{"id":"W2791802454","doi":"10.3758/s13428-018-1028-5","title":"Picture perfect: A stimulus set of 225 pairs of matched clipart and photographic images normed by Mechanical Turk and laboratory participants","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Multisensory perception and integration","field":"Psychology","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Normative; Artificial intelligence; Stimulus (psychology); Computer science; Set (abstract data type); Psychology; Modal; Computer vision; Pattern recognition (psychology); Cognitive psychology","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004487878,0.000165942,0.0003979128,0.000280353,0.000120293,0.00002578481,0.0001540432,0.0002635846,0.002286372],"category_scores_gemma":[0.0006109203,0.0001374218,0.00006035742,0.0004702186,0.001123727,0.00008732632,0.00009074193,0.0004543682,0.00001253947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002020617,"about_ca_system_score_gemma":0.00005404937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004247745,"about_ca_topic_score_gemma":0.00008442303,"domain_scores_codex":[0.994917,0.003358138,0.0004349,0.0004395282,0.0003909566,0.0004594215],"domain_scores_gemma":[0.9980921,0.0005454422,0.0001093116,0.0004292622,0.0005714254,0.000252489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003411014,0.0002464551,0.02702445,0.00004692328,0.00003272982,0.000004565044,0.004646026,2.704836e-8,0.9402403,0.0000890376,0.003913448,0.02341497],"study_design_scores_gemma":[0.002094011,0.002051883,0.5332113,0.00007305716,0.0001195368,0.00001455236,0.009581753,0.0002637786,0.4483861,0.0001422514,0.003770934,0.0002909046],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974398,0.0002646171,0.0009565311,0.0001026586,0.0001427367,0.000608927,0.0002185349,0.000029538,0.0002366357],"genre_scores_gemma":[0.9868436,0.0001008305,0.01230099,0.00004311856,0.00005782791,0.0001936829,0.00001680824,0.00002609222,0.0004170626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5061868,"threshold_uncertainty_score":0.9986257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2782693766483391,"score_gpt":0.5845073464812839,"score_spread":0.3062379698329448,"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."}}