{"id":"W3080422948","doi":"10.48550/arxiv.2008.10719","title":"Interactive Annotation of 3D Object Geometry using 2D Scribbles","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Point cloud; Key (lock); Scene graph; Artificial intelligence; Graph; Convolutional neural network; Exploit; Object (grammar); Computer graphics (images); Rendering (computer graphics); Computer vision; Human–computer interaction; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007243985,0.0002286664,0.0003782147,0.0003976016,0.00004384374,0.00002526026,0.0002685379,0.0001782584,0.00004181283],"category_scores_gemma":[0.00002980355,0.0002888349,0.0002095988,0.0005770338,0.00003882369,0.0001427716,0.000220113,0.0004366877,0.00001783384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001746992,"about_ca_system_score_gemma":0.00004972191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001819055,"about_ca_topic_score_gemma":0.0000168735,"domain_scores_codex":[0.9991217,0.00004239834,0.0002022005,0.0004008909,0.00006541808,0.0001674477],"domain_scores_gemma":[0.9993199,0.00005240818,0.0001295231,0.0002974079,0.0001274486,0.00007334911],"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":[0.00001640244,0.00001559151,0.0007221231,0.0002006961,0.0003352112,0.00003490623,0.0002853415,0.9966832,0.001281581,0.0001368548,0.00003574649,0.0002523164],"study_design_scores_gemma":[0.000148461,0.00001208091,0.0001022278,0.0001787522,0.0003322996,7.120148e-7,0.0004188626,0.9959123,0.001368751,0.001255017,0.00001266068,0.000257913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6262145,0.00008593854,0.3725897,0.000005592454,0.0001647695,0.00005792329,0.00004063499,0.0001349982,0.0007059367],"genre_scores_gemma":[0.9984512,0.0001729315,0.001154097,0.000009460719,0.00006538739,1.896931e-7,0.0000519097,0.00003260922,0.00006219647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3722367,"threshold_uncertainty_score":0.9999564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07821607424051495,"score_gpt":0.1957745905978024,"score_spread":0.1175585163572874,"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."}}