{"id":"W6922230263","doi":"10.1145/3708359.3712164","title":"Authoring LLM-Based Assistance for Real-World Contexts and Tasks","year":2025,"lang":"en","type":"article","venue":"","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Context (archaeology); Key (lock); Task (project management); Set (abstract data type); Process (computing)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000377484,0.00009393224,0.0001367088,0.00008604458,0.0001210904,0.0001713942,0.0003732827,0.00003612835,0.000009508083],"category_scores_gemma":[0.00006542672,0.00008449615,0.00004167296,0.0002429166,0.00004274593,0.000199708,0.00007522368,0.0000662665,0.000004213719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004300527,"about_ca_system_score_gemma":0.000077235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006862725,"about_ca_topic_score_gemma":0.0005447995,"domain_scores_codex":[0.9991677,0.00003827225,0.0001691566,0.000354003,0.00008065697,0.0001902502],"domain_scores_gemma":[0.9990504,0.0004084773,0.0000311495,0.0003856465,0.00007451996,0.00004979663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000684431,0.0001291561,0.006614796,0.0001540794,0.00002891348,0.000002293143,0.0002214646,0.00008434807,0.001594975,0.9231865,0.01803971,0.0498753],"study_design_scores_gemma":[0.003213542,0.0004698873,0.07341039,0.0004082813,0.00004135166,0.000001237087,0.00007185023,0.4812041,0.1510448,0.1066187,0.1826657,0.000850153],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007913336,0.00007071676,0.9717122,0.004561541,0.0002985222,0.0002522383,0.000002885856,0.000178271,0.01501032],"genre_scores_gemma":[0.908195,0.000002095959,0.07975093,0.001083787,0.00001366011,0.00004774211,6.404813e-7,0.000003600837,0.01090259],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9002816,"threshold_uncertainty_score":0.3445653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03098957098552297,"score_gpt":0.3156403876429901,"score_spread":0.2846508166574671,"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."}}