{"id":"W4318617360","doi":"10.1038/s41550-022-01872-z","title":"A deep-learning search for technosignatures from 820 nearby stars","year":2023,"lang":"en","type":"article","venue":"Nature Astronomy","topic":"Space Science and Extraterrestrial Life","field":"Physics and Astronomy","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Theoretical Astrophysics; University of Toronto","funders":"Breakthrough Prize Foundation","keywords":"Search for extraterrestrial intelligence; Autoencoder; Radio telescope; Narrowband; Radio astronomy; Computer science; Broadband; Physics; Radio spectrum; Deep learning; Astronomy; Artificial intelligence; Telecommunications","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":[0.0002755737,0.0002050597,0.0002199333,0.0001618915,0.0002971269,0.0001627109,0.0003967373,0.0001920571,0.0002809724],"category_scores_gemma":[0.00001697759,0.0001868074,0.0001671038,0.0005846397,0.00007164996,0.0002231688,0.0001001308,0.0009571192,0.0002071277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002597836,"about_ca_system_score_gemma":0.0001194421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001872392,"about_ca_topic_score_gemma":0.000008583201,"domain_scores_codex":[0.9984456,0.00003707049,0.0001797943,0.000459692,0.000267156,0.000610742],"domain_scores_gemma":[0.9992793,0.0001942113,0.00006998787,0.0002469849,0.00007174729,0.0001377286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005087892,0.0002298653,0.3461684,0.00002956912,0.0005797013,0.00001047501,0.001867652,0.0145343,0.03527578,0.04421255,0.07738908,0.4791938],"study_design_scores_gemma":[0.003902207,0.0004113277,0.0368642,0.0001041933,0.0001172357,4.406838e-7,0.01126446,0.01303528,0.06104779,0.008369762,0.8636495,0.001233522],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9433532,0.0003426573,0.04250761,0.002068522,0.001344617,0.001332539,0.0002105458,0.0005668954,0.008273392],"genre_scores_gemma":[0.9883271,0.000001223915,0.008823988,0.00005621331,0.001359651,0.0001231385,0.0004559634,0.00003094197,0.0008217334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7862605,"threshold_uncertainty_score":0.7617783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01105464867635242,"score_gpt":0.2820548805285996,"score_spread":0.2710002318522471,"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."}}