{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":3,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":3,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"dce3a9b90115","filters":{"venue":"Digital Finance"}},"results":[{"id":"W2945699837","doi":"10.1007/s42521-020-00026-y","title":"Neural networks and arbitrage in the VIX","year":2020,"lang":"en","type":"article","venue":"Digital Finance","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Nexen (Canada)","funders":"Zürcher Hochschule für Angewandte Wissenschaften; Horizon 2020 Framework Programme; European Commission; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Arbitrage; Exploit; Stylized fact; Futures contract; Volatility (finance); Economics; Index (typography); Financial economics; Algorithmic trading; Econometrics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1075030860011232,"gpt":0.3548786526973931,"spread":0.2473755666962699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001030955,0.00009191001,0.000153557,0.00003119443,0.00005282686,0.0004606151,0.0005522801,0.0000338083,0.000009122645],"category_scores_gemma":[0.005476543,0.0000561902,0.00004327342,0.0007980074,0.00009344496,0.0003808743,0.0001330134,0.0002205087,0.00001808594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004214571,"about_ca_system_score_gemma":0.00001064842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002593516,"about_ca_topic_score_gemma":0.000003103385,"domain_scores_codex":[0.9987077,0.0001159004,0.0002728158,0.0003251214,0.0003843012,0.0001941731],"domain_scores_gemma":[0.9974194,0.002190427,0.0000799249,0.0002428963,0.00002843365,0.00003889012],"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":[0.00006079261,0.00001777954,0.0696707,0.000002361481,0.000001556346,0.00008075478,0.001006567,0.002887705,0.00000525103,0.002399903,0.004361656,0.919505],"study_design_scores_gemma":[0.0003407597,0.0001467551,0.5134282,0.0000143193,0.000002041461,0.00004724953,0.0002828338,0.4204556,0.00001151262,0.0202607,0.04478453,0.0002254646],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.95236,0.0003567836,0.01393015,0.003853385,0.0001538638,0.000147894,0.000008698068,0.00002398812,0.02916519],"genre_scores_gemma":[0.997479,0.000004698627,0.0004562552,0.001812628,0.00008303981,0.000005682083,7.415522e-7,0.00000569013,0.0001523184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9192795,"threshold_uncertainty_score":0.6556329,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3210564383","doi":"10.1007/s42521-023-00075-z","title":"Deep learning algorithms for hedging with frictions","year":2023,"lang":"en","type":"article","venue":"Digital Finance","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Deep learning; Scalability; Computer science; Solver; Artificial intelligence; Algorithm; Focus (optics); Domain (mathematical analysis); Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01240328283368553,"gpt":0.2067609986923916,"spread":0.194357715858706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000259298,0.00008589943,0.00007717386,0.00004939162,0.0001077475,0.00006908402,0.00005441189,0.00002109496,0.000001669506],"category_scores_gemma":[0.0000223114,0.00008227524,0.0000314018,0.0003133092,0.00001190012,0.0002407765,0.0000117307,0.00007947128,0.0000424034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001444731,"about_ca_system_score_gemma":0.000004154003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.949066e-7,"about_ca_topic_score_gemma":0.000002230888,"domain_scores_codex":[0.9995288,0.000001102924,0.00007903414,0.0001066859,0.00005357134,0.0002308694],"domain_scores_gemma":[0.9998246,0.00005639968,0.00001273267,0.00006647329,0.000017517,0.00002225423],"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":[0.000002767501,0.000003829662,0.0009181693,0.00003060207,0.00001469527,0.00001047577,0.0002947017,0.8239322,0.00005786807,0.001093208,0.0002906717,0.1733508],"study_design_scores_gemma":[0.000202222,0.00005880313,0.001231184,0.00008108586,0.000004010057,0.00001279758,0.0001243432,0.86539,0.0005229788,0.0002654754,0.1318841,0.0002230054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5120037,0.0005338728,0.4115551,0.00004729366,0.0008000262,0.0001965151,0.00004094659,0.002909393,0.0719131],"genre_scores_gemma":[0.9959708,0.000038044,0.00146302,0.000005271127,0.0001010366,0.00004227368,0.00005394291,0.00003667835,0.002288877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4839671,"threshold_uncertainty_score":0.3355087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408901988","doi":"10.1007/s42521-024-00121-4","title":"Detecting Pump &Dump stock market manipulation from online forums","year":2025,"lang":"en","type":"article","venue":"Digital Finance","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Market manipulation; Business; Stock (firearms); Stock market; Finance; Engineering; Mechanical engineering; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.1227775245954385,"gpt":0.3952578932856372,"spread":0.2724803686901986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001530386,0.000237022,0.0003752915,0.000289448,0.0002253695,0.0006558564,0.0008478006,0.0001279088,0.0001823155],"category_scores_gemma":[0.020701,0.0002085823,0.0001730577,0.00142733,0.00007877217,0.0008519726,0.000405366,0.0002351459,0.000147919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008951231,"about_ca_system_score_gemma":0.00007935885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004760931,"about_ca_topic_score_gemma":0.0001449925,"domain_scores_codex":[0.9970251,0.0001529935,0.0008165984,0.0007998624,0.0007969883,0.0004085072],"domain_scores_gemma":[0.9936911,0.004715738,0.0003528587,0.0009225087,0.0002609371,0.00005689989],"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":[0.0001086911,0.00005046911,0.07664591,0.000004696766,0.00001339122,0.000004695651,0.00006541299,0.0001906169,0.0001048813,0.000393154,0.007426196,0.9149919],"study_design_scores_gemma":[0.000490664,0.00004429089,0.6634284,0.0001489849,0.00001288515,0.000008504474,0.0001131344,0.02547594,0.0003839605,0.1561464,0.1533813,0.0003654936],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7751682,0.0001539236,0.1669499,0.0003100888,0.0009992111,0.0002353289,0.0001775,0.0001161229,0.05588975],"genre_scores_gemma":[0.9402025,0.00000434737,0.02568705,0.0001973704,0.0001265549,0.00001650847,0.00003871623,0.00002057902,0.03370632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9146264,"threshold_uncertainty_score":0.9875481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}