{"id":"W2962737936","doi":"","title":"Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction.","year":2018,"lang":"en","type":"article","venue":"British Machine Vision Conference","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Semantics (computer science); Task (project management); Dual (grammatical number); Domain (mathematical analysis); Natural language processing; Artificial intelligence; Programming language; Mathematics; Engineering; Systems 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"],"consensus_categories":[],"category_scores_codex":[0.0007328165,0.0002242341,0.0002807424,0.0001354009,0.0006307718,0.0008953486,0.0006872542,0.00009817574,0.00003541635],"category_scores_gemma":[0.0002273626,0.0002651284,0.00006535131,0.0003844848,0.0002386035,0.002112224,0.0005759512,0.0001472358,0.00002551963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003597638,"about_ca_system_score_gemma":0.0001171527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005267178,"about_ca_topic_score_gemma":0.0009840835,"domain_scores_codex":[0.9976835,0.00009902456,0.000471487,0.0008293691,0.0003988518,0.000517829],"domain_scores_gemma":[0.9983237,0.0002130815,0.0001334499,0.0005858011,0.0005192193,0.0002247776],"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":[0.00005066002,0.0002824942,0.0003667298,0.0001036563,0.00003357183,0.00007883745,0.003542571,0.0004196739,0.005332791,0.7083652,0.005357641,0.2760662],"study_design_scores_gemma":[0.0003496148,0.0005601769,0.0006439978,0.0002138045,0.00001033082,0.000135356,0.0001756029,0.7535427,0.005114777,0.233337,0.005538087,0.0003785582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08917577,0.0002514588,0.9060926,0.00103954,0.0006866393,0.0004494704,0.00008695423,0.0003374172,0.001880138],"genre_scores_gemma":[0.9324213,0.0003996115,0.0664821,0.0002255707,0.000205781,0.00009966885,0.0000102141,0.0000220241,0.0001337793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8432455,"threshold_uncertainty_score":0.9999801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06426731988318665,"score_gpt":0.2848324016629119,"score_spread":0.2205650817797253,"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."}}