{"id":"W6929467949","doi":"10.48550/arxiv.2107.02389","title":"Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling","year":2021,"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":"","funders":"","keywords":"Point cloud; Segmentation; Semantics (computer science); Sampling (signal processing); Point process; Conditional random field; Point (geometry); Key (lock)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001979677,0.0002292751,0.0004362032,0.0001783571,0.00008189474,0.00003793787,0.0001753292,0.0001563247,0.00006354298],"category_scores_gemma":[0.00001901144,0.0002550272,0.0002142409,0.000346612,0.00002785521,0.00009355279,0.0001508922,0.000498165,0.000006440906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000096452,"about_ca_system_score_gemma":0.00004550714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007649334,"about_ca_topic_score_gemma":0.0001028837,"domain_scores_codex":[0.9990114,0.00006693575,0.0002055969,0.0004073219,0.00008278377,0.0002259651],"domain_scores_gemma":[0.9992567,0.0000545617,0.0001161683,0.000317438,0.000185808,0.00006937037],"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":[0.00003292697,0.00002629354,0.003708516,0.0002915123,0.000312634,0.00003079663,0.0007146188,0.9942171,0.0005262198,0.00002944067,0.000005834307,0.0001040859],"study_design_scores_gemma":[0.0009791011,0.00002180793,0.0001704928,0.0003475751,0.0004558583,0.000001231899,0.002737516,0.9936236,0.001220222,0.0001484033,0.000009557441,0.0002847059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5205259,0.0000780703,0.4789177,0.000002650836,0.00007342864,0.00005597475,0.000004750983,0.000106665,0.0002348271],"genre_scores_gemma":[0.9974411,0.0003515201,0.001728043,0.000005948843,0.00004923176,6.437783e-7,0.0001147372,0.00003836958,0.0002704361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4771897,"threshold_uncertainty_score":0.9999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03014793033646192,"score_gpt":0.1813244687634017,"score_spread":0.1511765384269398,"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."}}