{"id":"W2997669297","doi":"10.1609/aaai.v34i04.6034","title":"Hierarchically Clustered Representation Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Cluster analysis; Embedding; Representation (politics); Feature learning; Artificial intelligence; Computer science; Abstraction; Hierarchy; Focus (optics); Pattern recognition (psychology); Space (punctuation); Hierarchical clustering; Machine learning","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":[0.0001920345,0.0001375173,0.0001729717,0.00007638296,0.0001726201,0.0002719982,0.002000969,0.00007341601,0.00004779356],"category_scores_gemma":[0.001032987,0.0001041214,0.00008494287,0.0007966355,0.0002021683,0.0004478041,0.0005097288,0.0003602494,0.0001186874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001955165,"about_ca_system_score_gemma":0.00004674387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006251417,"about_ca_topic_score_gemma":6.226222e-7,"domain_scores_codex":[0.9985246,0.00001900152,0.0004132524,0.0004358529,0.0004007881,0.0002065094],"domain_scores_gemma":[0.9989778,0.00007783066,0.0003345827,0.0002162912,0.000321151,0.00007232505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002691342,0.00002988958,0.0002992315,0.00001279095,0.000005528343,1.698557e-7,0.001236385,0.00005562789,0.05239802,0.7851306,0.0001752192,0.1606297],"study_design_scores_gemma":[0.00002956136,0.0002436155,0.0003520388,0.00005038654,0.000005522661,0.000001281647,0.0009552988,0.1324511,0.6668175,0.198293,0.0006295937,0.0001711227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1799694,0.00004629348,0.5546765,0.2148141,0.0005526284,0.00113247,0.000003003363,0.001617626,0.04718805],"genre_scores_gemma":[0.9939347,0.00003274559,0.005321213,0.0004398267,0.0000367488,0.00001838433,3.763099e-7,0.000006623999,0.0002094028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8139653,"threshold_uncertainty_score":0.4245946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1244690751837098,"score_gpt":0.3113484694946094,"score_spread":0.1868793943108996,"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."}}