{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01608528,0.0002840183,0.0007851697,0.001628929,0.0006884413,0.01147457,0.001967696,0.000131379,0.0003077978],"category_scores_gemma":[0.002518621,0.0002069799,0.0004137853,0.002699703,0.0001527151,0.0002303889,0.006750832,0.0001718082,0.00004853388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005661588,"about_ca_system_score_gemma":0.0001133043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001403864,"about_ca_topic_score_gemma":0.0007416213,"domain_scores_codex":[0.9934174,0.000276319,0.001175656,0.003192296,0.00157316,0.0003651707],"domain_scores_gemma":[0.9925776,0.001437202,0.0004975537,0.004536171,0.0007571781,0.0001943142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001570564,0.00009887329,0.002111656,0.0002424145,0.0008156481,0.0000139858,0.0003877878,0.003286048,0.00001222736,0.001270898,0.9018666,0.08987814],"study_design_scores_gemma":[0.0003313811,0.00001210667,0.001740283,0.0001098006,0.001204756,0.000005321632,0.007159908,0.6707815,0.00007312416,0.001861729,0.3161732,0.0005469605],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02329269,0.0006949605,0.9542745,0.001740617,0.01045728,0.0008603247,0.006071643,0.0002060096,0.002401947],"genre_scores_gemma":[0.8735537,0.000013816,0.0874472,0.0002675455,0.0003019829,0.0001234224,0.02052796,0.00002703392,0.01773733],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8668273,"threshold_uncertainty_score":0.9895516,"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."}}