{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HXWUHAF6LLOMPPLOB2AVK6NM4Q","short_pith_number":"pith:HXWUHAF6","schema_version":"1.0","canonical_sha256":"3ded4380be5adcc7bd6e0e815579ace424ab3c10d4abfc2ed9e0dc8c82b6c020","source":{"kind":"arxiv","id":"2605.25731","version":1},"attestation_state":"computed","paper":{"title":"Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxi Miao, Jiaxin Wang, Sanwoo Lee, Weikang Li, Yunfang Wu, Zhengyang Wang","submitted_at":"2026-05-25T11:41:37Z","abstract_excerpt":"Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring models remains underexplored. In this paper, we propose Trait-Aware Policy Optimization (TAPO), a post-training framework tailored to autoregressive multi-trait scoring. Our method decomposes rewards along both the sample and trait dimensions, combining global scoring consistency, trait-level accuracy, format validity, and inter-trait dependency preservation. In addition, we enhance supervised fine-tuning with enhanced pr"},"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":"2605.25731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T11:41:37Z","cross_cats_sorted":[],"title_canon_sha256":"9c1812d22af6cb032ad61562cbcdd503c03f5d14fe9ef18ccdb0a3a552d5e298","abstract_canon_sha256":"1ac3e7dad776f8211276bf34030b03a141de2db0e1ae933eca2a2de3f29a179f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:52.491964Z","signature_b64":"IVWA2C80WvJ7Z9Elyj3FMaPrh9ayPvMfUX8Zk2cIVRZh8DfbrD+sZEq8k0kK8sRaynLrT2MPzpS6dj95zx8HBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ded4380be5adcc7bd6e0e815579ace424ab3c10d4abfc2ed9e0dc8c82b6c020","last_reissued_at":"2026-05-26T02:04:52.491230Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:52.491230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxi Miao, Jiaxin Wang, Sanwoo Lee, Weikang Li, Yunfang Wu, Zhengyang Wang","submitted_at":"2026-05-25T11:41:37Z","abstract_excerpt":"Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring models remains underexplored. In this paper, we propose Trait-Aware Policy Optimization (TAPO), a post-training framework tailored to autoregressive multi-trait scoring. Our method decomposes rewards along both the sample and trait dimensions, combining global scoring consistency, trait-level accuracy, format validity, and inter-trait dependency preservation. In addition, we enhance supervised fine-tuning with enhanced pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25731","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/2605.25731/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":"2605.25731","created_at":"2026-05-26T02:04:52.491373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25731v1","created_at":"2026-05-26T02:04:52.491373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25731","created_at":"2026-05-26T02:04:52.491373+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXWUHAF6LLOM","created_at":"2026-05-26T02:04:52.491373+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXWUHAF6LLOMPPLO","created_at":"2026-05-26T02:04:52.491373+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXWUHAF6","created_at":"2026-05-26T02:04:52.491373+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/HXWUHAF6LLOMPPLOB2AVK6NM4Q","json":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q.json","graph_json":"https://pith.science/api/pith-number/HXWUHAF6LLOMPPLOB2AVK6NM4Q/graph.json","events_json":"https://pith.science/api/pith-number/HXWUHAF6LLOMPPLOB2AVK6NM4Q/events.json","paper":"https://pith.science/paper/HXWUHAF6"},"agent_actions":{"view_html":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q","download_json":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q.json","view_paper":"https://pith.science/paper/HXWUHAF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25731&json=true","fetch_graph":"https://pith.science/api/pith-number/HXWUHAF6LLOMPPLOB2AVK6NM4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/HXWUHAF6LLOMPPLOB2AVK6NM4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q/action/storage_attestation","attest_author":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q/action/author_attestation","sign_citation":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q/action/citation_signature","submit_replication":"https://pith.science/pith/HXWUHAF6LLOMPPLOB2AVK6NM4Q/action/replication_record"}},"created_at":"2026-05-26T02:04:52.491373+00:00","updated_at":"2026-05-26T02:04:52.491373+00:00"}