{"id":"W1982795102","doi":"10.1109/icalt.2010.47","title":"Automarking: Automatic Assessment of Open Questions","year":2010,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University","funders":"Athabasca University","keywords":"Computer science; Meaning (existential); Leverage (statistics); Question answering; Probabilistic logic; Taxonomy (biology); Natural language processing; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003693232,0.00005081695,0.00009606284,0.00004975505,0.0000474286,0.0001617345,0.001471004,0.00002873203,0.0001531357],"category_scores_gemma":[0.00003176605,0.0000427792,0.00002212399,0.0001355696,0.0000163504,0.0004073486,0.0006558942,0.0001068251,0.000009217454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001080939,"about_ca_system_score_gemma":0.0001558423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001746706,"about_ca_topic_score_gemma":0.00006701674,"domain_scores_codex":[0.9993725,0.00002409423,0.0001813879,0.0001713388,0.000146884,0.0001038046],"domain_scores_gemma":[0.9991482,0.00005477997,0.00005886471,0.0006446435,0.00004718921,0.00004631838],"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":[4.106758e-8,0.00004003502,0.001764936,0.000005994788,0.00000469685,0.000001003941,0.00006786929,0.00007247663,0.003162126,0.9415213,0.0002313052,0.0531282],"study_design_scores_gemma":[0.00009003341,0.00001216989,0.02655925,0.000009130854,0.000001782936,0.000005133966,0.00000426513,0.9620345,0.0004309271,0.009651747,0.001142667,0.00005836662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0481988,0.000001678928,0.8786272,0.001081762,0.0003715815,0.0001334988,2.170479e-7,0.0001675351,0.07141772],"genre_scores_gemma":[0.5322788,1.829597e-7,0.4673367,0.00006306603,0.00000902471,0.000006836175,1.396203e-7,0.000001561855,0.0003036481],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.961962,"threshold_uncertainty_score":0.2733516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03326472433835425,"score_gpt":0.3561803345393306,"score_spread":0.3229156102009764,"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."}}