{"meta":{"query_hash":"500ed7ac3e0d","filters":{"venue":"The Journal of Financial Data Science"},"cohort_total":3,"direct_labels_cover":0,"predictions_cover":3,"exported":3,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/500ed7ac3e0d","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+Journal+of+Financial+Data+Science"},"results":[{"id":"W3175426713","doi":"10.3905/jfds.2021.1.070","title":"Weak Supervision and Black-Litterman for Automated ESG Portfolio Construction","year":2021,"lang":"en","type":"article","venue":"The Journal of Financial Data Science","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Black–Litterman model; Computer science; Portfolio; Portfolio optimization; Key (lock); Project portfolio management; Consistency (knowledge bases); Machine learning; Artificial intelligence; Replicating portfolio; Business; Engineering; Finance; Systems engineering; Project management","score_opus":0.04686496758925521,"score_gpt":0.26502349080897636,"score_spread":0.21815852321972115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175426713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98468053,0.0020222932,0.004862892,0.0019134863,0.0013579412,0.00017390757,0.00031101215,0.000020871581,0.004657081],"genre_scores_gemma":[0.9924542,0.0022490993,0.0044981553,0.0004102875,0.00026072154,0.0000010899961,0.000015812544,0.00000855494,0.00010213027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99886715,0.000018848172,0.00056616555,0.0002336785,0.000085822176,0.0002283285],"domain_scores_gemma":[0.9987918,0.00007529268,0.00046944738,0.00042053958,0.00017282528,0.00007010835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021407278,0.00009543887,0.00025332638,0.00014100558,0.00034171043,0.0001648257,0.00069823617,0.000043624863,0.000031657164],"category_scores_gemma":[0.0009828208,0.00007604529,0.000038421946,0.0004427261,0.0006802574,0.0016401268,0.0002378376,0.000118131786,0.000007321407],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015795787,0.0001190994,0.012734209,0.00007865409,0.000021811702,0.000028094966,0.0006207854,0.00006223721,0.0027048683,0.9310921,0.03703668,0.015343517],"study_design_scores_gemma":[0.0017109894,0.00055407046,0.6460899,0.00016911358,0.00005589017,0.0009037053,0.00063395547,0.028862787,0.0014708566,0.13292702,0.1860982,0.0005235176],"about_ca_topic_score_codex":0.00003265714,"about_ca_topic_score_gemma":0.000009460065,"teacher_disagreement_score":0.7981651,"about_ca_system_score_codex":0.000034945086,"about_ca_system_score_gemma":0.0003242787,"threshold_uncertainty_score":0.31010368},"labels":[],"label_agreement":null},{"id":"W4386988846","doi":"10.3905/jfds.2023.1.138","title":"RIFT: Pretraining and Applications for Representations of Interrelated Financial Time Series","year":2023,"lang":"en","type":"article","venue":"The Journal of Financial Data Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pairwise comparison; Portfolio optimization; Computer science; Portfolio; Autoencoder; Artificial intelligence; Representation (politics); Machine learning; Encoder; Artificial neural network; Econometrics; Finance; Economics","score_opus":0.18339505293215752,"score_gpt":0.4569542543097912,"score_spread":0.2735592013776337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386988846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53270644,0.0002278244,0.4587027,0.002748752,0.0012905557,0.00108993,0.0007946002,0.00004513107,0.0023940355],"genre_scores_gemma":[0.8488462,0.00014373787,0.14837365,0.00015938422,0.0007587333,0.00002940541,0.00002046294,0.000023995748,0.0016444308],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975279,0.00019063645,0.0008193553,0.0002696207,0.0009663293,0.00022617225],"domain_scores_gemma":[0.9927112,0.0045856237,0.00090910593,0.000891261,0.0008182068,0.00008463496],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026202941,0.00008182831,0.0002479227,0.00045242335,0.00055133784,0.00010992439,0.002938739,0.00003996696,0.000019568573],"category_scores_gemma":[0.0727268,0.000052250634,0.000047673373,0.0034505115,0.001132661,0.0014241147,0.0007737529,0.00017176659,0.000010161288],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058602274,0.000060861188,0.0031076297,0.000021359614,0.000015028639,0.0000047941126,0.0064401682,0.00083157164,0.027318614,0.012698077,0.043664668,0.9052512],"study_design_scores_gemma":[0.0014168374,0.0010838637,0.56554985,0.0002822775,0.00018393906,0.0005339676,0.0020713517,0.08490521,0.0055945413,0.28546667,0.05243416,0.00047731143],"about_ca_topic_score_codex":0.000009074983,"about_ca_topic_score_gemma":0.000012175933,"teacher_disagreement_score":0.9047739,"about_ca_system_score_codex":0.000016619178,"about_ca_system_score_gemma":0.0007252847,"threshold_uncertainty_score":0.935084},"labels":[],"label_agreement":null},{"id":"W4390060205","doi":"10.3905/jfds.2023.1.145","title":"Enhancing the Inverse Volatility Portfolio through Clustering","year":2023,"lang":"en","type":"article","venue":"The Journal of Financial Data Science","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CARE Canada","funders":"","keywords":"Volatility (finance); Portfolio; Econometrics; Pairwise comparison; Inverse; Sharpe ratio; Portfolio optimization; Volatility clustering; Stochastic volatility; Economics; Cluster analysis; Implied volatility; Computer science; Mathematics; Financial economics; Statistics; Autoregressive conditional heteroskedasticity","score_opus":0.09733052983039726,"score_gpt":0.281608047179705,"score_spread":0.18427751734930775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390060205","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9708954,0.0009602953,0.0063094995,0.0027784249,0.0028359846,0.00023189098,0.00018301969,0.000030894273,0.015774556],"genre_scores_gemma":[0.99651325,0.00136944,0.00061939686,0.0008335134,0.00040191735,0.0000015451222,0.0000043772875,0.000009660628,0.00024688913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99833107,0.000033121447,0.00081561104,0.00024465466,0.00017935189,0.0003962049],"domain_scores_gemma":[0.99803954,0.00015491659,0.00075221976,0.0009068137,0.0000900024,0.00005653174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008688376,0.0001222547,0.00026775833,0.00015230871,0.0007506071,0.00016369366,0.0026781384,0.000039746916,0.00007407952],"category_scores_gemma":[0.0019998744,0.00007656714,0.00006226378,0.0015376075,0.0007588182,0.0026446593,0.0007542104,0.00029562783,0.000118557764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004475305,0.00025392507,0.02633585,0.00016530519,0.00008158086,0.00011424595,0.01898819,0.0017348541,0.007145428,0.68335605,0.24896206,0.0124149555],"study_design_scores_gemma":[0.00066417095,0.00031121995,0.52568525,0.00014494915,0.000035086065,0.000104655956,0.0014837326,0.026241167,0.0008897261,0.17855725,0.26537538,0.0005073877],"about_ca_topic_score_codex":0.00034639944,"about_ca_topic_score_gemma":0.00031434122,"teacher_disagreement_score":0.5047988,"about_ca_system_score_codex":0.0000677052,"about_ca_system_score_gemma":0.00034230397,"threshold_uncertainty_score":0.5773139},"labels":[],"label_agreement":null}]}