{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5HJWPXAXLKTEE5CKXMGI6M4KL3","short_pith_number":"pith:5HJWPXAX","schema_version":"1.0","canonical_sha256":"e9d367dc175aa642744abb0c8f338a5ee757b5707ce0f7f0f0f53890d468f69e","source":{"kind":"arxiv","id":"2501.14431","version":2},"attestation_state":"computed","paper":{"title":"Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Guanyu Wang, Hanlin Xue, Tong Mo, Weiping Li, Xu Chu, Zhijie Tan","submitted_at":"2025-01-24T11:57:39Z","abstract_excerpt":"Large Language Models (LLMs) are widely applied to downstream domains. However, current LLMs for high-stakes domain tasks, such as financial investment and legal QA, typically generate brief answers without reasoning processes and explanations. This limits users' confidence in making decisions based on their responses. While original CoT shows promise, it lacks self-correction mechanisms during reasoning. This work introduces Domain$o1$s, which enhances LLMs' reasoning capabilities on domain tasks through supervised fine-tuning and tree search. We construct CoT-stock-2k and CoT-legal-2k datase"},"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":"2501.14431","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T11:57:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb07d19ac288aec00a77cc6a1820f79e8761a33108e2bd5257e7fbf8e27f4775","abstract_canon_sha256":"8b1819b52e1b40dcbe5fdaf12ed8b1142003fb8e7906b2819f2c876ed383e550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:50.652075Z","signature_b64":"6Xky402zgvtTFCc9ww/M2Fxtn+KsVlYOy1zuTwmkZbfeXYAbFMaRQ8pzMtBCZ0HfJYwx/hSFS9M+xQuhGr0nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d367dc175aa642744abb0c8f338a5ee757b5707ce0f7f0f0f53890d468f69e","last_reissued_at":"2026-07-05T11:10:50.651504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:50.651504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Guanyu Wang, Hanlin Xue, Tong Mo, Weiping Li, Xu Chu, Zhijie Tan","submitted_at":"2025-01-24T11:57:39Z","abstract_excerpt":"Large Language Models (LLMs) are widely applied to downstream domains. However, current LLMs for high-stakes domain tasks, such as financial investment and legal QA, typically generate brief answers without reasoning processes and explanations. This limits users' confidence in making decisions based on their responses. While original CoT shows promise, it lacks self-correction mechanisms during reasoning. This work introduces Domain$o1$s, which enhances LLMs' reasoning capabilities on domain tasks through supervised fine-tuning and tree search. We construct CoT-stock-2k and CoT-legal-2k datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14431","kind":"arxiv","version":2},"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/2501.14431/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":"2501.14431","created_at":"2026-07-05T11:10:50.651584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14431v2","created_at":"2026-07-05T11:10:50.651584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14431","created_at":"2026-07-05T11:10:50.651584+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HJWPXAXLKTE","created_at":"2026-07-05T11:10:50.651584+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HJWPXAXLKTEE5CK","created_at":"2026-07-05T11:10:50.651584+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HJWPXAX","created_at":"2026-07-05T11:10:50.651584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07020","citing_title":"MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insights","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11974","citing_title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3","json":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3.json","graph_json":"https://pith.science/api/pith-number/5HJWPXAXLKTEE5CKXMGI6M4KL3/graph.json","events_json":"https://pith.science/api/pith-number/5HJWPXAXLKTEE5CKXMGI6M4KL3/events.json","paper":"https://pith.science/paper/5HJWPXAX"},"agent_actions":{"view_html":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3","download_json":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3.json","view_paper":"https://pith.science/paper/5HJWPXAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14431&json=true","fetch_graph":"https://pith.science/api/pith-number/5HJWPXAXLKTEE5CKXMGI6M4KL3/graph.json","fetch_events":"https://pith.science/api/pith-number/5HJWPXAXLKTEE5CKXMGI6M4KL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3/action/storage_attestation","attest_author":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3/action/author_attestation","sign_citation":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3/action/citation_signature","submit_replication":"https://pith.science/pith/5HJWPXAXLKTEE5CKXMGI6M4KL3/action/replication_record"}},"created_at":"2026-07-05T11:10:50.651584+00:00","updated_at":"2026-07-05T11:10:50.651584+00:00"}