{"id":"W4310419110","doi":"10.48550/arxiv.2211.14912","title":"Impact of Strategic Sampling and Supervision Policies on Semi-supervised Learning","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Representativeness heuristic; Computer science; Context (archaeology); Sample (material); Artificial intelligence; Machine learning; Labelling; Set (abstract data type); Selection (genetic algorithm); Training set; Labeled data; Representation (politics); Process (computing); Quality (philosophy); Supervised learning; Ask price; Data set; Variety (cybernetics); Statistics; Mathematics; Artificial neural network; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003549293,0.0002833899,0.0003462662,0.0004404898,0.0003075917,0.0001484447,0.0008969443,0.0001479756,0.0001624195],"category_scores_gemma":[0.00004577525,0.0003079654,0.0002341919,0.0005758891,0.00007965269,0.0002296872,0.001515577,0.0009373577,0.000009910236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001919738,"about_ca_system_score_gemma":0.0002083594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005491718,"about_ca_topic_score_gemma":0.000007487561,"domain_scores_codex":[0.9982481,0.000298661,0.0002164807,0.0007755081,0.0001560111,0.0003052097],"domain_scores_gemma":[0.9986623,0.0002512964,0.0002461032,0.0005925445,0.00009343337,0.0001543514],"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":[0.0000427228,0.00005992375,0.02266216,0.00005000064,0.00006804545,0.00003757069,0.001535056,0.8973311,0.0003621784,0.07707554,0.000004451742,0.000771263],"study_design_scores_gemma":[0.0007323207,0.0005293644,0.03418805,0.0001236862,0.00003485271,0.000005740842,0.00172744,0.9474736,0.00002407802,0.01452749,0.0001276351,0.0005057703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9353805,0.00007007859,0.05908346,0.00002909135,0.000136068,0.000152225,0.000008090081,0.000157114,0.004983406],"genre_scores_gemma":[0.9983034,0.0002425826,0.000871837,0.00003415988,0.00002525259,5.518345e-7,0.00002260402,0.00001871816,0.0004808847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06292294,"threshold_uncertainty_score":0.9999372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1721840926498918,"score_gpt":0.2534048193886386,"score_spread":0.08122072673874686,"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."}}