{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001096656,0.000429252,0.0004500292,0.0005447112,0.000617172,0.002510038,0.006930817,0.0002684915,0.000003046785],"category_scores_gemma":[0.00006588694,0.000403256,0.0001320483,0.001127091,0.0006631432,0.001542376,0.003981871,0.0004398496,0.00005663994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003859411,"about_ca_system_score_gemma":0.000948567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004180956,"about_ca_topic_score_gemma":0.00001062595,"domain_scores_codex":[0.9957166,0.00003670303,0.0005790971,0.002009982,0.0009208331,0.0007367893],"domain_scores_gemma":[0.9957919,0.0001171145,0.0006412956,0.002550494,0.0007514553,0.0001477565],"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":[0.00004724978,0.0008002339,0.003580921,0.0006183709,0.0000716813,0.000005678912,0.001755881,0.01279453,0.01227635,0.479536,0.00486854,0.4836446],"study_design_scores_gemma":[0.0007927506,0.00006331972,0.002180388,0.00009625705,0.00001153844,0.000004160735,0.00002226935,0.9862229,0.002601802,0.004566097,0.002914015,0.0005245298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01396388,0.0002810259,0.9768309,0.002047654,0.004474627,0.001263483,0.00003578819,0.0009868505,0.0001158004],"genre_scores_gemma":[0.2637241,0.0000274784,0.735468,0.0001523792,0.0001346648,0.0001380498,0.00002731266,0.0000184281,0.0003095891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9734284,"threshold_uncertainty_score":0.9998419,"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."}}