{"id":"W2081892160","doi":"10.3166/isi.19.3.93-105","title":"Big data analytics – Retour vers le futur 3. De statisticien à data scientist","year":2014,"lang":"fr","type":"preprint","venue":"Ingénierie des systèmes d information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Statistician; Big data; Data science; Completeness (order theory); Variety (cybernetics); Computer science; Analytics; Data analysis; Order (exchange); Volume (thermodynamics); Data mining; Statistics; Mathematics; Business; Artificial intelligence; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004196449,0.0005257064,0.0005757914,0.0004068351,0.001216032,0.004734659,0.01096541,0.0003577147,0.00002346825],"category_scores_gemma":[0.001671357,0.0005901031,0.00007110018,0.001197139,0.0007722378,0.008931948,0.01200889,0.0006632191,0.0005718798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006114669,"about_ca_system_score_gemma":0.002777698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004605596,"about_ca_topic_score_gemma":0.0003047326,"domain_scores_codex":[0.9952934,0.0002317509,0.001500664,0.001168962,0.0008935589,0.0009116407],"domain_scores_gemma":[0.9888045,0.0002790668,0.001392205,0.008448685,0.0006914733,0.000384131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008663092,0.00009034824,0.0002064608,0.000827582,0.0001366449,0.000008278823,0.003993233,0.004682585,0.0000141285,0.1001055,0.1018037,0.7881229],"study_design_scores_gemma":[0.0002508763,0.00003297056,0.002315436,0.0003652539,0.00009015068,0.00006980366,0.0005132759,0.6822588,0.00001956475,0.003735068,0.3098944,0.0004544594],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001116682,0.0001930625,0.9730617,0.001167226,0.003501212,0.0005349375,0.01393939,0.0002314283,0.006254312],"genre_scores_gemma":[0.1709538,0.000411668,0.7559556,0.0007186788,0.001536829,0.00008622689,0.06907818,0.00005652467,0.001202419],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7876684,"threshold_uncertainty_score":0.999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09202070383690884,"score_gpt":0.2954372656307753,"score_spread":0.2034165617938664,"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."}}