{"id":"W4417143366","doi":"10.48550/arxiv.2512.05759","title":"Label-Efficient Point Cloud Segmentation with Active Learning","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Point cloud; Segmentation; Context (archaeology); Active learning (machine learning); Heuristics; Annotation; Process (computing); Cloud computing","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":[0.0004639131,0.0008533291,0.000919009,0.0004660198,0.0004547801,0.0001449225,0.000437215,0.000448668,0.0003458913],"category_scores_gemma":[0.00009643645,0.0008501261,0.0003405599,0.0007755198,0.00008474295,0.0001112516,0.000435669,0.00221405,0.0003115008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00068953,"about_ca_system_score_gemma":0.000225361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003070173,"about_ca_topic_score_gemma":0.00003535506,"domain_scores_codex":[0.9964421,0.0002108248,0.0008246211,0.001221387,0.0005535203,0.0007475019],"domain_scores_gemma":[0.9981732,0.0001663633,0.0003568316,0.0007509004,0.0003434567,0.0002092286],"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":[0.00008659509,0.0001596411,0.01679919,0.0004246497,0.001317045,0.00002148226,0.003803837,0.9647403,0.001177539,0.00002619169,0.00003663409,0.01140692],"study_design_scores_gemma":[0.001169853,0.0001360039,0.004602336,0.00153001,0.001238888,0.000004413739,0.003006184,0.9769138,0.01007245,0.00003152408,0.0002334881,0.00106112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.740395,0.0004692385,0.2537821,0.0002283811,0.0007565483,0.00039628,0.00003298863,0.0003597493,0.003579699],"genre_scores_gemma":[0.9920364,0.0006035604,0.002092205,0.00007288568,0.0003858707,0.0001141206,0.000190662,0.00009729259,0.004406983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2516899,"threshold_uncertainty_score":0.999395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02267898462268104,"score_gpt":0.2532713842241294,"score_spread":0.2305923996014484,"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."}}