{"id":"W2161493293","doi":"10.1109/crv.2009.30","title":"Optimal Online Data Sampling or How to Hire the Best Secretaries","year":2009,"lang":"en","type":"article","venue":"","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Generalization; Sampling (signal processing); Sample (material); Selection (genetic algorithm); Secretary problem; Simple (philosophy); Artificial intelligence; Machine learning; Online algorithm; Sequence (biology); Data mining; Mathematical optimization; Algorithm; 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":[0.0002624671,0.0000856507,0.00008508806,0.00004268623,0.000204566,0.0006446989,0.002091996,0.00002563301,0.000073659],"category_scores_gemma":[0.0001563388,0.00004662543,0.00001528461,0.000382459,0.00002559697,0.0007435672,0.0006515063,0.0001054011,0.00004524158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001015901,"about_ca_system_score_gemma":0.0000896837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000209593,"about_ca_topic_score_gemma":0.0001057528,"domain_scores_codex":[0.9990754,0.00003325207,0.0001073118,0.000316495,0.0002345886,0.0002329245],"domain_scores_gemma":[0.998625,0.00008790672,0.00002305212,0.001075145,0.00007934464,0.0001094845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006580613,0.0006059946,0.0002785599,0.00002022193,0.00005652435,0.00003695158,0.004976285,0.1767983,0.0005063056,0.1614687,0.09271546,0.5624708],"study_design_scores_gemma":[0.0001480642,0.0001994766,0.0002832249,0.00001216544,0.000002669875,0.00001075923,0.0003358472,0.8994213,0.00005665726,0.0002210886,0.0991706,0.0001381914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008134022,0.00002679904,0.9001545,0.09776248,0.00007033352,0.0001715095,0.00001275755,0.0001129884,0.00087524],"genre_scores_gemma":[0.04085294,0.00003362604,0.9451671,0.006941627,0.00008438875,0.000002356754,0.00005255264,0.000004690057,0.006860684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7226229,"threshold_uncertainty_score":0.6216846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1732802181241352,"score_gpt":0.3577267200153544,"score_spread":0.1844465018912191,"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."}}