{"id":"W2919446416","doi":"10.18162/ritpu.2009.159","title":"10.18162/ritpu.2009.159","year":2016,"lang":"fr","type":"dataset","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Pencil (optics); Multiple choice; Test (biology); Significant difference; Psychology; Cognition; Mathematics education; Computer science; Statistics; Mathematics; Engineering","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008474849,0.0005894683,0.0006712819,0.000153541,0.0007640643,0.0003008328,0.001700487,0.0008330147,0.510806],"category_scores_gemma":[0.0001553028,0.0004495639,0.0003761298,0.0005553672,0.0009814163,0.0004692447,0.0004418652,0.0003893983,0.2386037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003096841,"about_ca_system_score_gemma":0.0003526014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002439331,"about_ca_topic_score_gemma":0.002733456,"domain_scores_codex":[0.9957151,0.0003626527,0.0006036427,0.0008247552,0.001354935,0.001138851],"domain_scores_gemma":[0.9978324,0.0005126743,0.0003462152,0.0007213667,0.000183727,0.0004036466],"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":[0.0000208665,0.0002181044,0.0002188431,0.00003427438,0.0001388804,0.00002020444,0.0002393606,6.651846e-8,0.000003695536,0.00756563,0.9837248,0.00781528],"study_design_scores_gemma":[0.00052607,0.000166226,0.0003174645,0.0001472176,0.0001648447,0.00000131675,0.0008753476,0.000001130926,0.00000372649,0.0007605344,0.9963136,0.0007224628],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.00003650552,0.0009523214,0.00002270134,0.005506084,0.003012403,0.000413388,0.5380069,0.00008614673,0.4519635],"genre_scores_gemma":[0.00004590218,0.002727764,0.0001328745,0.0005780258,0.004087963,0.0000347414,0.2471579,0.00002836918,0.7452065],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.293243,"threshold_uncertainty_score":0.9997956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03289347138127198,"score_gpt":0.3469420268414372,"score_spread":0.3140485554601652,"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."}}