{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MWGKR26BFF2FIMKVWM3XEGJORM","short_pith_number":"pith:MWGKR26B","schema_version":"1.0","canonical_sha256":"658ca8ebc12974543155b33772192e8b27e9fdd4cc84d00925ee34073f20cbc8","source":{"kind":"arxiv","id":"2412.16849","version":1},"attestation_state":"computed","paper":{"title":"OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiangming Shu, Jinlin Xiao, Jitao Sang, Yuhang Wang, Yuqi Yang, Yuxiang Zhang","submitted_at":"2024-12-22T04:21:30Z","abstract_excerpt":"OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents \\emph{OpenRFT}, our attempt to fine-tune generalist reasoning models for domain-specific tasks under the same settings as RFT. OpenRFT addresses two key challenges of lacking reasoning step data and the limited quantity of training samples, by leveraging the domain-specific samples in three ways: question augmentation, synthesizing reasoning-process data, and few-shot ICL. "},"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":"2412.16849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-22T04:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"16061d2007559a719af746ae2762c34e9f3ef8343361216c1e95dd2721aa26e2","abstract_canon_sha256":"db5489e364e6717ee07d383324b78e352c8cc4471cab113db0eb6f05cd64db9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:13.663982Z","signature_b64":"B5pxRP+HjBGybdW9HXVNKd6KY8BMYyV8R4VTIvfnBhmLOyfl5A/Sj/Y7ulSih+fvnc4IXvIXQf08fwwQnmB2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"658ca8ebc12974543155b33772192e8b27e9fdd4cc84d00925ee34073f20cbc8","last_reissued_at":"2026-07-05T09:53:13.663529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:13.663529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiangming Shu, Jinlin Xiao, Jitao Sang, Yuhang Wang, Yuqi Yang, Yuxiang Zhang","submitted_at":"2024-12-22T04:21:30Z","abstract_excerpt":"OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents \\emph{OpenRFT}, our attempt to fine-tune generalist reasoning models for domain-specific tasks under the same settings as RFT. OpenRFT addresses two key challenges of lacking reasoning step data and the limited quantity of training samples, by leveraging the domain-specific samples in three ways: question augmentation, synthesizing reasoning-process data, and few-shot ICL. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16849","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/2412.16849/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":"2412.16849","created_at":"2026-07-05T09:53:13.663585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16849v1","created_at":"2026-07-05T09:53:13.663585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16849","created_at":"2026-07-05T09:53:13.663585+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWGKR26BFF2F","created_at":"2026-07-05T09:53:13.663585+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWGKR26BFF2FIMKV","created_at":"2026-07-05T09:53:13.663585+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWGKR26B","created_at":"2026-07-05T09:53:13.663585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":162,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM","json":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM.json","graph_json":"https://pith.science/api/pith-number/MWGKR26BFF2FIMKVWM3XEGJORM/graph.json","events_json":"https://pith.science/api/pith-number/MWGKR26BFF2FIMKVWM3XEGJORM/events.json","paper":"https://pith.science/paper/MWGKR26B"},"agent_actions":{"view_html":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM","download_json":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM.json","view_paper":"https://pith.science/paper/MWGKR26B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16849&json=true","fetch_graph":"https://pith.science/api/pith-number/MWGKR26BFF2FIMKVWM3XEGJORM/graph.json","fetch_events":"https://pith.science/api/pith-number/MWGKR26BFF2FIMKVWM3XEGJORM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM/action/storage_attestation","attest_author":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM/action/author_attestation","sign_citation":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM/action/citation_signature","submit_replication":"https://pith.science/pith/MWGKR26BFF2FIMKVWM3XEGJORM/action/replication_record"}},"created_at":"2026-07-05T09:53:13.663585+00:00","updated_at":"2026-07-05T09:53:13.663585+00:00"}