{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.118631,0.001523406,0.00179722,0.001832035,0.001671111,0.00363976,0.003518976,0.002773688,0.003505898],"category_scores_gemma":[0.4849073,0.00157664,0.001097665,0.001313768,0.004645515,0.00521837,0.003362845,0.003694464,0.0004050029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003187767,"about_ca_system_score_gemma":0.003603947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008837656,"about_ca_topic_score_gemma":0.001217178,"domain_scores_codex":[0.8339751,0.1330465,0.01017323,0.009502329,0.01207993,0.001222896],"domain_scores_gemma":[0.3880925,0.518767,0.02451939,0.05068323,0.01472919,0.003208694],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.08672929,0.01018702,0.02653744,0.006909213,0.004342821,0.0002823391,0.008656628,0.03121758,0.02141803,0.2822379,0.009774257,0.5117075],"study_design_scores_gemma":[0.0279036,0.02223162,0.0341007,0.00137355,0.004774983,0.0004989864,0.001079935,0.2540903,0.04163604,0.5843763,0.02700798,0.000925995],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1592183,0.001727788,0.8162736,0.001325564,0.001207002,0.008555151,0.000307839,0.001340828,0.01004378],"genre_scores_gemma":[0.5527974,0.0002902423,0.4334454,0.001004471,0.0001629302,0.01090923,0.0002383667,0.0002757205,0.0008762863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.881369,"threshold_uncertainty_score":0.6273881,"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."}}