{"id":"W2917776700","doi":"10.48550/arxiv.1902.07104","title":"Adaptive Cross-Modal Few-Shot Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Modalities; Discriminative model; Margin (machine learning); Machine learning; Metric (unit); Modal; Modality (human–computer interaction); Context (archaeology); Feature (linguistics); Feature learning; Focus (optics); Pattern recognition (psychology); Natural language processing","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000490827,0.0004598907,0.000461495,0.0003662646,0.0003738555,0.0004983876,0.00227097,0.000437773,0.0001614368],"category_scores_gemma":[0.00009806438,0.0005599285,0.0003442698,0.000646606,0.0001705271,0.0007611096,0.002627749,0.00176801,0.0012462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003055565,"about_ca_system_score_gemma":0.000382828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000110752,"about_ca_topic_score_gemma":0.00001233746,"domain_scores_codex":[0.9969291,0.0003386106,0.0002881704,0.001626553,0.0002167497,0.0006007943],"domain_scores_gemma":[0.99756,0.0002354626,0.0004603719,0.001198799,0.0002876786,0.000257694],"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":[0.00004772297,0.00004644534,0.007533543,0.00003445574,0.00008220813,0.0002055935,0.0006744646,0.8440418,0.00002654497,0.1461219,0.0001150741,0.001070235],"study_design_scores_gemma":[0.0007909122,0.0001199302,0.007302993,0.00009172197,0.00003296912,0.000007940331,0.0002905244,0.975503,0.00004217083,0.009308282,0.005765387,0.0007441691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1225035,0.00007182308,0.8340038,0.00006643709,0.001151774,0.0003218897,0.000005732234,0.0005723127,0.04130271],"genre_scores_gemma":[0.9734705,0.00006802316,0.003149284,0.0001647768,0.0001110584,0.000001188482,0.00002203544,0.00003662884,0.02297648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.850967,"threshold_uncertainty_score":0.9996852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1125502070785356,"score_gpt":0.2191286905123671,"score_spread":0.1065784834338315,"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."}}