{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ETVUGFVTJRI7PSGQTYFSSA36OU","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":"618c9f5694226d6e30c3fc230cc46f6d3fdb122595345ea8c8fa82f204b3f473","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.mes-hall","cond-mat.mtrl-sci","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T08:46:26Z","title_canon_sha256":"4d26200b3541540026def8036e39fadcbfaed78e5e2a7d7a65f5c927a724f3bc"},"schema_version":"1.0","source":{"id":"2410.12375","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12375","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12375v1","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12375","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_12","alias_value":"ETVUGFVTJRI7","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_16","alias_value":"ETVUGFVTJRI7PSGQ","created_at":"2026-07-05T09:21:18Z"},{"alias_kind":"pith_short_8","alias_value":"ETVUGFVT","created_at":"2026-07-05T09:21:18Z"}],"graph_snapshots":[{"event_id":"sha256:54e9e4cfb43ccc5dfa75356358f31738c13684eab95302e38c11f3f151ac822f","target":"graph","created_at":"2026-07-05T09:21:18Z","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/2410.12375/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"PRefLexOR (Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning) combines preference optimization with concepts from Reinforcement Learning to enable models to self-teach through iterative reasoning improvements. We propose a recursive learning approach that engages the model in multi-step reasoning, revisiting, and refining intermediate steps before producing a final output in training and inference phases. Through multiple training stages, the model first learns to align its reasoning with accurate decision paths by optimizing the log odds between preferred ","authors_text":"Markus J. Buehler","cross_cats":["cond-mat.dis-nn","cond-mat.mes-hall","cond-mat.mtrl-sci","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T08:46:26Z","title":"PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12375","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":"sha256:4e55931d3d08cc029724ddf8bfd0c6a74f18f4b3c52110abccd241117ade7855","target":"record","created_at":"2026-07-05T09:21:18Z","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":"618c9f5694226d6e30c3fc230cc46f6d3fdb122595345ea8c8fa82f204b3f473","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.mes-hall","cond-mat.mtrl-sci","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T08:46:26Z","title_canon_sha256":"4d26200b3541540026def8036e39fadcbfaed78e5e2a7d7a65f5c927a724f3bc"},"schema_version":"1.0","source":{"id":"2410.12375","kind":"arxiv","version":1}},"canonical_sha256":"24eb4316b34c51f7c8d09e0b29037e75157c320ad0f5610ab0e70541fdd20d50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24eb4316b34c51f7c8d09e0b29037e75157c320ad0f5610ab0e70541fdd20d50","first_computed_at":"2026-07-05T09:21:18.066350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:18.066350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zbSWkatMtlNnSffgI5ywG7vz3sp1df3qRxUoizWKoprZfBLlThNrlsvtZiBtGKOCSy2NxHAYraVZSLaAXVNqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:18.066696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12375","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e55931d3d08cc029724ddf8bfd0c6a74f18f4b3c52110abccd241117ade7855","sha256:54e9e4cfb43ccc5dfa75356358f31738c13684eab95302e38c11f3f151ac822f"],"state_sha256":"3e06d2d56a0a300ec6c9440a5d743aaaac1f8f14ad6c5f9eec1acea443971c1a"}