{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YVGR45M6NSAWGZFUIBYH4LKC3Z","short_pith_number":"pith:YVGR45M6","schema_version":"1.0","canonical_sha256":"c54d1e759e6c816364b440707e2d42de76efc0c01866a7c53f2d7695b15dcd57","source":{"kind":"arxiv","id":"2111.13468","version":1},"attestation_state":"computed","paper":{"title":"Emotion Embedding Spaces for Matching Music to Stories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gautham J. Mysore, Justin Salamon, Minz Won, Nicholas J. Bryan, Xavier Serra","submitted_at":"2021-11-26T12:31:41Z","abstract_excerpt":"Content creators often use music to enhance their stories, as it can be a powerful tool to convey emotion. In this paper, our goal is to help creators find music to match the emotion of their story. We focus on text-based stories that can be auralized (e.g., books), use multiple sentences as input queries, and automatically retrieve matching music. We formalize this task as a cross-modal text-to-music retrieval problem. Both the music and text domains have existing datasets with emotion labels, but mismatched emotion vocabularies prevent us from using mood or emotion annotations directly for m"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.13468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-11-26T12:31:41Z","cross_cats_sorted":[],"title_canon_sha256":"5a9fd974ffc79b832bb7ad29ce6edbde33054d80324d064e617e91cdcc7a0489","abstract_canon_sha256":"2a0d7dd2bebfc2320c476dcaf4dce02afdc324f8b0beb286e55991f269c615c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:21.652785Z","signature_b64":"7BeSicfB95GJePtxcYhoJWWkkl6S2en667OS02O6z3LWEHlYTl5YK4qmOaXwZAIFO6+CI3uN77vGN9l6jPwIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c54d1e759e6c816364b440707e2d42de76efc0c01866a7c53f2d7695b15dcd57","last_reissued_at":"2026-07-05T03:35:21.652212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:21.652212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emotion Embedding Spaces for Matching Music to Stories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gautham J. Mysore, Justin Salamon, Minz Won, Nicholas J. Bryan, Xavier Serra","submitted_at":"2021-11-26T12:31:41Z","abstract_excerpt":"Content creators often use music to enhance their stories, as it can be a powerful tool to convey emotion. In this paper, our goal is to help creators find music to match the emotion of their story. We focus on text-based stories that can be auralized (e.g., books), use multiple sentences as input queries, and automatically retrieve matching music. We formalize this task as a cross-modal text-to-music retrieval problem. Both the music and text domains have existing datasets with emotion labels, but mismatched emotion vocabularies prevent us from using mood or emotion annotations directly for m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13468","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.13468/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.13468","created_at":"2026-07-05T03:35:21.652264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13468v1","created_at":"2026-07-05T03:35:21.652264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13468","created_at":"2026-07-05T03:35:21.652264+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVGR45M6NSAW","created_at":"2026-07-05T03:35:21.652264+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVGR45M6NSAWGZFU","created_at":"2026-07-05T03:35:21.652264+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVGR45M6","created_at":"2026-07-05T03:35:21.652264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12573","citing_title":"Video-Guided Text-to-Music Generation Using Public Domain Movie Collections","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z","json":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z.json","graph_json":"https://pith.science/api/pith-number/YVGR45M6NSAWGZFUIBYH4LKC3Z/graph.json","events_json":"https://pith.science/api/pith-number/YVGR45M6NSAWGZFUIBYH4LKC3Z/events.json","paper":"https://pith.science/paper/YVGR45M6"},"agent_actions":{"view_html":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z","download_json":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z.json","view_paper":"https://pith.science/paper/YVGR45M6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13468&json=true","fetch_graph":"https://pith.science/api/pith-number/YVGR45M6NSAWGZFUIBYH4LKC3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/YVGR45M6NSAWGZFUIBYH4LKC3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z/action/storage_attestation","attest_author":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z/action/author_attestation","sign_citation":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z/action/citation_signature","submit_replication":"https://pith.science/pith/YVGR45M6NSAWGZFUIBYH4LKC3Z/action/replication_record"}},"created_at":"2026-07-05T03:35:21.652264+00:00","updated_at":"2026-07-05T03:35:21.652264+00:00"}