{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009713752,0.0002194726,0.0002404111,0.0006054447,0.0002157167,0.0002361033,0.0003020742,0.0001150959,0.01145379],"category_scores_gemma":[0.001223773,0.0001690873,0.0001462317,0.0008711343,0.00005668517,0.001267031,0.00002631969,0.0001389492,0.0009926495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004672486,"about_ca_system_score_gemma":0.001016102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002381308,"about_ca_topic_score_gemma":0.0007713031,"domain_scores_codex":[0.9944335,0.0005540317,0.0007827567,0.000625641,0.003327966,0.0002761534],"domain_scores_gemma":[0.9953578,0.0003737025,0.0005801295,0.0005659725,0.002970226,0.0001521699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001285794,0.0004887917,0.02512361,0.00001552443,0.0002417346,5.324846e-7,0.03601621,0.003045821,0.0008227548,0.001805335,0.03802973,0.8931242],"study_design_scores_gemma":[0.009654631,0.001365003,0.1733542,0.00008060967,0.0007345598,0.00002568238,0.007355947,0.7264556,0.003707619,0.03146711,0.04524055,0.0005585041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6133327,0.0005666818,0.2070441,0.005391363,0.006261089,0.009201546,0.00006719652,0.0003026188,0.1578327],"genre_scores_gemma":[0.9925314,0.00002764217,0.004075015,0.0002134255,0.0002760134,0.0003221997,0.0001203602,0.000022049,0.002411908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8925657,"threshold_uncertainty_score":0.9997852,"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."}}