{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SUZ5PF4QUWL6FZP2RLOMWRECAP","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":"e480a00cc7984942d539d64ba06eb7d944591cccf147ddd04c066268b7fdc1ad","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-18T05:51:36Z","title_canon_sha256":"7675d50c3124ac472b3f61cad6e8a89cfb926ec2b819ecea1ea619b5091e716a"},"schema_version":"1.0","source":{"id":"2506.15154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15154","created_at":"2026-07-05T11:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15154v1","created_at":"2026-07-05T11:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15154","created_at":"2026-07-05T11:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"SUZ5PF4QUWL6","created_at":"2026-07-05T11:23:38Z"},{"alias_kind":"pith_short_16","alias_value":"SUZ5PF4QUWL6FZP2","created_at":"2026-07-05T11:23:38Z"},{"alias_kind":"pith_short_8","alias_value":"SUZ5PF4Q","created_at":"2026-07-05T11:23:38Z"}],"graph_snapshots":[{"event_id":"sha256:7ac2694bde18823d16aa484e8e7f6c797cc1d235bf77593d65fe706f2c210a2c","target":"graph","created_at":"2026-07-05T11:23:38Z","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/2506.15154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detailed captions that accurately reflect the characteristics of a music piece can enrich music databases and drive forward research in music AI. This paper introduces a multi-task music captioning model, SonicVerse, that integrates caption generation with auxiliary music feature detection tasks such as key detection, vocals detection, and more, so as to directly capture both low-level acoustic details as well as high-level musical attributes. The key contribution is a projection-based architecture that transforms audio input into language tokens, while simultaneously detecting music features ","authors_text":"Abhinaba Roy, Anuradha Chopra, Dorien Herremans","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-18T05:51:36Z","title":"SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15154","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":"sha256:1290e207d64f0fcc9d0af1d012c10d916cd25e66fd6b14a41a0cbf1c81f1f8e2","target":"record","created_at":"2026-07-05T11:23:38Z","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":"e480a00cc7984942d539d64ba06eb7d944591cccf147ddd04c066268b7fdc1ad","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-18T05:51:36Z","title_canon_sha256":"7675d50c3124ac472b3f61cad6e8a89cfb926ec2b819ecea1ea619b5091e716a"},"schema_version":"1.0","source":{"id":"2506.15154","kind":"arxiv","version":1}},"canonical_sha256":"9533d79790a597e2e5fa8adccb448203dbbcee03828cb175ebf622e51922dcfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9533d79790a597e2e5fa8adccb448203dbbcee03828cb175ebf622e51922dcfc","first_computed_at":"2026-07-05T11:23:38.236091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:38.236091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F8KDrDLtul79W0HANxjNBUHMoIQgrDdmKDmUhWWKQa5HkBIlnY2a0KlKjY7V6YYmDqw9xdVZ0WGkUDcgb2v4DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:38.236666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1290e207d64f0fcc9d0af1d012c10d916cd25e66fd6b14a41a0cbf1c81f1f8e2","sha256:7ac2694bde18823d16aa484e8e7f6c797cc1d235bf77593d65fe706f2c210a2c"],"state_sha256":"648a56c1ac69c835bf1e120a22a3899e24fa708036e059e6a3b4a606eb9b3580"}