{"id":"W1999570557","doi":"10.1006/ijhc.2000.0393","title":"Experimental design heuristics for scientific discovery: the use of “baseline” and “known standard” controls","year":2000,"lang":"en","type":"article","venue":"International Journal of Human-Computer Studies","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Heuristics; Baseline (sea); Control (management); Heuristic; Computer science; Test (biology); Design of experiments; Key (lock); Management science; Data science; Statistics; Artificial intelligence; Mathematics; Engineering; Computer security","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":[0.0005465391,0.0001427121,0.0003482515,0.00007265831,0.0002341321,0.0001697499,0.0003085592,0.00003312068,0.0001252862],"category_scores_gemma":[0.00004127219,0.00008043685,0.0001487117,0.00004651759,0.0005489125,0.0001775908,0.00007388964,0.0001137148,0.000002934323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003220337,"about_ca_system_score_gemma":0.000009858962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007319582,"about_ca_topic_score_gemma":0.000003229613,"domain_scores_codex":[0.9986562,0.0001343394,0.0005483139,0.0001819245,0.0003295526,0.0001496309],"domain_scores_gemma":[0.998307,0.0006923174,0.0002931265,0.0001072498,0.0005680246,0.00003227184],"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":[0.009765463,0.003326592,0.009067834,0.00003783275,0.009092517,0.0003471023,0.03462189,0.001073298,0.005667096,0.02376746,0.5340199,0.369213],"study_design_scores_gemma":[0.0305347,0.02163189,0.1129093,0.001065094,0.001308286,0.0009780187,0.008740323,0.0008698737,0.008532566,0.02063238,0.7910053,0.001792281],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9463273,0.009884967,0.03748693,0.001578315,0.004144222,0.0003502119,0.0001403958,0.00001164734,0.00007598887],"genre_scores_gemma":[0.9936745,0.0001599531,0.0040284,0.0003106964,0.0007321217,0.00001896242,0.000002578078,0.000008999261,0.001063818],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3674207,"threshold_uncertainty_score":0.328012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3767082615817805,"score_gpt":0.4321597185868045,"score_spread":0.05545145700502402,"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."}}