{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:36WYPCLPTGQOZ3QC5YTEYPUCIQ","short_pith_number":"pith:36WYPCLP","schema_version":"1.0","canonical_sha256":"dfad87896f99a0ecee02ee264c3e824403a89ebbce1a13423969c7e9ad939727","source":{"kind":"arxiv","id":"2606.10010","version":1},"attestation_state":"computed","paper":{"title":"DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Chien-Chun Wang, Hsin-Min Wang, Hung-Shin Lee","submitted_at":"2026-06-08T18:01:20Z","abstract_excerpt":"Evaluating text-to-music (TTM) systems remains expensive because music impression (MI) and text alignment (TA) scores rely on human mean opinion scores (MOS). Most automatic MOS estimators are trained with point-wise regression or distributional classification. These objectives do not directly optimize rank-based metrics and provide weak geometric constraints for cross-modal coherence. To address these gaps, we propose DeRA-MOS, a decoupled optimization framework for TTM evaluation. For MI, we introduce a batch-aware listwise ranking loss that models relative order within each mini-batch and b"},"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":"2606.10010","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T18:01:20Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"title_canon_sha256":"97384b502f7d31d8cbb887c6f0f42b44b851944e705c856d7384a0b45b7b2e5a","abstract_canon_sha256":"16186e1ec841458b9214d33ea80abe4d85c7effe3f0809f00a4523f8f0fd5032"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:42.640457Z","signature_b64":"9U+Cxxe+DG1wV0huYC+COy6wQFMK8Ocn9+N88rndg/3wcMTYglM2UF3DhUpU6FVm2kVr1Q7ynuGTSu1HOWyOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfad87896f99a0ecee02ee264c3e824403a89ebbce1a13423969c7e9ad939727","last_reissued_at":"2026-06-10T00:08:42.639137Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:42.639137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Chien-Chun Wang, Hsin-Min Wang, Hung-Shin Lee","submitted_at":"2026-06-08T18:01:20Z","abstract_excerpt":"Evaluating text-to-music (TTM) systems remains expensive because music impression (MI) and text alignment (TA) scores rely on human mean opinion scores (MOS). Most automatic MOS estimators are trained with point-wise regression or distributional classification. These objectives do not directly optimize rank-based metrics and provide weak geometric constraints for cross-modal coherence. To address these gaps, we propose DeRA-MOS, a decoupled optimization framework for TTM evaluation. For MI, we introduce a batch-aware listwise ranking loss that models relative order within each mini-batch and b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10010","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/2606.10010/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":"2606.10010","created_at":"2026-06-10T00:08:42.639292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10010v1","created_at":"2026-06-10T00:08:42.639292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10010","created_at":"2026-06-10T00:08:42.639292+00:00"},{"alias_kind":"pith_short_12","alias_value":"36WYPCLPTGQO","created_at":"2026-06-10T00:08:42.639292+00:00"},{"alias_kind":"pith_short_16","alias_value":"36WYPCLPTGQOZ3QC","created_at":"2026-06-10T00:08:42.639292+00:00"},{"alias_kind":"pith_short_8","alias_value":"36WYPCLP","created_at":"2026-06-10T00:08:42.639292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ","json":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ.json","graph_json":"https://pith.science/api/pith-number/36WYPCLPTGQOZ3QC5YTEYPUCIQ/graph.json","events_json":"https://pith.science/api/pith-number/36WYPCLPTGQOZ3QC5YTEYPUCIQ/events.json","paper":"https://pith.science/paper/36WYPCLP"},"agent_actions":{"view_html":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ","download_json":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ.json","view_paper":"https://pith.science/paper/36WYPCLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10010&json=true","fetch_graph":"https://pith.science/api/pith-number/36WYPCLPTGQOZ3QC5YTEYPUCIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/36WYPCLPTGQOZ3QC5YTEYPUCIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ/action/storage_attestation","attest_author":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ/action/author_attestation","sign_citation":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ/action/citation_signature","submit_replication":"https://pith.science/pith/36WYPCLPTGQOZ3QC5YTEYPUCIQ/action/replication_record"}},"created_at":"2026-06-10T00:08:42.639292+00:00","updated_at":"2026-06-10T00:08:42.639292+00:00"}