{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":943,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":943,"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":"42f37ebcb240","filters":{"topic":"Stock Market Forecasting Methods"}},"results":[{"id":"W4298110867","doi":"10.1111/1911-3846.12832","title":"<scp>FinBERT</scp>: A Large Language Model for Extracting Information from Financial Text*","year":2022,"lang":"en","type":"article","venue":"Contemporary Accounting Research","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":648,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Finance; Encoder; Natural language processing; Sample (material); Salient; Earnings; Random forest; Language model; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.2136271072296654,"gpt":0.458767453549553,"spread":0.2451403463198876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0562151,0.0002519881,0.0004704462,0.001239894,0.002667908,0.001117133,0.002170425,0.0001524963,0.000267332],"category_scores_gemma":[0.161648,0.0002402011,0.00024485,0.002224969,0.0001115577,0.002459303,0.001955138,0.001424638,0.0001422452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002095345,"about_ca_system_score_gemma":0.001295034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002997523,"about_ca_topic_score_gemma":0.00003461797,"domain_scores_codex":[0.9908092,0.001606616,0.001349969,0.0008229237,0.004299468,0.00111184],"domain_scores_gemma":[0.9627835,0.03382504,0.0007785075,0.00115211,0.001275526,0.0001853733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004789138,0.0002693448,0.04262121,0.000062803,0.00004606539,0.00003813573,0.03155552,0.001655162,0.00289993,0.00312279,0.7224797,0.1947704],"study_design_scores_gemma":[0.001314157,0.0001011615,0.00519207,0.00003519926,0.000004748576,0.000007386457,0.01592873,0.584602,0.0002528679,0.02587011,0.3665346,0.0001569753],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8077481,0.0007695928,0.1327445,0.0008108274,0.0009853285,0.00177018,0.001092434,0.0002279988,0.05385103],"genre_scores_gemma":[0.9768146,0.000001460962,0.01439913,0.0004908835,0.0004193965,0.0005114828,0.0001931197,0.00004459367,0.00712538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5829468,"threshold_uncertainty_score":0.9999198,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021938316","doi":"10.1016/j.eswa.2011.04.222","title":"Forecasting stock indices with back propagation neural network","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":484,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education; Lanzhou University","keywords":"Artificial neural network; Stock (firearms); Computer science; Backpropagation; Stock market index; Stock price; Composite index; Econometrics; Index (typography); Stock market; Data mining; Artificial intelligence; Series (stratigraphy); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.189853560597106,"gpt":0.3608030537518224,"spread":0.1709494931547164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002544904,0.0003018196,0.0004242292,0.0002204831,0.0005974009,0.0002890765,0.0008953635,0.0001062075,0.0001794326],"category_scores_gemma":[0.0003084823,0.0001832065,0.00005933725,0.001961882,0.0001987303,0.0004692169,0.0001063286,0.0002064908,0.0001524465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006548073,"about_ca_system_score_gemma":0.0001188152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000271786,"about_ca_topic_score_gemma":0.0001096294,"domain_scores_codex":[0.9961531,0.0004626002,0.0008213616,0.0008505575,0.001194562,0.0005178772],"domain_scores_gemma":[0.9959287,0.001195752,0.0008921288,0.001163895,0.000591904,0.000227616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001570654,0.0006465856,0.4988707,0.000166434,0.0004015468,0.00004509146,0.02357291,0.01849621,0.0003956624,0.01438651,0.04567038,0.3957773],"study_design_scores_gemma":[0.003843105,0.002674393,0.06670389,0.001063404,0.0001694127,0.002296306,0.01348708,0.6413955,0.0009082323,0.006495441,0.257572,0.003391301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04485315,0.0005754802,0.8809019,0.0001446948,0.0003800606,0.004122963,0.0000112776,0.0002832513,0.0687272],"genre_scores_gemma":[0.8569217,0.000001491742,0.1371796,0.00008870746,0.0006445322,0.003062573,0.00001022469,0.00005895863,0.002032231],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8120685,"threshold_uncertainty_score":0.7470946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2946975908","doi":"10.3390/ijfs7020026","title":"Stock Market Analysis: A Review and Taxonomy of Prediction Techniques","year":2019,"lang":"en","type":"review","venue":"International Journal of Financial Studies","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":456,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Stock (firearms); Stock market; Voting; Stock market bubble; Stock market prediction; Financial economics; Computer