{"id":"W6979306740","doi":"","title":"Value-Guided Search for Efficient Chain-of-Thought Reasoning","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Materials Research; Materials Research Science and Engineering Center, Harvard University; Natural Sciences and Engineering Research Council of Canada; Cornell Center for Materials Research; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Inference; Process (computing); Value (mathematics); Simple (philosophy); Model-based reasoning; Voting; Encoding (memory); Codebase","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007183124,0.0001841783,0.0003272259,0.0004242986,0.0003007835,0.0001003747,0.0003252742,0.00008335609,0.00002852762],"category_scores_gemma":[0.0002884728,0.0001672605,0.0001909186,0.001325424,0.00005866901,0.0002130633,0.0001803704,0.0001194863,0.00004631952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002639131,"about_ca_system_score_gemma":0.00005854732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004034616,"about_ca_topic_score_gemma":0.00000735985,"domain_scores_codex":[0.9986116,0.000009848562,0.0003879229,0.0003935224,0.0002314275,0.0003656569],"domain_scores_gemma":[0.9988403,0.00007660923,0.000161594,0.0003279459,0.0005816197,0.00001195986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001629421,0.0004602731,0.7422102,0.003060991,0.000386189,0.000006571312,0.000160485,0.1025017,0.005232068,0.123654,0.003813121,0.01835148],"study_design_scores_gemma":[0.001815693,0.00001148022,0.03978843,0.0007995965,0.0005900379,7.286522e-7,0.0004851338,0.926715,0.006899291,0.001394974,0.02092235,0.0005773041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9268557,0.0003616411,0.06463373,0.001834261,0.0002925636,0.0002249661,0.000001887283,0.0001325097,0.005662699],"genre_scores_gemma":[0.9960682,0.0000115196,0.0007638859,0.0009071518,0.0004756378,0.00004153138,0.00002640615,0.00002729495,0.00167831],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8242133,"threshold_uncertainty_score":0.6820686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04552908279416131,"score_gpt":0.2935877001436489,"score_spread":0.2480586173494876,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}