{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01526828,0.001071529,0.0009453993,0.001197601,0.0009391199,0.001851921,0.003141511,0.002106603,0.001509172],"category_scores_gemma":[0.03918643,0.00059794,0.0006616029,0.001392578,0.001912327,0.003543015,0.00228958,0.002334795,0.0004012343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002308404,"about_ca_system_score_gemma":0.001571827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002784379,"about_ca_topic_score_gemma":0.00210368,"domain_scores_codex":[0.9855345,0.01031277,0.001070132,0.0009010283,0.001496456,0.0006851074],"domain_scores_gemma":[0.9594274,0.02452666,0.003074604,0.007934732,0.003312323,0.001724333],"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":[0.003137604,0.008953772,0.03449382,0.001560482,0.0005874816,0.000718341,0.001710576,0.779853,0.02685308,0.06369945,0.0106272,0.06780513],"study_design_scores_gemma":[0.0004740896,0.002227446,0.003399201,0.0001152133,0.0000819937,0.0001544265,0.0004690007,0.9611338,0.0138342,0.01411593,0.003926735,0.00006792689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6726576,0.0004274173,0.3139469,0.001253036,0.0002876059,0.002529068,0.001562177,0.002989593,0.0043466],"genre_scores_gemma":[0.8344482,0.0002290367,0.1616577,0.0001621487,0.00003021542,0.001612672,0.001118608,0.0001115814,0.0006298735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01526828,"threshold_uncertainty_score":0.08074737,"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."}}