{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UFFSFMCKLFRXL5NLIRY7W47JY2","short_pith_number":"pith:UFFSFMCK","canonical_record":{"source":{"id":"2305.19602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:15:06Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2cdd532f66b499718be50fc2f928d1318f7532cdb6c9348f713b9438cf75db94","abstract_canon_sha256":"c146524ae5b1436627f703594534a59c33fb3366218874ff95884ae995243cd9"},"schema_version":"1.0"},"canonical_sha256":"a14b22b04a596375f5ab4471fb73e9c6b0382be550798779163295437c2f2b09","source":{"kind":"arxiv","id":"2305.19602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19602","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19602v1","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19602","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"UFFSFMCKLFRX","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"UFFSFMCKLFRXL5NL","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"UFFSFMCK","created_at":"2026-07-05T06:15:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UFFSFMCKLFRXL5NLIRY7W47JY2","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:15:06Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2cdd532f66b499718be50fc2f928d1318f7532cdb6c9348f713b9438cf75db94","abstract_canon_sha256":"c146524ae5b1436627f703594534a59c33fb3366218874ff95884ae995243cd9"},"schema_version":"1.0"},"canonical_sha256":"a14b22b04a596375f5ab4471fb73e9c6b0382be550798779163295437c2f2b09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:52.719821Z","signature_b64":"gRsqHvjDNaQ89y8KakLlCCdDNO40kTF3CYSdX3agqtLjal5I2vt2yHDUovRGt01QXMBxoTYgs1UOvTbRuzJcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a14b22b04a596375f5ab4471fb73e9c6b0382be550798779163295437c2f2b09","last_reissued_at":"2026-07-05T06:15:52.719346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:52.719346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19602","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":"2026-07-05T06:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6IibtN0qEDvzDLPYZ8UrLma71JTOf4MKZQ2aGktNkxURpPpzCLiA9oXQDQPZO0yMOKMkISgmAfGYaAUca2qAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:03:28.870855Z"},"content_sha256":"26293b6fe9feeaca95b815288cbffbc52b5b6dd082c0b720bac87bb4f8ff0ef3","schema_version":"1.0","event_id":"sha256:26293b6fe9feeaca95b815288cbffbc52b5b6dd082c0b720bac87bb4f8ff0ef3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UFFSFMCKLFRXL5NLIRY7W47JY2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Music Sequence Representation from Text Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoyi Zhou, Jianxin Li, Shaohan Huang, Shuai Zhang, Tianyu Chen, Yuan Xie","submitted_at":"2023-05-31T07:15:06Z","abstract_excerpt":"Music representation learning is notoriously difficult for its complex human-related concepts contained in the sequence of numerical signals. To excavate better MUsic SEquence Representation from labeled audio, we propose a novel text-supervision pre-training method, namely MUSER. MUSER adopts an audio-spectrum-text tri-modal contrastive learning framework, where the text input could be any form of meta-data with the help of text templates while the spectrum is derived from an audio sequence. Our experiments reveal that MUSER could be more flexibly adapted to downstream tasks compared with the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19602","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/2305.19602/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":"2026-07-05T06:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R3W/YoijQbrCII+ZjpOH5XW2aQ/e9daRxPl53CL792Qr+MHqU6EvZ/fG72ou7C00hbKCcivzISoVf2z33oidBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:03:28.871225Z"},"content_sha256":"9584cb1daa0eb555e5c2fbb6d858f2aed19523620b9e6422df60ac755269ebe7","schema_version":"1.0","event_id":"sha256:9584cb1daa0eb555e5c2fbb6d858f2aed19523620b9e6422df60ac755269ebe7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFFSFMCKLFRXL5NLIRY7W47JY2/bundle.json","state_url":"https://pith.science/pith/UFFSFMCKLFRXL5NLIRY7W47JY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFFSFMCKLFRXL5NLIRY7W47JY2/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":"2026-07-07T09:03:28Z","links":{"resolver":"https://pith.science/pith/UFFSFMCKLFRXL5NLIRY7W47JY2","bundle":"https://pith.science/pith/UFFSFMCKLFRXL5NLIRY7W47JY2/bundle.json","state":"https://pith.science/pith/UFFSFMCKLFRXL5NLIRY7W47JY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFFSFMCKLFRXL5NLIRY7W47JY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UFFSFMCKLFRXL5NLIRY7W47JY2","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":"c146524ae5b1436627f703594534a59c33fb3366218874ff95884ae995243cd9","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:15:06Z","title_canon_sha256":"2cdd532f66b499718be50fc2f928d1318f7532cdb6c9348f713b9438cf75db94"},"schema_version":"1.0","source":{"id":"2305.19602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19602","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19602v1","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19602","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"UFFSFMCKLFRX","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"UFFSFMCKLFRXL5NL","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"UFFSFMCK","created_at":"2026-07-05T06:15:52Z"}],"graph_snapshots":[{"event_id":"sha256:9584cb1daa0eb555e5c2fbb6d858f2aed19523620b9e6422df60ac755269ebe7","target":"graph","created_at":"2026-07-05T06:15:52Z","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/2305.19602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Music representation learning is notoriously difficult for its complex human-related concepts contained in the sequence of numerical signals. To excavate better MUsic SEquence Representation from labeled audio, we propose a novel text-supervision pre-training method, namely MUSER. MUSER adopts an audio-spectrum-text tri-modal contrastive learning framework, where the text input could be any form of meta-data with the help of text templates while the spectrum is derived from an audio sequence. Our experiments reveal that MUSER could be more flexibly adapted to downstream tasks compared with the","authors_text":"Haoyi Zhou, Jianxin Li, Shaohan Huang, Shuai Zhang, Tianyu Chen, Yuan Xie","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:15:06Z","title":"Learning Music Sequence Representation from Text Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19602","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":"sha256:26293b6fe9feeaca95b815288cbffbc52b5b6dd082c0b720bac87bb4f8ff0ef3","target":"record","created_at":"2026-07-05T06:15:52Z","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":"c146524ae5b1436627f703594534a59c33fb3366218874ff95884ae995243cd9","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:15:06Z","title_canon_sha256":"2cdd532f66b499718be50fc2f928d1318f7532cdb6c9348f713b9438cf75db94"},"schema_version":"1.0","source":{"id":"2305.19602","kind":"arxiv","version":1}},"canonical_sha256":"a14b22b04a596375f5ab4471fb73e9c6b0382be550798779163295437c2f2b09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a14b22b04a596375f5ab4471fb73e9c6b0382be550798779163295437c2f2b09","first_computed_at":"2026-07-05T06:15:52.719346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:52.719346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gRsqHvjDNaQ89y8KakLlCCdDNO40kTF3CYSdX3agqtLjal5I2vt2yHDUovRGt01QXMBxoTYgs1UOvTbRuzJcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:52.719821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26293b6fe9feeaca95b815288cbffbc52b5b6dd082c0b720bac87bb4f8ff0ef3","sha256:9584cb1daa0eb555e5c2fbb6d858f2aed19523620b9e6422df60ac755269ebe7"],"state_sha256":"0cdc643cedb34fc0fad29c5dc55672a9c4869afbb6f39dbd02af0d75d8f7a339"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"012RwMJIYCUMqNlm3qEK/karOeNTWX4Iw7+OjxUV98dPSVT8UBSKPu1NDnm6t95sOOqBJkuTWrHq/FmM5HCiDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:03:28.873409Z","bundle_sha256":"7b62cdbed1dac675a1f97d2917dfd715205eedaa03aebc9b41564e450db980b1"}}