{"id":"W2055999462","doi":"10.1002/ev.392","title":"Internal evaluation a quarter‐century later: A conversation with Arnold J. Love","year":2011,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Conversation; Evaluation methods; Perspective (graphical); Association (psychology); Quarter (Canadian coin); Sociology; Psychology; Computer science; Artificial intelligence; History; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09419937,0.0006579602,0.001872243,0.002343828,0.0124392,0.02158207,0.001646522,0.01517172,0.004861577],"category_scores_gemma":[0.119316,0.0008502112,0.001356166,0.002471659,0.026157,0.01842818,0.009645966,0.04370635,0.001711575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02585227,"about_ca_system_score_gemma":0.02190256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009212085,"about_ca_topic_score_gemma":0.0111806,"domain_scores_codex":[0.8968788,0.07444954,0.003813156,0.003709535,0.01665396,0.00449504],"domain_scores_gemma":[0.8701782,0.08354291,0.003248955,0.002432587,0.0236155,0.01698193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005611399,0.0001596456,0.000728461,0.0004044189,0.0000277892,0.0007254373,0.04633964,0.0001501543,0.0002220844,0.1414363,0.7515459,0.05820408],"study_design_scores_gemma":[0.0000157348,0.00004968336,0.0005336078,0.001858749,0.0000119451,0.0005781096,0.0198112,0.0001683184,0.0001758784,0.01959663,0.9571233,0.00007682951],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"other","genre_scores_codex":[0.0008269026,0.01930354,0.0007554638,0.9642933,0.00766812,0.0000100522,0.000006820345,0.00001112215,0.007124709],"genre_scores_gemma":[0.08146647,0.0453897,0.002549585,0.8189036,0.01543609,0.0001211309,0.00002529127,0.0002109306,0.03589711],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.09419937,"threshold_uncertainty_score":0.4981798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2229234698309984,"score_gpt":0.4641575431803136,"score_spread":0.2412340733493152,"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."}}