{"id":"W7000794688","doi":"","title":"Hard attention finding using reinforcement learning","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Reinforcement; Control (management); Action (physics); Matching (statistics)","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","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001486429,0.001052698,0.0009164923,0.001216549,0.002645477,0.0006824323,0.002326875,0.000930975,0.0001145757],"category_scores_gemma":[0.001091455,0.001244416,0.0005892115,0.001482182,0.000036535,0.002105516,0.000767574,0.002928114,0.0003597341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001802848,"about_ca_system_score_gemma":0.0001999959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001706937,"about_ca_topic_score_gemma":0.00003750083,"domain_scores_codex":[0.993311,0.0004791613,0.00156627,0.001689141,0.001695607,0.001258824],"domain_scores_gemma":[0.9958681,0.0002862079,0.001494975,0.001441149,0.0006227457,0.0002867939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006540462,0.00006028913,0.0001187084,0.0008502147,0.0004297352,0.00007951826,0.00003034605,0.7222087,0.03900438,0.168098,0.000009460721,0.06904513],"study_design_scores_gemma":[0.003637126,0.0008566992,0.002565845,0.008094477,0.001038047,0.00008384298,0.0006732438,0.7920033,0.05859128,0.007394649,0.11865,0.00641154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6035037,0.0004043261,0.02826677,0.00004766316,0.01493197,0.003026956,0.00005724942,0.003011834,0.3467495],"genre_scores_gemma":[0.8417531,0.0001900564,0.02256227,0.0003223686,0.0001038192,0.0001088769,0.001009488,0.0002091509,0.1337408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2382495,"threshold_uncertainty_score":0.9993722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03451985705745916,"score_gpt":0.2720961607043954,"score_spread":0.2375763036469362,"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."}}