{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OV44D3WUXZJLMRYWDI3SEVKSBQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"393ac2b652ce497fc5bffcff884e957a6d124005d7cb0de89770729e13cb66dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-29T07:19:56Z","title_canon_sha256":"0fcff0c8a0832ed8ea5207db19bb41e6a5b5426c29779782d4cd5f8143a7992b"},"schema_version":"1.0","source":{"id":"2412.00154","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00154","created_at":"2026-07-05T09:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00154v2","created_at":"2026-07-05T09:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00154","created_at":"2026-07-05T09:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"OV44D3WUXZJL","created_at":"2026-07-05T09:46:55Z"},{"alias_kind":"pith_short_16","alias_value":"OV44D3WUXZJLMRYW","created_at":"2026-07-05T09:46:55Z"},{"alias_kind":"pith_short_8","alias_value":"OV44D3WU","created_at":"2026-07-05T09:46:55Z"}],"graph_snapshots":[{"event_id":"sha256:ebf896fc65bbfdc1301e613693212a3c52c5be4146f3c0ada9a209f6f6165234","target":"graph","created_at":"2026-07-05T09:46:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.00154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Kong, Jiangming Shu, Jinlin Xiao, Jitao Sang, Shangxi Wu, Yuqi Yang, Yuxiang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-29T07:19:56Z","title":"o1-Coder: an o1 Replication for Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00154","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:84ae48bcde1422f7ab6e14e4fc9713ea92b0447118ed031b96ebefe224b9b536","target":"record","created_at":"2026-07-05T09:46:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"393ac2b652ce497fc5bffcff884e957a6d124005d7cb0de89770729e13cb66dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-29T07:19:56Z","title_canon_sha256":"0fcff0c8a0832ed8ea5207db19bb41e6a5b5426c29779782d4cd5f8143a7992b"},"schema_version":"1.0","source":{"id":"2412.00154","kind":"arxiv","version":2}},"canonical_sha256":"7579c1eed4be52b647161a372255520c18aeac60a8e42f4dfada142e3bb66e92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7579c1eed4be52b647161a372255520c18aeac60a8e42f4dfada142e3bb66e92","first_computed_at":"2026-07-05T09:46:55.377608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:55.377608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zfwzCMbNGSt9Bq+zYPVLHn6J+iTiyvzdMofTlRPBnLR1fJjAxWqtne/BQojfbonXD9SN3xDXy8GmOo+dPckIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:55.378143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00154","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84ae48bcde1422f7ab6e14e4fc9713ea92b0447118ed031b96ebefe224b9b536","sha256:ebf896fc65bbfdc1301e613693212a3c52c5be4146f3c0ada9a209f6f6165234"],"state_sha256":"f971956ef287d31d1aadedfd5af473966f3fa1863cb00803c67561eeeffc7172"}