{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DO4IHICFROUSHULKMR6YF2P2XO","short_pith_number":"pith:DO4IHICF","schema_version":"1.0","canonical_sha256":"1bb883a0458ba923d16a647d82e9fabba51be56600119f7cad41de8cb3a5e175","source":{"kind":"arxiv","id":"2411.16489","version":1},"attestation_state":"computed","paper":{"title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ethan Chern, Haoyang Zou, Pengfei Liu, Shijie Xia, Weizhe Yuan, Xuefeng Li, Yiwei Qin, Yixiu Liu, Yuxiang Zheng, Zhen Huang","submitted_at":"2024-11-25T15:31:27Z","abstract_excerpt":"This paper presents a critical examination of current approaches to replicating OpenAI's O1 model capabilities, with particular focus on the widespread but often undisclosed use of knowledge distillation techniques. While our previous work explored the fundamental technical path to O1 replication, this study reveals how simple distillation from O1's API, combined with supervised fine-tuning, can achieve superior performance on complex mathematical reasoning tasks. Through extensive experiments, we show that a base model fine-tuned on simply tens of thousands of samples O1-distilled long-though"},"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":"2411.16489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T15:31:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d8700e1a180fb3b27d5a1b9f787aefa45ff00c4c114c8c5c2ebe29b3462a92b","abstract_canon_sha256":"c6fe6d5d0a5323693e77b83cd34c39cd757aa04c0793b2737c1e614f6d49fce4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:10.167370Z","signature_b64":"gXp6Zk7iixBVYiLGurjytd+xHyeUC/GvRTi2Id/TNu9ozRytatgZ3W2ZTBFnxXjq1RYLQ3uPbKAWcCQI7AyWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bb883a0458ba923d16a647d82e9fabba51be56600119f7cad41de8cb3a5e175","last_reissued_at":"2026-07-05T09:40:10.166947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:10.166947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ethan Chern, Haoyang Zou, Pengfei Liu, Shijie Xia, Weizhe Yuan, Xuefeng Li, Yiwei Qin, Yixiu Liu, Yuxiang Zheng, Zhen Huang","submitted_at":"2024-11-25T15:31:27Z","abstract_excerpt":"This paper presents a critical examination of current approaches to replicating OpenAI's O1 model capabilities, with particular focus on the widespread but often undisclosed use of knowledge distillation techniques. While our previous work explored the fundamental technical path to O1 replication, this study reveals how simple distillation from O1's API, combined with supervised fine-tuning, can achieve superior performance on complex mathematical reasoning tasks. Through extensive experiments, we show that a base model fine-tuned on simply tens of thousands of samples O1-distilled long-though"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16489","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/2411.16489/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":"2411.16489","created_at":"2026-07-05T09:40:10.167003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16489v1","created_at":"2026-07-05T09:40:10.167003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16489","created_at":"2026-07-05T09:40:10.167003+00:00"},{"alias_kind":"pith_short_12","alias_value":"DO4IHICFROUS","created_at":"2026-07-05T09:40:10.167003+00:00"},{"alias_kind":"pith_short_16","alias_value":"DO4IHICFROUSHULK","created_at":"2026-07-05T09:40:10.167003+00:00"},{"alias_kind":"pith_short_8","alias_value":"DO4IHICF","created_at":"2026-07-05T09:40:10.167003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08401","citing_title":"AIPO: Learning to Reason from Active Interaction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09413","citing_title":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13262","citing_title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13958","citing_title":"ToolRL: Reward is All Tool Learning Needs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":19,"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":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08401","citing_title":"AIPO: Learning to Reason from Active Interaction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05893","citing_title":"Logic-Regularized Verifier Elicits Reasoning from LLMs","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13564","citing_title":"Memory in the Age of AI Agents","ref_index":192,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO","json":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO.json","graph_json":"https://pith.science/api/pith-number/DO4IHICFROUSHULKMR6YF2P2XO/graph.json","events_json":"https://pith.science/api/pith-number/DO4IHICFROUSHULKMR6YF2P2XO/events.json","paper":"https://pith.science/paper/DO4IHICF"},"agent_actions":{"view_html":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO","download_json":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO.json","view_paper":"https://pith.science/paper/DO4IHICF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16489&json=true","fetch_graph":"https://pith.science/api/pith-number/DO4IHICFROUSHULKMR6YF2P2XO/graph.json","fetch_events":"https://pith.science/api/pith-number/DO4IHICFROUSHULKMR6YF2P2XO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO/action/storage_attestation","attest_author":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO/action/author_attestation","sign_citation":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO/action/citation_signature","submit_replication":"https://pith.science/pith/DO4IHICFROUSHULKMR6YF2P2XO/action/replication_record"}},"created_at":"2026-07-05T09:40:10.167003+00:00","updated_at":"2026-07-05T09:40:10.167003+00:00"}