{"id":"W2608258611","doi":"10.48550/arxiv.1704.02998","title":"Weakly-Supervised Spatial Context Networks","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; ENCODE; Feature learning; Encoder; Spatial contextual awareness; Pattern recognition (psychology); Offset (computer science); Context (archaeology); Initialization; Representation (politics); Categorization; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003287744,0.0003512099,0.0003913739,0.0001848945,0.0004867584,0.0005129309,0.003099048,0.0003772533,0.0001223922],"category_scores_gemma":[0.00007128592,0.0004185494,0.0002739645,0.0001791751,0.0001608596,0.0004835362,0.002290136,0.000914813,0.0002646109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001357072,"about_ca_system_score_gemma":0.0002275301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005085373,"about_ca_topic_score_gemma":0.0001823011,"domain_scores_codex":[0.9978756,0.0002031633,0.0002165338,0.001140795,0.0001190539,0.0004448437],"domain_scores_gemma":[0.9971675,0.0001146713,0.0004054928,0.001871337,0.0001803608,0.000260595],"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":[0.00007450706,0.0001146545,0.003528961,0.00005344269,0.0001855777,0.0008033448,0.0008464998,0.662549,0.00001966018,0.2655763,0.001491559,0.06475646],"study_design_scores_gemma":[0.0006370792,0.00003537732,0.002290468,0.00008491118,0.00003299673,0.000003644241,0.00008211354,0.982331,0.00001106135,0.00708742,0.006920057,0.0004838963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01504294,0.0001148103,0.9665014,0.0002101164,0.001709858,0.0002583018,0.000004433825,0.0003412822,0.01581689],"genre_scores_gemma":[0.9919423,0.0001568709,0.001404848,0.000294757,0.0002208989,0.000001040659,0.00002057136,0.00002284088,0.005935879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9768993,"threshold_uncertainty_score":0.9998266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0861122389193354,"score_gpt":0.1937504477911517,"score_spread":0.1076382088718163,"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."}}