{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:62HQLE7D4GUQK4DAUGOWDC2VMG","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":"0b54dac172dabe855c23e785df4d5ad5ddfa0615e6f8f1d7beda6a21cc19c393","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T05:03:27Z","title_canon_sha256":"4b6a880a8b5bac3c4916fdf0353f70063f82de373e2d59e4136152c8ae56468f"},"schema_version":"1.0","source":{"id":"2606.17524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17524","created_at":"2026-06-19T16:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17524v1","created_at":"2026-06-19T16:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17524","created_at":"2026-06-19T16:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"62HQLE7D4GUQ","created_at":"2026-06-19T16:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"62HQLE7D4GUQK4DA","created_at":"2026-06-19T16:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"62HQLE7D","created_at":"2026-06-19T16:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:bc75fdfa9bfd1893183c2cf3b1f8382766dbd7ef6622905c3541302f3e94b08d","target":"graph","created_at":"2026-06-19T16:10:15Z","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/2606.17524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where early hidden-state errors may propagate to incorrect predictions. We propose ReLAR, a reinforcement-guided latent refinement framework that iteratively updates hidden representations before decoding. ReLAR maintains a compact latent reasoning state and uses learned depth and action controllers to adaptively determine both the number and direction of refinement steps. The controllers are trained with a policy gradient objective based on step-wise li","authors_text":"Chia-Hsuan Hsu, Jui-Ming Yao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T05:03:27Z","title":"Learning to Refine Hidden States for Reliable LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17524","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:a39b79f1128761af52f86baa851eed9d51cf252018e8cee2f3836ca3a1d73be4","target":"record","created_at":"2026-06-19T16:10:15Z","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":"0b54dac172dabe855c23e785df4d5ad5ddfa0615e6f8f1d7beda6a21cc19c393","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T05:03:27Z","title_canon_sha256":"4b6a880a8b5bac3c4916fdf0353f70063f82de373e2d59e4136152c8ae56468f"},"schema_version":"1.0","source":{"id":"2606.17524","kind":"arxiv","version":1}},"canonical_sha256":"f68f0593e3e1a9057060a19d618b55618e19ac89457c928cbb9d156793f378e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f68f0593e3e1a9057060a19d618b55618e19ac89457c928cbb9d156793f378e2","first_computed_at":"2026-06-19T16:10:15.103081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:15.103081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m3AZbqr8XrDMKOMb46UBAQNBnQGdE87o7q9VEE814hacOlbd3cgYMIBttoAn+gjLwwvAGDe89KhGM0pg2viiAA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:15.103445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a39b79f1128761af52f86baa851eed9d51cf252018e8cee2f3836ca3a1d73be4","sha256:bc75fdfa9bfd1893183c2cf3b1f8382766dbd7ef6622905c3541302f3e94b08d"],"state_sha256":"6f6abb64bc3d3236c23874323f7d9fa27606745ec5dfd4d13370f4a277a430d9"}