{"id":"W4391793582","doi":"10.1145/3632971.3632980","title":"Open-ended questions automated evaluation: proposal of a new generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0005916418,0.00007289408,0.0001229294,0.0001903595,0.00007493196,0.0001298924,0.0008402991,0.00003662524,0.0000618046],"category_scores_gemma":[0.0001179499,0.00006400391,0.00003427346,0.001521235,0.00001734971,0.0008765668,0.0004078532,0.00003904858,0.00007854354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000483911,"about_ca_system_score_gemma":0.0004366625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001256682,"about_ca_topic_score_gemma":0.0001452555,"domain_scores_codex":[0.9989265,0.00008882183,0.0002413157,0.0002661228,0.0003609633,0.0001163284],"domain_scores_gemma":[0.9990461,0.00002145563,0.0000987109,0.0005072557,0.0002772804,0.00004919155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002339368,0.00008786749,0.00009726345,0.00000594378,0.00004734641,0.000003438817,0.000480583,0.006820112,0.1055245,0.6073777,0.1648333,0.1147197],"study_design_scores_gemma":[0.0001589632,0.00003695026,0.000745888,0.000006348962,0.00001133035,0.000001708787,0.000006668592,0.9129229,0.04756166,0.03802086,0.0004494728,0.00007720249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00439071,0.00001590333,0.985097,0.002225942,0.0000748732,0.0004880068,6.454378e-7,0.002891616,0.004815291],"genre_scores_gemma":[0.3838814,0.000007058438,0.6134317,0.00007281691,0.00003848714,0.00006600203,0.00002743027,0.00000581412,0.002469281],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9061028,"threshold_uncertainty_score":0.2610004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08351453324136883,"score_gpt":0.4042058395524386,"score_spread":0.3206913063110697,"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."}}