{"id":"W2610350176","doi":"10.1109/tkde.2017.2699965","title":"Finding Related Forum Posts through Content Similarity over Intention-Based Segmentation","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"European Research Council; Université Paris-Saclay; European Cooperation in Science and Technology","keywords":"Segmentation; Similarity (geometry); Computer science; Set (abstract data type); Point (geometry); Information retrieval; Contrast (vision); Content (measure theory); Artificial intelligence; Image (mathematics); 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":[],"consensus_categories":[],"category_scores_codex":[0.000169933,0.0001378195,0.0001250682,0.0000865303,0.0004085428,0.0002461894,0.0006821073,0.0000711594,0.00001027903],"category_scores_gemma":[0.00001900973,0.0001416037,0.00004052528,0.00006964125,0.00002053263,0.001507108,0.00002379608,0.0002045489,0.0000119463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000518121,"about_ca_system_score_gemma":0.0000280843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000691372,"about_ca_topic_score_gemma":0.0000630646,"domain_scores_codex":[0.999066,0.00001466737,0.0002045094,0.0004045838,0.000111916,0.0001983082],"domain_scores_gemma":[0.9986295,0.00007327894,0.00006166118,0.001131675,0.00004268373,0.00006122659],"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":[0.0001096401,0.001374291,0.004045326,0.0008410945,0.0007559388,0.00009380039,0.005938608,0.2699319,0.06875214,0.02075528,0.001242113,0.6261598],"study_design_scores_gemma":[0.0006140955,0.00003047044,0.001015259,0.0001165958,0.00001948959,0.000004700669,0.00002424056,0.9890051,0.008546203,0.00007567133,0.0003791565,0.0001689915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0193928,0.0001071657,0.9785621,0.0003136508,0.001153312,0.0001423801,0.00004201914,0.0001477606,0.0001388401],"genre_scores_gemma":[0.9760288,0.00003152437,0.02374676,0.00004485886,0.0000190486,0.00001166953,0.00001722801,0.00001148358,0.00008863272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.956636,"threshold_uncertainty_score":0.577443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0766944298027059,"score_gpt":0.3090613877724966,"score_spread":0.2323669579697907,"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."}}