{"id":"W4372279189","doi":"10.48550/arxiv.2305.02797","title":"The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing Research","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Institute for Work & Health","funders":"Deutscher Akademischer Austauschdienst; Niedersächsische Ministerium für Wissenschaft und Kultur","keywords":"Transparency (behavior); Artificial intelligence; Internship; Metadata; Computer science; Field (mathematics); Natural language processing; Corpus linguistics; Data science; Political science; World Wide Web","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.004653864,0.0001698558,0.000192668,0.0005948782,0.0004655284,0.0003600398,0.006186899,0.0001272811,0.000001159351],"category_scores_gemma":[0.0007522934,0.0001043999,0.00007951249,0.007093893,0.0003331008,0.0002572975,0.003387396,0.001949933,0.00001281902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001776412,"about_ca_system_score_gemma":0.0004227676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001871589,"about_ca_topic_score_gemma":0.003980149,"domain_scores_codex":[0.9974254,0.0007948213,0.0003065282,0.0006611279,0.0003290915,0.0004829782],"domain_scores_gemma":[0.9958715,0.001935805,0.0002276154,0.001610345,0.0003294285,0.00002527941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001787764,0.0006855248,0.1894273,0.0007448464,0.0002635462,0.002659629,0.1033426,0.2991677,0.001032114,0.2474663,0.002742531,0.1522891],"study_design_scores_gemma":[0.000467101,0.00004632164,0.0578898,0.0008721388,0.00002196497,0.000009028599,0.01712841,0.8737898,0.0002919049,0.0483906,0.0006039763,0.0004889346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9149792,0.001074164,0.07649267,0.004397486,0.0004626507,0.001360655,0.000007407468,0.0001719894,0.001053806],"genre_scores_gemma":[0.9986502,0.00007931692,0.0002381164,0.00002693372,0.00004572597,0.000007458803,0.000002741075,0.00001227264,0.0009372607],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5746222,"threshold_uncertainty_score":0.9991901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1539755596109414,"score_gpt":0.2841513684074624,"score_spread":0.130175808796521,"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."}}