{"id":"W3104938695","doi":"10.18653/v1/2020.sdp-1.19","title":"Cydex: Neural Search Infrastructure for the Scholarly Literature","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Open source; Search engine; Generality; Ranking (information retrieval); Digital library; Domain (mathematical analysis); World Wide Web; Software; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001296437,0.00007926512,0.00006806309,0.00001825579,0.0001450842,0.001145588,0.001163503,0.00005147594,0.00001627262],"category_scores_gemma":[0.00008012437,0.00004568261,0.00005401317,0.0002797208,0.00001290871,0.0009187495,0.0002851865,0.0003259655,0.000009490477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008475111,"about_ca_system_score_gemma":0.00003745282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003868636,"about_ca_topic_score_gemma":8.162818e-7,"domain_scores_codex":[0.9992177,0.00002645244,0.00009905276,0.000270468,0.0001959186,0.0001903365],"domain_scores_gemma":[0.9993254,0.00009810062,0.00001510562,0.0003658457,0.0001110289,0.0000845023],"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":[0.00002757182,0.00001186651,0.001662875,0.00008525037,0.00004543581,0.00001839898,0.01744457,0.02454215,0.003844113,0.5035123,0.02295945,0.425846],"study_design_scores_gemma":[0.0001607389,0.00003678705,0.0008553339,0.000003799885,0.000001842948,0.000006616196,0.00004713742,0.9811069,0.0003660301,0.002419272,0.01492443,0.00007112097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007579493,0.0003124843,0.941097,0.0500259,0.0002130305,0.0002090401,0.000002515646,0.000127937,0.0004326163],"genre_scores_gemma":[0.8656044,0.00000540719,0.1221722,0.01151384,0.0003890776,0.00001030141,0.00000137985,0.000006389903,0.0002969863],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9565647,"threshold_uncertainty_score":0.9998913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03427892096320958,"score_gpt":0.2669885034713679,"score_spread":0.2327095825081583,"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."}}