{"id":"W1775351421","doi":"10.1007/978-3-642-20677-1_16","title":"Test-Driven Development of Graphical User Interfaces: A Pilot Evaluation","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Graphical user interface; Graphical user interface testing; Computer science; Human–computer interaction; User interface; Pilot test; Process (computing); Test (biology); Interface (matter); Software engineering; User interface design; User experience design; Operating system","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":[0.0006835015,0.0003713449,0.0003929386,0.0009088131,0.0001257972,0.0001931785,0.0007677594,0.0003365392,0.00002795183],"category_scores_gemma":[0.001418781,0.0003355614,0.00003966924,0.0004800637,0.00009901638,0.001578828,0.0002779817,0.0004066911,0.00001497932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001682544,"about_ca_system_score_gemma":0.0007940298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001469642,"about_ca_topic_score_gemma":0.00002227563,"domain_scores_codex":[0.997726,0.00002050374,0.001020421,0.0002994963,0.0007012691,0.0002323177],"domain_scores_gemma":[0.9968601,0.0002707947,0.0009514875,0.0004416318,0.001433745,0.00004217132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001726185,0.00004317076,0.0004317389,0.0006873872,0.00001312493,0.000001190091,0.003771619,0.0007228992,0.00001854963,0.001985993,0.00006183018,0.9922453],"study_design_scores_gemma":[0.001937831,0.0003945059,0.006830619,0.01923505,0.0001463906,0.00009556759,0.000006535402,0.1874952,0.008393546,0.760996,0.01146856,0.003000163],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001715378,0.0002498294,0.9889078,0.0001030405,0.0001638198,0.0004154945,0.000002516871,0.001447082,0.008538925],"genre_scores_gemma":[0.5503091,0.00001974615,0.4491662,0.0002527451,0.00003631111,0.00006401203,0.00006403575,0.00002930443,0.00005860665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9892451,"threshold_uncertainty_score":0.9999096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04664004837837124,"score_gpt":0.2719769454355778,"score_spread":0.2253368970572066,"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."}}