{"id":"W4389524336","doi":"10.18653/v1/2023.emnlp-main.942","title":"A State-Vector Framework for Dataset Effects","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Component (thermodynamics); Machine learning; Artificial intelligence; Quality (philosophy); Vector space; Artificial neural network; State (computer science); Data mining; Space (punctuation); Mathematics; Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01674627,0.002055336,0.002792014,0.00272991,0.001440537,0.006305494,0.005125985,0.002875816,0.01300753],"category_scores_gemma":[0.04711937,0.001458706,0.002221391,0.002832087,0.004344768,0.01291473,0.006388263,0.006825409,0.001867381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002635957,"about_ca_system_score_gemma":0.002934359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007129977,"about_ca_topic_score_gemma":0.005095584,"domain_scores_codex":[0.9934469,0.003367744,0.000408641,0.001293871,0.0009696671,0.0005130791],"domain_scores_gemma":[0.9600417,0.02705517,0.002720831,0.005765891,0.003681874,0.000734562],"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":[0.0002064158,0.0001415263,0.002437138,0.0002237257,0.0001322062,0.000142511,0.0002083982,0.245921,0.001181543,0.7104647,0.004208239,0.03473257],"study_design_scores_gemma":[0.00002974045,0.00008041741,0.0003702645,0.00004839494,0.00006100303,0.00003370347,0.00002804784,0.7636945,0.0005560582,0.2323103,0.002738495,0.00004923423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006813756,0.0005134378,0.9869093,0.001338124,0.0001212406,0.00009951591,0.0006856631,0.0005627206,0.002956251],"genre_scores_gemma":[0.6023324,0.002889082,0.3696105,0.001379776,0.0009909668,0.00305569,0.003549002,0.0009446074,0.01524816],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01674627,"threshold_uncertainty_score":0.0885638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0339349691202402,"score_gpt":0.311670077488155,"score_spread":0.2777351083679148,"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."}}