{"id":"W2753568608","doi":"","title":"Microblog contextualization using continuous space vectors: Multi-sentence compression of cultural documents","year":2017,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Contextualization; Microblogging; Computer science; Social media; Sentence; Space (punctuation); Compression (physics); Natural language processing; Information retrieval; Artificial intelligence; World Wide Web; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004322988,0.0008239528,0.0007351993,0.003010884,0.0004810994,0.0008499225,0.0004050964,0.0005703119,0.002981746],"category_scores_gemma":[0.001998694,0.000165553,0.0004701248,0.002957045,0.0002507465,0.000911954,0.0007210497,0.0006482641,0.001843814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003791555,"about_ca_system_score_gemma":0.000791099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00613895,"about_ca_topic_score_gemma":0.01054562,"domain_scores_codex":[0.9995818,0.00008630798,0.0000416311,0.00008819493,0.0001292591,0.00007292347],"domain_scores_gemma":[0.9989927,0.0003845563,0.0000771782,0.0001214078,0.000358341,0.00006578964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001659493,0.0003408949,0.003702679,0.0004965179,0.00009472569,0.0005408612,0.0003541222,0.01151814,0.08677424,0.001855621,0.02079305,0.8718697],"study_design_scores_gemma":[0.0001310512,0.0008704542,0.03214853,0.0001463028,0.0003156846,0.0009797324,0.001531094,0.8158293,0.1075932,0.00571768,0.03464141,0.00009550497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.581902,0.01090518,0.3734645,0.002061622,0.001884338,0.0004212,0.01336267,0.007216007,0.008782453],"genre_scores_gemma":[0.8047726,0.003026457,0.1672953,0.0002549544,0.001133771,0.0002652096,0.01459254,0.0004951025,0.00816415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00613895,"threshold_uncertainty_score":0.01220644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03079778230909317,"score_gpt":0.294759967713554,"score_spread":0.2639621854044608,"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."}}