{"id":"W4247024223","doi":"10.22360/springsim.2017.cns.009","title":"A Comparative Study On Content-Based Papepr-To-Paper Recommendation Approaches in Scientific Literature","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; Set (abstract data type); tf–idf; Word embedding; Word (group theory); Domain (mathematical analysis); Representation (politics); Term (time); Recommender system; Embedding; Data mining; Artificial intelligence; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006916681,0.0001806452,0.0002810678,0.0003924106,0.0004561333,0.001562056,0.001319237,0.00004592517,0.00001730242],"category_scores_gemma":[0.00009276406,0.0001427311,0.00006004148,0.0005194877,0.00006841496,0.001317869,0.0002731422,0.0001927636,0.00005482207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008323067,"about_ca_system_score_gemma":0.0000316891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002858414,"about_ca_topic_score_gemma":0.0005585778,"domain_scores_codex":[0.9983279,0.0001450608,0.0002622541,0.000759902,0.0002713038,0.000233543],"domain_scores_gemma":[0.9980782,0.0000794091,0.0001646891,0.001467037,0.0001310739,0.00007962662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005453808,0.01846354,0.142528,0.00006581022,0.0003786379,0.0001750691,0.0797495,0.002368785,0.04784388,0.2364314,0.008714975,0.462735],"study_design_scores_gemma":[0.006566182,0.003078648,0.5757176,0.0005550924,0.00005346355,0.000004287626,0.007146216,0.2402861,0.1396832,0.01251521,0.01174796,0.002645993],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2766084,0.0000153923,0.7013018,0.006018193,0.0002480673,0.001690346,0.000004992656,0.0004109638,0.01370187],"genre_scores_gemma":[0.93173,2.303657e-7,0.06712158,0.000409011,0.00001341466,0.0001257953,0.00001106383,0.000005701785,0.0005831811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6551216,"threshold_uncertainty_score":0.9994744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2070829786174614,"score_gpt":0.3709459189431054,"score_spread":0.1638629403256439,"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."}}