{"id":"W4411120228","doi":"10.18653/v1/2025.repl4nlp-1.1","title":"DEPTH: Discourse Education through Pre-Training Hierarchically","year":2025,"lang":"en","type":"article","venue":"","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Open Philanthropy Project","keywords":"Training (meteorology); Computer science; Meteorology; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001566889,0.002090585,0.0005364962,0.0008667872,0.0005492551,0.001331478,0.002688685,0.001511227,0.01316136],"category_scores_gemma":[0.007322501,0.0007558833,0.001126982,0.0006020055,0.0005934273,0.003669551,0.002697855,0.003962786,0.008137804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001251866,"about_ca_system_score_gemma":0.001765619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006270042,"about_ca_topic_score_gemma":0.01857969,"domain_scores_codex":[0.999119,0.0003340371,0.00005214019,0.0003417688,0.0000894882,0.00006359531],"domain_scores_gemma":[0.9977579,0.001270695,0.00008617942,0.0005090891,0.0002806105,0.00009551791],"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":[0.0004536941,0.0005748232,0.004851716,0.001226736,0.0002254243,0.0002574954,0.0010845,0.07737577,0.0192243,0.009704362,0.1465345,0.7384866],"study_design_scores_gemma":[0.0002468052,0.0003975866,0.001923207,0.0002484299,0.0001185486,0.0001589055,0.0005352568,0.8766758,0.03063561,0.024822,0.06416203,0.00007587747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1300747,0.003398905,0.6621864,0.002765185,0.001029681,0.0009888585,0.02476211,0.1467715,0.02802248],"genre_scores_gemma":[0.4241183,0.0009240975,0.4790301,0.001515678,0.0001684349,0.00166108,0.06908465,0.003826703,0.01967097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01316136,"threshold_uncertainty_score":0.04402912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03132813193739518,"score_gpt":0.3427221726305565,"score_spread":0.3113940406931613,"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."}}