{"id":"W4403486620","doi":"10.3233/faia240955","title":"SETTP: Style Extraction and Tunable Inference via Dual-Level Transferable Prompt Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Inference; Style (visual arts); Extraction (chemistry); Dual (grammatical number); Computer science; Artificial intelligence; Geography; Art; Chemistry; Chromatography; Archaeology","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":[0.001489143,0.001982511,0.0008163891,0.0008933,0.000438399,0.001422807,0.002316166,0.001398401,0.008858125],"category_scores_gemma":[0.00780908,0.0005555366,0.001266561,0.001070144,0.0005969808,0.00373247,0.002243418,0.002814349,0.004733075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006175802,"about_ca_system_score_gemma":0.001066304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001224501,"about_ca_topic_score_gemma":0.002118488,"domain_scores_codex":[0.9986503,0.0003389669,0.00007130962,0.0006321243,0.0002254316,0.00008184557],"domain_scores_gemma":[0.9977884,0.001010757,0.0001095856,0.0005774284,0.000371549,0.0001422666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005749649,0.000347359,0.002842512,0.0003580333,0.00009295876,0.0002884735,0.0003554401,0.02098099,0.02913219,0.00449388,0.02180443,0.9187288],"study_design_scores_gemma":[0.0002145425,0.0004635953,0.002488919,0.00005238902,0.00008373625,0.0003398979,0.0002281525,0.910163,0.03079037,0.03900762,0.01609321,0.00007451777],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02972493,0.0006296009,0.9297764,0.0002648267,0.0004480009,0.0002699255,0.001454115,0.03297415,0.004458094],"genre_scores_gemma":[0.3882701,0.0005051158,0.5859992,0.0007792251,0.0003083559,0.000659968,0.007129834,0.001399227,0.01494893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008858125,"threshold_uncertainty_score":0.02963334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03530895307235937,"score_gpt":0.2970115076203186,"score_spread":0.2617025545479593,"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."}}