{"id":"W2585000520","doi":"10.1109/bigdata.2016.7840938","title":"Software engineering for big data projects: Domains, methodologies and gaps","year":2016,"lang":"en","type":"article","venue":"","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Big data; Computer science; Data science; Context (archaeology); Milestone; Scalability; Software; Software engineering; Database; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005221755,0.0001444936,0.0001546814,0.0001308643,0.0000834471,0.000189742,0.0004977618,0.0000593051,0.00005004082],"category_scores_gemma":[0.002851708,0.00008395476,0.00002015602,0.0001858036,0.00005020825,0.001510131,0.0007570102,0.00003424334,0.00003747129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006965654,"about_ca_system_score_gemma":0.0000119031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009419071,"about_ca_topic_score_gemma":0.00004649272,"domain_scores_codex":[0.9991023,0.000003538294,0.0001625277,0.0003858523,0.0000990597,0.0002467448],"domain_scores_gemma":[0.9989129,0.0003979852,0.00006681992,0.0005253335,0.00008940933,0.000007575652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009139189,0.00003557455,0.01455582,0.001167782,0.00006642774,0.000004779135,0.00001390501,0.000003592527,0.005913879,0.02883187,0.07475585,0.8745591],"study_design_scores_gemma":[0.000436125,0.000008874063,0.003773978,0.0001679585,0.00005678997,0.000004733433,0.0000883394,0.0006541371,0.001454077,0.003902317,0.9890711,0.0003816143],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01002891,0.0003732835,0.9855571,0.001521068,0.00110916,0.0003939804,0.00008392174,0.000436353,0.0004962267],"genre_scores_gemma":[0.3261631,0.001029701,0.6482588,0.004403401,0.01465544,0.0003159403,0.0008163572,0.0002110463,0.004146246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9143152,"threshold_uncertainty_score":0.3423576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3419614475189196,"score_gpt":0.3394599206551451,"score_spread":0.002501526863774528,"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."}}