{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UXZOZGFKHEVBJSEK55U53HCK2R","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":"7e4a9d3b860952eb7e1a5840675ba953259bc7ccf01b5052375d4dd46c27d621","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-12-30T16:05:30Z","title_canon_sha256":"700bc4d23e654179ccf7dfaeae3a52b228522af00cc8c58e21e57dcf73213b9b"},"schema_version":"1.0","source":{"id":"2112.15110","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.15110","created_at":"2026-07-05T03:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"2112.15110v2","created_at":"2026-07-05T03:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.15110","created_at":"2026-07-05T03:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"UXZOZGFKHEVB","created_at":"2026-07-05T03:59:00Z"},{"alias_kind":"pith_short_16","alias_value":"UXZOZGFKHEVBJSEK","created_at":"2026-07-05T03:59:00Z"},{"alias_kind":"pith_short_8","alias_value":"UXZOZGFK","created_at":"2026-07-05T03:59:00Z"}],"graph_snapshots":[{"event_id":"sha256:7183e395638563a2ef9147a804b6345456f9f66e10f2e366ab3300b8ef7ce3ae","target":"graph","created_at":"2026-07-05T03:59:00Z","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/2112.15110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Could we automatically derive the score of a piano accompaniment based on the audio of a pop song? This is the audio-to-symbolic arrangement problem we tackle in this paper. A good arrangement model should not only consider the audio content but also have prior knowledge of piano composition (so that the generation \"sounds like\" the audio and meanwhile maintains musicality). To this end, we contribute a cross-modal representation-learning model, which 1) extracts chord and melodic information from the audio, and 2) learns texture representation from both audio and a corrupted ground truth arra","authors_text":"Dejing Xu, Gus Xia, Ying Shan, Ziyu Wang","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-12-30T16:05:30Z","title":"Audio-to-symbolic Arrangement via Cross-modal Music Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.15110","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":"sha256:2ce634d6ca8e87ec8e4bfa5a3844fd318249a12482b3a68c6d0f6a6330ee9b4d","target":"record","created_at":"2026-07-05T03:59:00Z","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":"7e4a9d3b860952eb7e1a5840675ba953259bc7ccf01b5052375d4dd46c27d621","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-12-30T16:05:30Z","title_canon_sha256":"700bc4d23e654179ccf7dfaeae3a52b228522af00cc8c58e21e57dcf73213b9b"},"schema_version":"1.0","source":{"id":"2112.15110","kind":"arxiv","version":2}},"canonical_sha256":"a5f2ec98aa392a14c88aef69dd9c4ad45994c9250e829a4d5c7d2bfb16ea93e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5f2ec98aa392a14c88aef69dd9c4ad45994c9250e829a4d5c7d2bfb16ea93e5","first_computed_at":"2026-07-05T03:59:00.617140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:00.617140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5/iB3ze9RgsvwNSdK78nnSEhohmmOLG2VvND8JWBvcHt542A6vJGRFEDnQ84epqHeWNWeGXaBK88OtEGl8+3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:00.617649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.15110","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ce634d6ca8e87ec8e4bfa5a3844fd318249a12482b3a68c6d0f6a6330ee9b4d","sha256:7183e395638563a2ef9147a804b6345456f9f66e10f2e366ab3300b8ef7ce3ae"],"state_sha256":"db6dc820bd0edc4b5f6954de435aa79dffe6fda6519b1a117bdfcc6bd3539194"}