{"id":"W3021251585","doi":"10.1016/j.patter.2020.100016","title":"The End-to-End Provenance Project","year":2020,"lang":"en","type":"article","venue":"Patterns","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"FAS Center for Systems Biology, Harvard University; Harvard University; National Science Foundation","keywords":"Provenance; Computer science; Software; End-to-end principle; Value (mathematics); Data science; Artificial intelligence; Machine learning; Geology; Paleontology; Operating system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002171278,0.00008370261,0.0001032558,0.00005519816,0.0002716518,0.0008719069,0.001533449,0.00001223674,0.000198626],"category_scores_gemma":[0.002000069,0.00004553967,0.0000556358,0.0007297602,0.00004042052,0.0001088066,0.0007273582,0.00007928718,0.001853108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001221331,"about_ca_system_score_gemma":0.00003419949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007791269,"about_ca_topic_score_gemma":0.00007019217,"domain_scores_codex":[0.9976323,0.0001018827,0.0003110624,0.0006180421,0.001077965,0.0002587156],"domain_scores_gemma":[0.9983386,0.000524628,0.0000938066,0.0008651007,0.00007496866,0.0001028795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001338942,0.00001699794,0.01321801,0.000004218407,0.000007632289,0.00001034799,0.001832401,0.00007866227,0.0000836565,0.001109329,0.433999,0.5496264],"study_design_scores_gemma":[0.00008959309,0.00004754187,0.02016507,0.000008364918,0.000002884066,9.353426e-7,0.0008441123,0.00597685,0.0001961712,0.0006614125,0.9719146,0.000092437],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5343689,0.0001750452,0.2332089,0.1720262,0.006063398,0.002119494,0.0003773255,0.000426954,0.05123375],"genre_scores_gemma":[0.992738,0.000002795132,0.0003433651,0.002882494,0.0002011427,0.00001851372,0.000003669605,0.000005577858,0.003804412],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.549534,"threshold_uncertainty_score":0.9989241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.215457626748179,"score_gpt":0.4000039262666429,"score_spread":0.1845462995184639,"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."}}