{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J4TCRQG7Q65MVYJYJPSLQFCF3G","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":"9293aac815bf82082227e93275fbffc42c2e844a309caa8aeed455c77a5d9273","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-24T16:34:47Z","title_canon_sha256":"74c260bbda7c4f1b54f072123360e5543c567c6a7117036cc55d7dec15ca2f7b"},"schema_version":"1.0","source":{"id":"2104.11984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.11984","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2104.11984v1","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11984","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"J4TCRQG7Q65M","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"pith_short_16","alias_value":"J4TCRQG7Q65MVYJY","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"pith_short_8","alias_value":"J4TCRQG7","created_at":"2026-07-05T03:38:59Z"}],"graph_snapshots":[{"event_id":"sha256:a58b2ed7ffc64a4a01cb428dbe0d6771ccfa4b61316a7dbd702ff7f5d560b5ce","target":"graph","created_at":"2026-07-05T03:38:59Z","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/2104.11984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Content-based music information retrieval has seen rapid progress with the adoption of deep learning. Current approaches to high-level music description typically make use of classification models, such as in auto-tagging or genre and mood classification. In this work, we propose to address music description via audio captioning, defined as the task of generating a natural language description of music audio content in a human-like manner. To this end, we present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convo","authors_text":"Elio Quinton, Emmanouil Benetos, Gyorgy Fazekas, Ilaria Manco","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-24T16:34:47Z","title":"MusCaps: Generating Captions for Music Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11984","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:d4e944bc476caebccb7a8ac87898d70b887f7c5af46ed49addc71d9c64d5cc1b","target":"record","created_at":"2026-07-05T03:38:59Z","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":"9293aac815bf82082227e93275fbffc42c2e844a309caa8aeed455c77a5d9273","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-24T16:34:47Z","title_canon_sha256":"74c260bbda7c4f1b54f072123360e5543c567c6a7117036cc55d7dec15ca2f7b"},"schema_version":"1.0","source":{"id":"2104.11984","kind":"arxiv","version":1}},"canonical_sha256":"4f2628c0df87bacae1384be4b81445d9bd1c1a04803d3279d832e7c2685e3237","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f2628c0df87bacae1384be4b81445d9bd1c1a04803d3279d832e7c2685e3237","first_computed_at":"2026-07-05T03:38:59.792625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:59.792625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TVTIZmHBJgiXRE2WAIBFL55KVrkEJBhMXk3n4yTvrwKcf31ghTN1TODSg5glOIJ2HUD2WVnkn/WYhpizicHTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:59.792987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.11984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4e944bc476caebccb7a8ac87898d70b887f7c5af46ed49addc71d9c64d5cc1b","sha256:a58b2ed7ffc64a4a01cb428dbe0d6771ccfa4b61316a7dbd702ff7f5d560b5ce"],"state_sha256":"5bc757552a13ac2285a1aa541ed46eb8e8c0c581aecd313dd42c2ec5ff845bda"}