{"id":"W4398946215","doi":"10.7910/dvn/wndofl","title":"Replication data for Identifying science in the news","year":2022,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"","keywords":"Replication (statistics); Computer science; Computational biology; Data science; Information retrieval; Biology; Virology","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01395421,0.001110575,0.001116641,0.005704674,0.002339139,0.00260245,0.003074249,0.00195335,0.0360999],"category_scores_gemma":[0.0837463,0.0006542859,0.00138333,0.009994095,0.001309415,0.001654576,0.003301407,0.002645905,0.03827941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002484174,"about_ca_system_score_gemma":0.004690381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01745218,"about_ca_topic_score_gemma":0.03112199,"domain_scores_codex":[0.9834707,0.005064312,0.00275835,0.002507361,0.005322971,0.0008761925],"domain_scores_gemma":[0.9322274,0.02192547,0.004732076,0.02068839,0.01873068,0.001696049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000508751,0.0003267675,0.008068633,0.001312286,0.00009027878,0.0001051204,0.0006467266,0.0006080538,0.0006697439,0.003135484,0.9687376,0.01579049],"study_design_scores_gemma":[0.0008159865,0.0001649746,0.02512158,0.0004896221,0.00008235923,0.0002087094,0.001082327,0.001171711,0.002091446,0.002419607,0.9662393,0.0001124995],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006319781,0.0001513351,0.001445698,0.0003963192,0.0002448569,0.001205338,0.9834568,0.0006712763,0.006108757],"genre_scores_gemma":[0.0068435,0.00006070378,0.004470712,0.0002200625,0.00005934714,0.005188751,0.9802699,0.000200675,0.002686299],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9973975,"threshold_uncertainty_score":0.1207662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08390283603802001,"score_gpt":0.369975438381868,"score_spread":0.286072602343848,"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."}}