science; Economics; Econometrics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.30251073791625,"gpt":0.5024034625427622,"spread":0.1998927246265123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009947625,0.0003308699,0.004039913,0.001761889,0.000051868,0.00006490242,0.001330166,0.000163918,0.000119069],"category_scores_gemma":[0.02777251,0.0002131048,0.001405337,0.001337374,0.000182314,0.0002660041,0.0004740093,0.0004233263,0.000003847907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002009938,"about_ca_system_score_gemma":0.0004452652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004776081,"about_ca_topic_score_gemma":0.000006414526,"domain_scores_codex":[0.9936123,0.0008235693,0.003238329,0.0003746007,0.001798208,0.0001530255],"domain_scores_gemma":[0.9859027,0.003955539,0.005956719,0.0003271625,0.003796679,0.00006115711],"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":[0.00002494514,0.00002601666,0.0004101478,0.002494455,0.002676889,0.00001178755,0.00002721068,3.338713e-7,5.115315e-8,0.00004257763,0.0378337,0.9564519],"study_design_scores_gemma":[0.00009588282,0.0001481335,0.000903824,0.0205992,0.007242331,0.0001535502,0.00001677428,0.000003410149,5.984461e-7,0.000688241,0.97,0.0001480665],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004855042,0.9933498,0.002930561,0.0001220497,0.001342532,0.0005943715,0.0001896211,0.000008239639,0.001457962],"genre_scores_gemma":[0.000009633505,0.9906471,0.008046689,0.00007455711,0.0004620954,0.00005315761,0.000003003594,0.00001337678,0.0006903459],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9563038,"threshold_uncertainty_score":0.980417,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2085444045","doi":"10.1016/j.omega.2011.07.008","title":"Stock index forecasting based on a hybrid model","year":2011,"lang":"en","type":"article","venue":"Omega","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":377,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Lanzhou University","keywords":"Autoregressive integrated moving average; Exponential smoothing; Index (typography); Autoregressive model; Artificial neural network; Computer science; Stock market index; Moving average; Time series; Econometrics; Stock market; Statistics; Mathematics; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.3318230884209961,"gpt":0.388666807430418,"spread":0.05684371900942187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005703243,0.0002333103,0.000338848,0.0005628301,0.0002121768,0.0001242757,0.001001029,0.00007870749,0.0006251857],"category_scores_gemma":[0.01195242,0.0001792255,0.0001823949,0.0008029329,0.00009539187,0.0002192017,0.0001735652,0.0002803099,0.0001813378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006364092,"about_ca_system_score_gemma":0.000144404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002653838,"about_ca_topic_score_gemma":0.00001001719,"domain_scores_codex":[0.9963889,0.000356801,0.0005981966,0.0007057293,0.001468027,0.0004824086],"domain_scores_gemma":[0.9955524,0.002615012,0.0003068922,0.001057251,0.0002583188,0.0002101077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006220411,0.0002190681,0.05462619,0.000008541487,0.00001655166,0.00007637643,0.0007355348,0.01494771,0.0001088899,0.0005835555,0.01856288,0.9094927],"study_design_scores_gemma":[0.0004305015,0.0001446612,0.005614806,0.00002752071,0.000006837601,0.00001496544,0.00003472966,0.9494491,0.0007568322,0.04181946,0.001482763,0.0002178507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3106948,0.000007887091,0.4659243,0.0000782596,0.000568128,0.0002270829,0.00001322449,0.0001192295,0.2223671],"genre_scores_gemma":[0.870268,1.360534e-7,0.1249392,0.0004808702,0.00007168357,0.0000311197,0.000001063424,0.00003170076,0.004176203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9345013,"threshold_uncertainty_score":0.9963703,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081799531","doi":"10.1186/s40537-020-00333-6","title":"Short-term stock market price trend prediction using a comprehensive deep learning system","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":370,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Carleton University","keywords":"Feature engineering; Computer science; Stock market; Stock (firearms); Artificial intelligence; Deep learning; Machine learning; Big data; Personalization; Stock market prediction; Econometrics; Data mining; Economics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.4401202832170943,"gpt":0.4249298837676808,"spread":0.01519039944941347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006365264,0.0002015666,0.0006193729,0.0003819555,0.0002390758,0.0003596591,0.002067556,0.0001021803,0.000108147],"category_scores_gemma":[0.009888594,0.0001526508,0.0001492446,0.001086061,0.00006667105,0.0008895806,0.0009625956,0.000651199,0.00001188748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001265111,"about_ca_system_score_gemma":0.0001247245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003070545,"about_ca_topic_score_gemma":0.000003009072,"domain_scores_codex":[0.9941157,0.001560639,0.001508989,0.0005179005,0.002004171,0.0002926757],"domain_scores_gemma":[0.9940764,0.002804996,0.001385511,0.0008156211,0.0005627522,0.0003546964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009701519,0.00005743655,0.06892932,0.0001164157,0.0002410435,0.0003975741,0.00127691,0.003475545,0.00474613,0.000007092907,0.02214641,0.897636],"study_design_scores_gemma":[0.001020032,0.0005249967,0.1422325,0.0004070127,0.000267209,0.002662706,0.003751342,0.8005726,0.00006941627,0.0000536754,0.04812706,0.0003114771],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4757818,0.0008359603,0.5160824,0.0003225169,0.003183528,0.0002608979,0.0001937635,0.00007026929,0.003268852],"genre_scores_gemma":[0.9592069,0.00002389375,0.03867051,0.00007690216,0.001885049,7.604288e-7,0.00001501357,0.00003037649,0.0000905307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8973245,"threshold_uncertainty_score":0.9984515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4398243663","doi":"10.1108/ajeb-01-2024-0007","title":"Wholesale price forecasts of green grams using the neural network","year":2024,"lang":"en","type":"article","venue":"Asian