{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007499956,0.0006464333,0.001071656,0.000529795,0.0004677972,0.001075566,0.003563668,0.0006085322,0.00001135563],"category_scores_gemma":[0.0004380914,0.0006103347,0.0004213921,0.0002998676,0.0002443942,0.0008119259,0.003648999,0.0007662654,0.000007537179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003919023,"about_ca_system_score_gemma":0.000365759,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04285603,"about_ca_topic_score_gemma":0.001370238,"domain_scores_codex":[0.9962448,0.0003442005,0.0009243867,0.001164732,0.0006081228,0.0007137572],"domain_scores_gemma":[0.9941236,0.00009452806,0.001943744,0.003004699,0.0005561836,0.0002772187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002667245,0.002966277,0.2085815,0.00162403,0.001985988,0.0005327979,0.009909277,0.1017305,0.5722548,0.02192876,0.02260952,0.05560986],"study_design_scores_gemma":[0.000854051,0.00007410231,0.006210186,0.001654332,0.0001718321,0.00006944151,0.000198146,0.9518953,0.03661017,0.0005354992,0.0008138555,0.0009130595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1183493,0.0017703,0.8776263,0.0004816728,0.0004509129,0.0006068853,0.0001793447,0.0004410001,0.00009427339],"genre_scores_gemma":[0.6956456,0.0002791201,0.3028955,0.000159535,0.00009299959,0.0000708734,0.0001765288,0.0000424437,0.0006373691],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8501649,"threshold_uncertainty_score":0.9999614,"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."}}