{"id":"W7117252587","doi":"10.1109/vl-hcc65237.2025.00051","title":"Cracking CodeWhisperer: Analyzing Developers’ Interactions and Patterns During Programming Tasks","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structuring; Software; Code (set theory); Baseline (sea); Abstraction; Process (computing); Natural language; Task analysis","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":[0.004278054,0.0004348512,0.0003088073,0.001652971,0.0006775116,0.0009877039,0.0006567696,0.0007268051,0.0007073791],"category_scores_gemma":[0.03596031,0.0003673307,0.0001937105,0.000925179,0.0007145563,0.001534957,0.001502477,0.0007022738,0.0003084357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005850554,"about_ca_system_score_gemma":0.0008478488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004223119,"about_ca_topic_score_gemma":0.01212593,"domain_scores_codex":[0.9964501,0.00184576,0.0001959182,0.0005814236,0.0007271994,0.0001997094],"domain_scores_gemma":[0.9547647,0.03399831,0.004089796,0.002517798,0.003750604,0.0008789187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007274299,0.0005930454,0.4749618,0.0006663238,0.0000974651,0.0009720352,0.2227133,0.0009658483,0.05519985,0.0008623306,0.002909669,0.2393309],"study_design_scores_gemma":[0.0001096574,0.001248993,0.8387688,0.0002555984,0.0001059034,0.001313605,0.08520316,0.03048003,0.02364277,0.002354543,0.01627685,0.0002401469],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926153,0.00005950164,0.006184602,0.00009438759,0.000003846291,0.00007967812,0.0001276287,0.00020686,0.0006281051],"genre_scores_gemma":[0.9769412,0.00006109647,0.02099418,0.00007195471,0.000004379076,0.0001895396,0.0004458386,0.0001035628,0.001188303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004278054,"threshold_uncertainty_score":0.02262473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0188104640193474,"score_gpt":0.2996216054758287,"score_spread":0.2808111414564813,"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."}}