{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GVTGTF6XJCHKGGZDZXFBRR5LK2","short_pith_number":"pith:GVTGTF6X","schema_version":"1.0","canonical_sha256":"35666997d7488ea31b23cdca18c7ab568fee0b5a0b153a659daf525c0a7b85fb","source":{"kind":"arxiv","id":"2401.08902","version":1},"attestation_state":"computed","paper":{"title":"Similar but Faster: Manipulation of Tempo in Music Audio Embeddings for Tempo Prediction and Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Henkel, Jaehun Kim, Matthew C. McCallum, Matthew E. P. Davies, Samuel E. Sandberg","submitted_at":"2024-01-17T01:06:22Z","abstract_excerpt":"Audio embeddings enable large scale comparisons of the similarity of audio files for applications such as search and recommendation. Due to the subjectivity of audio similarity, it can be desirable to design systems that answer not only whether audio is similar, but similar in what way (e.g., wrt. tempo, mood or genre). Previous works have proposed disentangled embedding spaces where subspaces representing specific, yet possibly correlated, attributes can be weighted to emphasize those attributes in downstream tasks. However, no research has been conducted into the independence of these subspa"},"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":"2401.08902","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-17T01:06:22Z","cross_cats_sorted":["cs.DL","cs.IR","cs.LG","eess.AS"],"title_canon_sha256":"a0691be470ba5c242d8e13b2f16c33f31b972f992de92e1e89ce95d5cb6bc992","abstract_canon_sha256":"eb68363e3fcc347c58b3d62ebae868278262534a3c337c501e9444b0172b82a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:23.269945Z","signature_b64":"FngujvtPP1X9LJW6qXRucWEWDYK+aUNhfnlokMRo8C8zOUwg7JWxE+7Br9V0SobIDZi5ZtRzamWp749btpfCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35666997d7488ea31b23cdca18c7ab568fee0b5a0b153a659daf525c0a7b85fb","last_reissued_at":"2026-07-05T07:34:23.269423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:23.269423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Similar but Faster: Manipulation of Tempo in Music Audio Embeddings for Tempo Prediction and Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Henkel, Jaehun Kim, Matthew C. McCallum, Matthew E. P. Davies, Samuel E. Sandberg","submitted_at":"2024-01-17T01:06:22Z","abstract_excerpt":"Audio embeddings enable large scale comparisons of the similarity of audio files for applications such as search and recommendation. Due to the subjectivity of audio similarity, it can be desirable to design systems that answer not only whether audio is similar, but similar in what way (e.g., wrt. tempo, mood or genre). Previous works have proposed disentangled embedding spaces where subspaces representing specific, yet possibly correlated, attributes can be weighted to emphasize those attributes in downstream tasks. However, no research has been conducted into the independence of these subspa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08902","kind":"arxiv","version":1},"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/2401.08902/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":"2401.08902","created_at":"2026-07-05T07:34:23.269485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08902v1","created_at":"2026-07-05T07:34:23.269485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08902","created_at":"2026-07-05T07:34:23.269485+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVTGTF6XJCHK","created_at":"2026-07-05T07:34:23.269485+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVTGTF6XJCHKGGZD","created_at":"2026-07-05T07:34:23.269485+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVTGTF6X","created_at":"2026-07-05T07:34:23.269485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18955","citing_title":"Leave-One-EquiVariant: Alleviating invariance-related information loss in contrastive music representations","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2","json":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2.json","graph_json":"https://pith.science/api/pith-number/GVTGTF6XJCHKGGZDZXFBRR5LK2/graph.json","events_json":"https://pith.science/api/pith-number/GVTGTF6XJCHKGGZDZXFBRR5LK2/events.json","paper":"https://pith.science/paper/GVTGTF6X"},"agent_actions":{"view_html":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2","download_json":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2.json","view_paper":"https://pith.science/paper/GVTGTF6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08902&json=true","fetch_graph":"https://pith.science/api/pith-number/GVTGTF6XJCHKGGZDZXFBRR5LK2/graph.json","fetch_events":"https://pith.science/api/pith-number/GVTGTF6XJCHKGGZDZXFBRR5LK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2/action/storage_attestation","attest_author":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2/action/author_attestation","sign_citation":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2/action/citation_signature","submit_replication":"https://pith.science/pith/GVTGTF6XJCHKGGZDZXFBRR5LK2/action/replication_record"}},"created_at":"2026-07-05T07:34:23.269485+00:00","updated_at":"2026-07-05T07:34:23.269485+00:00"}