{"id":"W1841948975","doi":"10.1186/s40493-015-0019-z","title":"Toward a testbed for evaluating computational trust models: experiments and analysis","year":2015,"lang":"en","type":"article","venue":"Journal of Trust Management","topic":"Access Control and Trust","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Testbed; Computer science; Flexibility (engineering); Promotion (chess); Compliance (psychology); Computer security; Distributed computing; Computer network; Psychology; Social psychology","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":[0.001833394,0.0000946446,0.0002714385,0.0002872274,0.0002058077,0.0001745076,0.000229354,0.00003589533,0.00003314119],"category_scores_gemma":[0.0001215401,0.00008099138,0.0001509405,0.0003349567,0.00006628726,0.0004564084,0.00006099474,0.00006290758,0.000001722972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001408629,"about_ca_system_score_gemma":0.00008921799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007457409,"about_ca_topic_score_gemma":0.00001274356,"domain_scores_codex":[0.9984102,0.000102018,0.0004042952,0.0001370266,0.0007574476,0.0001890433],"domain_scores_gemma":[0.9988788,0.00009126819,0.0003740404,0.00007011783,0.0003970452,0.0001886874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001660029,0.0008818507,0.03179809,0.0001445895,0.009675613,0.0001100493,0.05139845,0.4807215,0.00001006775,0.2315318,0.009872746,0.1821953],"study_design_scores_gemma":[0.008344356,0.0007093092,0.007939843,0.00005668794,0.00343077,0.000005948667,0.05031255,0.8042552,0.00000590803,0.1121476,0.01237819,0.0004136255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3677054,0.002583821,0.5588934,0.007582403,0.001034513,0.001557492,0.00002874639,0.00006438691,0.06054984],"genre_scores_gemma":[0.961781,0.00003291432,0.03734761,0.0001740992,0.0001691728,0.00001797903,0.000004012462,0.000006901419,0.000466329],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5940756,"threshold_uncertainty_score":0.3302733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.199831855969858,"score_gpt":0.4174499507830207,"score_spread":0.2176180948131627,"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."}}