{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001132693,0.0007271057,0.0007568965,0.003030297,0.000596457,0.003859319,0.002059374,0.001220103,0.005220497],"category_scores_gemma":[0.009970533,0.0003888236,0.001055418,0.002885008,0.0007163672,0.006118689,0.002782268,0.001707266,0.001329043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035901,"about_ca_system_score_gemma":0.001375085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01372367,"about_ca_topic_score_gemma":0.01972573,"domain_scores_codex":[0.9990529,0.0002023652,0.00008273107,0.0002920377,0.0002496259,0.0001202331],"domain_scores_gemma":[0.9968948,0.001342539,0.0001443791,0.0009165078,0.0005791897,0.0001224313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008572589,0.0004756703,0.01225088,0.0009153574,0.0002569705,0.000588902,0.002143796,0.07212029,0.01987022,0.1069928,0.02603531,0.7574926],"study_design_scores_gemma":[0.00003497929,0.00009168066,0.002661018,0.0002907353,0.0000983771,0.0002083132,0.001248414,0.7195969,0.01460984,0.2358643,0.02522689,0.00006858743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08004997,0.0006471831,0.8910353,0.0009142438,0.0002972982,0.0001973286,0.006167536,0.009822647,0.01086851],"genre_scores_gemma":[0.6600615,0.0006027388,0.3265091,0.0002360248,0.00007082343,0.0001606491,0.008527398,0.0005934273,0.003238398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01372367,"threshold_uncertainty_score":0.0272876,"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."}}