{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008147277,0.001588434,0.001207201,0.006237664,0.0007778066,0.00319806,0.002176367,0.002056378,0.009720596],"category_scores_gemma":[0.03684847,0.0005601963,0.0007909367,0.00260728,0.0006263554,0.005945988,0.003808594,0.001932184,0.008629402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008689463,"about_ca_system_score_gemma":0.001525333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001928158,"about_ca_topic_score_gemma":0.002124563,"domain_scores_codex":[0.9908537,0.004250856,0.0007626141,0.001686786,0.00212004,0.0003260579],"domain_scores_gemma":[0.9684075,0.0215442,0.001836217,0.00228712,0.005173774,0.0007511238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006091148,0.000342371,0.006194355,0.0006091258,0.0000652306,0.0001676297,0.001422737,0.001607341,0.02465597,0.003451787,0.02406722,0.9368071],"study_design_scores_gemma":[0.0004722488,0.001075404,0.04915985,0.0005337529,0.0002153661,0.001537039,0.004237325,0.5187938,0.1569704,0.07466489,0.1919267,0.0004132338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05737974,0.001348529,0.8487139,0.0006698826,0.0003416471,0.002217712,0.00520016,0.07744686,0.00668146],"genre_scores_gemma":[0.2649587,0.0006624977,0.7073035,0.0003125804,0.0003410905,0.001686756,0.01430694,0.001451589,0.00897628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009720596,"threshold_uncertainty_score":0.04308748,"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."}}