{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004036429,0.0008482331,0.0006926358,0.0004198382,0.000295976,0.000508454,0.001624869,0.0009008641,0.002091231],"category_scores_gemma":[0.002231698,0.0003514606,0.0004974965,0.0003972673,0.0006785742,0.001529093,0.001352983,0.001219065,0.0004658891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006646154,"about_ca_system_score_gemma":0.0005777836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00388343,"about_ca_topic_score_gemma":0.008240636,"domain_scores_codex":[0.9996943,0.00007635978,0.00001015005,0.0001415534,0.0000411155,0.00003654388],"domain_scores_gemma":[0.9994076,0.0002014347,0.0000752108,0.0001545771,0.0001133686,0.00004772703],"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":[0.0005149805,0.000235393,0.005233173,0.0002223653,0.0001373782,0.0002181737,0.000185277,0.6131257,0.02639664,0.0235333,0.006471708,0.3237259],"study_design_scores_gemma":[0.000007791758,0.00004950512,0.0004188876,0.000007187879,0.000009635853,0.0000267769,0.000008006692,0.9873667,0.002783726,0.008761575,0.000555234,0.000004896895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1602654,0.001046182,0.8295187,0.0005492766,0.0001059474,0.00007360665,0.0005481886,0.002621721,0.005270893],"genre_scores_gemma":[0.9217662,0.0002136913,0.07314961,0.0002570306,0.00006714003,0.00006073241,0.0005993375,0.00009992173,0.003786344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00388343,"threshold_uncertainty_score":0.007721663,"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."}}