f7545","source":{"kind":"arxiv","id":"2602.19778","version":4},"attestation_state":"computed","paper":{"title":"Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG","cs.MM"],"primary_cat":"cs.SD","authors_text":"Gang Liu, Nghia Phan, Rong Jin, Xiao Dong","submitted_at":"2026-02-23T12:32:53Z","abstract_excerpt":"Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire. At the same time, open-weight pre-trained models are more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use a pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on th"},"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":"2602.19778","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-02-23T12:32:53Z","cross_cats_sorted":["cs.IR","cs.LG","cs.MM"],"title_canon_sha256":"65cab2599b394680e75fc9a2bddf929f8a7a1649f68c47555819c8e571ffabde","abstract_canon_sha256":"8ca81450dbfd41de9e06be8c7b065d12e7554fd5b8e9359531f4e1aa46d8753e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:16.626420Z","signature_b64":"aNSK6dM2Ys30xtc14c2jO6ibRAOmNuIGKTnjaf29G21xXC9sHtaB9FCGU6bZksIFiZTWsMjHFXHcWXw61F4DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c679d43d0e3814189d88de2adf649529f1baa34166050023f9089b8f4f7545","last_reissued_at":"2026-06-30T02:17:16.625882Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:16.625882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG","cs.MM"],"primary_cat":"cs.SD","authors_text":"Gang Liu, Nghia Phan, Rong Jin, Xiao Dong","submitted_at":"2026-02-23T12:32:53Z","abstract_excerpt":"Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire. At the same time, open-weight pre-trained models are more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use a pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19778","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.19778/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2602.19778","created_at":"2026-06-30T02:17:16.625955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.19778v4","created_at":"2026-06-30T02:17:16.625955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19778","created_at":"2026-06-30T02:17:16.625955+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTDHTVB5BY4B","created_at":"2026-06-30T02:17:16.625955+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTDHTVB5BY4BIGE5","created_at":"2026-06-30T02:17:16.625955+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTDHTVB5","created_at":"2026-06-30T02:17:16.625955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU","json":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU.json","graph_json":"https://pith.science/api/pith-number/GTDHTVB5BY4BIGE5RDPCVX3ESU/graph.json","events_json":"https://pith.science/api/pith-number/GTDHTVB5BY4BIGE5RDPCVX3ESU/events.json","paper":"https://pith.science/paper/GTDHTVB5"},"agent_actions":{"view_html":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU","download_json":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU.json","view_paper":"https://pith.science/paper/GTDHTVB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.19778&json=true","fetch_graph":"https://pith.science/api/pith-number/GTDHTVB5BY4BIGE5RDPCVX3ESU/graph.json","fetch_events":"https://pith.science/api/pith-number/GTDHTVB5BY4BIGE5RDPCVX3ESU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU/action/storage_attestation","attest_author":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU/action/author_attestation","sign_citation":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU/action/citation_signature","submit_replication":"https://pith.science/pith/GTDHTVB5BY4BIGE5RDPCVX3ESU/action/replication_record"}},"created_at":"2026-06-30T02:17:16.625955+00:00","updated_at":"2026-06-30T02:17:16.625955+00:00"}