{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WKBGRUX4UG5LKFYFIYWYE4PLUY","short_pith_number":"pith:WKBGRUX4","canonical_record":{"source":{"id":"2502.06773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T18:52:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"cb069f3027b69dc4d274a2a9fc5371b39cdbbcdc1943df03607dfea4a8bc6ae1","abstract_canon_sha256":"4b87dabfa36cc9a7e6ecd8ea6b33d0c3a8c16c201b36445ad3ee20bccae5b9ca"},"schema_version":"1.0"},"canonical_sha256":"b28268d2fca1bab51705462d8271eba6326032aa733900844762501c5690586d","source":{"kind":"arxiv","id":"2502.06773","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WKBGRUX4UG5LKFYFIYWYE4PLUY","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T18:52:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"cb069f3027b69dc4d274a2a9fc5371b39cdbbcdc1943df03607dfea4a8bc6ae1","abstract_canon_sha256":"4b87dabfa36cc9a7e6ecd8ea6b33d0c3a8c16c201b36445ad3ee20bccae5b9ca"},"schema_version":"1.0"},"canonical_sha256":"b28268d2fca1bab51705462d8271eba6326032aa733900844762501c5690586d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:11.806002Z","signature_b64":"E6MQNSVNxLMCshRJ9nZkE6LYOqV82iTbtvHfgIO/O+XMg1WZNeKEKp2Ny+kXUjQ5pfnFE/4Pnmukl25Y4HhjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28268d2fca1bab51705462d8271eba6326032aa733900844762501c5690586d","last_reissued_at":"2026-07-05T10:12:11.805500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:11.805500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06773","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5W52CoTOxUzfSQ0xo04VnEuxjUNHo7/Do6PJdNkuISzAgh9RQz6/skSJ8idBL9sBXjdhFNh6pqialagQNMzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:33:51.252072Z"},"content_sha256":"4a291a9541ce61f8c60ea507b15dddd05110bda7fd9208a8d4dfc2d4ff4c04d3","schema_version":"1.0","event_id":"sha256:4a291a9541ce61f8c60ea507b15dddd05110bda7fd9208a8d4dfc2d4ff4c04d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WKBGRUX4UG5LKFYFIYWYE4PLUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Baolin Peng, Beibin Li, Guanghao Ye, Huseyin A. Inan, Janardhan Kulkarni, Khiem Duc Pham, Sivakanth Gopi, Xinzhi Zhang","submitted_at":"2025-02-10T18:52:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06773","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/2502.06773/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RRlHhWQmM7FYlIvS9yRtyUD85nuheb3UfZzK95mlqoE+W0Y6rudnCf5QffFJooI1ns9aNKesE6R/Uzqf5iG1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:33:51.252573Z"},"content_sha256":"62b9ac454817aa99627cae916e53c11e8d653c23951f45774509b13b21c7d097","schema_version":"1.0","event_id":"sha256:62b9ac454817aa99627cae916e53c11e8d653c23951f45774509b13b21c7d097"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKBGRUX4UG5LKFYFIYWYE4PLUY/bundle.json","state_url":"https://pith.science/pith/WKBGRUX4UG5LKFYFIYWYE4PLUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKBGRUX4UG5LKFYFIYWYE4PLUY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T21:33:51Z","links":{"resolver":"https://pith.science/pith/WKBGRUX4UG5LKFYFIYWYE4PLUY","bundle":"https://pith.science/pith/WKBGRUX4UG5LKFYFIYWYE4PLUY/bundle.json","state":"https://pith.science/pith/WKBGRUX4UG5LKFYFIYWYE4PLUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKBGRUX4UG5LKFYFIYWYE4PLUY/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W61JiPjLMcPpOyGn4qGqjerMNO8C9p5iZphJwvDVVk53X8arUvVNEkG8YxZwurbq+cQcNl/yR9qqKtOVXcMgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:33:51.255911Z","bundle_sha256":"83fae316aa51c58c7df838332370db1c3061e909c4a0cecb2becebca9d502222"}}