{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MBSTGMMVN4SZNHC3SPHTFEO7KN","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":"aecaa4c1cf43a698a706d79bea589eeaac5d6460209098687561111efeb4fa62","cross_cats_sorted":["cs.CL","cs.SD","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-08-26T03:13:21Z","title_canon_sha256":"12118640b1cae47ad5510e0543a5c65cd48d49e7f35880e8fa776f8ce27c797e"},"schema_version":"1.0","source":{"id":"2208.12415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12415","created_at":"2026-07-05T04:51:45Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12415v1","created_at":"2026-07-05T04:51:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12415","created_at":"2026-07-05T04:51:45Z"},{"alias_kind":"pith_short_12","alias_value":"MBSTGMMVN4SZ","created_at":"2026-07-05T04:51:45Z"},{"alias_kind":"pith_short_16","alias_value":"MBSTGMMVN4SZNHC3","created_at":"2026-07-05T04:51:45Z"},{"alias_kind":"pith_short_8","alias_value":"MBSTGMMV","created_at":"2026-07-05T04:51:45Z"}],"graph_snapshots":[{"event_id":"sha256:546982441da9ca36e6d6e241017aa01cbc8f74d37d4f3e36e46d9853ba6b0b89","target":"graph","created_at":"2026-07-05T04:51:45Z","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/2208.12415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Music tagging and content-based retrieval systems have traditionally been constructed using pre-defined ontologies covering a rigid set of music attributes or text queries. This paper presents MuLan: a first attempt at a new generation of acoustic models that link music audio directly to unconstrained natural language music descriptions. MuLan takes the form of a two-tower, joint audio-text embedding model trained using 44 million music recordings (370K hours) and weakly-associated, free-form text annotations. Through its compatibility with a wide range of music genres and text styles (includi","authors_text":"Aren Jansen, Daniel P. W. Ellis, Joonseok Lee, Judith Yue Li, Qingqing Huang, Ravi Ganti","cross_cats":["cs.CL","cs.SD","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-08-26T03:13:21Z","title":"MuLan: A Joint Embedding of Music Audio and Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12415","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":"sha256:17d357073d16726fed74b38e416ed57d6f70b39599a691b9976def42efb092a4","target":"record","created_at":"2026-07-05T04:51:45Z","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":"aecaa4c1cf43a698a706d79bea589eeaac5d6460209098687561111efeb4fa62","cross_cats_sorted":["cs.CL","cs.SD","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-08-26T03:13:21Z","title_canon_sha256":"12118640b1cae47ad5510e0543a5c65cd48d49e7f35880e8fa776f8ce27c797e"},"schema_version":"1.0","source":{"id":"2208.12415","kind":"arxiv","version":1}},"canonical_sha256":"60653331956f25969c5b93cf3291df53582aa43904401f5873cd1b1869f83a38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60653331956f25969c5b93cf3291df53582aa43904401f5873cd1b1869f83a38","first_computed_at":"2026-07-05T04:51:45.023380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:45.023380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I9wbx8az2F7e63CwwunL5rSew2EejQ1Yl77uFNhknaN1n/xY7WU6UW5v0418p0kewQX3YrE+UbW8i9O5SF/iCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:45.023802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17d357073d16726fed74b38e416ed57d6f70b39599a691b9976def42efb092a4","sha256:546982441da9ca36e6d6e241017aa01cbc8f74d37d4f3e36e46d9853ba6b0b89"],"state_sha256":"5f9f1c6c3ca1336bea3d87740795d5453672908617a0e6301b1b2d13308161c6"}