{"id":"W7037005269","doi":"","title":"Comparative Analysis of Transformer-Based Language Models for Text Analysis in the Domain of Sustainable Development","year":2023,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Invertebrate Taxonomy and Ecology","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Automatic summarization; Relevance (law); Similarity (geometry); Domain (mathematical analysis); Natural language; Representation (politics); Language model; Semantic similarity; Transfer of learning","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":[0.004055852,0.0007264602,0.0005742228,0.002602371,0.0003250712,0.001159477,0.0007710864,0.0006193565,0.001467977],"category_scores_gemma":[0.0131784,0.0001888965,0.0009398159,0.001424565,0.0003195385,0.002218568,0.000643597,0.0007248959,0.0007171931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001429999,"about_ca_system_score_gemma":0.001152634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007779333,"about_ca_topic_score_gemma":0.006337219,"domain_scores_codex":[0.9980795,0.00111138,0.0001516602,0.0002485036,0.000308807,0.0001001744],"domain_scores_gemma":[0.9867793,0.01104352,0.0003906884,0.0003484112,0.001278205,0.0001598395],"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":[0.001617115,0.0006419671,0.01005601,0.0005859238,0.0004147206,0.0002297477,0.0005518882,0.5196338,0.006570979,0.0141213,0.003248589,0.442328],"study_design_scores_gemma":[0.00001012156,0.0001144148,0.0008094902,0.00001040981,0.00003923621,0.00002587853,0.00006758997,0.9953588,0.0009749022,0.002230342,0.0003483392,0.00001051528],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4539244,0.003332352,0.5283005,0.001006083,0.0001479747,0.0002963752,0.001420505,0.003031177,0.008540818],"genre_scores_gemma":[0.9261481,0.001035193,0.06856035,0.00009070522,0.00005324144,0.0001936896,0.002045147,0.000128655,0.001745039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007779333,"threshold_uncertainty_score":0.02144969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0183519411887067,"score_gpt":0.1756545025929117,"score_spread":0.157302561404205,"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."}}