{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6ITHSQS7CKUWAENL73W73MIERU","short_pith_number":"pith:6ITHSQS7","schema_version":"1.0","canonical_sha256":"f22679425f12a96011abfeedfdb1048d1b0ea7862a74e5b6fc11076ad6997aa3","source":{"kind":"arxiv","id":"2412.14135","version":1},"attestation_state":"computed","paper":{"title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bo Wang, Qinyuan Cheng, Qipeng Guo, Shimin Li, Xipeng Qiu, Xuanjing Huang, Yunhua Zhou, Zhangyue Yin, Zhiyuan Zeng","submitted_at":"2024-12-18T18:24:47Z","abstract_excerpt":"OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability.OpenAI has claimed that the main techinique behinds o1 is the reinforcement learining. Recent works use alternative approaches like knowledge distillation to imitate o1's reasoning style, but their effectiveness is limited by the capability ceiling of the teacher model. Therefore, this paper analyzes the roadmap to achieving o1 from the perspective of reinforcement learning, focusing on four key components: policy init"},"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":"2412.14135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-18T18:24:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e2e56da829f34f1265e87974b4f6b4927a678d9af4d9e13bb036b33d1244b7e","abstract_canon_sha256":"bb57e7a6b32bfafeffd3e5f08ac491e7709c533d52078abddf99c2db76b125e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:14.125008Z","signature_b64":"XVKel8buYx6s3Rpy0606aGpXp5WxQufo+wzyL+XAuhAbNfIvVXFFCBjtesM/+EImjA4tffYKwa0iep+ul+8wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f22679425f12a96011abfeedfdb1048d1b0ea7862a74e5b6fc11076ad6997aa3","last_reissued_at":"2026-07-05T09:51:14.124606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:14.124606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bo Wang, Qinyuan Cheng, Qipeng Guo, Shimin Li, Xipeng Qiu, Xuanjing Huang, Yunhua Zhou, Zhangyue Yin, Zhiyuan Zeng","submitted_at":"2024-12-18T18:24:47Z","abstract_excerpt":"OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability.OpenAI has claimed that the main techinique behinds o1 is the reinforcement learining. Recent works use alternative approaches like knowledge distillation to imitate o1's reasoning style, but their effectiveness is limited by the capability ceiling of the teacher model. Therefore, this paper analyzes the roadmap to achieving o1 from the perspective of reinforcement learning, focusing on four key components: policy init"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14135","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/2412.14135/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":"2412.14135","created_at":"2026-07-05T09:51:14.124663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14135v1","created_at":"2026-07-05T09:51:14.124663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14135","created_at":"2026-07-05T09:51:14.124663+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ITHSQS7CKUW","created_at":"2026-07-05T09:51:14.124663+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ITHSQS7CKUWAENL","created_at":"2026-07-05T09:51:14.124663+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ITHSQS7","created_at":"2026-07-05T09:51:14.124663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00862","citing_title":"CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13351","citing_title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":251,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":266,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU","json":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU.json","graph_json":"https://pith.science/api/pith-number/6ITHSQS7CKUWAENL73W73MIERU/graph.json","events_json":"https://pith.science/api/pith-number/6ITHSQS7CKUWAENL73W73MIERU/events.json","paper":"https://pith.science/paper/6ITHSQS7"},"agent_actions":{"view_html":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU","download_json":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU.json","view_paper":"https://pith.science/paper/6ITHSQS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14135&json=true","fetch_graph":"https://pith.science/api/pith-number/6ITHSQS7CKUWAENL73W73MIERU/graph.json","fetch_events":"https://pith.science/api/pith-number/6ITHSQS7CKUWAENL73W73MIERU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/action/storage_attestation","attest_author":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/action/author_attestation","sign_citation":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/action/citation_signature","submit_replication":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/action/replication_record"}},"created_at":"2026-07-05T09:51:14.124663+00:00","updated_at":"2026-07-05T09:51:14.124663+00:00"}