{"id":"W2575509578","doi":"","title":"Cultural micro-blog Contextualization 2016 Workshop Overview: data and pilot tasks","year":2016,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Contextualization; Clef; Computer science; Set (abstract data type); World Wide Web; Data science; Social media; Microblogging; Information retrieval; Engineering","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":[0.004401213,0.0003839789,0.0004612303,0.0002104304,0.0003854789,0.001327438,0.003816613,0.000210343,0.00009948818],"category_scores_gemma":[0.0007695471,0.0003222181,0.0001270486,0.0003776559,0.0002177361,0.0006797794,0.007586668,0.0003637806,0.00006262041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000693833,"about_ca_system_score_gemma":0.0001901687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002253951,"about_ca_topic_score_gemma":0.0002943659,"domain_scores_codex":[0.9940822,0.00300493,0.000656346,0.001409744,0.0004682618,0.0003785409],"domain_scores_gemma":[0.9922851,0.001102617,0.000716799,0.004340758,0.001359545,0.0001951698],"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":[0.0000362889,0.001231805,0.007764832,0.0004002211,0.0008407764,0.00001669374,0.01978367,0.00003112327,0.01376275,0.5136954,0.1111631,0.3312734],"study_design_scores_gemma":[0.005363319,0.000004483594,0.007852217,0.02001691,0.0005059545,0.00007000867,0.0009891664,0.4929328,0.04935073,0.03694763,0.3813601,0.004606712],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01137602,0.01420856,0.9401107,0.02110137,0.0005986228,0.0004574324,0.0001421868,0.0003169698,0.01168812],"genre_scores_gemma":[0.6983908,0.02373726,0.2390163,0.001087286,0.0002509674,0.0001017471,0.00471164,0.0001192305,0.03258475],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7010944,"threshold_uncertainty_score":0.999923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05803436753107027,"score_gpt":0.2942271212126183,"score_spread":0.236192753681548,"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."}}