{"id":"W2950034323","doi":"10.21307/connections-2017-002","title":"Are We in Agreement? Benchmarking and Reliability Issues between Social Network Analytic Programs","year":2018,"lang":"en","type":"article","venue":"Connections","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Dental and Craniofacial Research; National Institutes of Health","keywords":"Betweenness centrality; Benchmarking; CLARITY; Computer science; Reliability (semiconductor); Closeness; Variety (cybernetics); Social network analysis; Centrality; Measure (data warehouse); Data science; Network analysis; Social network (sociolinguistics); Key (lock); Data mining; Artificial intelligence; Computer security; World Wide Web; Statistics; Mathematics; Social media; Business; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000290066,0.0001204503,0.0002453099,0.00007203672,0.000382119,0.00006996639,0.00009338455,0.00003853994,0.0003063066],"category_scores_gemma":[0.000006542954,0.0001252092,0.00008381586,0.0005852895,0.000145038,0.00007838893,0.00009447813,0.0001437743,0.000007608459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003861808,"about_ca_system_score_gemma":0.00001228102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004746094,"about_ca_topic_score_gemma":0.0007729746,"domain_scores_codex":[0.9990374,0.00008514911,0.0002403055,0.0002893449,0.00008620116,0.0002615854],"domain_scores_gemma":[0.999477,0.00006712555,0.0001387327,0.0001918738,0.00007960013,0.00004567572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002295299,0.00004766146,0.9575395,0.000004248155,0.00005304298,2.339367e-7,0.0002073814,0.00002235428,0.000001657512,0.002668367,0.004066164,0.03538711],"study_design_scores_gemma":[0.0003004302,0.0001127537,0.811079,0.0001177242,0.0001851359,2.586625e-7,0.0007435192,0.004814947,0.00003419055,0.1080639,0.07418295,0.0003651979],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9805039,0.0001140917,0.01260928,0.001904686,0.0001113785,0.0003816937,0.000008843279,0.0001295916,0.004236504],"genre_scores_gemma":[0.9958279,0.000005001497,0.001100693,0.00001599771,0.002820925,0.00004707901,0.00002516245,0.000009012962,0.0001482004],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1464605,"threshold_uncertainty_score":0.5105883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03855043969690652,"score_gpt":0.3239763626548496,"score_spread":0.2854259229579431,"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."}}