{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OV44D3WUXZJLMRYWDI3SEVKSBQ","short_pith_number":"pith:OV44D3WU","schema_version":"1.0","canonical_sha256":"7579c1eed4be52b647161a372255520c18aeac60a8e42f4dfada142e3bb66e92","source":{"kind":"arxiv","id":"2412.00154","version":2},"attestation_state":"computed","paper":{"title":"o1-Coder: an o1 Replication for Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chao Kong, Jiangming Shu, Jinlin Xiao, Jitao Sang, Shangxi Wu, Yuqi Yang, Yuxiang Zhang","submitted_at":"2024-11-29T07:19:56Z","abstract_excerpt":"The technical report introduces O1-CODER, an attempt to replicate OpenAI's o1 model with a focus on coding tasks. It integrates reinforcement learning (RL) and Monte Carlo Tree Search (MCTS) to enhance the model's System-2 thinking capabilities. The framework includes training a Test Case Generator (TCG) for standardized code testing, using MCTS to generate code data with reasoning processes, and iteratively fine-tuning the policy model to initially produce pseudocode and then generate the full code. The report also addresses the opportunities and challenges in deploying o1-like models in real"},"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":"2412.00154","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-29T07:19:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fcff0c8a0832ed8ea5207db19bb41e6a5b5426c29779782d4cd5f8143a7992b","abstract_canon_sha256":"393ac2b652ce497fc5bffcff884e957a6d124005d7cb0de89770729e13cb66dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:55.378143Z","signature_b64":"zfwzCMbNGSt9Bq+zYPVLHn6J+iTiyvzdMofTlRPBnLR1fJjAxWqtne/BQojfbonXD9SN3xDXy8GmOo+dPckIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7579c1eed4be52b647161a372255520c18aeac60a8e42f4dfada142e3bb66e92","last_reissued_at":"2026-07-05T09:46:55.377608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:55.377608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"o1-Coder: an o1 Replication for Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chao Kong, Jiangming Shu, Jinlin Xiao, Jitao Sang, Shangxi Wu, Yuqi Yang, Yuxiang Zhang","submitted_at":"2024-11-29T07:19:56Z","abstract_excerpt":"The technical report introduces O1-CODER, an attempt to replicate OpenAI's o1 model with a focus on coding tasks. It integrates reinforcement learning (RL) and Monte Carlo Tree Search (MCTS) to enhance the model's System-2 thinking capabilities. The framework includes training a Test Case Generator (TCG) for standardized code testing, using MCTS to generate code data with reasoning processes, and iteratively fine-tuning the policy model to initially produce pseudocode and then generate the full code. The report also addresses the opportunities and challenges in deploying o1-like models in real"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00154","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/2412.00154/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":"2412.00154","created_at":"2026-07-05T09:46:55.377671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00154v2","created_at":"2026-07-05T09:46:55.377671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00154","created_at":"2026-07-05T09:46:55.377671+00:00"},{"alias_kind":"pith_short_12","alias_value":"OV44D3WUXZJL","created_at":"2026-07-05T09:46:55.377671+00:00"},{"alias_kind":"pith_short_16","alias_value":"OV44D3WUXZJLMRYW","created_at":"2026-07-05T09:46:55.377671+00:00"},{"alias_kind":"pith_short_8","alias_value":"OV44D3WU","created_at":"2026-07-05T09:46:55.377671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"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":13,"is_internal_anchor":false},{"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":160,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06856","citing_title":"Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11989","citing_title":"Thought Graph Traversal for Test-time Scaling in Chest X-ray VLLMs","ref_index":7,"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":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07906","citing_title":"AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2503.01785","citing_title":"Visual-RFT: Visual Reinforcement Fine-Tuning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03144","citing_title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":81,"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":122,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19144","citing_title":"ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ","json":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ.json","graph_json":"https://pith.science/api/pith-number/OV44D3WUXZJLMRYWDI3SEVKSBQ/graph.json","events_json":"https://pith.science/api/pith-number/OV44D3WUXZJLMRYWDI3SEVKSBQ/events.json","paper":"https://pith.science/paper/OV44D3WU"},"agent_actions":{"view_html":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ","download_json":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ.json","view_paper":"https://pith.science/paper/OV44D3WU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00154&json=true","fetch_graph":"https://pith.science/api/pith-number/OV44D3WUXZJLMRYWDI3SEVKSBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/OV44D3WUXZJLMRYWDI3SEVKSBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ/action/storage_attestation","attest_author":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ/action/author_attestation","sign_citation":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ/action/citation_signature","submit_replication":"https://pith.science/pith/OV44D3WUXZJLMRYWDI3SEVKSBQ/action/replication_record"}},"created_at":"2026-07-05T09:46:55.377671+00:00","updated_at":"2026-07-05T09:46:55.377671+00:00"}