{"id":"W4385571788","doi":"10.18653/v1/2023.acl-long.734","title":"The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing Research","year":2023,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Institute for Work & Health","funders":"LG Display; Deutscher Akademischer Austauschdienst; Niedersächsische Ministerium für Wissenschaft und Kultur","keywords":"Computer science; Georgia tech; Volume (thermodynamics); Library science; Physics","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":[0.01448146,0.0000404086,0.0000754873,0.0001733201,0.0006371603,0.0001300313,0.0006575252,0.00002375121,0.00001189337],"category_scores_gemma":[0.001769734,0.00001664763,0.00004000577,0.004902213,0.0002572013,0.00006728168,0.00009870761,0.0002819144,0.000005370265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002942467,"about_ca_system_score_gemma":0.0001528577,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.009717065,"about_ca_topic_score_gemma":0.07118982,"domain_scores_codex":[0.9972174,0.001525454,0.0001769782,0.0001211893,0.0006887881,0.0002701786],"domain_scores_gemma":[0.9953271,0.004377922,0.00004143883,0.0001292155,0.0001113279,0.00001301362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001330736,0.00003426295,0.01695987,0.00001142212,0.0000117616,0.00001099371,0.089217,0.0004971356,0.000621492,0.01375056,0.0006612174,0.878211],"study_design_scores_gemma":[0.0002534727,0.00002626475,0.2352505,0.0001135092,0.00001372498,0.000001084877,0.5338547,0.163111,0.0004474076,0.0561957,0.01054693,0.0001857151],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9399161,0.003880752,0.0004547092,0.0308756,0.0001035622,0.0004488288,6.304378e-7,0.00004179341,0.02427803],"genre_scores_gemma":[0.9969738,0.00008650937,0.0001237477,0.00002729788,0.00008507152,0.00001981986,6.813536e-7,0.000002256969,0.002680829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8780252,"threshold_uncertainty_score":0.9968773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1197683283919852,"score_gpt":0.4937736672440102,"score_spread":0.374005338852025,"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."}}