{"id":"W7132968469","doi":"","title":"Meaningful Datatypes: Ontologically-Sound Dependent Type Systems for Data Science","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Soundness; Ontology; Data type; Type (biology); Status quo; Data modeling","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"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":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.03827814,0.0007639167,0.001123297,0.001330663,0.004259789,0.007112141,0.02297103,0.0002277366,0.003753681],"category_scores_gemma":[0.02513738,0.000657982,0.0001691047,0.005271871,0.0006882907,0.001834617,0.009314302,0.0007122421,0.0009695479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005170167,"about_ca_system_score_gemma":0.002142013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001982327,"about_ca_topic_score_gemma":0.0008000347,"domain_scores_codex":[0.9815331,0.000542147,0.001935135,0.006729604,0.007736623,0.001523374],"domain_scores_gemma":[0.9804731,0.003335809,0.001938817,0.01179888,0.001911574,0.000541836],"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":[0.003049559,0.002051372,0.00128648,0.001339538,0.0007679819,0.0002754504,0.04065761,0.02501421,0.001332465,0.07443616,0.6949995,0.1547897],"study_design_scores_gemma":[0.0006814162,0.0005210879,0.0004647011,0.0001593237,0.0003141196,0.0000273944,0.1175732,0.2507817,0.00002905962,0.001204941,0.6271808,0.001062257],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2158018,0.03131528,0.2991788,0.001973288,0.2834314,0.01771631,0.00735604,0.001163346,0.1420636],"genre_scores_gemma":[0.6996488,0.0008709524,0.009903986,0.0003308744,0.000946632,0.0002660594,0.02460668,0.0001515416,0.2632745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.483847,"threshold_uncertainty_score":0.9998083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3664178335006312,"score_gpt":0.5186089205593112,"score_spread":0.15219108705868,"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."}}