{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FJHYPY5S2LJMTYLWX76LBYAESH","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":"53c68b18236d6a216596b6d812315169b048b74caabde6b0af9978451c274c56","cross_cats_sorted":["cs.IR","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-21T15:23:00Z","title_canon_sha256":"96fced408be5c753b565e106518a0c6508cae8d9c8e8680c4471478aa2164fbb"},"schema_version":"1.0","source":{"id":"2304.11029","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11029","created_at":"2026-07-05T07:02:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11029v4","created_at":"2026-07-05T07:02:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11029","created_at":"2026-07-05T07:02:01Z"},{"alias_kind":"pith_short_12","alias_value":"FJHYPY5S2LJM","created_at":"2026-07-05T07:02:01Z"},{"alias_kind":"pith_short_16","alias_value":"FJHYPY5S2LJMTYLW","created_at":"2026-07-05T07:02:01Z"},{"alias_kind":"pith_short_8","alias_value":"FJHYPY5S","created_at":"2026-07-05T07:02:01Z"}],"graph_snapshots":[{"event_id":"sha256:ecb4a3e9a699f27b13151f213d1c2a1a7328c66cb523676c6757c776cc5ad9d3","target":"graph","created_at":"2026-07-05T07:02:01Z","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/2304.11029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce CLaMP: Contrastive Language-Music Pre-training, which learns cross-modal representations between natural language and symbolic music using a music encoder and a text encoder trained jointly with a contrastive loss. To pre-train CLaMP, we collected a large dataset of 1.4 million music-text pairs. It employed text dropout as a data augmentation technique and bar patching to efficiently represent music data which reduces sequence length to less than 10\\%. In addition, we developed a masked music model pre-training objective to enhance the music encoder's comprehension of musical cont","authors_text":"Dingyao Yu, Maosong Sun, Shangda Wu, Xu Tan","cross_cats":["cs.IR","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-21T15:23:00Z","title":"CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11029","kind":"arxiv","version":4},"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":"sha256:3df8934e2a3898540669823d08ae44499c1d5cf47290a9d584df264bda7fab86","target":"record","created_at":"2026-07-05T07:02:01Z","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":"53c68b18236d6a216596b6d812315169b048b74caabde6b0af9978451c274c56","cross_cats_sorted":["cs.IR","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-21T15:23:00Z","title_canon_sha256":"96fced408be5c753b565e106518a0c6508cae8d9c8e8680c4471478aa2164fbb"},"schema_version":"1.0","source":{"id":"2304.11029","kind":"arxiv","version":4}},"canonical_sha256":"2a4f87e3b2d2d2c9e176bffcb0e00491e2412d388c54ac63fd76852df84bc28d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a4f87e3b2d2d2c9e176bffcb0e00491e2412d388c54ac63fd76852df84bc28d","first_computed_at":"2026-07-05T07:02:01.246699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:01.246699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"egNWE/+cU6D0IDZJYnhm065TkmuiqY8AUKZjZLPxUtZ/V1pteMEw5Pkt8/IFsU8WNXt9HcLR+aPliJiaiManCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:01.247204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.11029","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3df8934e2a3898540669823d08ae44499c1d5cf47290a9d584df264bda7fab86","sha256:ecb4a3e9a699f27b13151f213d1c2a1a7328c66cb523676c6757c776cc5ad9d3"],"state_sha256":"4b7f65d1c4ce47a90d0695e2874cf60115c1f656868a02817d88a8293fab227e"}