{"id":"W2460159515","doi":"10.18653/v1/s16-1003","title":"SemEval-2016 Task 6: Detecting Stance in Tweets","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":857,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"SemEval; Task (project management); Computer science; Natural language processing; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003699617,0.00007834782,0.0001106377,0.0001283832,0.00004540855,0.00006506702,0.000403624,0.00002576483,0.0001238103],"category_scores_gemma":[0.00004045967,0.00004730146,0.00004710314,0.0003502005,0.00001245979,0.0004297966,0.0001362481,0.00003529158,0.000205948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003641033,"about_ca_system_score_gemma":0.00002409626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002291628,"about_ca_topic_score_gemma":0.00005568174,"domain_scores_codex":[0.9990342,0.00003925939,0.0002056247,0.0002998902,0.0001875843,0.0002334254],"domain_scores_gemma":[0.9994204,0.0001214907,0.00006117494,0.0003208725,0.00002973826,0.00004631057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007035986,0.00006595251,0.08867098,0.000007829321,0.00003934295,0.00002447579,0.0008167911,0.00003382214,0.08333106,0.02348607,0.003017822,0.8004988],"study_design_scores_gemma":[0.00939859,0.0004801591,0.1808835,0.001718077,0.00003879492,0.00003213262,0.0009049199,0.2060167,0.4768183,0.02786214,0.0923304,0.00351627],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1830171,0.0001441843,0.8052099,0.00155269,0.0002863835,0.00005990474,3.288026e-7,0.0001266026,0.009602903],"genre_scores_gemma":[0.9835967,0.00002193925,0.01303156,0.0001722025,0.00004679455,0.000003455794,1.111627e-7,0.000004094054,0.003123122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8005796,"threshold_uncertainty_score":0.2647114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01537311927603455,"score_gpt":0.2510792161289844,"score_spread":0.2357060968529498,"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."}}