{"id":"W3209525680","doi":"10.1016/j.knosys.2021.107623","title":"Enabling the interpretability of pretrained venue representations using semantic categories","year":2021,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China; Shandong University","keywords":"Interpretability; Computer science; Representation (politics); Semantics (computer science); Embedding; Feature (linguistics); Similarity (geometry); Focus (optics); Artificial intelligence; Popularity; Dimension (graph theory); Natural language processing; Information retrieval; Linguistics; Mathematics","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":[0.0007755624,0.0001244452,0.0002240461,0.00009051778,0.0001865761,0.0002940842,0.0007566141,0.00003706848,0.000007133797],"category_scores_gemma":[0.0002774867,0.00009538719,0.00009962704,0.0008518784,0.00009969458,0.0003597407,0.0002874111,0.0001052525,0.00001461858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005001363,"about_ca_system_score_gemma":0.0002418924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001306892,"about_ca_topic_score_gemma":0.00004615635,"domain_scores_codex":[0.998458,0.0003652538,0.0003835509,0.0003676261,0.0002208935,0.0002046713],"domain_scores_gemma":[0.9980112,0.0003200903,0.0001640275,0.001157232,0.0003048307,0.0000426265],"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":[0.0001231017,0.004434529,0.09232312,0.01648533,0.002124775,0.0005477489,0.09102058,0.07103949,0.1151496,0.4885389,0.01231647,0.1058963],"study_design_scores_gemma":[0.0003845288,0.0000284431,0.0009890473,0.0002881028,0.00005309962,0.00001064034,0.001170198,0.9803715,0.01182954,0.0006566782,0.004016459,0.0002017238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03651503,0.002544476,0.9555354,0.0002854446,0.002335011,0.0004103022,0.00002445184,0.0001092154,0.002240678],"genre_scores_gemma":[0.9975733,0.000003150757,0.001902564,0.00001572124,0.0001265538,0.00002425757,0.00001820832,0.000008905926,0.0003273338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9610583,"threshold_uncertainty_score":0.3889777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03900939636961332,"score_gpt":0.2960602136880118,"score_spread":0.2570508173183985,"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."}}