Journal of Economics and Banking","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":236,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Artificial neural network; Computer science; Econometrics; Economics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1173282424017869,"gpt":0.3561236716669954,"spread":0.2387954292652085,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006873725,0.0001095916,0.0003212758,0.0001858352,0.0001396659,0.0003823892,0.0004822459,0.00004700848,0.0000387608],"category_scores_gemma":[0.0003813524,0.00006723872,0.0001869695,0.0003453785,0.0001108918,0.0003648493,0.000134133,0.0002404241,9.690443e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003053227,"about_ca_system_score_gemma":0.00009253649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001044766,"about_ca_topic_score_gemma":0.00002394711,"domain_scores_codex":[0.9983584,0.000201656,0.0008764623,0.0001804237,0.0001738782,0.0002091522],"domain_scores_gemma":[0.9976209,0.001311434,0.0006743463,0.000200078,0.0001233683,0.00006989801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004102356,0.000006098699,0.005754703,0.00001094619,0.00007207084,0.00002216293,0.001272752,0.01265741,0.00004208026,0.00505951,0.0003458658,0.9747154],"study_design_scores_gemma":[0.0003226523,0.0002250657,0.01029292,0.0003493794,0.00009316028,0.002046181,0.001233939,0.623756,0.00007497581,0.3473961,0.01399338,0.0002162481],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830217,0.001439308,0.009948705,0.001288017,0.001506041,0.0000706248,0.000002692294,0.000003922459,0.002719041],"genre_scores_gemma":[0.9836431,0.00003903531,0.01546847,0.00006473157,0.0006975608,2.732533e-7,1.057535e-7,0.00001456055,0.00007220774],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9744991,"threshold_uncertainty_score":0.3687388,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974304087","doi":"10.1016/j.eswa.2007.09.034","title":"A type-2 fuzzy rule-based expert system model for stock price analysis","year":2007,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":190,"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":"Fuzzy logic; Computer science; Econometrics; Stock price; Automotive industry; Stock (firearms); Expert system; Fuzzy set; Data mining; Artificial intelligence; Operations research; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1175076733738869,"gpt":0.4130005603318492,"spread":0.2954928869579623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007244418,0.000364484,0.0008159596,0.001048684,0.0006249133,0.0003086134,0.001211528,0.0001995144,0.00001745704],"category_scores_gemma":[0.0008497376,0.0002610156,0.0003067665,0.005059614,0.00009384104,0.0001787859,0.00007318374,0.0001395432,0.00008086463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003672012,"about_ca_system_score_gemma":0.0002991696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001861999,"about_ca_topic_score_gemma":0.00006853056,"domain_scores_codex":[0.9949738,0.00026676,0.001341976,0.001178691,0.001589598,0.0006491602],"domain_scores_gemma":[0.9907829,0.004338483,0.0007803428,0.002159115,0.001558959,0.0003802643],"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":[0.00435742,0.001893632,0.0230499,0.0005995524,0.003914291,0.00002841271,0.0152016,0.5621737,0.01296379,0.1357467,0.1086797,0.1313912],"study_design_scores_gemma":[0.0007025331,0.00008455003,0.0005474676,0.00005912303,0.0001331271,0.00001982354,0.002820947,0.9407712,0.0002648444,0.0002612912,0.05386115,0.0004739695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002152278,0.0007733811,0.9838727,0.0001809431,0.000242437,0.003037394,0.00005233333,0.0003513471,0.009337223],"genre_scores_gemma":[0.7192261,0.000001425781,0.2720095,0.0001661148,0.0003648441,0.004938039,0.00003213207,0.000061957,0.003199864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7170739,"threshold_uncertainty_score":0.9999842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137525015","doi":"10.1109/tkde.2006.80","title":"Pattern discovery of fuzzy time series for financial prediction","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Research Council Canada; University of Illinois at Urbana-Champaign; National Science Council","keywords":"Fuzzy logic; Investment (military); Computer science; Fuzzy set; Time series; Data mining; Finance; Process (computing); Representation (politics); Artificial intelligence; Machine learning; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.05021834214437013,"gpt":0.3252064956071853,"spread":0.2749881534628152,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001104979,0.0001359446,0.0002311815,0.0002525208,0.0001039906,0.00007789517,0.0003406969,0.00007346839,0.00001739768],"category_scores_gemma":[0.0002523719,0.0001190444,0.00006439662,0.0003284275,0.00003908728,0.0007846606,0.000009209162,0.0001002892,0.00001063602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001739807,"about_ca_system_score_gemma":0.00003960312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001486347,"about_ca_topic_score_gemma":0.00003868654,"domain_scores_codex":[0.9987673,0.00004082522,0.0004172678,0.0003863891,0.0002211696,0.0001670277],"domain_scores_gemma":[0.9980663,0.00115436,0.00007055332,0.0005746637,0.00009727045,0.0000368747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003532162,0.0004303732,0.0006279076,0.0002435836,0.00007232557,0.000003205924,0.0004118286,0.04702095,0.02507468,0.000365841,0.01628241,0.9091137],"study_design_scores_gemma":[0.002577515,0.0009116956,0.02449855,0.0004271707,0.0002647133,0.00007337407,0.00009555326,0.8256016,0.08448612,0.004824019,0.0552382,0.001001521],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02964831,0.0001104008,0.9670722,0.00002355826,0.0008646747,0.0001743009,0.001669141,0.00005658152,0.0003808174],"genre_scores_gemma":[0.982339,0.00001318563,0.01508823,0.000005024991,0.000270364,0.00003656173,0.00005049837,0.0000245243,0.002172566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9526907,"threshold_uncertainty_score":0.485449,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036679573","doi":"10.1109/72.935086","title":"Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Overfitting; Early