{"id":"W4412737319","doi":"10.5194/isprs-archives-xlviii-g-2025-765-2025","title":"PolyAttractNet: Graph-Based Polygonal Segmentation of Building Footprints Using Attraction Field Maps","year":2025,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Segmentation; Graph; Attraction; Computer science; Field (mathematics); Artificial intelligence; Computer graphics (images); Cartography; Geography; Mathematics; Theoretical computer science; Pure mathematics","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":[0.0009184885,0.0003420024,0.0003531899,0.001226019,0.0008707173,0.0003995952,0.0009298287,0.0001103041,0.000006005859],"category_scores_gemma":[0.0003571943,0.0002389291,0.0003197261,0.001020507,0.001298474,0.0004815335,0.0003256217,0.0004091329,7.364073e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006445007,"about_ca_system_score_gemma":0.0001840409,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5645201,"about_ca_topic_score_gemma":0.04481094,"domain_scores_codex":[0.9966688,0.0001648824,0.001288974,0.00027936,0.001219163,0.0003788166],"domain_scores_gemma":[0.9973417,0.0008805404,0.001149801,0.0003231131,0.0002195226,0.00008533893],"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":[0.0001176445,0.00001772138,0.0003674749,0.00008333026,0.0001030624,1.470432e-7,0.0007397034,0.04708491,0.03607296,0.000009741168,0.00003127606,0.915372],"study_design_scores_gemma":[0.0005613082,0.00007218955,0.003243775,0.000513093,0.0000555999,0.00004740727,0.000791837,0.8952819,0.09543528,0.003012439,0.0007743394,0.0002108174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05078479,0.00003644981,0.9413009,0.00135065,0.00227488,0.0004599341,0.00006468752,0.00006938121,0.00365828],"genre_scores_gemma":[0.9930031,0.00009422814,0.006278977,0.0004755225,0.0000834833,3.157455e-7,0.0000284583,0.00001050514,0.00002544964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9422182,"threshold_uncertainty_score":0.9743245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01517322473823695,"score_gpt":0.2665310103607559,"score_spread":0.251357785622519,"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."}}