{"id":"W2040225071","doi":"10.1002/spip.146","title":"Findings from Phase 2 of the SPICE trials","year":2001,"lang":"en","type":"article","venue":"Software Process Improvement and Practice","topic":"Software Engineering Research","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Spice; Usability; Computer science; Empirical research; Software engineering; Dimension (graph theory); Process (computing); Reliability engineering; Systems engineering; Process management; Engineering; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002384788,0.0001581321,0.0002650195,0.00007235575,0.0001462385,0.0001859663,0.0009000448,0.00006929503,0.00004343598],"category_scores_gemma":[0.02985427,0.0001113749,0.0000654054,0.0005747912,0.00005901112,0.001183333,0.0003563789,0.0002514079,0.000007210316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002869075,"about_ca_system_score_gemma":0.0001367717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001090793,"about_ca_topic_score_gemma":0.000002780824,"domain_scores_codex":[0.9981639,0.0001687773,0.0004109919,0.0003831762,0.0005954067,0.000277705],"domain_scores_gemma":[0.9909194,0.00789748,0.0002754119,0.0005507846,0.0002637406,0.00009319051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006757169,0.001006557,0.0281414,0.0003535227,0.0003661061,0.00004018654,0.006234218,0.00005065457,0.01999216,0.001278259,0.001819276,0.940042],"study_design_scores_gemma":[0.03389775,0.005626704,0.04852263,0.001235962,0.001107959,0.0003761727,0.003007713,0.009905506,0.5042951,0.04999761,0.3382014,0.003825495],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5329897,0.001364038,0.459815,0.003869485,0.0006696949,0.0007901861,0.00003272726,0.0002873042,0.0001818469],"genre_scores_gemma":[0.9713162,0.0002271352,0.02735346,0.0006414929,0.0001212041,0.00007112523,0.000004687274,0.00001897467,0.000245692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9362165,"threshold_uncertainty_score":0.9783177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05926722609592025,"score_gpt":0.3780309595307635,"score_spread":0.3187637334348432,"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."}}