{"id":"W7136489490","doi":"10.5281/zenodo.19056876","title":"LLM Coding Agent Experiments","year":2025,"lang":"en","type":"dataset","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"","keywords":"Coding (social sciences); Architecture; Statistical model; Statistical analysis; Data collection","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0128641,0.004902555,0.001920269,0.002100429,0.002188984,0.002813232,0.005760889,0.004596219,0.01721508],"category_scores_gemma":[0.0330363,0.0008270942,0.002723985,0.002262439,0.001968657,0.003803444,0.003654493,0.005354347,0.02059671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00449287,"about_ca_system_score_gemma":0.004221515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02699484,"about_ca_topic_score_gemma":0.04951962,"domain_scores_codex":[0.9874536,0.006653051,0.0007053663,0.002481968,0.00175933,0.000946671],"domain_scores_gemma":[0.9844835,0.006452599,0.0004765722,0.005366453,0.002478013,0.0007427235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002110163,0.002024659,0.003415345,0.00133101,0.0005151408,0.0001636274,0.0002021546,0.04960258,0.001363017,0.006534872,0.8783386,0.05439886],"study_design_scores_gemma":[0.006360024,0.002124195,0.01169549,0.0008914317,0.0006155993,0.000662766,0.001058536,0.5058075,0.01535494,0.0617717,0.3932299,0.0004279437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1794127,0.00798448,0.07178313,0.008809428,0.00619805,0.004438645,0.571527,0.08470403,0.06514254],"genre_scores_gemma":[0.1355547,0.0006955865,0.07569656,0.002381944,0.0004284409,0.002386396,0.7567415,0.003944268,0.02217059],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02699484,"threshold_uncertainty_score":0.06803268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059111763147082,"score_gpt":0.4134990536538276,"score_spread":0.3075878773391195,"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."}}