stopping; Regularization (linguistics); Bayesian probability; Econometrics; Computer science; Artificial neural network; Generalization; Standard deviation; Black–Scholes model; Derivative (finance); Baseline (sea); Artificial intelligence; Mathematics; Statistics; Volatility (finance); Economics; Financial economics","retraction":null,"screen_n_in":null,"score":{"opus":0.03771736784902873,"gpt":0.3041129530411983,"spread":0.2663955851921695,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001385592,0.0004009111,0.0004683334,0.0004250263,0.001110947,0.0006808786,0.0003081235,0.0001637111,0.00005706907],"category_scores_gemma":[0.0001679037,0.0003244665,0.00008699831,0.001559287,0.0003677784,0.0008565792,0.00001225828,0.0007046749,6.25749e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004798334,"about_ca_system_score_gemma":0.0000201299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006194739,"about_ca_topic_score_gemma":0.0001471438,"domain_scores_codex":[0.9965195,0.0006536616,0.0006357381,0.0008685688,0.0006851808,0.0006373213],"domain_scores_gemma":[0.9956043,0.003191988,0.0002971928,0.0004610572,0.0001877622,0.0002576349],"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":[0.0002328326,0.00002341439,0.006701388,0.000005943702,0.00003568866,0.00003422094,0.000995603,0.6766234,0.00002027874,0.0000639292,0.00004358439,0.3152197],"study_design_scores_gemma":[0.000563962,0.0002690972,0.01126339,0.0001232368,0.00004915029,0.0003194903,0.0004284995,0.9858002,0.00003987069,0.0006209989,0.0001475941,0.000374521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2949522,0.0002830305,0.7033162,0.0002921013,0.0004713016,0.0002843268,0.000001673989,0.0001365369,0.0002626369],"genre_scores_gemma":[0.9933596,0.0001484524,0.005317563,0.0004335094,0.0002159775,0.00003328789,0.000001269854,0.00005653955,0.0004337827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6984075,"threshold_uncertainty_score":0.9999207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1549523743","doi":"10.1002/sres.2179","title":"An ARIMA‐ANN Hybrid Model for Time Series Forecasting","year":2013,"lang":"en","type":"article","venue":"Systems Research and Behavioral Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":167,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Autoregressive integrated moving average; Artificial neural network; Computer science; Autoregressive model; Time series; IBM; Series (stratigraphy); Set (abstract data type); Nonlinear system; Data set; Artificial intelligence; Machine learning; Data mining; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4855013005832682,"gpt":0.5321557290034189,"spread":0.04665442842015066,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.03203802,0.000195891,0.0003665656,0.0007848662,0.001809777,0.003539688,0.001969742,0.0000698115,0.00008688265],"category_scores_gemma":[0.005642238,0.0001362114,0.00006015694,0.001885476,0.002005481,0.003252659,0.000522862,0.0002791579,0.0001215508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001373596,"about_ca_system_score_gemma":0.000499888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008832009,"about_ca_topic_score_gemma":0.0000307425,"domain_scores_codex":[0.9926931,0.0005150149,0.0006542632,0.001178938,0.0036248,0.001333939],"domain_scores_gemma":[0.9935017,0.001389046,0.0001752634,0.0008956903,0.003254274,0.0007839988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002740148,0.0005233133,0.03116786,0.0000871232,0.000008414804,0.00003129132,0.002599318,0.001617974,0.2482675,0.003171235,0.01868529,0.6935667],"study_design_scores_gemma":[0.0002004684,0.0009500106,0.002777061,0.00004069748,0.000003548875,0.000100363,0.0008874223,0.9710248,0.001663494,0.02178897,0.0003258971,0.0002373033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9733549,0.00006694191,0.02293598,0.0001569921,0.0002897134,0.001559064,0.00004540609,0.00006852357,0.001522474],"genre_scores_gemma":[0.9616958,0.000001205735,0.02827987,0.00000789279,0.0001234918,0.0003681904,0.000002717181,0.00001809259,0.009502747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9694068,"threshold_uncertainty_score":0.9994897,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051705420","doi":"10.1198/016214504000001510","title":"Diagnostic Checking in ARMA Models With Uncorrelated Errors","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Uncorrelated; Mathematics; Statistics; Computer