{"id":"W3106073139","doi":"10.48550/arxiv.2011.04280","title":"Sketch-Inspector: a Deep Mixture Model for High-Quality Sketch Generation of Cats","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sketch; Computer science; Artificial intelligence; Discriminator; Convolutional neural network; Interpretation (philosophy); Sketch recognition; Quality (philosophy); Set (abstract data type); Object (grammar); Process (computing); Product (mathematics); Pattern recognition (psychology); Natural language processing; Algorithm; Programming language; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0002528091,0.000352533,0.00054342,0.0001672816,0.0001253764,0.00006995795,0.001578007,0.000359123,0.00000497447],"category_scores_gemma":[0.0001248366,0.0004012109,0.0003008634,0.0004872758,0.00008947321,0.0005431958,0.001226684,0.0004452387,0.000005365316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002120078,"about_ca_system_score_gemma":0.0002506862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008604009,"about_ca_topic_score_gemma":0.00007361613,"domain_scores_codex":[0.9978358,0.0001133707,0.0003696047,0.001234207,0.0001442787,0.0003026951],"domain_scores_gemma":[0.9975884,0.0001063891,0.0005030228,0.00120142,0.000445787,0.0001549624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001498159,0.0002215208,0.0002729393,0.0005692833,0.0001667955,0.00006332409,0.0009312427,0.1491877,0.01382825,0.8289182,0.001091653,0.004599301],"study_design_scores_gemma":[0.0003058882,0.00007353441,0.0001354205,0.00003161035,0.00004712138,6.661597e-7,0.000009556584,0.7174669,0.0391095,0.2424058,0.0000685301,0.0003454598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04541769,0.0001051781,0.9527193,0.0002151189,0.0002261258,0.000648051,0.00008856355,0.0004056768,0.0001743125],"genre_scores_gemma":[0.883616,0.0002166616,0.1155078,0.0001683219,0.0001287925,0.000004375677,0.00006435721,0.00002296496,0.0002708072],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8381982,"threshold_uncertainty_score":0.999844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1813746130952874,"score_gpt":0.2610275321374876,"score_spread":0.07965291904220018,"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."}}