{"id":"W2343814825","doi":"10.1109/tla.2016.7459622","title":"Automatic algorithm to classify and locate research papers using natural language","year":2016,"lang":"en","type":"article","venue":"IEEE Latin America Transactions","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Data mining; Upload; Natural language; Set (abstract data type); Statistical classification; Artificial intelligence; Knowledge base; Algorithm; Information retrieval; Machine learning; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.000187359,0.0001200965,0.0001393959,0.0001809405,0.0003844265,0.0001368343,0.0004112014,0.00003804224,0.00006114543],"category_scores_gemma":[0.00001807892,0.00008951429,0.00003780421,0.0009150831,0.0001718227,0.0003236048,0.00002793916,0.00018699,0.00008860177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006948379,"about_ca_system_score_gemma":0.00006592857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002459937,"about_ca_topic_score_gemma":0.00001842305,"domain_scores_codex":[0.9986737,0.00008077596,0.0001837719,0.0004133868,0.0002858722,0.0003625016],"domain_scores_gemma":[0.9989324,0.0002863435,0.00003903354,0.0004945953,0.00006912697,0.0001785328],"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":[5.696227e-7,0.00002531301,0.000003554504,0.000003144351,0.00001186751,0.000003356308,0.0007660853,0.00002347156,0.02247698,0.0000519301,0.0001595929,0.9764741],"study_design_scores_gemma":[0.0003783694,0.0001146311,0.001808847,0.0001128993,0.00001924956,0.00004904782,0.0005554651,0.9799407,0.004006818,0.0001346352,0.01250074,0.0003786616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01396667,0.00004485347,0.981989,0.003058502,0.0001853,0.0001842688,0.00004714885,0.0002062895,0.0003180264],"genre_scores_gemma":[0.4839947,0.00001945539,0.5149883,0.0001876226,0.00005289794,0.00005777961,0.000001360463,0.00001382941,0.000684074],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9799172,"threshold_uncertainty_score":0.3650287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04327746162101873,"score_gpt":0.3328154659512365,"score_spread":0.2895380043302178,"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."}}