{"id":"W4404822922","doi":"10.1007/978-3-031-77915-2_9","title":"TRAPL: Transformer-Based Patch Learning for Enhancing Semantic Representations Using Aggregated Features to Estimate Patch-Class Distribution","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Transformer; Class (philosophy); Artificial intelligence; Natural language processing; Electrical engineering; Engineering; Voltage","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001059784,0.0005953329,0.0005594717,0.0008416791,0.0007445881,0.00128179,0.001355502,0.0003103951,0.00001116661],"category_scores_gemma":[0.0002819287,0.0005839808,0.0002632001,0.001332279,0.0002589147,0.0005634356,0.0002116757,0.001044022,0.00002844266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004825618,"about_ca_system_score_gemma":0.0006632385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001265402,"about_ca_topic_score_gemma":0.0006535716,"domain_scores_codex":[0.9956855,0.00006051048,0.0007072075,0.001751034,0.0009291003,0.0008666071],"domain_scores_gemma":[0.9976632,0.0007321405,0.0002778534,0.0006919521,0.0003640742,0.0002707792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001943997,0.00002187579,0.00004170431,0.0001691963,0.00002238346,0.00004633056,0.001844171,0.7810671,0.002742552,0.008648647,0.00001597562,0.2053607],"study_design_scores_gemma":[0.0003540362,0.0002054819,0.0000955471,0.001199677,0.00003694558,0.00004220333,0.000002806143,0.970337,0.00690096,0.01819876,0.001951205,0.0006753705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006656488,0.0002526274,0.9942359,0.00154677,0.001463653,0.0009633038,0.00002054748,0.0004386806,0.000412893],"genre_scores_gemma":[0.6304576,0.00001110587,0.3675196,0.0006843929,0.000264653,0.00005312443,0.0001231443,0.00008722013,0.0007990603],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.629792,"threshold_uncertainty_score":0.999755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02167470190889631,"score_gpt":0.3072406585293771,"score_spread":0.2855659566204808,"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."}}