{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UL5VIBMOKNTW5LP4EVIKLTMUT3","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":"2d09be8fd18d98489102277dd0721717223a068cad712ba468b692c58f06ff6d","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T22:02:30Z","title_canon_sha256":"3869e440608c97063823e157d21cd0a46caaa695876bc8ca17d5674421179a0d"},"schema_version":"1.0","source":{"id":"2411.04282","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04282","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04282v2","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04282","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"UL5VIBMOKNTW","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"UL5VIBMOKNTW5LP4","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"UL5VIBMO","created_at":"2026-07-05T09:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:7edf193b48d566be574a6788a19345a421f8c8c99b9dea3f465d14e885e6706c","target":"graph","created_at":"2026-07-05T09:38:50Z","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/2411.04282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time, optimizing reasoning capabilities during training remains challenging. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution and optimizes it via variational approaches. LaTRO enables LLMs to concurrently improve both their reasoning process and ability to evaluate reasoning","authors_text":"Akshara Prabhakar, Caiming Xiong, Haolin Chen, Huan Wang, Phil Mui, Ricky Ho, Shelby Heinecke, Silvio Savarese, Weiran Yao, Yihao Feng, Zuxin Liu","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T22:02:30Z","title":"Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04282","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":"sha256:4e79396bcb666f67c7bdfa209b2d699d915aab141818b1eca73bc152b08a6461","target":"record","created_at":"2026-07-05T09:38:50Z","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":"2d09be8fd18d98489102277dd0721717223a068cad712ba468b692c58f06ff6d","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T22:02:30Z","title_canon_sha256":"3869e440608c97063823e157d21cd0a46caaa695876bc8ca17d5674421179a0d"},"schema_version":"1.0","source":{"id":"2411.04282","kind":"arxiv","version":2}},"canonical_sha256":"a2fb54058e53676eadfc2550a5cd949ec7ee85e360a661f85e42f56e68f9f3c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2fb54058e53676eadfc2550a5cd949ec7ee85e360a661f85e42f56e68f9f3c8","first_computed_at":"2026-07-05T09:38:50.597816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:50.597816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G+f9VfX/PxRcMbL1hhN3s9Y1fmSYP4wYnPPSkn8HhYwR6YFEeKjzFb+uguFcdB+O9isX0R16bmMBkoJQODFXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:50.598330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04282","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e79396bcb666f67c7bdfa209b2d699d915aab141818b1eca73bc152b08a6461","sha256:7edf193b48d566be574a6788a19345a421f8c8c99b9dea3f465d14e885e6706c"],"state_sha256":"e6630bbf08adbe8c8ccd50b56acd9c66e5500741dbb3bb0990eae5a00824d365"}