{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TJL7GJHD2AV7J7PXN3NZJZALAL","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":"b038cdfe38de45f93f1cfd47885d89be8159cc25894845ca4477a649eff39ba0","cross_cats_sorted":["cs.IR","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-26T12:52:56Z","title_canon_sha256":"bbe9bf7a830ecc34ec3b479eb5e5470f7877f56152a63d54664312f6d8628091"},"schema_version":"1.0","source":{"id":"2401.14826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14826","created_at":"2026-07-05T07:38:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14826v1","created_at":"2026-07-05T07:38:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14826","created_at":"2026-07-05T07:38:02Z"},{"alias_kind":"pith_short_12","alias_value":"TJL7GJHD2AV7","created_at":"2026-07-05T07:38:02Z"},{"alias_kind":"pith_short_16","alias_value":"TJL7GJHD2AV7J7PX","created_at":"2026-07-05T07:38:02Z"},{"alias_kind":"pith_short_8","alias_value":"TJL7GJHD","created_at":"2026-07-05T07:38:02Z"}],"graph_snapshots":[{"event_id":"sha256:915db3dbd674fa5b5efadb21030c90b14d4784d13f6e5ca3f02aa5b93408e6b8","target":"graph","created_at":"2026-07-05T07:38:02Z","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/2401.14826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores a specific sub-task of cross-modal music retrieval. We consider the delicate task of retrieving a performance or rendition of a musical piece based on a description of its style, expressive character, or emotion from a set of different performances of the same piece. We observe that a general purpose cross-modal system trained to learn a common text-audio embedding space does not yield optimal results for this task. By introducing two changes -- one each to the text encoder and the audio encoder -- we demonstrate improved performance on a dataset of piano performances and a","authors_text":"Gerhard Widmer, Shreyan Chowdhury","cross_cats":["cs.IR","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-26T12:52:56Z","title":"Expressivity-aware Music Performance Retrieval using Mid-level Perceptual Features and Emotion Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14826","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:b7d82336dbe039dcd00125d82ebeb971ae8f5c6e5b3ede8c264865e6ac865562","target":"record","created_at":"2026-07-05T07:38:02Z","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":"b038cdfe38de45f93f1cfd47885d89be8159cc25894845ca4477a649eff39ba0","cross_cats_sorted":["cs.IR","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-26T12:52:56Z","title_canon_sha256":"bbe9bf7a830ecc34ec3b479eb5e5470f7877f56152a63d54664312f6d8628091"},"schema_version":"1.0","source":{"id":"2401.14826","kind":"arxiv","version":1}},"canonical_sha256":"9a57f324e3d02bf4fdf76edb94e40b02f1098bf506908e4e26799414432e3e23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a57f324e3d02bf4fdf76edb94e40b02f1098bf506908e4e26799414432e3e23","first_computed_at":"2026-07-05T07:38:02.353071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:02.353071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dEHs8dn8cT2RMf2mXzJJQ4cFi4BkC2F68arjfSFlLyJq+49yhXkRh3zy5Dv7v4cWog9HO9yqOcJUEVNHiladCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:02.353517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7d82336dbe039dcd00125d82ebeb971ae8f5c6e5b3ede8c264865e6ac865562","sha256:915db3dbd674fa5b5efadb21030c90b14d4784d13f6e5ca3f02aa5b93408e6b8"],"state_sha256":"33f09c303bac89f6ef14beb14b677a7959da087fd8e1b37e1a8ff21564cfbab2"}