{"id":"W1432573875","doi":"10.1145/2732407","title":"Learning to Remove Soft Shadows","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Artificial intelligence; Computer vision; Shadow (psychology); Set (abstract data type); Image (mathematics); Shadow mapping; Computer graphics (images)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002225788,0.0001222958,0.0001090246,0.0002815105,0.0002169509,0.00009939693,0.0007431363,0.00004540888,0.00001136342],"category_scores_gemma":[0.0001405114,0.000119812,0.00007466582,0.0009527749,0.0000280519,0.0004723421,0.00002316151,0.0003737436,0.0001921379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003222867,"about_ca_system_score_gemma":0.0000490038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001213818,"about_ca_topic_score_gemma":0.00001016984,"domain_scores_codex":[0.9989156,0.00004791278,0.0001517367,0.0003342045,0.000306752,0.0002437617],"domain_scores_gemma":[0.998767,0.0001046698,0.00003390966,0.0007004274,0.000122663,0.0002713109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002399585,0.0001371978,0.0001624273,0.000005357182,0.00001911353,0.00001729416,0.003323618,0.02076542,0.0003961618,0.007549095,0.001004898,0.9665954],"study_design_scores_gemma":[0.00211086,0.001667612,0.001195346,0.0001702597,0.00003345433,0.0001243339,0.001893394,0.32375,0.006098712,0.1545147,0.5069779,0.001463592],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001115046,0.00002985923,0.9922298,0.005018598,0.0004044065,0.00009596317,0.000001046074,0.0003370807,0.00076817],"genre_scores_gemma":[0.5696904,0.00003981267,0.4237553,0.005447179,0.00003691305,0.00001847125,0.000001113077,0.00002221261,0.0009886161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9651318,"threshold_uncertainty_score":0.4885793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03644447380885323,"score_gpt":0.2966938560824108,"score_spread":0.2602493822735575,"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."}}