{"id":"W2950942184","doi":"10.48550/arxiv.1604.02580","title":"On the Composition of Scientific Abstracts","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Université du Québec à Montréal","keywords":"Sentence; Relevance (law); Similarity (geometry); Computer science; Information retrieval; Composition (language); Phenomenon; Natural language processing; Content (measure theory); Linguistics; Artificial intelligence; Mathematics; Epistemology; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01437389,0.0007560015,0.001094175,0.01940788,0.003158647,0.006232289,0.001075343,0.001191981,0.004020267],"category_scores_gemma":[0.1560795,0.0006904306,0.0008759701,0.01769636,0.001913934,0.008166995,0.003338014,0.00122235,0.001955844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001702844,"about_ca_system_score_gemma":0.002691088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001279589,"about_ca_topic_score_gemma":0.001076019,"domain_scores_codex":[0.9707862,0.009240532,0.005657265,0.003465097,0.01030629,0.0005446044],"domain_scores_gemma":[0.8147185,0.09673125,0.03659606,0.009527781,0.03952252,0.002903767],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003178396,0.0003696333,0.1093879,0.008332234,0.0009146906,0.002975864,0.02711548,0.009743929,0.07495951,0.07560669,0.02652419,0.6608915],"study_design_scores_gemma":[0.0003318396,0.001440121,0.2863149,0.002228381,0.001631505,0.008074673,0.01827531,0.09159166,0.06326738,0.2650832,0.2611853,0.0005757669],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.655599,0.01423589,0.2637028,0.004197509,0.001777525,0.002066761,0.01286545,0.002929348,0.0426258],"genre_scores_gemma":[0.7340947,0.004228907,0.2336435,0.0005772433,0.001513847,0.001189406,0.01778681,0.0009557734,0.006009847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9856261,"threshold_uncertainty_score":0.07601732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06057520916101188,"score_gpt":0.2024935450848013,"score_spread":0.1419183359237894,"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."}}