{"id":"W6911821110","doi":"10.5281/zenodo.13368054","title":"AI-EA Implementation and Data","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Ancient Egypt and Archaeology","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Critical Systems Labs; University of Toronto","funders":"","keywords":"Quality assurance; Data collection; Feature (linguistics); Argumentation theory; Key (lock)","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002563247,0.0001386343,0.0001297673,0.000273948,0.0007113477,0.0007241518,0.0007257866,0.00005277654,0.2390995],"category_scores_gemma":[0.00003200549,0.0001320283,0.00002069681,0.00005912174,0.0003920397,0.0001357951,0.002265969,0.0002104592,0.0216901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002295676,"about_ca_system_score_gemma":0.000002522732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001147774,"about_ca_topic_score_gemma":0.00004230897,"domain_scores_codex":[0.9989192,0.00007265143,0.0001458295,0.0004577653,0.0001745888,0.0002299066],"domain_scores_gemma":[0.9993137,0.000005564257,0.00006966575,0.0004563801,0.00007975351,0.00007501231],"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":[0.000003775801,0.00001217402,1.913613e-7,0.00009656927,0.00004166835,0.000006857621,0.002952068,2.357095e-8,0.0000068293,0.1124039,0.8462974,0.03817859],"study_design_scores_gemma":[0.0001530749,0.00007171258,0.000002356042,0.00004566216,0.00003195583,0.00001931174,0.001397278,0.0000252531,0.000001683004,0.0008357998,0.9972706,0.00014535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001424817,0.0008057709,0.0001106247,0.00130856,0.0003195618,0.0002792719,0.002263562,0.00084011,0.9940583],"genre_scores_gemma":[0.003431827,0.0004513943,0.00004963355,0.0005392589,0.001362814,3.919018e-8,0.01755798,0.007016917,0.9695901],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2174094,"threshold_uncertainty_score":0.9790716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0832782339621347,"score_gpt":0.3063689334094639,"score_spread":0.2230906994473292,"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."}}