{"id":"W2298270464","doi":"","title":"The distribution of references in scientific papers: An analysis of the IMRaD structure","year":2013,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Categorization; Section (typography); Matching (statistics); Information retrieval; Scientific literature; Data science; Artificial intelligence; Mathematics; Statistics","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":[0.004801967,0.0002637853,0.0005124956,0.0003523526,0.0004294736,0.0005839441,0.005627499,0.0002197993,0.00002397047],"category_scores_gemma":[0.001150378,0.0001763298,0.0003676682,0.00313826,0.0008123514,0.0003372021,0.002541539,0.0005548163,9.33994e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001389411,"about_ca_system_score_gemma":0.0002774541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001857492,"about_ca_topic_score_gemma":0.01487155,"domain_scores_codex":[0.9927773,0.004506357,0.0008315231,0.0008321222,0.000758216,0.0002944515],"domain_scores_gemma":[0.9900923,0.001028514,0.001293508,0.005173748,0.00233491,0.00007695448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007158602,0.0005245815,0.02456374,0.00009845216,0.0005436061,6.874826e-7,0.0109559,0.003375504,0.01493953,0.8202688,0.0001812149,0.1245408],"study_design_scores_gemma":[0.0002852539,0.000001435507,0.2394042,0.001175785,0.0005157575,0.000001678063,0.0004099461,0.457027,0.1926314,0.1043057,0.003534709,0.0007072257],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7566378,0.0007429802,0.2366447,0.003122994,0.0002067311,0.0005642716,0.0001557337,0.0001320938,0.001792692],"genre_scores_gemma":[0.9788451,0.0001768893,0.02006032,0.00001046184,0.000004226235,0.00003588454,0.0003152767,0.00001002794,0.0005418102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7159632,"threshold_uncertainty_score":0.9997525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01170373291071532,"score_gpt":0.2459700009509747,"score_spread":0.2342662680402593,"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."}}