{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WKBGRUX4UG5LKFYFIYWYE4PLUY","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":"4b87dabfa36cc9a7e6ecd8ea6b33d0c3a8c16c201b36445ad3ee20bccae5b9ca","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T18:52:04Z","title_canon_sha256":"cb069f3027b69dc4d274a2a9fc5371b39cdbbcdc1943df03607dfea4a8bc6ae1"},"schema_version":"1.0","source":{"id":"2502.06773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06773","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06773v1","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06773","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"WKBGRUX4UG5L","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"WKBGRUX4UG5LKFYF","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"WKBGRUX4","created_at":"2026-07-05T10:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:62b9ac454817aa99627cae916e53c11e8d653c23951f45774509b13b21c7d097","target":"graph","created_at":"2026-07-05T10:12:11Z","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/2502.06773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent AI advancements, such as OpenAI's new models, are transforming LLMs into LRMs (Large Reasoning Models) that perform reasoning during inference, taking extra time and compute for higher-quality outputs. We aim to uncover the algorithmic framework for training LRMs. Methods like self-consistency, PRM, and AlphaZero suggest reasoning as guided search. We ask: what is the simplest, most scalable way to enable search in LLMs?\n  We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP). RLSP involves three steps: (1) supervised fine-tuning with human or synthetic","authors_text":"Baolin Peng, Beibin Li, Guanghao Ye, Huseyin A. Inan, Janardhan Kulkarni, Khiem Duc Pham, Sivakanth Gopi, Xinzhi Zhang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T18:52:04Z","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06773","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":"sha256:4a291a9541ce61f8c60ea507b15dddd05110bda7fd9208a8d4dfc2d4ff4c04d3","target":"record","created_at":"2026-07-05T10:12:11Z","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":"4b87dabfa36cc9a7e6ecd8ea6b33d0c3a8c16c201b36445ad3ee20bccae5b9ca","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T18:52:04Z","title_canon_sha256":"cb069f3027b69dc4d274a2a9fc5371b39cdbbcdc1943df03607dfea4a8bc6ae1"},"schema_version":"1.0","source":{"id":"2502.06773","kind":"arxiv","version":1}},"canonical_sha256":"b28268d2fca1bab51705462d8271eba6326032aa733900844762501c5690586d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b28268d2fca1bab51705462d8271eba6326032aa733900844762501c5690586d","first_computed_at":"2026-07-05T10:12:11.805500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:11.805500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E6MQNSVNxLMCshRJ9nZkE6LYOqV82iTbtvHfgIO/O+XMg1WZNeKEKp2Ny+kXUjQ5pfnFE/4Pnmukl25Y4HhjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:11.806002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a291a9541ce61f8c60ea507b15dddd05110bda7fd9208a8d4dfc2d4ff4c04d3","sha256:62b9ac454817aa99627cae916e53c11e8d653c23951f45774509b13b21c7d097"],"state_sha256":"1516fa11bd9ee743a56f63425c7b012cfb5177f8e2be0e99f98f3931de3fb07d"}