{"id":"W3195768561","doi":"10.1109/works54523.2021.00006","title":"A Recommender System for Scientific Datasets and Analysis Pipelines","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Pipeline transport; Pipeline (software); Data science; Recommender system; Domain (mathematical analysis); Information retrieval; Data mining; World Wide Web; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008366757,0.001300235,0.001444592,0.005659774,0.001764872,0.002414469,0.002677317,0.002492731,0.003324093],"category_scores_gemma":[0.02696186,0.0009577086,0.001722169,0.003743268,0.0003326886,0.004038772,0.001767599,0.002281978,0.002881373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001571837,"about_ca_system_score_gemma":0.003236211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04476544,"about_ca_topic_score_gemma":0.0882559,"domain_scores_codex":[0.9956808,0.0009553763,0.0005670926,0.001353279,0.001219825,0.0002236094],"domain_scores_gemma":[0.9796488,0.007598828,0.00106062,0.004965353,0.005692405,0.001034016],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001655449,0.001112065,0.05176539,0.001319635,0.0009637654,0.0008019793,0.001383678,0.02667787,0.02390418,0.008156539,0.1434331,0.7388263],"study_design_scores_gemma":[0.0003222477,0.0005004295,0.02140421,0.0003264778,0.0006527872,0.0009081719,0.0004620959,0.8290308,0.01706869,0.01168591,0.1173005,0.0003376526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08925162,0.002634345,0.7876813,0.003823685,0.0007419794,0.002088587,0.0151075,0.09179179,0.006879132],"genre_scores_gemma":[0.1776157,0.0008355094,0.7893509,0.0008147379,0.0001904464,0.0005505487,0.02275782,0.000925579,0.006958825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9916332,"threshold_uncertainty_score":0.08900976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2596876413258093,"score_gpt":0.4281492367904258,"score_spread":0.1684615954646165,"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."}}