{"id":"W7082258602","doi":"10.48448/nxyz-de54","title":"Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generalization; Consistency (knowledge bases); Process (computing); Deductive reasoning; Model-based reasoning; Opportunistic reasoning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001038454,0.0003284543,0.0003959894,0.0003436541,0.0003325431,0.0002769223,0.002563067,0.0002672665,0.0001425143],"category_scores_gemma":[0.0009963744,0.0002879309,0.00008299416,0.001171892,0.0003668173,0.0002288404,0.0005527819,0.0002263916,0.00002896112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009337699,"about_ca_system_score_gemma":0.001388076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001202669,"about_ca_topic_score_gemma":0.000004889931,"domain_scores_codex":[0.9971521,0.00001971939,0.0003621016,0.001104743,0.0006499525,0.0007113771],"domain_scores_gemma":[0.9980782,0.00007270116,0.0002711071,0.0009927757,0.0004182382,0.0001669681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002359092,0.0003026669,0.0000204631,0.001880812,0.00008371487,0.00001717219,0.000574889,0.03527207,0.001417971,0.5219231,0.4352579,0.003225581],"study_design_scores_gemma":[0.0002255919,0.00002484954,3.141754e-7,0.0004017917,0.0000166688,0.000007761464,0.00002273354,0.9082857,0.001399941,0.06288835,0.02641408,0.0003121812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000003121746,0.00008984701,0.6742195,0.001322234,0.0001752062,0.0003492922,0.00001410183,0.0003364226,0.3234902],"genre_scores_gemma":[0.001034014,0.00001719059,0.3313059,0.000454042,0.0001121654,0.00003876949,0.00002108347,0.00002726065,0.6669896],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8730137,"threshold_uncertainty_score":0.9999573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02482961139892289,"score_gpt":0.2977676714290438,"score_spread":0.2729380600301209,"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."}}