{"id":"W4402422143","doi":"10.1515/lingvan-2023-0102","title":"Bibliographic bias and information-density sampling","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Marcus och Amalia Wallenbergs minnesfond","keywords":"Sampling bias; Sampling (signal processing); Statistics; Information retrieval; Computer science; Geography; Mathematics; Sample size determination; Telecommunications","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":[0.0002958767,0.0001277588,0.0001418073,0.001683202,0.0001068023,0.0006350323,0.0003219405,0.00006018353,0.000003844234],"category_scores_gemma":[0.001131674,0.0001201307,0.00007298486,0.002736359,0.00004987914,0.0004701679,0.0002339889,0.0001789488,0.00004269451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001679643,"about_ca_system_score_gemma":0.00003301121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003091949,"about_ca_topic_score_gemma":0.000008130378,"domain_scores_codex":[0.9990843,0.00001887395,0.0002474861,0.0002350824,0.0002240596,0.0001902181],"domain_scores_gemma":[0.9989987,0.0002275576,0.00005338088,0.0003934102,0.0002487478,0.00007820459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001415808,0.000009976211,0.002087915,0.00008953161,0.00004973013,0.00003598423,0.0006902107,0.00004904174,0.00007479623,0.9393233,0.001636933,0.05595113],"study_design_scores_gemma":[0.0001211368,0.00007187185,0.003570243,0.0001780864,0.00007043198,0.00003193379,0.0000445423,0.09879767,0.001559801,0.2851722,0.6098071,0.0005749663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003108893,0.0007748639,0.9896422,0.0001230073,0.0006127658,0.000077845,0.000004662995,0.001117081,0.004538704],"genre_scores_gemma":[0.7037522,0.0003451489,0.2953639,0.0002694214,0.0002193179,0.000004930253,0.000006486187,0.00000769359,0.00003093257],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7006433,"threshold_uncertainty_score":0.6123632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02514485621604285,"score_gpt":0.2974952076023429,"score_spread":0.2723503513863001,"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."}}