{"id":"W4287022257","doi":"10.48550/arxiv.2108.09593","title":"SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D\\n Reconstruction","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Leverage (statistics); Computer science; Viewpoints; Artificial intelligence; Code (set theory); Polygon mesh; Differentiable function; Matching (statistics); Entropy (arrow of time); Source code; Pattern recognition (psychology); Image (mathematics); Computer vision; Computer graphics (images); 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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000406117,0.0009471105,0.00135403,0.0006491674,0.0003651609,0.0003166138,0.0008097838,0.0007955258,0.001255123],"category_scores_gemma":[0.0001250485,0.001288152,0.001175322,0.001316047,0.00009684158,0.0004294436,0.0006533963,0.0008016551,0.0002961991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007624303,"about_ca_system_score_gemma":0.0002164812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001130282,"about_ca_topic_score_gemma":0.0001031113,"domain_scores_codex":[0.9958227,0.0001750041,0.000782492,0.002118779,0.0001534117,0.0009476321],"domain_scores_gemma":[0.9969763,0.0001886519,0.0002493322,0.001415277,0.0006110106,0.0005594288],"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":[0.0001072876,0.000121953,0.0002187534,0.0009700323,0.0009924587,0.00009242631,0.000546385,0.9670113,0.00676526,0.000124319,0.00009733928,0.02295246],"study_design_scores_gemma":[0.001046586,0.000100148,0.0000147952,0.001401304,0.001648248,0.00002816551,0.00120704,0.9900183,0.00124644,0.0003542406,0.001517906,0.00141682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3010092,0.0004109314,0.6935733,0.00006431431,0.001597759,0.0005993684,0.0001054552,0.000284301,0.002355378],"genre_scores_gemma":[0.9864342,0.00118643,0.006311053,0.0001277788,0.0004027705,0.000008779764,0.0001688076,0.0001563428,0.005203805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6872622,"threshold_uncertainty_score":0.9996579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07566523252940513,"score_gpt":0.1778845107066042,"score_spread":0.1022192781771991,"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."}}