{"id":"W4403434583","doi":"10.1609/hcomp.v12i1.31597","title":"Disclosures & Disclaimers: Investigating the Impact of Transparency Disclosures and Reliability Disclaimers on Learner-LLM Interactions","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Transparency (behavior); Reliability (semiconductor); Psychology; Political science; Law; Physics; Thermodynamics","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":[0.0004167688,0.0002416331,0.0002476141,0.0001778842,0.0005006985,0.0006816977,0.0003167342,0.00004870429,0.00006683773],"category_scores_gemma":[0.0001955946,0.0001331291,0.000127979,0.0004354201,0.000526506,0.0008675594,0.0001620606,0.0003392922,0.000004976442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002383192,"about_ca_system_score_gemma":0.00002640832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006788652,"about_ca_topic_score_gemma":0.00004852875,"domain_scores_codex":[0.9986944,0.00001373273,0.0004284563,0.0003824699,0.0002911289,0.0001898536],"domain_scores_gemma":[0.9991465,0.000149376,0.000328445,0.0001389438,0.0002143359,0.00002243706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0003511872,0.0008074711,0.3717671,0.005845317,0.0005026588,0.000001193577,0.01787477,0.01289662,0.07571097,0.4376457,0.007586901,0.06901009],"study_design_scores_gemma":[0.0008350008,0.0003457498,0.6827123,0.009096797,0.0005715297,0.0000167487,0.007682757,0.1467169,0.003786623,0.1456315,0.001382342,0.00122172],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915977,0.00007680026,0.000378124,0.002441439,0.0001368658,0.0002644578,0.0000121042,0.00005971202,0.005032855],"genre_scores_gemma":[0.9995122,0.0000187415,0.00005763273,0.00007131219,0.0001471768,0.00001237865,0.00001203472,0.00002002768,0.000148497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3109452,"threshold_uncertainty_score":0.6573627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1156158976501775,"score_gpt":0.3606875602226767,"score_spread":0.2450716625724992,"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."}}