{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:36WYPCLPTGQOZ3QC5YTEYPUCIQ","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":"16186e1ec841458b9214d33ea80abe4d85c7effe3f0809f00a4523f8f0fd5032","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T18:01:20Z","title_canon_sha256":"97384b502f7d31d8cbb887c6f0f42b44b851944e705c856d7384a0b45b7b2e5a"},"schema_version":"1.0","source":{"id":"2606.10010","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10010","created_at":"2026-06-10T00:08:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10010v1","created_at":"2026-06-10T00:08:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10010","created_at":"2026-06-10T00:08:42Z"},{"alias_kind":"pith_short_12","alias_value":"36WYPCLPTGQO","created_at":"2026-06-10T00:08:42Z"},{"alias_kind":"pith_short_16","alias_value":"36WYPCLPTGQOZ3QC","created_at":"2026-06-10T00:08:42Z"},{"alias_kind":"pith_short_8","alias_value":"36WYPCLP","created_at":"2026-06-10T00:08:42Z"}],"graph_snapshots":[{"event_id":"sha256:c36cd1b19af5c7e0ef27a4968ce7af90da5f2bba718d2950c897cae77d8fbd00","target":"graph","created_at":"2026-06-10T00:08:42Z","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/2606.10010/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Berlin Chen, Chien-Chun Wang, Hsin-Min Wang, Hung-Shin Lee","cross_cats":["cs.AI","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T18:01:20Z","title":"DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10010","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":"sha256:07c1e07163eb9f96d611d4e4a587c604a12182da0637555c222b2c16ae7965b5","target":"record","created_at":"2026-06-10T00:08:42Z","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":"16186e1ec841458b9214d33ea80abe4d85c7effe3f0809f00a4523f8f0fd5032","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T18:01:20Z","title_canon_sha256":"97384b502f7d31d8cbb887c6f0f42b44b851944e705c856d7384a0b45b7b2e5a"},"schema_version":"1.0","source":{"id":"2606.10010","kind":"arxiv","version":1}},"canonical_sha256":"dfad87896f99a0ecee02ee264c3e824403a89ebbce1a13423969c7e9ad939727","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfad87896f99a0ecee02ee264c3e824403a89ebbce1a13423969c7e9ad939727","first_computed_at":"2026-06-10T00:08:42.639137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:42.639137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9U+Cxxe+DG1wV0huYC+COy6wQFMK8Ocn9+N88rndg/3wcMTYglM2UF3DhUpU6FVm2kVr1Q7ynuGTSu1HOWyOCg==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:42.640457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10010","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07c1e07163eb9f96d611d4e4a587c604a12182da0637555c222b2c16ae7965b5","sha256:c36cd1b19af5c7e0ef27a4968ce7af90da5f2bba718d2950c897cae77d8fbd00"],"state_sha256":"eae4a9222dfab901002e9e5607c9c2a8845969461e2fd5f76169eb211f882993"}