{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DB45ZUNPPZ7NENGHYQPQN5NKZO","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":"a2963d2b88dc334136f5cacbea52060cf2ca48846df97a83e3c75cb15be68c1e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T11:12:19Z","title_canon_sha256":"85646d32091ce1448606056233610177a0cf154541c7621576567fb40f6965c3"},"schema_version":"1.0","source":{"id":"2502.07461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07461","created_at":"2026-07-05T11:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07461v2","created_at":"2026-07-05T11:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07461","created_at":"2026-07-05T11:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"DB45ZUNPPZ7N","created_at":"2026-07-05T11:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"DB45ZUNPPZ7NENGH","created_at":"2026-07-05T11:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"DB45ZUNP","created_at":"2026-07-05T11:03:56Z"}],"graph_snapshots":[{"event_id":"sha256:db14279d4ceb979e343f61f651f820268553c9dce524354d4ab9d8604cfd4552","target":"graph","created_at":"2026-07-05T11:03:56Z","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/2502.07461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce JamendoMaxCaps, a large-scale music-caption dataset featuring over 362,000 freely licensed instrumental tracks from the renowned Jamendo platform. The dataset includes captions generated by a state-of-the-art captioning model, enhanced with imputed metadata. We also introduce a retrieval system that leverages both musical features and metadata to identify similar songs, which are then used to fill in missing metadata using a local large language model (LLLM). This approach allows us to provide a more comprehensive and informative dataset for researchers working on music-language u","authors_text":"Abhinaba Roy, Dorien Herremans, Renhang Liu, Tongyu Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T11:12:19Z","title":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07461","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:be9ce6890ef7ccdee196b2a71ff4835ae12345829e34ec4adb79d8d073a3713d","target":"record","created_at":"2026-07-05T11:03:56Z","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":"a2963d2b88dc334136f5cacbea52060cf2ca48846df97a83e3c75cb15be68c1e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T11:12:19Z","title_canon_sha256":"85646d32091ce1448606056233610177a0cf154541c7621576567fb40f6965c3"},"schema_version":"1.0","source":{"id":"2502.07461","kind":"arxiv","version":2}},"canonical_sha256":"1879dcd1af7e7ed234c7c41f06f5aacba0171d08727d25dcfe9bf2cb03f34ab6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1879dcd1af7e7ed234c7c41f06f5aacba0171d08727d25dcfe9bf2cb03f34ab6","first_computed_at":"2026-07-05T11:03:56.554239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:56.554239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SxzKWEqBiPar0Fgl556QfgJkl5y71qNaHe2dIGfRyPbn2jOlIS6KgkccjAQiUu7BJaJ28LJYBmQKL2moFVTGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:56.554832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be9ce6890ef7ccdee196b2a71ff4835ae12345829e34ec4adb79d8d073a3713d","sha256:db14279d4ceb979e343f61f651f820268553c9dce524354d4ab9d8604cfd4552"],"state_sha256":"f7ca4d264329b56c0ea320dab46780eb0cf196d5cc13f9d81dd3658cf85e7902"}