{"id":"W4229029442","doi":"10.24963/ijcai.2022/168","title":"TopoSeg: Topology-aware Segmentation for Point Clouds","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Point cloud; Segmentation; Topology (electrical circuits); Computer science; Correctness; Network topology; Persistent homology; Robustness (evolution); Scale-space segmentation; Computational topology; Artificial intelligence; Image segmentation; Algorithm; Mathematics; Computer network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000808202,0.0002059811,0.0002742545,0.0003292787,0.000561934,0.0002064327,0.002833805,0.00005893351,0.0006794274],"category_scores_gemma":[0.0004807932,0.0001569258,0.0002723225,0.0008793839,0.0001839115,0.0003968448,0.001259293,0.0003155053,0.00003288051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001825793,"about_ca_system_score_gemma":0.00006955564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009427528,"about_ca_topic_score_gemma":0.00001687097,"domain_scores_codex":[0.9976122,0.00002748428,0.0006779735,0.000580673,0.0007997018,0.0003019017],"domain_scores_gemma":[0.9982437,0.0001826062,0.0005466101,0.0002729896,0.0006784422,0.00007568124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008346382,0.0002536083,0.0001726562,0.00001331927,0.00005810513,7.530713e-7,0.000497654,0.00056025,0.003266594,0.9753995,0.001164173,0.01852995],"study_design_scores_gemma":[0.0001208357,0.0007082158,0.0003773218,0.00004510332,0.00003698304,0.0000238793,0.002585505,0.1125052,0.135447,0.7440127,0.003760912,0.0003763328],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08797341,0.00005633471,0.721185,0.168965,0.005999339,0.001840756,0.0004351818,0.0003459392,0.01319906],"genre_scores_gemma":[0.9930152,0.00002389491,0.005168408,0.0008818508,0.0001137897,0.0001733217,0.00001491482,0.000008435335,0.0006001637],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9050418,"threshold_uncertainty_score":0.7439254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07334618563402434,"score_gpt":0.2990297860908401,"score_spread":0.2256836004568158,"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."}}