{"id":"W1998060612","doi":"10.1145/1920778.1920786","title":"Critic-proofing","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Usability; Heuristic evaluation; Computer science; Heuristic; Categorization; Software; Value (mathematics); Human–computer interaction; Artificial intelligence; Machine learning; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001588533,0.00003508206,0.00003153578,0.00005060489,0.00003224937,0.0001040259,0.000562989,0.00002274709,0.00009006345],"category_scores_gemma":[0.0006282748,0.00003085276,0.00001394405,0.0001613952,0.00001270829,0.0001860296,0.0001560709,0.0001644127,0.0002592529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004441517,"about_ca_system_score_gemma":0.00002221679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001042862,"about_ca_topic_score_gemma":0.000004235981,"domain_scores_codex":[0.9995061,0.000003964296,0.00004395802,0.0001298376,0.0001476172,0.0001685619],"domain_scores_gemma":[0.9992217,0.000298033,0.000002922684,0.0003756737,0.00003858362,0.00006302679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[4.874089e-7,0.00003774623,0.01755661,0.00001737118,0.000006327679,0.00004559768,0.0002443051,0.00003322047,0.0696787,0.8059044,0.01024406,0.09623118],"study_design_scores_gemma":[0.0007790021,0.0001457576,0.2539434,0.00002395165,0.000002881481,0.0002371283,0.00002012198,0.286581,0.2952031,0.03182713,0.1301461,0.001090369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09331101,0.000008138473,0.8976455,0.000838799,0.0007021502,0.0000379621,6.937714e-8,0.0006508197,0.006805564],"genre_scores_gemma":[0.8074683,1.810829e-7,0.1917418,0.00008000909,0.00005670071,0.000004121695,5.96478e-8,0.000003253805,0.0006455716],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7740773,"threshold_uncertainty_score":0.3332258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01268735318000955,"score_gpt":0.2718507677242913,"score_spread":0.2591634145442817,"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."}}