{"id":"W4385570873","doi":"10.18653/v1/2023.cawl-1.11","title":"Learning the Character Inventories of Undeciphered Scripts Using Unsupervised Deep Clustering","year":2023,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scripting language; Computer science; Cluster analysis; Character (mathematics); Artificial intelligence; Exploit; Task (project management); Natural language processing; Set (abstract data type); Process (computing); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003694787,0.0007368181,0.0004693907,0.001029289,0.0003163084,0.0009379797,0.001234005,0.0007922371,0.001726992],"category_scores_gemma":[0.00212608,0.0004698258,0.0007927152,0.0008326482,0.0006843957,0.001583135,0.0005312056,0.001556012,0.001076283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001022205,"about_ca_system_score_gemma":0.0006316782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008293892,"about_ca_topic_score_gemma":0.01546949,"domain_scores_codex":[0.9997771,0.00003954667,0.00001042287,0.000106915,0.00002941108,0.00003658279],"domain_scores_gemma":[0.9992214,0.0002600217,0.0001146297,0.0001984558,0.0001460997,0.00005926551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002400427,0.000149009,0.007873314,0.0001250577,0.0001075705,0.0002055627,0.0003568102,0.5804976,0.01737979,0.008466155,0.006017501,0.3785816],"study_design_scores_gemma":[0.000002753702,0.0000109446,0.0006437115,0.000006713404,0.000005161305,0.0000239158,0.00002842722,0.993594,0.001910175,0.003395985,0.0003723972,0.000005693452],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3333396,0.0004770326,0.6556704,0.0003922326,0.00006337683,0.0001090906,0.001013407,0.004647428,0.004287485],"genre_scores_gemma":[0.8591408,0.0002169905,0.1317493,0.0001509845,0.00003135659,0.00006501258,0.002888338,0.00025818,0.005498988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008293892,"threshold_uncertainty_score":0.01649123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05054510033694829,"score_gpt":0.2796570827119955,"score_spread":0.2291119823750472,"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."}}