{"id":"W4396827151","doi":"10.1145/3613904.3641895","title":"The HaLLMark Effect: Supporting Provenance and Transparent Use of Large Language Models in Writing with Interactive Visualization","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Agency (philosophy); Computer science; Visualization; Control (management); Artificial intelligence; Sociology; Social science","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":[0.0004483012,0.00006711536,0.00008850169,0.00004418869,0.00003757466,0.0001652078,0.000117921,0.00001739293,8.687928e-7],"category_scores_gemma":[0.00002452615,0.00004035231,0.00001388167,0.0001589327,0.0000123762,0.000740845,0.00005477363,0.00007833587,2.174195e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001884063,"about_ca_system_score_gemma":0.00002252265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000105042,"about_ca_topic_score_gemma":0.0002135098,"domain_scores_codex":[0.9992626,0.00005912644,0.0001968409,0.000211616,0.0001205641,0.0001492799],"domain_scores_gemma":[0.9994519,0.0003232625,0.00004342421,0.0001420414,0.00002205428,0.00001725478],"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":[0.00006185822,0.00007679729,0.01038079,0.0006641747,0.00005240585,0.0001077256,0.05479563,0.02357467,0.003764421,0.6689376,0.00002028161,0.2375637],"study_design_scores_gemma":[0.000127502,0.00004326574,0.0003707026,0.000298919,0.000002740392,0.000005150094,0.0002766479,0.9954058,0.002985247,0.0004137105,0.00001640977,0.00005388842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3208462,0.0001811988,0.6784456,0.0001080626,0.00002735035,0.0001455831,7.944701e-7,0.0000412826,0.000203947],"genre_scores_gemma":[0.9941204,0.00001244046,0.005751974,0.00002913834,0.00000845436,0.00001579189,8.686902e-7,0.000005848932,0.00005506495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9718311,"threshold_uncertainty_score":0.164552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01848380606514614,"score_gpt":0.3086321793749555,"score_spread":0.2901483733098093,"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."}}