{"id":"W2364913443","doi":"10.48550/arxiv.1605.03072","title":"Semi-Supervised Representation Learning based on Probabilistic Labeling","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Probabilistic logic; Artificial intelligence; Representation (politics); Computer science; Machine learning; Supervised learning; Natural language processing; Pattern recognition (psychology); Artificial neural network; Political science","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002445469,0.0002570982,0.0002355263,0.0002745372,0.000211973,0.0001333621,0.0008630481,0.000251695,0.00007623983],"category_scores_gemma":[0.0001776667,0.000247066,0.0001602388,0.0003705327,0.00004867602,0.0003362875,0.0006378465,0.0005179472,0.0002821421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000159581,"about_ca_system_score_gemma":0.0001450983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003103672,"about_ca_topic_score_gemma":0.000003641569,"domain_scores_codex":[0.9979587,0.0002939587,0.0001882938,0.001119612,0.000146847,0.0002926466],"domain_scores_gemma":[0.9982793,0.0002977611,0.0002131381,0.0008827908,0.0001947575,0.0001322636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000657073,0.000104436,0.001620389,0.0001052775,0.0000263204,0.0001241928,0.0001593864,0.9859441,0.0008566453,0.007316401,0.0004892125,0.00318791],"study_design_scores_gemma":[0.000636512,0.00006599256,0.0001913833,0.0005562191,0.00002700402,7.774547e-7,0.00003623755,0.9715196,0.001114118,0.02529108,0.0002170594,0.0003440488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1532008,0.00001057591,0.8398283,0.0003775891,0.0005280435,0.0003720505,0.000008446204,0.0004750173,0.005199156],"genre_scores_gemma":[0.9969178,0.00003345386,0.001412502,0.0001866066,0.00007154524,0.000003488959,0.00003749655,0.00001771616,0.001319414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8437169,"threshold_uncertainty_score":0.9999982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08014613218572131,"score_gpt":0.206100075125378,"score_spread":0.1259539429396567,"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."}}