{"id":"W4405485744","doi":"10.2139/ssrn.5045901","title":"A Unified Multi-Task Learning Framework for Dtm Generation Using Surface Differencing","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Nanofabrication and Lithography Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Task (project management); Computer science; Multi-task learning; Surface (topology); Artificial intelligence; Mathematics; Engineering; Systems engineering; Geometry","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":[0.001355702,0.001195226,0.001500045,0.001088582,0.0007545077,0.001442614,0.003103812,0.002631946,0.008736894],"category_scores_gemma":[0.002951716,0.000674515,0.00124687,0.001527565,0.0004908931,0.001528063,0.002148482,0.002453323,0.003849993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007352557,"about_ca_system_score_gemma":0.00166605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01119709,"about_ca_topic_score_gemma":0.01268022,"domain_scores_codex":[0.9995085,0.00008202668,0.00003331149,0.0001659537,0.0001418802,0.000068277],"domain_scores_gemma":[0.9990734,0.0003301392,0.00005333057,0.0001483622,0.0003136283,0.00008113233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002963641,0.0002038952,0.000345129,0.0001447373,0.0000939961,0.0001133969,0.00006147484,0.1700065,0.01677821,0.007240578,0.007067635,0.797648],"study_design_scores_gemma":[0.00001217535,0.00002731956,0.00006815677,0.000006032746,0.000007738482,0.00002105432,0.000005565274,0.9926291,0.002963949,0.003048648,0.001202354,0.000007916859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001817361,0.0001495152,0.9954087,0.00007359237,0.0000595864,0.00004683511,0.0001136617,0.001817267,0.0005133638],"genre_scores_gemma":[0.1073204,0.0002334143,0.8859646,0.0002425033,0.0001360183,0.0002752061,0.0009310631,0.0005167014,0.00438002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01119709,"threshold_uncertainty_score":0.02922779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02973209705950363,"score_gpt":0.2892054744880762,"score_spread":0.2594733774285726,"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."}}