science; Econometrics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.05216969875186943,"gpt":0.3776856446279548,"spread":0.3255159458760854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007469678,0.0001245054,0.0004783621,0.0002318965,0.00008869184,0.0001017227,0.000545487,0.00004033417,0.00005619543],"category_scores_gemma":[0.07091636,0.0000693646,0.00009709035,0.001501616,0.0001206564,0.0003267449,0.00007309217,0.0005344518,0.00001582106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008084731,"about_ca_system_score_gemma":0.0001687114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009275733,"about_ca_topic_score_gemma":0.0001482561,"domain_scores_codex":[0.9951314,0.001342402,0.001012859,0.0001798609,0.00204629,0.0002871665],"domain_scores_gemma":[0.9723785,0.02384844,0.00290231,0.0002093606,0.0005544351,0.0001069431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003565057,0.0001708721,0.5532215,0.000002076184,0.00009526348,0.00003553665,0.0009384145,0.1245857,0.00006765495,0.00147582,0.006480467,0.3125702],"study_design_scores_gemma":[0.0006872618,0.0002485138,0.854075,0.00007644927,0.00008016487,0.00005653321,0.0003875088,0.1031813,0.00003803956,0.04025619,0.0007645193,0.0001484627],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7097375,0.00002654094,0.2842075,0.004458516,0.0002829556,0.0001149709,0.00001355532,0.000008988154,0.001149457],"genre_scores_gemma":[0.9191469,0.000006315526,0.08013215,0.0003381285,0.0001246744,0.000002138601,3.214342e-7,0.00001224974,0.0002371063],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3124217,"threshold_uncertainty_score":0.9369097,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2055503689","doi":"10.5539/mas.v3n12p28","title":"Prediction of Stock Market Index Movement by Ten Data Mining Techniques","year":2009,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Support vector machine; Computer science; Artificial intelligence; Naive Bayes classifier; Machine learning; Linear discriminant analysis; Data mining; Stock market; Stock market index; Artificial neural network; Quadratic classifier; Econometrics; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.151126865433362,"gpt":0.3896164916834791,"spread":0.2384896262501171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01798327,0.0002042092,0.0003422301,0.0005273244,0.0003272951,0.0002505816,0.004366868,0.00009014383,0.0001219054],"category_scores_gemma":[0.002579112,0.0001632911,0.00003992107,0.002103192,0.0005786229,0.0006684105,0.0009761803,0.000173498,0.00000494188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058691,"about_ca_system_score_gemma":0.000214595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001422275,"about_ca_topic_score_gemma":0.000003001742,"domain_scores_codex":[0.9937594,0.0001247425,0.0008461664,0.001338504,0.003434549,0.0004966534],"domain_scores_gemma":[0.9960063,0.0007093493,0.0004960176,0.002338161,0.0002735894,0.0001766252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005378978,0.00006522885,0.003207006,0.000002131864,0.000002707969,4.815849e-7,0.0002840896,0.00002338188,0.2397565,0.000106299,0.02970886,0.7267895],"study_design_scores_gemma":[0.0003444182,0.0001936495,0.06174151,0.00003398504,0.00001404012,0.000005425456,0.0002787708,0.8231947,0.04453818,0.06478365,0.004554973,0.0003166593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03991426,0.0000452803,0.8497968,0.0002414051,0.0001565793,0.0005395455,0.0001200709,0.0001575234,0.1090286],"genre_scores_gemma":[0.8762843,0.000002990078,0.1222164,0.0004966577,0.00004268962,0.00002020376,0.000006153797,0.000009837222,0.000920825],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8363701,"threshold_uncertainty_score":0.8114799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366828973","doi":"10.3390/math11091985","title":"Stock Price Prediction Using CNN-BiLSTM-Attention Model","year":2023,"lang":"en","type":"article","venue":"Mathematics","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Stock (firearms); Stock price; Recurrent neural network; Deep learning; Stock market index; Artificial neural network; Machine learning; Pattern recognition (psychology); Stock market; Series (stratigraphy)","retraction":null,"screen_n_in":null,"score":{"opus":0.3669801181344376,"gpt":0.4576636418749997,"spread":0.09068352374056216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007985817,0.0001634297,0.0002928193,0.0004737265,0.0002476146,0.0002073234,0.0005130169,0.0001229949,0.0001315487],"category_scores_gemma":[0.009113184,0.0001307538,0.0001381976,0.001844746,0.00005498851,0.0002842038,0.0002439939,0.0001628888,0.0004088252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008913764,"about_ca_system_score_gemma":0.00005791275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002790195,"about_ca_topic_score_gemma":0.000001056193,"domain_scores_codex":[0.996662,0.0001941949,0.0008161507,0.0004082321,0.001576968,0.0003424672],"domain_scores_gemma":[0.9965869,0.001876308,0.0003898831,0.0007535635,0.0002947723,0.00009860425],"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":[0.0001246274,0.001072206,0.03468003,0.000740797,0.0002567463,0.00005876232,0.02218413,0.4126162,0.08186382,0.02191439,0.125364,0.2991243],"study_design_scores_gemma":[0.0001235919,0.00001823824,0.002051112,0.00004416773,0.00002012874,0.00001520649,0.000421451,0.8323548,0.0001167649,0.1645481,0.0001827918,0.0001036678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4480266,0.000005568461,0.5443757,0.00006359933,0.0003632993,0.0002144669,0.00001177439,0.0002381247,0.006700845],"genre_scores_gemma":[0.3121915,0.000004436002,0.6699277,0.00005890434,0.0002153384,0.00004057159,0.000008456142,0.00006952768,0.0174836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4197386,"threshold_uncertainty_score":0.9992335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313831028","doi":"10.1016/j.eswa.2023.119509","title":"News-based intelligent prediction of financial markets using text mining and machine learning: A systematic literature