{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.004298416,0.0002264589,0.0002704648,0.0005870133,0.0005163302,0.0006775508,0.02595288,0.00007152939,0.001963916],"category_scores_gemma":[0.001779284,0.0001916804,0.00006670383,0.001933184,0.0001747713,0.003200174,0.008608898,0.0004442435,0.0007245177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002155565,"about_ca_system_score_gemma":0.0003382927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004522489,"about_ca_topic_score_gemma":0.0004757919,"domain_scores_codex":[0.9961837,0.0001429321,0.0004515161,0.001895391,0.0009275354,0.0003989437],"domain_scores_gemma":[0.9780872,0.0002755917,0.0004183871,0.02108213,0.00008428886,0.0000524279],"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":[0.000002745758,0.0000433927,0.000001445892,0.00002331665,0.000005350289,0.00001203677,0.00003200035,0.00000700782,0.00003657896,0.0009285873,0.995281,0.003626524],"study_design_scores_gemma":[0.0001080392,0.00002088499,0.00001307756,0.00001659118,0.00003509616,0.00001303809,0.0000728691,0.002755625,0.00002551486,0.00121771,0.9955028,0.0002187689],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[7.636178e-7,0.00000198628,0.1914669,0.0000568077,0.0002279216,0.0006200071,0.8075169,0.00008265217,0.00002616012],"genre_scores_gemma":[0.000005433988,0.0001944733,0.04331483,0.0007953631,0.00007038143,0.0002998764,0.955283,0.00000929535,0.00002736569],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.148152,"threshold_uncertainty_score":0.9994093,"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."}}