{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FFXVSLCLBKRUROYU4YA2XLQIAA","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":"9f8f2ed987b754e6d35497815bbcff9477c1011ad6fffa9fa782d8e1e61e4664","cross_cats_sorted":["cs.CL","cs.IR","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-12-08T10:30:52Z","title_canon_sha256":"e96624d1a420e8d09029eff313c78777107462ee48439096f07f16e90a67aaf1"},"schema_version":"1.0","source":{"id":"2112.04214","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04214","created_at":"2026-07-05T03:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04214v2","created_at":"2026-07-05T03:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04214","created_at":"2026-07-05T03:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"FFXVSLCLBKRU","created_at":"2026-07-05T03:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"FFXVSLCLBKRUROYU","created_at":"2026-07-05T03:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"FFXVSLCL","created_at":"2026-07-05T03:57:55Z"}],"graph_snapshots":[{"event_id":"sha256:4526ce387652d58c28cc559da5ea25923334e2d80a2f19bdcaac0f369f1f0608","target":"graph","created_at":"2026-07-05T03:57:55Z","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/2112.04214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio representations for music information retrieval are typically learned via supervised learning in a task-specific fashion. Although effective at producing state-of-the-art results, this scheme lacks flexibility with respect to the range of applications a model can have and requires extensively annotated datasets. In this work, we pose the question of whether it may be possible to exploit weakly aligned text as the only supervisory signal to learn general-purpose music audio representations. To address this question, we design a multimodal architecture for music and language pre-training (","authors_text":"Elio Quinton, Emmanouil Benetos, Gyorgy Fazekas, Ilaria Manco","cross_cats":["cs.CL","cs.IR","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-12-08T10:30:52Z","title":"Learning music audio representations via weak language supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04214","kind":"arxiv","version":2},"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:f480579a03a85f5c82db80c697080bd0dbe9f02afde67fa974cd0163bf995656","target":"record","created_at":"2026-07-05T03:57:55Z","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":"9f8f2ed987b754e6d35497815bbcff9477c1011ad6fffa9fa782d8e1e61e4664","cross_cats_sorted":["cs.CL","cs.IR","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-12-08T10:30:52Z","title_canon_sha256":"e96624d1a420e8d09029eff313c78777107462ee48439096f07f16e90a67aaf1"},"schema_version":"1.0","source":{"id":"2112.04214","kind":"arxiv","version":2}},"canonical_sha256":"296f592c4b0aa348bb14e601abae08002910e5a8b20350705c4456b475d48597","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"296f592c4b0aa348bb14e601abae08002910e5a8b20350705c4456b475d48597","first_computed_at":"2026-07-05T03:57:55.166212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:57:55.166212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AqQ/9sk8CJlEAH1LNF+9RNJ4gdbsvALMLi2HX0FENtQYikyFmQ/61jKZoBb+iHNFp9F5oKZX9JbIxVzbOD5jCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:57:55.166624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04214","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f480579a03a85f5c82db80c697080bd0dbe9f02afde67fa974cd0163bf995656","sha256:4526ce387652d58c28cc559da5ea25923334e2d80a2f19bdcaac0f369f1f0608"],"state_sha256":"1cb68479129fbcff9a0136f34041fab9f9357292244996599c37cfb412b87192"}