{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AJFYYQWHLDEVMEZJ2GFV4ZWPX4","short_pith_number":"pith:AJFYYQWH","canonical_record":{"source":{"id":"2502.06813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T22:08:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07b3cd70d20737b0c316e1178e26b8b9a7ff5083dadacff3fc251665f11dcdb2","abstract_canon_sha256":"caa0f4678d2a6e49ea6e3b63e62cf241c439cbdb63ec73b1aafc3b99052ba426"},"schema_version":"1.0"},"canonical_sha256":"024b8c42c758c9561329d18b5e66cfbf0c72ecb31709e5b379ca65e483f5dd47","source":{"kind":"arxiv","id":"2502.06813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06813","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06813v1","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06813","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"AJFYYQWHLDEV","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"AJFYYQWHLDEVMEZJ","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"AJFYYQWH","created_at":"2026-07-05T10:12:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AJFYYQWHLDEVMEZJ2GFV4ZWPX4","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T22:08:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07b3cd70d20737b0c316e1178e26b8b9a7ff5083dadacff3fc251665f11dcdb2","abstract_canon_sha256":"caa0f4678d2a6e49ea6e3b63e62cf241c439cbdb63ec73b1aafc3b99052ba426"},"schema_version":"1.0"},"canonical_sha256":"024b8c42c758c9561329d18b5e66cfbf0c72ecb31709e5b379ca65e483f5dd47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:28.178781Z","signature_b64":"V9MKPWVDbkzDz6TsDFz1qkZsoRJD8TpmU+464lfSeSwkqSJzFr3f+TngvSxRXFO5dncePEho/45qn4nSMoWPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"024b8c42c758c9561329d18b5e66cfbf0c72ecb31709e5b379ca65e483f5dd47","last_reissued_at":"2026-07-05T10:12:28.178279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:28.178279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06813","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":"2026-07-05T10:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cy7+q7A5+OMFsfDITKS8gyErhMYrqE7s2crSjT2O/+NU8ehgBtNHEk+Zu5jubVoajilC5d4cNK59na0xXKAfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T17:10:13.744950Z"},"content_sha256":"7df19163dea80327569cbb18f4bbc99510e9d2beb812389cbc3427be14f2902b","schema_version":"1.0","event_id":"sha256:7df19163dea80327569cbb18f4bbc99510e9d2beb812389cbc3427be14f2902b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AJFYYQWHLDEVMEZJ2GFV4ZWPX4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Guided Tree Search for Enhanced LLM Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yang Li","submitted_at":"2025-02-04T22:08:20Z","abstract_excerpt":"Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show promise, they are limited by their reliance on predefined heuristics and computationally expensive exploration strategies. We propose Policy-Guided Tree Search (PGTS), a framework that combines reinforcement learning with structured tree exploration to efficiently navigate reasoning paths. Our key innovation is a learned policy that dynamically decides between expanding, branchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06813","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/2502.06813/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":"2026-07-05T10:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUlMAM6bKGBKDtm53+9thQEjBNkZJFJdalvGjnZPb61EwbkSu99HCBoEq7IbzjPUmvwPQAS61oFTW9UH0IxJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T17:10:13.745592Z"},"content_sha256":"83dddf80104afe5dac06bd5c8a8f381e86a427bf238fbc0bab696da06dca00e9","schema_version":"1.0","event_id":"sha256:83dddf80104afe5dac06bd5c8a8f381e86a427bf238fbc0bab696da06dca00e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJFYYQWHLDEVMEZJ2GFV4ZWPX4/bundle.json","state_url":"https://pith.science/pith/AJFYYQWHLDEVMEZJ2GFV4ZWPX4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJFYYQWHLDEVMEZJ2GFV4ZWPX4/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":"2026-07-12T17:10:13Z","links":{"resolver":"https://pith.science/pith/AJFYYQWHLDEVMEZJ2GFV4ZWPX4","bundle":"https://pith.science/pith/AJFYYQWHLDEVMEZJ2GFV4ZWPX4/bundle.json","state":"https://pith.science/pith/AJFYYQWHLDEVMEZJ2GFV4ZWPX4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJFYYQWHLDEVMEZJ2GFV4ZWPX4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AJFYYQWHLDEVMEZJ2GFV4ZWPX4","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":"caa0f4678d2a6e49ea6e3b63e62cf241c439cbdb63ec73b1aafc3b99052ba426","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T22:08:20Z","title_canon_sha256":"07b3cd70d20737b0c316e1178e26b8b9a7ff5083dadacff3fc251665f11dcdb2"},"schema_version":"1.0","source":{"id":"2502.06813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06813","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06813v1","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06813","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"AJFYYQWHLDEV","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"AJFYYQWHLDEVMEZJ","created_at":"2026-07-05T10:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"AJFYYQWH","created_at":"2026-07-05T10:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:83dddf80104afe5dac06bd5c8a8f381e86a427bf238fbc0bab696da06dca00e9","target":"graph","created_at":"2026-07-05T10:12:28Z","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/2502.06813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show promise, they are limited by their reliance on predefined heuristics and computationally expensive exploration strategies. We propose Policy-Guided Tree Search (PGTS), a framework that combines reinforcement learning with structured tree exploration to efficiently navigate reasoning paths. Our key innovation is a learned policy that dynamically decides between expanding, branchi","authors_text":"Yang Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T22:08:20Z","title":"Policy Guided Tree Search for Enhanced LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06813","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":"sha256:7df19163dea80327569cbb18f4bbc99510e9d2beb812389cbc3427be14f2902b","target":"record","created_at":"2026-07-05T10:12:28Z","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":"caa0f4678d2a6e49ea6e3b63e62cf241c439cbdb63ec73b1aafc3b99052ba426","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T22:08:20Z","title_canon_sha256":"07b3cd70d20737b0c316e1178e26b8b9a7ff5083dadacff3fc251665f11dcdb2"},"schema_version":"1.0","source":{"id":"2502.06813","kind":"arxiv","version":1}},"canonical_sha256":"024b8c42c758c9561329d18b5e66cfbf0c72ecb31709e5b379ca65e483f5dd47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"024b8c42c758c9561329d18b5e66cfbf0c72ecb31709e5b379ca65e483f5dd47","first_computed_at":"2026-07-05T10:12:28.178279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:28.178279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V9MKPWVDbkzDz6TsDFz1qkZsoRJD8TpmU+464lfSeSwkqSJzFr3f+TngvSxRXFO5dncePEho/45qn4nSMoWPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:28.178781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7df19163dea80327569cbb18f4bbc99510e9d2beb812389cbc3427be14f2902b","sha256:83dddf80104afe5dac06bd5c8a8f381e86a427bf238fbc0bab696da06dca00e9"],"state_sha256":"18acbd8fe4f10e03f39487db340fc6048a2dea3a06775def751790b28491fcf1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1ti9z2xKtvnjKdn/R4PurPiegKp25w0JLZEx78kvd5AFF262ZT+MkCLIyLCDEVk08I7oOEW983PIb/e4sS2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T17:10:13.749552Z","bundle_sha256":"01f5420b3100264f9d27a268971a5d05a46dfcced27bbb54dcd7620a70522401"}}