{"id":"W3172425208","doi":"10.2139/ssrn.4768661","title":"Learning Compositional Shape Priors for Few-Shot 3d Reconstruction","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Anatomy and Medical Technology","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Prior probability; Shot (pellet); One shot; Artificial intelligence; Computer science; Computer vision; Computer graphics (images); Pattern recognition (psychology); Geometry; Mathematics; Materials science; Bayesian probability; Engineering; Mechanical engineering","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":[0.001383022,0.001362905,0.002006486,0.001441285,0.0005040935,0.001660145,0.002187101,0.003479743,0.003580275],"category_scores_gemma":[0.005773433,0.002106077,0.001864367,0.001328232,0.00136623,0.002374306,0.003376818,0.00308249,0.002759518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006410677,"about_ca_system_score_gemma":0.001328928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003806074,"about_ca_topic_score_gemma":0.006166104,"domain_scores_codex":[0.9993446,0.0001353845,0.00002911688,0.0001976281,0.0002178547,0.00007541088],"domain_scores_gemma":[0.9980014,0.001014298,0.0001550518,0.0004422794,0.0002377521,0.0001492564],"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":[0.0007194615,0.0002516415,0.001435829,0.0004749463,0.0002541415,0.0002103544,0.0002372952,0.4489536,0.04945359,0.01723419,0.006515526,0.4742593],"study_design_scores_gemma":[0.00001220783,0.00003378175,0.0001668646,0.00001759083,0.00001498426,0.00008957605,0.00001619828,0.9822734,0.003680556,0.0130016,0.0006810653,0.00001219684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007874398,0.0001912157,0.9900277,0.0001250202,0.00002468548,0.00002739764,0.0001130852,0.001172483,0.0004439679],"genre_scores_gemma":[0.2963093,0.0009144612,0.6945526,0.0004723988,0.0001843895,0.0001595288,0.002133113,0.001070219,0.004203933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003806074,"threshold_uncertainty_score":0.0119772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007800936038938186,"score_gpt":0.2398286276634685,"score_spread":0.2320276916245303,"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."}}