{"id":"W1813435591","doi":"10.3982/ecta7163","title":"The Complexity of Forecast Testing","year":2008,"lang":"en","type":"article","venue":"Econometrica","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Test (biology); Sequence (biology); Computer science; Forecast skill; Econometrics; Mathematics; Statistics","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":[0.000466183,0.0001011681,0.0001965204,0.0002188135,0.0003425021,0.00007315876,0.001274018,0.00002785294,0.00001723956],"category_scores_gemma":[0.0007995824,0.00007663928,0.00008024331,0.002220595,0.0004490502,0.0002667001,0.0005546269,0.0001055165,0.00004763724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006437652,"about_ca_system_score_gemma":0.00007212738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005879976,"about_ca_topic_score_gemma":0.000006451976,"domain_scores_codex":[0.9988653,0.0000523384,0.0003500805,0.0003035802,0.0001535746,0.0002751059],"domain_scores_gemma":[0.9975683,0.001325571,0.0001787465,0.0007171613,0.0001316699,0.00007853071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000006574757,0.0003716343,0.09012254,0.00002616711,0.00005575896,0.00002052067,0.0008333556,0.0008088116,0.00003184123,0.1415372,0.002188554,0.7639971],"study_design_scores_gemma":[0.000346838,0.0003019135,0.5407434,0.000005016132,0.000003205769,0.0001232849,0.00002674728,0.3814703,0.0003747698,0.06539642,0.01092136,0.0002867365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3157333,0.001182737,0.5870859,0.003302698,0.001456663,0.0006245548,0.00001204487,0.0004628048,0.09013934],"genre_scores_gemma":[0.8897582,0.00000923822,0.1100474,0.00004302668,0.00005955113,0.000006173885,4.046631e-7,0.000004451186,0.00007153353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7637103,"threshold_uncertainty_score":0.3125259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1934291853155568,"score_gpt":0.2551249838271196,"score_spread":0.06169579851156284,"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."}}