{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4VARHFECJCWMGMOJPQSDVGPNYO","short_pith_number":"pith:4VARHFEC","schema_version":"1.0","canonical_sha256":"e54113948248acc331c97c243a99edc3823bd734b1ea7cccfe80d73b6216bf60","source":{"kind":"arxiv","id":"2510.11391","version":3},"attestation_state":"computed","paper":{"title":"DocReward: A Document Reward Model for Structuring and Stylizing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bowen Cao, FNU Kartik, Furu Wei, Huitian Jiao, Jiayu Ding, Junpeng Liu, Lei Cui, Li Dong, Nan Yang, Shaohan Huang, Si-Qing Chen, Sun Mao, Tao Ge, Tengchao Lv, Wai Lam, Wenshan Wu, Xun Wang, Yilin Jia, Yupan Huang, Yuzhong Zhao","submitted_at":"2025-10-13T13:36:32Z","abstract_excerpt":"Recent agentic workflows automate professional document generation but focus narrowly on textual quality, overlooking structural and stylistic professionalism, which is equally critical for readability. This gap stems mainly from a lack of effective reward models capable of guiding agents toward producing documents with high structural and stylistic professionalism. We introduce DocReward, a document reward model that evaluates documents based on their structure and style. To achieve this, we propose a textual-quality-agnostic framework that ensures assessments are not confounded by content qu"},"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":"2510.11391","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-13T13:36:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7c75f6d530ede1ba7cfe58c670d705ca80fc3317dc8afee11d0c7bcc6fd7763a","abstract_canon_sha256":"6c87c743894c3caab1a948d27718aa613ecc5fb79f303fb44aaacb7604930b3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:34.908115Z","signature_b64":"2+Fa79SXBq1hfD8RgOtA0ww1w5jLqi+Y7SUroi8r1Lz55m+nQ84O00+awo4X4Ndy2KVAr0xAJhyr+NoXaUY5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e54113948248acc331c97c243a99edc3823bd734b1ea7cccfe80d73b6216bf60","last_reissued_at":"2026-05-20T00:05:34.907282Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:34.907282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocReward: A Document Reward Model for Structuring and Stylizing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bowen Cao, FNU Kartik, Furu Wei, Huitian Jiao, Jiayu Ding, Junpeng Liu, Lei Cui, Li Dong, Nan Yang, Shaohan Huang, Si-Qing Chen, Sun Mao, Tao Ge, Tengchao Lv, Wai Lam, Wenshan Wu, Xun Wang, Yilin Jia, Yupan Huang, Yuzhong Zhao","submitted_at":"2025-10-13T13:36:32Z","abstract_excerpt":"Recent agentic workflows automate professional document generation but focus narrowly on textual quality, overlooking structural and stylistic professionalism, which is equally critical for readability. This gap stems mainly from a lack of effective reward models capable of guiding agents toward producing documents with high structural and stylistic professionalism. We introduce DocReward, a document reward model that evaluates documents based on their structure and style. To achieve this, we propose a textual-quality-agnostic framework that ensures assessments are not confounded by content qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.11391","kind":"arxiv","version":3},"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/2510.11391/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":"2510.11391","created_at":"2026-05-20T00:05:34.907438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.11391v3","created_at":"2026-05-20T00:05:34.907438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11391","created_at":"2026-05-20T00:05:34.907438+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VARHFECJCWM","created_at":"2026-05-20T00:05:34.907438+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VARHFECJCWMGMOJ","created_at":"2026-05-20T00:05:34.907438+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VARHFEC","created_at":"2026-05-20T00:05:34.907438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.10341","citing_title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","ref_index":131,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO","json":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO.json","graph_json":"https://pith.science/api/pith-number/4VARHFECJCWMGMOJPQSDVGPNYO/graph.json","events_json":"https://pith.science/api/pith-number/4VARHFECJCWMGMOJPQSDVGPNYO/events.json","paper":"https://pith.science/paper/4VARHFEC"},"agent_actions":{"view_html":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO","download_json":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO.json","view_paper":"https://pith.science/paper/4VARHFEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.11391&json=true","fetch_graph":"https://pith.science/api/pith-number/4VARHFECJCWMGMOJPQSDVGPNYO/graph.json","fetch_events":"https://pith.science/api/pith-number/4VARHFECJCWMGMOJPQSDVGPNYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO/action/storage_attestation","attest_author":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO/action/author_attestation","sign_citation":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO/action/citation_signature","submit_replication":"https://pith.science/pith/4VARHFECJCWMGMOJPQSDVGPNYO/action/replication_record"}},"created_at":"2026-05-20T00:05:34.907438+00:00","updated_at":"2026-05-20T00:05:34.907438+00:00"}