{"id":"W2885369894","doi":"10.1093/reseval/rvy023","title":"Formative, embedded evaluation to strengthen interdisciplinary team science: Results of a 4-year, mixed methods, multi-country case study","year":2018,"lang":"en","type":"article","venue":"Research Evaluation","topic":"Interdisciplinary Research and Collaboration","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; University of Waterloo; Public Safety Canada; University of Ottawa","funders":"Seventh Framework Programme; Terveyden ja hyvinvoinnin laitos; Universiteit van Tilburg; Syddansk Universitet; European Commission; University of Ottawa","keywords":"Formative assessment; Stakeholder; Participatory evaluation; Citizen journalism; Psychology; Social network analysis; Participatory action research; Variance (accounting); Knowledge management; Medical education; Public relations; Sociology; Political science; Business; Computer science; Medicine; Pedagogy","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2840274,0.0002613615,0.0004551141,0.003789663,0.002259111,0.0008765997,0.00176917,0.0001286353,0.0005997751],"category_scores_gemma":[0.06964085,0.0001984339,0.00009911411,0.01324036,0.001185633,0.002649055,0.00302773,0.0005211508,0.0005851856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001193136,"about_ca_system_score_gemma":0.003789956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001800189,"about_ca_topic_score_gemma":0.004221179,"domain_scores_codex":[0.9597002,0.01480408,0.002005798,0.001547576,0.02073277,0.001209607],"domain_scores_gemma":[0.9541558,0.003242017,0.0005058377,0.001937875,0.03965718,0.0005013138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004567016,0.002512304,0.0007161793,0.00002301529,0.00009964693,0.00004317547,0.2058661,0.001576541,0.02682864,0.0003080481,0.02829263,0.7291667],"study_design_scores_gemma":[0.003930029,0.005686111,0.009095051,0.00006213714,0.00003834461,0.00004452292,0.3845305,0.5820596,0.009195108,0.004967999,0.000172676,0.0002178949],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9771904,0.00003800053,0.005316993,0.0006931035,0.0006854192,0.006006108,0.00009319222,0.00003416909,0.009942666],"genre_scores_gemma":[0.9873487,0.000001132376,0.01099369,0.00001039109,0.000288663,0.000700571,0.0000366417,0.0000215547,0.0005986591],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7289488,"threshold_uncertainty_score":0.9990398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4498606977137448,"score_gpt":0.6562607191916434,"score_spread":0.2064000214778986,"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."}}