{"id":"W4318824050","doi":"10.1109/icdm54844.2022.00125","title":"Set2Box: Similarity Preserving Representation Learning for Sets","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Data Mining (ICDM)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Similarity (geometry); Computer science; ENCODE; Set (abstract data type); Representation (politics); Source code; Code (set theory); Theoretical computer science; Data mining; Artificial intelligence; Algorithm; Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001162557,0.0002084158,0.0001996776,0.0002626916,0.0008299335,0.000443574,0.005304681,0.00005041321,0.0007644573],"category_scores_gemma":[0.0009017986,0.000247276,0.00006988025,0.0003858184,0.0000377272,0.000875972,0.002708214,0.0007075078,0.00003996925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001724567,"about_ca_system_score_gemma":0.000174615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003410012,"about_ca_topic_score_gemma":0.00003605399,"domain_scores_codex":[0.9968761,0.0003094678,0.0004206333,0.001144806,0.0009270507,0.0003220086],"domain_scores_gemma":[0.9970747,0.0006660201,0.0003734902,0.00156319,0.0002241551,0.00009839324],"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":[0.0007642226,0.001319449,0.04638805,0.0001107018,0.0006750496,0.00008062921,0.009402017,0.2550268,0.02142239,0.2844718,0.146972,0.2333668],"study_design_scores_gemma":[0.0006503809,0.00013043,0.003357378,0.0000193935,0.00001119621,0.00001718937,0.0004850974,0.9758323,0.0002109704,0.002052914,0.01697196,0.0002607311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2597801,0.0000512461,0.6618473,0.03773794,0.004949186,0.002035511,0.001985378,0.001226248,0.03038709],"genre_scores_gemma":[0.9542998,0.00001149059,0.04047726,0.0005422648,0.0001731821,0.00054308,0.002590782,0.00002840818,0.001333707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7208055,"threshold_uncertainty_score":0.999998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2345270794719642,"score_gpt":0.419734007872125,"score_spread":0.1852069284001608,"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."}}