{"id":"W2256558689","doi":"10.48550/arxiv.1511.05616","title":"Learning Structured Inference Neural Networks with Label Relations","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Categorization; Abstraction; Exploit; Artificial intelligence; Benchmark (surveying); Semantics (computer science); Inference; Set (abstract data type); Multi-label classification; Encoding (memory); Image (mathematics); Machine learning; Artificial neural network; Pattern recognition (psychology); Deep learning; Contextual image classification","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":[0.0001587992,0.0003052361,0.0002866143,0.0001785643,0.0002012505,0.0001614729,0.001299889,0.0002673201,0.00001041193],"category_scores_gemma":[0.0000961118,0.0003007224,0.00006916301,0.0007889635,0.0001221524,0.000801045,0.001543308,0.001344571,0.00001101635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001714923,"about_ca_system_score_gemma":0.0001906977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000459086,"about_ca_topic_score_gemma":0.00002562863,"domain_scores_codex":[0.9984021,0.0001400368,0.0001585608,0.0008537597,0.0001095798,0.0003359272],"domain_scores_gemma":[0.9981741,0.0001148713,0.0002814002,0.0008680449,0.0003813746,0.000180159],"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":[0.00002881692,0.00002060043,0.005386387,0.00001122191,0.00003266684,0.0001763815,0.000136084,0.9643759,0.000005950575,0.0252181,0.0001365901,0.004471275],"study_design_scores_gemma":[0.0003288975,0.0001768651,0.0007387251,0.00006082255,0.00003536126,0.000007070512,0.00002916638,0.9609605,0.00005581762,0.03687337,0.0003304102,0.0004029986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03965469,0.00009748317,0.9578096,0.00004580215,0.0001608878,0.0002319372,0.00000312576,0.0007303267,0.001266193],"genre_scores_gemma":[0.9776807,0.00009128279,0.02066854,0.0000521452,0.00005441742,9.753684e-7,0.00002101944,0.00001941668,0.001411465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9380261,"threshold_uncertainty_score":0.9999445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07096644628058629,"score_gpt":0.2247982694540282,"score_spread":0.1538318231734419,"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."}}