{"id":"W4417420254","doi":"10.5281/zenodo.16899501","title":"AIDev: Studying AI Coding Agents on GitHub","year":2025,"lang":"en","type":"dataset","venue":"ArXiv.org","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Workflow; Metadata; Coding (social sciences); Software; Code (set theory); Source code; Codebase; Software agent","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":[0.001740154,0.001703141,0.0007643088,0.005519731,0.001186361,0.002065705,0.002595921,0.001569778,0.003612016],"category_scores_gemma":[0.009030233,0.0006090672,0.001192736,0.00664043,0.000980422,0.003060875,0.004194604,0.002032703,0.008367985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001571961,"about_ca_system_score_gemma":0.001693349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03475226,"about_ca_topic_score_gemma":0.06624486,"domain_scores_codex":[0.9972103,0.0007128918,0.0001971979,0.0006299005,0.0009157815,0.0003338304],"domain_scores_gemma":[0.9938233,0.001379335,0.0005574005,0.002005741,0.001471077,0.0007631138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001163207,0.0008908248,0.06635484,0.002267295,0.0004323689,0.0009198255,0.003028456,0.01380583,0.004016412,0.008704764,0.8186879,0.07972825],"study_design_scores_gemma":[0.0003706556,0.0005023162,0.118383,0.0004682803,0.0001261277,0.0007433908,0.002945087,0.08040728,0.007035055,0.01028819,0.7784598,0.0002708054],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2966066,0.004594035,0.01230439,0.002233659,0.0007684567,0.0006673787,0.5986528,0.05651981,0.02765287],"genre_scores_gemma":[0.09706408,0.0005294472,0.01967304,0.000494413,0.00006964867,0.0004157445,0.8727924,0.00327904,0.005682117],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03475226,"threshold_uncertainty_score":0.06909996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1058571510532622,"score_gpt":0.3519879855468445,"score_spread":0.2461308344935824,"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."}}