{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006435156,0.0001111051,0.0001432326,0.0002863666,0.0001458389,0.000258495,0.000258299,0.00007333851,0.00005486717],"category_scores_gemma":[0.00009865071,0.0001210483,0.00003162603,0.0007957083,0.00000943894,0.001983133,0.0001369383,0.0001547719,0.000008710706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008799208,"about_ca_system_score_gemma":0.00007574307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003058811,"about_ca_topic_score_gemma":0.0001448274,"domain_scores_codex":[0.9986049,0.00007700159,0.0004981488,0.0003548761,0.0002353653,0.0002296951],"domain_scores_gemma":[0.9993163,0.0001075309,0.00007579397,0.0003263271,0.0001397851,0.00003428412],"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":[0.000001048859,0.0001382238,0.00347887,0.000226196,0.00002580747,0.00001784268,0.03401622,0.2064536,0.2218359,0.5251913,0.0001063193,0.00850859],"study_design_scores_gemma":[0.0001988101,0.000004659838,0.00009068062,0.0001216389,0.000004772562,0.00000400827,0.0006728735,0.9913459,0.004873578,0.002536667,0.00001962233,0.0001268214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1259751,0.00009758497,0.872615,0.0002029771,0.0001009524,0.0001509941,0.000006908441,0.0002501959,0.0006002467],"genre_scores_gemma":[0.8708065,0.000004331804,0.1288954,0.00009439731,0.00008451311,0.000005435635,0.00004512682,0.00001708374,0.00004727171],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7848922,"threshold_uncertainty_score":0.4936205,"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."}}