{"id":"W3215306199","doi":"10.1145/3516431.3516435","title":"Federated Data Science to Break Down Silos [Vision]","year":2022,"lang":"en","type":"preprint","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Data sharing; Focus (optics); Data science; Open science; Pipeline transport; Open data; Open research; World Wide Web; Engineering","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":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.02594532,0.0005006154,0.0007438546,0.001857299,0.001931737,0.006915872,0.0346861,0.0001390642,0.005331205],"category_scores_gemma":[0.03437344,0.0003907762,0.0001684367,0.005438578,0.0004277114,0.001041186,0.1551409,0.0009744046,0.002311948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003025311,"about_ca_system_score_gemma":0.001100488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001313639,"about_ca_topic_score_gemma":0.0003317166,"domain_scores_codex":[0.9842762,0.0004731122,0.001532473,0.00633881,0.006432884,0.0009465056],"domain_scores_gemma":[0.9753107,0.002223134,0.0007573827,0.02027526,0.0008224873,0.0006109813],"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":[0.00003385919,0.0001076085,0.0006172686,0.000009291763,0.00001940784,0.00003955357,0.0001754232,0.001390997,0.0001109217,0.0001061839,0.545927,0.4514625],"study_design_scores_gemma":[0.000284803,0.0001666652,0.006413073,0.00009713379,0.00004013941,0.00001290194,0.0008439026,0.07537628,0.00007649985,0.02015814,0.8956181,0.0009123157],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6418005,0.0004768292,0.09282695,0.04429793,0.09837902,0.006042994,0.006179287,0.00172741,0.1082692],"genre_scores_gemma":[0.908389,0.00003937869,0.05121928,0.00289318,0.0009529786,0.0001433991,0.001649431,0.0000878006,0.03462555],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4505502,"threshold_uncertainty_score":0.9998544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2879919536735037,"score_gpt":0.4653046036934881,"score_spread":0.1773126500199845,"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."}}