{"id":"W3173104782","doi":"","title":"Markpainting: Adversarial Machine Learning meets Inpainting","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Inpainting; Computer science; Watermark; Artificial intelligence; Computer vision; Image (mathematics); Interpolation (computer graphics); Generative grammar; Adversarial system; Image editing","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":[0.0009159343,0.0003296671,0.0003184353,0.0002097635,0.0004885495,0.0007504803,0.0009884764,0.0001080893,0.001469267],"category_scores_gemma":[0.001861627,0.0003301056,0.0001895507,0.0003558431,0.00005421153,0.0005953088,0.0007071626,0.001120586,0.0001681447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001000443,"about_ca_system_score_gemma":0.0001541328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000173018,"about_ca_topic_score_gemma":0.00007463067,"domain_scores_codex":[0.996842,0.0007392637,0.0004482444,0.0008138862,0.0006991106,0.0004575257],"domain_scores_gemma":[0.9982803,0.0003909808,0.0003151044,0.0003305394,0.0005411579,0.0001418652],"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":[0.0001893194,0.0003769125,0.03039021,0.0000359333,0.0006035285,0.0007429465,0.002251336,0.2373333,0.05364965,0.3440117,0.0006295021,0.3297856],"study_design_scores_gemma":[0.0006529338,0.0001147852,0.0006880328,0.00009309249,0.00001119101,0.00003560005,0.0001224811,0.9488956,0.002996522,0.00102967,0.04499641,0.0003636634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008758462,0.0003020755,0.8476328,0.01843268,0.002921214,0.0001913549,0.00001086783,0.0006112424,0.1211394],"genre_scores_gemma":[0.968097,0.0001249363,0.02533878,0.0006387932,0.0005558671,0.000009992447,0.00009213583,0.00002938989,0.005113069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9593385,"threshold_uncertainty_score":0.9999151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02711126113374799,"score_gpt":0.2661754514699486,"score_spread":0.2390641903362006,"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."}}