{"id":"W2953642885","doi":"10.1145/3331184.3331354","title":"Dynamic Sampling Meets Pooling","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Institute of Standards and Technology","keywords":"Pooling; NIST; Computer science; Sampling (signal processing); Statistics; Set (abstract data type); Sample (material); Data mining; Information retrieval; Artificial intelligence; Natural language processing; Mathematics; Computer vision","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":[0.0001399145,0.00006181807,0.00007628979,0.00004779098,0.0000329395,0.00008242929,0.0005072494,0.00002852211,0.00006396411],"category_scores_gemma":[0.000009222141,0.00005503656,0.000030597,0.00009957593,0.000003438133,0.0002657839,0.0001951418,0.00006544789,0.0004545491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002597151,"about_ca_system_score_gemma":0.00002199665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002471907,"about_ca_topic_score_gemma":0.000005608189,"domain_scores_codex":[0.9992931,0.000009450247,0.0001147205,0.0002629738,0.0001355797,0.0001841588],"domain_scores_gemma":[0.9994065,0.00003920495,0.00002347111,0.0004696622,0.00002153708,0.00003968602],"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":[0.000002135101,0.00003184176,0.003274125,0.00003685974,0.00002191242,0.000007287053,0.0008854942,0.04470598,0.01878662,0.7528192,0.00006827649,0.1793602],"study_design_scores_gemma":[0.00009160106,0.000007579752,0.0005138417,0.0000101792,7.093712e-7,0.000005941587,0.0000136085,0.9936507,0.0002582039,0.003742129,0.001612277,0.00009319423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1524453,0.00004337282,0.8347846,0.0006462536,0.0004002739,0.00005951933,7.247966e-8,0.0001969057,0.01142364],"genre_scores_gemma":[0.6865374,0.000001861893,0.3122158,0.0002679131,0.0000105408,9.129469e-7,2.084453e-7,0.000003309236,0.000962098],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9489447,"threshold_uncertainty_score":0.5842461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02051590183612376,"score_gpt":0.2626628086594748,"score_spread":0.2421469068233511,"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."}}