{"id":"W4391350246","doi":"10.2139/ssrn.4710034","title":"Point-Snamae: Att-Masked Autoencoder Based on Self-Distillation And Normal Vector Estimation for Self-Supervised Point Cloud Representation Learning","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Autoencoder; Point cloud; Artificial intelligence; Point (geometry); Representation (politics); Computer science; Estimation; Pattern recognition (psychology); Mathematics; Deep learning; 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":[0.001276345,0.001063772,0.00102272,0.0004237531,0.0004311119,0.0006244114,0.001844083,0.001930802,0.004294981],"category_scores_gemma":[0.002791927,0.0006771148,0.0008791911,0.0005635365,0.0006329375,0.001564313,0.002505044,0.002340755,0.002981748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004083538,"about_ca_system_score_gemma":0.001150918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004812928,"about_ca_topic_score_gemma":0.008598967,"domain_scores_codex":[0.9994298,0.0001267996,0.00003389121,0.0001791008,0.0001581013,0.00007234104],"domain_scores_gemma":[0.999134,0.0002903125,0.0000461629,0.0002301928,0.0002476675,0.00005166037],"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":[0.0005007974,0.000197768,0.0009905768,0.0001258045,0.0001827772,0.00009823879,0.0001117133,0.1286061,0.03009827,0.006336516,0.01096579,0.8217856],"study_design_scores_gemma":[0.00001058248,0.00003713729,0.000227572,0.000006849813,0.00001071517,0.00003030334,0.000006536013,0.9898359,0.006681497,0.002013495,0.00113002,0.000009387521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01130722,0.0002892084,0.983439,0.0001370622,0.0001321876,0.00004796264,0.0002232407,0.00383976,0.0005843502],"genre_scores_gemma":[0.2256839,0.000272567,0.7616426,0.000352361,0.0001280644,0.0002562625,0.002089318,0.0005894229,0.008985454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004812928,"threshold_uncertainty_score":0.01436818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121109917731566,"score_gpt":0.2414692353275628,"score_spread":0.2293582435544062,"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."}}