{"id":"W6948899260","doi":"10.5281/zenodo.11234583","title":"RUEG Corpus","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"German; Heritage language; Variation (astronomy); Relevance (law); Language contact; Reading (process); Rule-based machine translation; Subject (documents)","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":[0.002893019,0.001813954,0.00165346,0.009201081,0.002288908,0.004852185,0.00404712,0.002092999,0.2849644],"category_scores_gemma":[0.008712118,0.001108464,0.0008812455,0.0104221,0.001093625,0.004874073,0.004858346,0.002241309,0.172816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002216732,"about_ca_system_score_gemma":0.003480345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01696957,"about_ca_topic_score_gemma":0.02038453,"domain_scores_codex":[0.9970124,0.0007996772,0.0004088783,0.0008732783,0.0006809184,0.0002249211],"domain_scores_gemma":[0.9955599,0.00151521,0.0002282378,0.001350875,0.001217862,0.0001278593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003548235,0.00007710575,0.00110221,0.001700921,0.00007500242,0.0004012246,0.001240728,0.0004657493,0.001450429,0.02431362,0.9012051,0.06761302],"study_design_scores_gemma":[0.00005606129,0.00001411002,0.001481863,0.0001889409,0.00002024504,0.0001691197,0.0003493702,0.0002253946,0.0005484304,0.002964122,0.99396,0.00002223466],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.005250993,0.001281175,0.005280131,0.00115083,0.0006788676,0.0006135722,0.8267364,0.00508916,0.153919],"genre_scores_gemma":[0.01355207,0.0007294719,0.01008339,0.0004471285,0.0002019,0.001560664,0.9270549,0.004089606,0.04228095],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2849644,"threshold_uncertainty_score":0.9533008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01516536557530488,"score_gpt":0.260243302567665,"score_spread":0.2450779369923602,"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."}}