{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KUULKHDQZD6I3PLXFPQB5AMDPW","short_pith_number":"pith:KUULKHDQ","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"},"canonical_sha256":"5528b51c70c8fc8dbd772be01e81837db7d0ec5b2be71184866dd711ef190ded","source":{"kind":"arxiv","id":"2208.12208","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12208","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12208v1","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12208","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"pith_short_12","alias_value":"KUULKHDQZD6I","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"pith_short_16","alias_value":"KUULKHDQZD6I3PLX","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"pith_short_8","alias_value":"KUULKHDQ","created_at":"2026-07-05T04:51:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KUULKHDQZD6I3PLXFPQB5AMDPW","target":"record","payload":{"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"},"canonical_sha256":"5528b51c70c8fc8dbd772be01e81837db7d0ec5b2be71184866dd711ef190ded","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"},"source_kind":"arxiv","source_id":"2208.12208","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:51:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ba1Eao54tmwVeDa8hV5UwOcbTHuU9GkR/fdhdF0GL1zfN/22dyhhj5q/He17GsDwiVxnDb9n9OJKVGKdV25RBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:12:25.739382Z"},"content_sha256":"7710e918fc24dfcb97ab68e225e06cdf2800c8a394a8fa15ac73c74d537f4097","schema_version":"1.0","event_id":"sha256:7710e918fc24dfcb97ab68e225e06cdf2800c8a394a8fa15ac73c74d537f4097"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KUULKHDQZD6I3PLXFPQB5AMDPW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:51:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvui4KCtnCL1kRM+lRAfMGDgdZJuqiLOFGA8aLizUO9Bj/lVc23NjqebjJBpvn8pEWiJRez1CwZHsCRBFH94DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:12:25.739767Z"},"content_sha256":"0a510d5886ac4d5cee7ad8473f1c2351fbcd4eec8ad54fdf02551a1bc46eeb50","schema_version":"1.0","event_id":"sha256:0a510d5886ac4d5cee7ad8473f1c2351fbcd4eec8ad54fdf02551a1bc46eeb50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/bundle.json","state_url":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T03:12:25Z","links":{"resolver":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW","bundle":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/bundle.json","state":"https://pith.science/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUULKHDQZD6I3PLXFPQB5AMDPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KUULKHDQZD6I3PLXFPQB5AMDPW","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":"d33db946f13596a61a2de81958f2415e27c4c17b151743fbc64ecd782c7d819c","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-25T16:55:15Z","title_canon_sha256":"3d1d91b705657a7708d4c8417e61392b3d5e04143a19627aa32e69467fff4662"},"schema_version":"1.0","source":{"id":"2208.12208","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12208","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12208v1","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12208","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"pith_short_12","alias_value":"KUULKHDQZD6I","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"pith_short_16","alias_value":"KUULKHDQZD6I3PLX","created_at":"2026-07-05T04:51:36Z"},{"alias_kind":"pith_short_8","alias_value":"KUULKHDQ","created_at":"2026-07-05T04:51:36Z"}],"graph_snapshots":[{"event_id":"sha256:0a510d5886ac4d5cee7ad8473f1c2351fbcd4eec8ad54fdf02551a1bc46eeb50","target":"graph","created_at":"2026-07-05T04:51:36Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.12208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Elio Quinton, Emmanouil Benetos, Gy\\\"orgy Fazekas, Ilaria Manco","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-25T16:55:15Z","title":"Contrastive Audio-Language Learning for Music"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12208","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7710e918fc24dfcb97ab68e225e06cdf2800c8a394a8fa15ac73c74d537f4097","target":"record","created_at":"2026-07-05T04:51:36Z","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":"d33db946f13596a61a2de81958f2415e27c4c17b151743fbc64ecd782c7d819c","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-25T16:55:15Z","title_canon_sha256":"3d1d91b705657a7708d4c8417e61392b3d5e04143a19627aa32e69467fff4662"},"schema_version":"1.0","source":{"id":"2208.12208","kind":"arxiv","version":1}},"canonical_sha256":"5528b51c70c8fc8dbd772be01e81837db7d0ec5b2be71184866dd711ef190ded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5528b51c70c8fc8dbd772be01e81837db7d0ec5b2be71184866dd711ef190ded","first_computed_at":"2026-07-05T04:51:36.090655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:36.090655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o6CbG83O9j2ht4ng2GJ+LgcITMaXed6pWrFjpT5Ce3Wa1j2eODuu98uudZaOnP1Sh8jW+YP+BvvbU9sDMLH/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:36.091030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12208","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7710e918fc24dfcb97ab68e225e06cdf2800c8a394a8fa15ac73c74d537f4097","sha256:0a510d5886ac4d5cee7ad8473f1c2351fbcd4eec8ad54fdf02551a1bc46eeb50"],"state_sha256":"11c7551fd93d1eb18952165cb98fbb77821fd38efe718096504bc6a47189b6c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2T6HSO8ULFxei7YEuCZh/K67rFY4ZysllgOInM2hZV+3mZtgzho6ARFdDLofLG0IzesZAWDrCSZJPy4ml1xCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:12:25.741781Z","bundle_sha256":"eff7c90310a2da3d0164b8a5646ec010590624c2b2998c9146a83e65c75cdacf"}}