{"id":"W4306317066","doi":"10.1145/3511808.3557526","title":"OpeNTF: A Benchmark Library for Neural Team Formation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Computer architecture; Geology","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":[0.000535368,0.0001865453,0.0001654606,0.0004414583,0.0004519526,0.0006050112,0.003821208,0.00003570609,0.000121209],"category_scores_gemma":[0.0001057519,0.0001550742,0.0001440651,0.0004405468,0.00003311289,0.003663482,0.002657772,0.0001811426,0.00008278398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001886442,"about_ca_system_score_gemma":0.00003963923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003381329,"about_ca_topic_score_gemma":0.000001350835,"domain_scores_codex":[0.9982156,0.00001965325,0.0006341903,0.0002202091,0.0006818369,0.0002285113],"domain_scores_gemma":[0.998538,0.00005026626,0.0006192281,0.0003493006,0.000389965,0.00005327359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006540698,0.0001094334,0.000238043,0.0002061855,0.00005541944,3.782282e-8,0.005013467,0.0001877596,0.0001086992,0.8356634,0.146879,0.01147305],"study_design_scores_gemma":[0.001093906,0.0001427196,0.0004954783,0.0001773846,0.00001581797,0.00001547675,0.00269916,0.1039596,0.0007901762,0.0138221,0.8764552,0.000332949],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01862804,0.00003909175,0.02015283,0.01223125,0.004780015,0.002496118,0.0001265953,0.0003707664,0.9411753],"genre_scores_gemma":[0.9793246,0.00002090301,0.009065026,0.0006928039,0.0001082895,0.0009163351,0.0001470017,0.00001264652,0.009712404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9606966,"threshold_uncertainty_score":0.7100819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04937004160800148,"score_gpt":0.28399999509923,"score_spread":0.2346299534912285,"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."}}