{"id":"W3135907709","doi":"10.1007/s11263-023-01750-9","title":"Disentangling Geometric Deformation Spaces in Generative Latent Shape Models","year":2023,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; Centre for Social Innovation; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung","keywords":"Generative model; Artificial intelligence; Representation (politics); Rotation (mathematics); Orientation (vector space); Computer science; Pattern recognition (psychology); Mathematics; Space (punctuation); Active shape model; Computer vision; Geometry; Generative grammar; Segmentation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002278531,0.00008032075,0.0001327171,0.001128704,0.00001835947,0.0001005338,0.0001982134,0.0000325463,0.00001412662],"category_scores_gemma":[0.000007178871,0.00006825088,0.0000966728,0.0004035262,0.000005558974,0.000468384,0.00004291354,0.0001278005,0.00001439966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001073008,"about_ca_system_score_gemma":0.000009468552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001864096,"about_ca_topic_score_gemma":0.000002062289,"domain_scores_codex":[0.9990314,0.00001421956,0.0003827997,0.0000642243,0.0004068913,0.0001005029],"domain_scores_gemma":[0.999606,0.00004448722,0.00008820661,0.00004295438,0.0001786496,0.00003975344],"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":[0.000007866704,0.00001423374,0.0006404317,0.000004864141,0.00005688724,0.00004563106,0.0002965838,0.9410475,0.0001579939,0.00003874418,0.0002116738,0.05747752],"study_design_scores_gemma":[0.0002828417,0.0000251407,0.001008349,0.000124571,0.000006839188,0.0000193884,0.0000249622,0.9973007,0.000212664,0.0008634797,0.0000624922,0.00006855217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6498092,0.0001418685,0.3491615,0.0001896637,0.0005965148,0.00001314005,0.000001754811,0.00003512523,0.0000512462],"genre_scores_gemma":[0.9960175,0.0004638912,0.003102328,0.00002944554,0.0003511597,6.504754e-7,0.00001364308,0.0000100456,0.00001140925],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3462082,"threshold_uncertainty_score":0.278319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01989600507921511,"score_gpt":0.2660723140501462,"score_spread":0.2461763089709311,"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."}}