{"id":"W4389422261","doi":"10.48550/arxiv.2312.02908","title":"Deep Learning Segmentation of Spiral Arms and Bars","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Astronomical Observations and Instrumentation","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto; University of Hertfordshire","keywords":"Spiral (railway); Bar (unit); Segmentation; Artificial intelligence; Crowdsourcing; Computer science; Deep learning; Market segmentation; Computer vision; Physics; Engineering; Mechanical engineering; Business; Marketing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004972875,0.0001096026,0.000131737,0.0001076234,0.00003254036,0.00001478689,0.00008180562,0.00009112151,0.00002359372],"category_scores_gemma":[0.00000581879,0.0001409874,0.00004701986,0.0001234315,0.00003522635,0.0001310513,0.0001067535,0.0001990158,0.00001531639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008406764,"about_ca_system_score_gemma":0.000008675316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005978607,"about_ca_topic_score_gemma":0.00001420417,"domain_scores_codex":[0.999534,0.000016999,0.0001310392,0.0001912485,0.00002606396,0.0001006836],"domain_scores_gemma":[0.9997393,0.00002321376,0.00006791409,0.0001057151,0.00002406418,0.00003974782],"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":[0.000004752751,0.000004756103,0.03735189,0.00007001985,0.00004287685,0.000001983012,0.0001510487,0.9591184,0.0003204512,0.0009045143,0.000008807809,0.002020477],"study_design_scores_gemma":[0.0002497113,0.00002540451,0.06686622,0.0000383506,0.00004754435,1.431789e-7,0.0006232776,0.9303166,0.0004979341,0.001167911,0.00002448128,0.000142433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8603712,0.0000150387,0.1390691,0.000005993761,0.0001491873,0.00009601341,0.000005741892,0.0001155471,0.0001721588],"genre_scores_gemma":[0.9983027,0.0001695362,0.001257848,0.00000265849,0.00002277695,6.903018e-7,0.00008542927,0.00001906158,0.0001393153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1379314,"threshold_uncertainty_score":0.5749299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05714293221053437,"score_gpt":0.1712588250683917,"score_spread":0.1141158928578573,"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."}}