{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KUULKHDQZD6I3PLXFPQB5AMDPW","short_pith_number":"pith:KUULKHDQ","schema_version":"1.0","canonical_sha256":"5528b51c70c8fc8dbd772be01e81837db7d0ec5b2be71184866dd711ef190ded","source":{"kind":"arxiv","id":"2208.12208","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Audio-Language Learning for Music","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Elio Quinton, Emmanouil Benetos, Gy\\\"orgy Fazekas, Ilaria Manco","submitted_at":"2022-08-25T16:55:15Z","abstract_excerpt":"As one of the most intuitive interfaces known to humans, natural language has the potential to mediate many tasks that involve human-computer interaction, especially in application-focused fields like Music Information Retrieval. In this work, we explore cross-modal learning in an attempt to bridge audio and language in the music domain. To this end, we propose MusCALL, a framework for Music Contrastive Audio-Language Learning. Our approach consists of a dual-encoder architecture that learns the alignment between pairs of music audio and descriptive sentences, producing multimodal embeddings t"},"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":"2208.12208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-25T16:55:15Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"3d1d91b705657a7708d4c8417e61392b3d5e04143a19627aa32e69467fff4662","abstract_canon_sha256":"d33db946f13596a61a2de81958f2415e27c4c17b151743fbc64ecd782c7d819c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:36.091030Z","signature_b64":"o6CbG83O9j2ht4ng2GJ+LgcITMaXed6pWrFjpT5Ce3Wa1j2eODuu98uudZaOnP1Sh8jW+YP+BvvbU9sDMLH/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5528b51c70c8fc8dbd772be01e81837db7d0ec5b2be71184866dd711ef190ded","last_reissued_at":"2026-07-05T04:51:36.090655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:36.090655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Audio-Language Learning for Music","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Elio Quinton, Emmanouil Benetos, Gy\\\"orgy Fazekas, Ilaria Manco","submitted_at":"2022-08-25T16:55:15Z","abstract_excerpt":"As one of the most intuitive interfaces known to humans, natural language has the potential to mediate many tasks that involve human-computer interaction, especially in application-focused fields like Music Information Retrieval. In this work, we explore cross-modal learning in an attempt to bridge audio and language in the music domain. To this end, we propose MusCALL, a framework for Music Contrastive Audio-Language Learning. Our approach consists of a dual-encoder architecture that learns the alignment between pairs of music audio and descriptive sentences, producing multimodal embeddings t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12208","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/2208.12208/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":"2208.12208","created_at":"2026-07-05T04:51:36.090716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.12208v1","created_at":"2026-07-05T04:51:36.090716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12208","created_at":"2026-07-05T04:51:36.090716+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUULKHDQZD6I","created_at":"2026-07-05T04:51:36.090716+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUULKHDQZD6I3PLX","created_at":"2026-07-05T04:51:36.090716+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUULKHDQ","created_at":"2026-07-05T04:51:36.090716+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/KUULKHDQZD6I3PLXFPQB5AMDPW","json":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW.json","graph_json":"https://pith.science/api/pith-number/KUULKHDQZD6I3PLXFPQB5AMDPW/graph.json","events_json":"https://pith.science/api/pith-number/KUULKHDQZD6I3PLXFPQB5AMDPW/events.json","paper":"https://pith.science/paper/KUULKHDQ"},"agent_actions":{"view_html":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW","download_json":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW.json","view_paper":"https://pith.science/paper/KUULKHDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.12208&json=true","fetch_graph":"https://pith.science/api/pith-number/KUULKHDQZD6I3PLXFPQB5AMDPW/graph.json","fetch_events":"https://pith.science/api/pith-number/KUULKHDQZD6I3PLXFPQB5AMDPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/action/storage_attestation","attest_author":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/action/author_attestation","sign_citation":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/action/citation_signature","submit_replication":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/action/replication_record"}},"created_at":"2026-07-05T04:51:36.090716+00:00","updated_at":"2026-07-05T04:51:36.090716+00:00"}