review","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":151,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Machine learning; Computer science; Artificial intelligence; Stock market; Stock market prediction; Social media; Sentiment analysis; Artificial neural network; Deep learning; Stock (firearms); Financial market; Data science; Data mining; Finance; World Wide Web; Business; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1097304280731196,"gpt":0.3816748664956033,"spread":0.2719444384224837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005101547,0.0002256147,0.000724411,0.0004976082,0.0002866271,0.0001541767,0.0003719325,0.0001045936,0.00001627126],"category_scores_gemma":[0.005060867,0.0001524816,0.00009241088,0.003275916,0.00008523175,0.0001304131,0.00008569124,0.0001530234,0.0000137499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005909149,"about_ca_system_score_gemma":0.000122328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002883374,"about_ca_topic_score_gemma":0.000006502706,"domain_scores_codex":[0.9959645,0.001052509,0.001220135,0.0005738775,0.0009513478,0.000237664],"domain_scores_gemma":[0.9953268,0.002416631,0.0008629106,0.0007555725,0.0005067255,0.0001313691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001103124,0.0009318024,0.1366645,0.4315429,0.0007039413,0.0001349,0.0276689,0.02043645,0.01385451,0.004742518,0.08696962,0.2752469],"study_design_scores_gemma":[0.0009355549,0.0003339493,0.004772812,0.1980503,0.0002300691,0.0005305958,0.002489973,0.7391326,0.000286185,0.000182792,0.05233299,0.0007221326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01463875,0.1763247,0.7976086,0.0005434034,0.0005526356,0.008455646,0.0001378212,0.0004741507,0.001264321],"genre_scores_gemma":[0.8792093,0.009344938,0.09310146,0.0005669532,0.0008390133,0.01099089,0.0002160088,0.0002233548,0.005508017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8645706,"threshold_uncertainty_score":0.621802,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1979464351","doi":"10.1016/j.ijar.2014.11.002","title":"Using interval information granules to improve forecasting in fuzzy time series","year":2014,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":140,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China; Canada Research Chairs","keywords":"Interval (graph theory); Computer science; Series (stratigraphy); Partition (number theory); Time series; Fuzzy logic; Benchmark (surveying); Data mining; Domain of discourse; Basis (linear algebra); Generalization; Artificial intelligence; Algorithm; Mathematics; Machine learning; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.06884974176019318,"gpt":0.3731629320079009,"spread":0.3043131902477078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0112367,0.0001927605,0.0004451447,0.001342282,0.00008278523,0.0006714137,0.001199438,0.00007937758,0.00004988825],"category_scores_gemma":[0.02833836,0.0001554915,0.0001836518,0.0005752083,0.00005417201,0.002574146,0.0003454017,0.0003098002,0.00003707384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002527028,"about_ca_system_score_gemma":0.000103018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003181053,"about_ca_topic_score_gemma":0.000007805786,"domain_scores_codex":[0.9956093,0.0003887328,0.001687968,0.0002167356,0.001793125,0.000304158],"domain_scores_gemma":[0.9952279,0.001374735,0.001452537,0.0002141481,0.001577681,0.000153046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001370441,0.00007438372,0.01921916,0.00002046928,0.0001127159,0.00005494107,0.00376378,0.02036539,0.006199307,0.007140518,0.0005435942,0.9411353],"study_design_scores_gemma":[0.002090007,0.0005080957,0.01075728,0.001514474,0.00003333388,0.002297195,0.00179414,0.8940044,0.005876789,0.07445858,0.006088614,0.00057707],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6957065,0.00001453086,0.2943136,0.000450845,0.001629745,0.0001362322,0.000009096341,0.00002632608,0.00771308],"genre_scores_gemma":[0.6192091,0.000001689339,0.3801799,0.0001390218,0.0003965148,0.000003118759,0.000001837831,0.00001542364,0.00005347995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9405583,"threshold_uncertainty_score":0.9798464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2914419771","doi":"10.1109/bigdata.2018.8622462","title":"A Comparative Study of LSTM and DNN for Stock Market Forecasting","year":2018,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Overfitting; Artificial neural network; Generalizability theory; Computer science; Artificial intelligence; Machine learning; Stock market; Econometrics; Recurrent neural network; Stock (firearms); Stock market index; Statistics; Economics; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.389495939320603,"gpt":0.4865951196741332,"spread":0.09709918035353021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008112527,0.0001618555,0.0005428865,0.0002698974,0.000232295,0.00009888309,0.0004553377,0.0000486874,0.0005780517],"category_scores_gemma":[0.01141493,0.000110692,0.00006617026,0.0006550057,0.0002332012,0.0001783371,0.0002834593,0.00007099733,0.000006231073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001641916,"about_ca_system_score_gemma":0.00004383857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003790972,"about_ca_topic_score_gemma":0.0003314064,"domain_scores_codex":[0.997151,0.0005490853,0.0007437016,0.0005545166,0.0007339283,0.0002677641],"domain_scores_gemma":[0.9862766,0.01184261,0.0003957195,0.000478223,0.0009061376,0.0001007453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002613569,0.0009287273,0.1976862,0.00003724472,0.0002461002,0.000003810653,0.04263623,0.00001758329,0.000799899,0.000627424,0.1630913,0.5913119],"study_design_scores_gemma":[0.007315973,0.01497223,0.256695,0.000086907,0.000170004,0.00006968614,0.08811438,0.5561914,0.003461301,0.0563038,0.01567943,0.0009398683],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8854231,0.00001527502,0.05526637,0.00003824894,0.0003031202,0.001050748,0.000009000243,0.00002860114,0.05786559],"genre_scores_gemma":[0.8955303,1.02781e-7,0.09860816,0.00003209482,0.0001048369,0.00004823615,2.237361e-7,0.000009991793,0.005665998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.590372,"threshold_uncertainty_score":0.9969124,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2911608625","doi":"10.1109/ssci.2018.8628641","title":"Hybrid