{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:22QSC6KGPZARMMILRB3BTWWDPZ","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":"54dac2a843f6eabdc2336cc13de35c690d5523075265ff52d8787d8235a78270","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:52:27Z","title_canon_sha256":"c4126397d69d49bbf89038193fd9fb8322ca4843d861e9aa88f82bbada75072c"},"schema_version":"1.0","source":{"id":"2506.07557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07557","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07557v1","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07557","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"pith_short_12","alias_value":"22QSC6KGPZAR","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"pith_short_16","alias_value":"22QSC6KGPZARMMIL","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"pith_short_8","alias_value":"22QSC6KG","created_at":"2026-07-05T11:18:29Z"}],"graph_snapshots":[{"event_id":"sha256:24dc39e4797b2507e58201e205aa65f9a635770cb2e811530071ec905a41750e","target":"graph","created_at":"2026-07-05T11:18:29Z","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/2506.07557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Models (LLMs) have achieved remarkable success in a wide range of applications, their performance often degrades in complex reasoning tasks. In this work, we introduce SELT (Self-Evaluation LLM Tree Search), a novel framework that leverages a modified Monte Carlo Tree Search (MCTS) to enhance LLM reasoning without relying on external reward models. By redefining the Upper Confidence Bound scoring to align with intrinsic self-evaluation capabilities of LLMs and decomposing the inference process into atomic subtasks augmented with semantic clustering at each node, SELT effec","authors_text":"Di Zhang, Dongzhan Zhou, Mengsong Wu, Wenliang Chen, Yuqiang Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:52:27Z","title":"SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07557","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":"sha256:372296372cf5a5119fc588ea6824ec134aa1338891a5c5b002469bf4b0fe7154","target":"record","created_at":"2026-07-05T11:18:29Z","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":"54dac2a843f6eabdc2336cc13de35c690d5523075265ff52d8787d8235a78270","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:52:27Z","title_canon_sha256":"c4126397d69d49bbf89038193fd9fb8322ca4843d861e9aa88f82bbada75072c"},"schema_version":"1.0","source":{"id":"2506.07557","kind":"arxiv","version":1}},"canonical_sha256":"d6a12179467e4116310b887619dac37e6f80411cb0ef1d8c25b3900e3080759e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6a12179467e4116310b887619dac37e6f80411cb0ef1d8c25b3900e3080759e","first_computed_at":"2026-07-05T11:18:29.403747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:29.403747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mTMfSpXBC3ZTWxhEOjGfR82LmTMBKnsDzR/QMllU/cPJc3jvlijOVRg8iHZrveGtIRZqPsM8UDYR7xiwAAIOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:29.404236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:372296372cf5a5119fc588ea6824ec134aa1338891a5c5b002469bf4b0fe7154","sha256:24dc39e4797b2507e58201e205aa65f9a635770cb2e811530071ec905a41750e"],"state_sha256":"da0f2c1d41e071528985a6f0c24c3164dddd473f01979de6fbe7d12a1d37bc5c"}