{"id":"W7131749478","doi":"","title":"AI for ancient languages, insights for small corpus processing","year":2023,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Corpus linguistics; Field (mathematics); Linguistic analysis; Digital humanities","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002489206,0.0005835037,0.0003833002,0.002532643,0.0009980652,0.005954119,0.0009041866,0.0007955635,0.01968403],"category_scores_gemma":[0.0112227,0.0004528277,0.0004699642,0.002077585,0.002543867,0.007142616,0.002219796,0.002406689,0.005966222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001700527,"about_ca_system_score_gemma":0.001932463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005923017,"about_ca_topic_score_gemma":0.01115729,"domain_scores_codex":[0.999087,0.0003596893,0.0000608706,0.0001607118,0.0002940161,0.00003775723],"domain_scores_gemma":[0.9932922,0.005219016,0.0001217357,0.0005167809,0.000658683,0.000191519],"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":[0.0002073562,0.00004734861,0.0005557701,0.0004879204,0.00004751775,0.0002130158,0.002368638,0.002514793,0.003502966,0.2530635,0.1814559,0.5555351],"study_design_scores_gemma":[0.00002182687,0.00001685395,0.000889616,0.0002012812,0.00001620361,0.0001978117,0.0007951843,0.02056586,0.002960075,0.619609,0.3546906,0.00003574249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008937165,0.02256622,0.7950985,0.04979658,0.001612948,0.0001114887,0.004033263,0.008491922,0.1093518],"genre_scores_gemma":[0.1787322,0.02321551,0.6713653,0.004654897,0.002755803,0.0004273038,0.006850221,0.00481964,0.1071792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01968403,"threshold_uncertainty_score":0.0658496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0863593118902437,"score_gpt":0.3646106347376942,"score_spread":0.2782513228474505,"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."}}