{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FS53FJCUMODZEV5M5QBKI27BSE","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":"99b73a9a313ba5f7af588248804b5b6650b8e0e941a0e3eecc84333822d69869","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-15T17:52:11Z","title_canon_sha256":"a7eaa2b64d71110caaf4036c744256449c734fdd6d0303b19a7a1b182e5013b3"},"schema_version":"1.0","source":{"id":"2502.10867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10867","created_at":"2026-07-05T10:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10867v1","created_at":"2026-07-05T10:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10867","created_at":"2026-07-05T10:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"FS53FJCUMODZ","created_at":"2026-07-05T10:14:59Z"},{"alias_kind":"pith_short_16","alias_value":"FS53FJCUMODZEV5M","created_at":"2026-07-05T10:14:59Z"},{"alias_kind":"pith_short_8","alias_value":"FS53FJCU","created_at":"2026-07-05T10:14:59Z"}],"graph_snapshots":[{"event_id":"sha256:948fdcd4c94ad578d836ed9688ae9c86b5045fd217b83fa93235c0fe50accd3b","target":"graph","created_at":"2026-07-05T10:14:59Z","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/2502.10867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the conventional autoregressive method of generating answers to a more deliberate approach that models the slow-thinking process through step-by-step reasoning training. Reinforcement learning plays a key role in both the model's training and decoding processes. In this article, we present a comprehensive formulation of reasoning problems and investigate the use of both m","authors_text":"Jun Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-15T17:52:11Z","title":"A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10867","kind":"arxiv","version":1},"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":"sha256:790b33d3ae4901a03b161b50323f509340af94f0d9d62ce0a9f48ee680142edb","target":"record","created_at":"2026-07-05T10:14:59Z","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":"99b73a9a313ba5f7af588248804b5b6650b8e0e941a0e3eecc84333822d69869","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-15T17:52:11Z","title_canon_sha256":"a7eaa2b64d71110caaf4036c744256449c734fdd6d0303b19a7a1b182e5013b3"},"schema_version":"1.0","source":{"id":"2502.10867","kind":"arxiv","version":1}},"canonical_sha256":"2cbbb2a45463879257acec02a46be1910127e42219acf52066b0fa058eb4885f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cbbb2a45463879257acec02a46be1910127e42219acf52066b0fa058eb4885f","first_computed_at":"2026-07-05T10:14:59.337088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:59.337088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uwjwNSke19NjcJ2dytpi9jbd/NdBWBDrw4ZVtvw/h5rElbr2sXPYMXwW59OHxVo6Q5JEZCiDrnWbocQSIgeiAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:59.337586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:790b33d3ae4901a03b161b50323f509340af94f0d9d62ce0a9f48ee680142edb","sha256:948fdcd4c94ad578d836ed9688ae9c86b5045fd217b83fa93235c0fe50accd3b"],"state_sha256":"a8d83157aa6bd2e87deed94b2eca92fc11279196bd710be3467dce84aa0dc4fe"}