{"id":"W2398419065","doi":"","title":"Characterizing In-text Citations using N-gram Distributions","year":2015,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Citation; Rhetorical question; Computer science; Information retrieval; Metadata; Natural language processing; Linguistics; Citation analysis; Artificial intelligence; World Wide Web; Philosophy","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004726644,0.0003130216,0.0003692951,0.0003444506,0.0003158452,0.0008224046,0.00228407,0.0002728104,0.00002074926],"category_scores_gemma":[0.00141244,0.0003711128,0.0001564246,0.0007204776,0.0001178336,0.0004452325,0.002780215,0.0007961494,0.00003286023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004046301,"about_ca_system_score_gemma":0.0007244674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001164558,"about_ca_topic_score_gemma":0.0007526927,"domain_scores_codex":[0.9946468,0.002832083,0.0006699323,0.0009381478,0.0004549455,0.0004581215],"domain_scores_gemma":[0.9940532,0.000645075,0.000468521,0.002732231,0.001875928,0.0002250555],"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":[0.000005028061,0.0009806729,0.004482788,0.0002225327,0.00008894948,0.00002993382,0.03365693,0.004020705,0.006630518,0.8698627,0.0003846396,0.07963464],"study_design_scores_gemma":[0.0004638779,2.437137e-7,0.003506226,0.001804844,0.00002539499,0.00002055457,0.000132806,0.9501132,0.004847768,0.03412321,0.004290567,0.0006712518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1228973,0.0003552698,0.8599452,0.00777629,0.0004220597,0.0003484345,0.00005381716,0.0002785538,0.007923144],"genre_scores_gemma":[0.7328955,0.00006897801,0.266024,0.00007026053,0.00002902451,0.0000532843,0.0002681525,0.00002426256,0.0005665505],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9460925,"threshold_uncertainty_score":0.9998741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04274793880720133,"score_gpt":0.2711949104622968,"score_spread":0.2284469716550955,"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."}}