{"id":"W4390872520","doi":"10.1109/iccv51070.2023.01063","title":"Continual Zero-Shot Learning through Semantically Guided Generative Random Walks","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Random walk; Zero (linguistics); Computer science; Generative grammar; Shot (pellet); Artificial intelligence; Generative model; Mathematics; Statistics; Linguistics; Materials science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002096322,0.001444352,0.001912344,0.001065252,0.0005893618,0.001295764,0.004071889,0.002205865,0.002688171],"category_scores_gemma":[0.005730133,0.0008336263,0.001492768,0.0009563281,0.001879478,0.003288195,0.002797151,0.003664173,0.001247952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001257661,"about_ca_system_score_gemma":0.001206955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004724641,"about_ca_topic_score_gemma":0.008198829,"domain_scores_codex":[0.9989051,0.000351412,0.00004710292,0.0004021215,0.0001787533,0.0001154922],"domain_scores_gemma":[0.9974107,0.001634168,0.0001385578,0.0004642547,0.0001983177,0.0001540503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003752229,0.0003997644,0.002703475,0.0003180513,0.0001822393,0.0002468712,0.0003188297,0.6100597,0.007118464,0.03203898,0.01075968,0.3354787],"study_design_scores_gemma":[0.00001550629,0.000039423,0.00010548,0.00001317788,0.000009688526,0.00004617098,0.00001355844,0.9807171,0.0009878989,0.01750969,0.0005319259,0.00001036847],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02500382,0.0007223443,0.9695826,0.0003445691,0.00005359437,0.00007668857,0.0002199509,0.002664228,0.00133227],"genre_scores_gemma":[0.7135119,0.0006036235,0.2732582,0.001087085,0.0001869462,0.0002833679,0.003070656,0.0007151785,0.007282962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004724641,"threshold_uncertainty_score":0.01108658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05919702822837183,"score_gpt":0.3118391435565556,"score_spread":0.2526421153281838,"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."}}