{"id":"W2555901596","doi":"","title":"Position Paper) Motivating the Need for Evaluation Criteria for Captchas","year":2012,"lang":"en","type":"article","venue":"","topic":"User Authentication and Security Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"CAPTCHA; Heuristics; Usability; Computer science; Set (abstract data type); Mantra; Human–computer interaction; Scheme (mathematics); Position paper; Heuristic evaluation; Artificial intelligence; World Wide Web; Programming language; Mathematics","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":[0.001510895,0.00006062267,0.00006252042,0.00002912269,0.0002120816,0.0001502398,0.0002519651,0.00003030913,0.00002880751],"category_scores_gemma":[0.0001400662,0.00004095383,0.00005232184,0.00009210138,0.000008983353,0.0005980064,0.00002968783,0.00002155926,0.00001293354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003060174,"about_ca_system_score_gemma":0.00002137231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001653325,"about_ca_topic_score_gemma":0.000004977656,"domain_scores_codex":[0.9992716,0.00008118886,0.0001689164,0.0001225125,0.0001757653,0.0001800222],"domain_scores_gemma":[0.9992126,0.0002105116,0.00006507253,0.000259023,0.000212738,0.00004004195],"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":[0.00001737197,0.0001884691,0.0005397675,0.00009153557,0.00004697081,2.128087e-8,0.140259,0.000007196029,0.03335736,0.7763461,0.01470643,0.03443976],"study_design_scores_gemma":[0.0006224539,0.00004274323,0.002516702,0.00001053051,0.00001774618,0.000003553061,0.0006292985,0.9730717,0.003154493,0.01229956,0.007525881,0.0001053294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03580063,0.00006341796,0.9525143,0.00878573,0.0007134374,0.001340434,0.000003442002,0.00008326283,0.0006953348],"genre_scores_gemma":[0.9885208,3.090013e-7,0.009443229,0.001196667,0.0002278701,0.0003789624,0.00001633516,0.000005240174,0.000210599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9730645,"threshold_uncertainty_score":0.1670049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06844448078194897,"score_gpt":0.3429094127338386,"score_spread":0.2744649319518896,"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."}}