{"id":"W2138630447","doi":"10.1109/dcc.2012.44","title":"A Machine Learning Perspective on Predictive Coding with PAQ8","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Perspective (graphical); Online machine learning; Lossy compression; Unsupervised learning; Computational learning theory; Coding (social sciences); Predictive coding","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":[0.0001457643,0.00009968545,0.00008696102,0.00005457302,0.0001747617,0.00006633746,0.0002646793,0.00002458109,0.00004401278],"category_scores_gemma":[0.0000238958,0.00006209823,0.00001920675,0.0001594394,0.00002104303,0.0007456287,0.0001980393,0.00018895,0.00005812726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000665539,"about_ca_system_score_gemma":0.0000166812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000122184,"about_ca_topic_score_gemma":0.000002712464,"domain_scores_codex":[0.9992042,0.0000453077,0.00006278266,0.0002249817,0.0002229816,0.0002397242],"domain_scores_gemma":[0.9994887,0.0000739993,0.00004132609,0.0002360778,0.00005531116,0.0001046171],"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":[0.0001069357,0.0003351256,0.01639362,0.00000642249,0.00006335187,0.00001765813,0.008501253,0.0009562757,0.0002505255,0.9472049,0.001377034,0.0247869],"study_design_scores_gemma":[0.001148876,0.00151219,0.02133002,0.0001129727,0.00001520666,0.0000703601,0.001783883,0.9529682,0.002452543,0.001448368,0.01663073,0.0005266428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001647445,0.0001388709,0.9435354,0.000268122,0.0001187014,0.00008975174,0.000002593356,0.0002282741,0.0539708],"genre_scores_gemma":[0.9627219,0.00001115124,0.03620311,0.0001729441,0.0001128275,0.000007450099,0.000003025519,0.000006873127,0.0007606861],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9610745,"threshold_uncertainty_score":0.2532292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01336615181079373,"score_gpt":0.2478123666983549,"score_spread":0.2344462148875611,"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."}}