{"id":"W4396832282","doi":"10.1145/3613904.3641899","title":"ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Workflow; Workload; Computer science; Task (project management); Writing process; Process (computing); Variation (astronomy); Human–computer interaction; Perception; Natural language processing; Programming language; Psychology; Database; Engineering; Mathematics education","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":[0.00239239,0.00144447,0.0006383772,0.0008061655,0.0004178836,0.002104331,0.002187088,0.001386501,0.02308917],"category_scores_gemma":[0.01336537,0.0006687858,0.001183456,0.0003842794,0.0004272107,0.003412281,0.003675164,0.001128516,0.007363417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003273545,"about_ca_system_score_gemma":0.0005257444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007909792,"about_ca_topic_score_gemma":0.002174157,"domain_scores_codex":[0.9989588,0.0003870363,0.00007814773,0.0002841614,0.0002380869,0.00005379878],"domain_scores_gemma":[0.9928719,0.004838211,0.0002486789,0.001259491,0.0004645433,0.0003171308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002267739,0.0009962952,0.005091855,0.001992889,0.0001539559,0.0007723349,0.008296999,0.005207684,0.07050432,0.008031059,0.1066453,0.7900396],"study_design_scores_gemma":[0.001696964,0.003735563,0.02020792,0.0009151534,0.0002677752,0.003264568,0.003618032,0.3419107,0.08519728,0.03429317,0.5040533,0.0008396457],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06881651,0.0005805746,0.7678558,0.0005996776,0.0002514738,0.0007715004,0.003532707,0.1452271,0.0123646],"genre_scores_gemma":[0.2204999,0.0004053763,0.7413788,0.0006590033,0.00009160377,0.001506137,0.005515189,0.008208209,0.02173569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02308917,"threshold_uncertainty_score":0.07724094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06407113873354855,"score_gpt":0.3229418175725084,"score_spread":0.2588706788389599,"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."}}