{"id":"W4382618980","doi":"10.48550/arxiv.2306.16177","title":"Defining data science: a new field of inquiry","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto","keywords":"Data science; Computer science; Field (mathematics); Ontology; e-Science; Paradigm shift; Scope (computer science); Philosophy of science; Cyberinfrastructure; Big data; Management science; Epistemology; Data mining; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09377711,0.001387788,0.003773146,0.01585678,0.01027708,0.04073884,0.006259148,0.009243444,0.003630002],"category_scores_gemma":[0.07950568,0.001280543,0.002484196,0.02215384,0.06807284,0.07794468,0.01966958,0.02750465,0.00154115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01279653,"about_ca_system_score_gemma":0.03270371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004492012,"about_ca_topic_score_gemma":0.002624788,"domain_scores_codex":[0.8947833,0.06805564,0.007307536,0.008406375,0.01960119,0.001846024],"domain_scores_gemma":[0.8011195,0.1551073,0.005777652,0.01674919,0.01699294,0.004253398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005761435,0.00001330816,0.0002216043,0.0002916408,0.00001152057,0.00003674802,0.002476615,0.0001444578,0.00007940918,0.9783206,0.004719632,0.01367877],"study_design_scores_gemma":[0.00001002405,0.00001564972,0.0001178556,0.001078427,0.00001074075,0.0001122116,0.003698388,0.000680814,0.0001098593,0.8159086,0.1782209,0.00003640008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004691134,0.08253309,0.5401369,0.2971675,0.008650661,0.0005427534,0.0006088883,0.0004860443,0.06518314],"genre_scores_gemma":[0.1880162,0.1072511,0.6070154,0.0635906,0.01884763,0.002243194,0.001312634,0.00072781,0.01099546],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09377711,"threshold_uncertainty_score":0.4959467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3856511589867645,"score_gpt":0.2898745267792724,"score_spread":0.09577663220749211,"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."}}