{"id":"W2769778028","doi":"10.5555/3107979.3107984","title":"A comparative study on content-based paper-to-paper recommendation approaches in scientific literature","year":2017,"lang":"en","type":"article","venue":"Communications and Networking Symposium","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"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); Representation (politics); Domain (mathematical analysis); Term (time); Embedding; Recommender system; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01002174,0.00126874,0.001510607,0.02602488,0.001190435,0.004328788,0.001803005,0.002162218,0.003737591],"category_scores_gemma":[0.04434249,0.0004475127,0.002306032,0.02272036,0.0007394165,0.005895363,0.00120541,0.0008965697,0.002670045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001698941,"about_ca_system_score_gemma":0.001952712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00593867,"about_ca_topic_score_gemma":0.007486577,"domain_scores_codex":[0.9860643,0.004449531,0.001320931,0.001361326,0.006302086,0.00050178],"domain_scores_gemma":[0.9544289,0.0281827,0.00218475,0.003854237,0.01030433,0.001045092],"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":[0.001007236,0.0007403871,0.02936801,0.003218633,0.001514693,0.0001356927,0.0009119333,0.005434959,0.006537749,0.005101184,0.007507993,0.9385217],"study_design_scores_gemma":[0.000765348,0.006784562,0.2840581,0.003160154,0.007023358,0.004444936,0.008108634,0.4260944,0.05061626,0.02663724,0.1811552,0.001151892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3750516,0.1387969,0.4055476,0.003581899,0.001466657,0.002460311,0.005170138,0.007542944,0.06038193],"genre_scores_gemma":[0.6037229,0.02493853,0.3519016,0.0005619627,0.0008962197,0.0006619215,0.006881854,0.0004503662,0.009984681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9956712,"threshold_uncertainty_score":0.05300069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2322246738040389,"score_gpt":0.3381059243104879,"score_spread":0.105881250506449,"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."}}