{"id":"W2587810790","doi":"10.7717/peerj-cs.242","title":"Nearest labelset using double distances for multi-label classification","year":2019,"lang":"en","type":"preprint","venue":"PeerJ Computer Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Multi-label classification; Pattern recognition (psychology); Benchmark (surveying); Hamming code; Feature (linguistics); Mathematics; Function (biology); Hamming distance; Computer science; Artificial intelligence; Measure (data warehouse); k-nearest neighbors algorithm; Binomial (polynomial); Space (punctuation); Algorithm; Statistics; Data mining","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004429074,0.001678763,0.002506039,0.004983691,0.001324545,0.002321705,0.003935131,0.003531919,0.002621381],"category_scores_gemma":[0.01250708,0.000476022,0.001339214,0.003826939,0.001319042,0.004450843,0.002882926,0.003908692,0.002314721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001603049,"about_ca_system_score_gemma":0.001477198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00245231,"about_ca_topic_score_gemma":0.00301365,"domain_scores_codex":[0.99391,0.001729886,0.000403615,0.001641143,0.001989407,0.0003259377],"domain_scores_gemma":[0.9919682,0.003463103,0.0008482466,0.002094301,0.001309588,0.0003165057],"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":[0.0007618133,0.0005233482,0.007115774,0.0003038337,0.000239094,0.0002125724,0.0002396578,0.2402782,0.004427714,0.02386838,0.01394419,0.7080855],"study_design_scores_gemma":[0.0000246299,0.00007400936,0.000491358,0.00002601625,0.00001412668,0.0001020985,0.00005396633,0.958648,0.002711745,0.0352251,0.002594237,0.00003470807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02864091,0.001039799,0.9650097,0.0004229141,0.0002111917,0.0001238754,0.0005727804,0.002167129,0.001811742],"genre_scores_gemma":[0.4433078,0.0005072174,0.5428401,0.0003827646,0.0003436981,0.00036373,0.004539646,0.0005084177,0.007206676],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004983691,"threshold_uncertainty_score":0.02342343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2164557323099007,"score_gpt":0.3839751774236232,"score_spread":0.1675194451137225,"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."}}