{"id":"W2099779943","doi":"10.3115/1621969.1621986","title":"SemEval-2010 task 8","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":497,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"SemEval; Computer science; Task (project management); Testbed; Natural language processing; Artificial intelligence; Information extraction; Natural language; Semantics (computer science); Information retrieval; World Wide Web; Programming language","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":[0.0001052907,0.00006362142,0.00005844257,0.00005114825,0.00004235767,0.0001151668,0.0007103434,0.00003871255,0.00002177332],"category_scores_gemma":[0.00002442291,0.0000470227,0.00002390885,0.0002119754,0.000009152843,0.0003918764,0.00007457638,0.00008945302,0.00006085324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001305159,"about_ca_system_score_gemma":0.00001790849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007648766,"about_ca_topic_score_gemma":0.000001185995,"domain_scores_codex":[0.999451,0.00001070894,0.00007708192,0.0001801212,0.0001369127,0.0001441248],"domain_scores_gemma":[0.9995379,0.00001226652,0.00002326388,0.0003465161,0.00003926038,0.00004076202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001110643,0.00003100212,0.00002249859,0.00000257293,0.000001779279,0.00002192076,0.000151704,3.49426e-7,0.03758967,0.5105587,0.02917468,0.422444],"study_design_scores_gemma":[0.0001515283,0.0001542699,0.0006047761,0.00002009085,0.000002514306,0.00005357451,0.000004058018,0.007235683,0.2722572,0.7082964,0.01088302,0.0003369435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005203325,0.0006059337,0.9795578,0.005277003,0.0001090401,0.0000510446,1.336482e-7,0.001639521,0.01223924],"genre_scores_gemma":[0.3596422,0.000002570979,0.6357693,0.002504512,0.00002752722,9.001047e-7,2.933348e-7,0.000001601892,0.002051034],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.422107,"threshold_uncertainty_score":0.191753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009039731999430325,"score_gpt":0.2638369322279143,"score_spread":0.254797200228484,"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."}}