{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TVHKZUZWSWA23QQ7DQI3LFMXXZ","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":"356b9380f2953d5f3fcf13aee4a33eee2f4daceee28111aa7490f226874d1f82","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-27T08:18:12Z","title_canon_sha256":"d60341afbd52b409fbd4cfd23227ff4568f29e51f5132a00c4c2499f287f799a"},"schema_version":"1.0","source":{"id":"2605.28842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28842","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28842v1","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28842","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_12","alias_value":"TVHKZUZWSWA2","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_16","alias_value":"TVHKZUZWSWA23QQ7","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_8","alias_value":"TVHKZUZW","created_at":"2026-05-29T00:04:13Z"}],"graph_snapshots":[{"event_id":"sha256:5cc8205c33297549c139d80105fb20d362204e3d1c7be58e177ad0b70cf4be8f","target":"graph","created_at":"2026-05-29T00:04:13Z","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/2605.28842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in aligning model behavior with task objectives. Existing reasoning chain tuning methods often rely on black-box heuristics or gradient-free search, which lack interpretability, generalization, and sample efficiency. In this work, we introduce \\textbf{Thoughts-as-Planning}, a novel framework that formalizes reasoning chain optimization as a sequential decision-making process over a latent semantic space. We model the LLM as a partially observable e","authors_text":"Dong Liu, Yanxuan Yu, Ying Nian Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-27T08:18:12Z","title":"Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28842","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":"sha256:78c6d4fccd45bc14e732fe0f523ee168242e0e12355271e07730ebef11702211","target":"record","created_at":"2026-05-29T00:04:13Z","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":"356b9380f2953d5f3fcf13aee4a33eee2f4daceee28111aa7490f226874d1f82","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-27T08:18:12Z","title_canon_sha256":"d60341afbd52b409fbd4cfd23227ff4568f29e51f5132a00c4c2499f287f799a"},"schema_version":"1.0","source":{"id":"2605.28842","kind":"arxiv","version":1}},"canonical_sha256":"9d4eacd3369581adc21f1c11b59597be757d204c9f8ef620c5614877dbcecfba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d4eacd3369581adc21f1c11b59597be757d204c9f8ef620c5614877dbcecfba","first_computed_at":"2026-05-29T00:04:13.744847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T00:04:13.744847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gr8E+RVd1X5ptru+kZDKj8lXBTGSBvRwtLeZCErmxiLAjbDwR2XBrdoBiHNlHgAzTXP+8YD4o7gfG5xHsP+fBA==","signature_status":"signed_v1","signed_at":"2026-05-29T00:04:13.745663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78c6d4fccd45bc14e732fe0f523ee168242e0e12355271e07730ebef11702211","sha256:5cc8205c33297549c139d80105fb20d362204e3d1c7be58e177ad0b70cf4be8f"],"state_sha256":"34b11af9773fbf21e3b9c30addcc28e11940111a1d3f4db58acd62aff27b83fa"}