{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007992062,0.0001399717,0.0001944733,0.0001549411,0.001388225,0.001606648,0.001885331,0.00004974459,0.000001253746],"category_scores_gemma":[0.00001329402,0.0001292037,0.00002989042,0.0002477496,0.0001059337,0.0005452654,0.0007923882,0.000270044,0.000005378606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004624683,"about_ca_system_score_gemma":0.00003260344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003919898,"about_ca_topic_score_gemma":0.0003828561,"domain_scores_codex":[0.9986966,0.000271379,0.0002570391,0.0004443061,0.0001257625,0.000204884],"domain_scores_gemma":[0.9964749,0.0001836854,0.0001461082,0.003050253,0.00007387963,0.00007115271],"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":[0.0001838435,0.005804882,0.1367995,0.00007547339,0.000191568,0.00001551073,0.1427682,0.005393358,0.009880058,0.1118501,0.001096032,0.5859415],"study_design_scores_gemma":[0.001848842,0.0003929825,0.04595509,0.0006714468,0.00002023601,0.000003655173,0.001562106,0.9119446,0.0001549769,0.0009157535,0.03594282,0.0005875347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6611838,0.003460915,0.1746254,0.1237207,0.003225594,0.004966377,0.00001877344,0.0004395906,0.02835887],"genre_scores_gemma":[0.9845726,0.00003840729,0.01470965,0.0003888039,0.00005085256,0.0001262362,0.00001870482,0.00000669622,0.00008803918],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9065512,"threshold_uncertainty_score":0.9999118,"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."}}