{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UVR655QA2GNGZSY5XGOCHH3EOV","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":"ff03a273bd90d01b3209426e75cfda9574f4bfb719bc6f5396b8620168f2e50b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T18:19:14Z","title_canon_sha256":"ee896692eeb94bc8a05bed07bef4f244933dea92060a001a41c73cf227db8d66"},"schema_version":"1.0","source":{"id":"2502.01694","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01694","created_at":"2026-07-05T10:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01694v2","created_at":"2026-07-05T10:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01694","created_at":"2026-07-05T10:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"UVR655QA2GNG","created_at":"2026-07-05T10:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"UVR655QA2GNGZSY5","created_at":"2026-07-05T10:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"UVR655QA","created_at":"2026-07-05T10:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:e8db871dc69eb8efbe1100ccb8e6b61d4829393a42d54b96c5189ca303239440","target":"graph","created_at":"2026-07-05T10:22:12Z","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/2502.01694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A key paradigm to improve the reasoning capabilities of large language models (LLMs) is to allocate more inference-time compute to search against a verifier or reward model. This process can then be utilized to refine the pretrained model or distill its reasoning patterns into more efficient models. In this paper, we study inference-time compute by viewing chain-of-thought (CoT) generation as a metastable Markov process: easy reasoning steps (e.g., algebraic manipulations) form densely connected clusters, while hard reasoning steps (e.g., applying a relevant theorem) create sparse, low-probabi","authors_text":"Denny Wu, Jason Lee, Juno Kim, Taiji Suzuki","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T18:19:14Z","title":"Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01694","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:c92db01436ddaa59c8d2881d50736563db16ceb07e4562f400b9e4c4e649a2cd","target":"record","created_at":"2026-07-05T10:22:12Z","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":"ff03a273bd90d01b3209426e75cfda9574f4bfb719bc6f5396b8620168f2e50b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T18:19:14Z","title_canon_sha256":"ee896692eeb94bc8a05bed07bef4f244933dea92060a001a41c73cf227db8d66"},"schema_version":"1.0","source":{"id":"2502.01694","kind":"arxiv","version":2}},"canonical_sha256":"a563eef600d19a6ccb1db99c239f64756b2098a6c246047d90b0d64cd9264164","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a563eef600d19a6ccb1db99c239f64756b2098a6c246047d90b0d64cd9264164","first_computed_at":"2026-07-05T10:22:12.773574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:12.773574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cNfxWAuPelbhy8SNq2/o03fojuklSnnB9mGh+DJQDXVMqFYKvukHMEfmPL62KCtGAW1/Ta4lZKu67DOLffHrAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:12.774120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01694","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c92db01436ddaa59c8d2881d50736563db16ceb07e4562f400b9e4c4e649a2cd","sha256:e8db871dc69eb8efbe1100ccb8e6b61d4829393a42d54b96c5189ca303239440"],"state_sha256":"0be6c7109b1d3b715b43870b2206220642be49b2186e7bb13510cf4f3ae3f7cb"}