Deep Learning Model for Stock Price Prediction","year":2018,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":130,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Deep learning; Time series; Machine learning; Mean squared error; Random forest; Stock price; Stock (firearms); Regression; Recurrent neural network; Econometrics; Series (stratigraphy); Statistics; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1639779155678442,"gpt":0.4171452619080596,"spread":0.2531673463402154,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007302132,0.0001278251,0.0001988474,0.0002205558,0.0004092382,0.0001679452,0.0005105552,0.0000570956,0.0005797462],"category_scores_gemma":[0.02152509,0.00009490856,0.0001117698,0.0003686062,0.00009749753,0.0003105645,0.0001485803,0.0001307746,0.0001677117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004766686,"about_ca_system_score_gemma":0.00004746924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005410348,"about_ca_topic_score_gemma":0.000009514337,"domain_scores_codex":[0.9975338,0.0002377154,0.0004936641,0.0005531342,0.000847292,0.0003344211],"domain_scores_gemma":[0.9953614,0.003110615,0.0002081437,0.0004387577,0.0007629193,0.0001182043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001852635,0.00003269833,0.004689298,0.0000042076,0.00001559768,4.767872e-7,0.0006517034,0.01236427,0.00069104,0.001562551,0.02869883,0.951104],"study_design_scores_gemma":[0.0002513385,0.0002092032,0.002465938,0.000004407997,0.000007984916,0.00001036667,0.00006810654,0.9252967,0.0007388447,0.05853863,0.01230619,0.0001022696],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06154819,0.00001085663,0.8656765,0.0001023623,0.000529572,0.0003044081,0.000005110133,0.0001789238,0.07164409],"genre_scores_gemma":[0.5990394,7.448465e-7,0.36082,0.0001293205,0.0003318434,0.0000425676,0.000001936902,0.00001834696,0.0396159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9510018,"threshold_uncertainty_score":0.986717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2997193501","doi":"10.1109/bigdata.2018.8621884","title":"Predicting the Effects of News Sentiments on the Stock Market","year":2018,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":120,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Stock market; Stock (firearms); Computer science; Stock market prediction; Econometrics; Economics; Geology; History","retraction":null,"screen_n_in":null,"score":{"opus":0.08809292895614587,"gpt":0.3962242166974393,"spread":0.3081312877412934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01024307,0.0001375142,0.0001994282,0.0001018936,0.000355257,0.0001240538,0.001279724,0.00005061406,0.002376556],"category_scores_gemma":[0.04399084,0.00005269251,0.0001249712,0.0007775299,0.0003033015,0.00008327246,0.0003626219,0.0001573459,0.0001779893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001786885,"about_ca_system_score_gemma":0.00003563664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006396354,"about_ca_topic_score_gemma":0.000027488,"domain_scores_codex":[0.9956065,0.001800276,0.0004836779,0.000358669,0.001486722,0.0002640866],"domain_scores_gemma":[0.9599386,0.03824638,0.0003376763,0.001178163,0.0002430385,0.00005612221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002083285,0.00008192364,0.1131537,0.00001240428,0.00007755109,0.000002130374,0.001272193,0.000004222228,0.001731533,0.00142915,0.4836663,0.3983605],"study_design_scores_gemma":[0.001641562,0.002356036,0.7224423,0.0003362127,0.0001312855,0.00003065289,0.002912547,0.06582948,0.07637058,0.06425653,0.06312114,0.0005717078],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6757029,0.00001751137,0.005416139,0.00110229,0.00143601,0.0005564076,0.000001776344,0.00003907831,0.3157279],"genre_scores_gemma":[0.9620731,0.000001748285,0.003944635,0.001070822,0.0003041199,0.00002626734,1.166089e-7,0.00001503512,0.0325641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6092885,"threshold_uncertainty_score":0.9985354,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283764803","doi":"10.1007/s10462-022-10226-0","title":"Deep learning in the stock market—a systematic survey of practice, backtesting, and applications","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Portfolio; Volatility (finance); Mainstream; Deep learning; Stock (firearms); Stock market; Financial market; Artificial intelligence; Machine learning; Data science; Econometrics; Context (archaeology); Finance; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.2870549963427843,"gpt":0.4776395364419016,"spread":0.1905845400991173,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08631636,0.0001441437,0.000635701,0.0001917728,0.0003661646,0.0001032748,0.001119337,0.00002639974,0.000570796],"category_scores_gemma":[0.152326,0.00009753762,0.00008712385,0.003648913,0.0001283238,0.0001598661,0.0003328074,0.0004436655,0.00004705036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000407487,"about_ca_system_score_gemma":0.00008435893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002102104,"about_ca_topic_score_gemma":0.0001767075,"domain_scores_codex":[0.9781849,0.01728695,0.002169516,0.0005375228,0.001543237,0.0002778149],"domain_scores_gemma":[0.9404888,0.05670841,0.001357088,0.0008395493,0.000547888,0.0000582577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002066742,0.0001149244,0.004289667,0.003516667,0.00001275909,0.000004655644,0.0006528799,0.0006400089,0.000005591042,0.003881069,0.0003096351,0.9865515],"study_design_scores_gemma":[0.0002369378,0.002118788,0.1205807,0.03684586,0.001467814,0.002391009,0.05254572,0.4080985,0.0001264117,0.2017557,0.1706807,0.003151891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003447107,0.383389,0.5689219,0.00319182,0.0005233327,0.01215005,0.00002269012,0.0001047433,0.0282493],"genre_scores_gemma":[0.9504105,0.02186797,0.02066542,0.002217797,0.0001034221,0.003869003,0.00001421664,0.00006662562,0.0007850187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9833996,"threshold_uncertainty_score":0.9408296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121356139","doi":"10.1002/(sici)1099-131x(200004)19:3<201::aid-for753>3.0.co;2-4","title":"Neural network versus econometric models in forecasting inflation","year":2000,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Econometric model; Autoregressive integrated moving average; Econometrics; Autoregressive model; Bayesian vector autoregression; Artificial neural network; Inflation (cosmology); Computer science; Mean squared error; Bayesian probability; Economics; Time series; Statistics; Machine learning; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3101054711190852,"gpt":0.3916595949918031,"spread":0.08155412387271788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01677379,0.0002785014,0.0007512355,0.001539828,0.0002349286,0.0003423074,0.0009264946,0.0001518751,0.0009525046],"category_scores_gemma":[0.01705647,0.0002296361,0.0003499245,0.004183603,0.00007172704,0.001923183,0.0001185391,0.0007175252,0.00002090752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002416422,"about_ca_system_score_gemma":0.0001458089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000204826,"about_ca_topic_score_gemma":0.00004068849,"domain_scores_codex":[0.9939829,0.0006774645,0.002804074,0.0004139458,0.001394092,0.0007275143],"domain_scores_gemma":[0.9859095,0.0109709,0.001954249,0.000372836,0.0005514603,0.0002411139],"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":[0.0004027985,0.00001379291,0.007545351,0.000002530804,0.00001124812,0.00004264209,0.000189017,0.5029147,0.000002461689,0.00004805297,0.0003088322,0.4885186],"study_design_scores_gemma":[0.001741629,0.0003593063,0.009384464,0.0001312759,0.00002374455,0.0004665972,0.000175018,0.9563287,0.0000121891,0.03025693,0.0008871204,0.0002329972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9421666,0.0003896032,0.006011405,0.0001121302,0.001662772,0.000163248,0.000001978296,0.00001920294,0.04947307],"genre_scores_gemma":[0.9440668,0.00001289713,0.05436768,0.00005145126,0.001147773,0.00000311657,7.501612e-7,0.00003251768,0.0003170166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4882856,"threshold_uncertainty_score":0.9999608,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1979637725","doi":"10.1016/j.engappai.2015.01.006","title":"Time series long-term forecasting model based on information granules and fuzzy clustering","year":2015,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":110,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Data mining; Series (stratigraphy); Curse of dimensionality; Time series; Cluster analysis; Term (time); Fuzzy logic; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1168733235904522,"gpt":0.353833244800893,"spread":0.2369599212104408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002381383,0.000169031,0.0002328613,0.0004812701,0.0001072617,0.0001602608,0.0004478486,0.00007414514,0.00001294213],"category_scores_gemma":[0.003716066,0.0001596338,0.00005478219,0.0007674439,0.0001196346,0.0005399564,0.0001208592,0.0001369745,0.00006666543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004397645,"about_ca_system_score_gemma":0.00006111182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006421842,"about_ca_topic_score_gemma":0.00000498766,"domain_scores_codex":[0.9980568,0.00004500595,0.0007915179,0.0002702263,0.000626105,0.0002103512],"domain_scores_gemma":[0.9976262,0.00104615,0.0002530866,0.000515898,0.0004155406,0.0001430606],"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":[0.00003697594,0.00001585988,0.00009633612,0.00001638422,0.000002874632,2.107311e-7,0.0002852621,0.740243,0.0002544277,0.00285507,0.00002230476,0.2561713],"study_design_scores_gemma":[0.00002598002,0.00006006128,0.0002128722,0.00004320097,0.000006994355,0.000005975124,0.0001178535,0.9814657,0.004707602,0.01311167,0.00009259093,0.0001495187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03756892,0.0000203299,0.9606697,0.0001138563,0.00008353355,0.0003243281,0.00001635729,0.00009928805,0.00110368],"genre_scores_gemma":[0.777667,0.000001490937,0.2221019,0.00001991241,0.00005086637,0.00009260111,0.000006966346,0.00001400038,0.00004517317],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7400981,"threshold_uncertainty_score":0.6509676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2550257869","doi":"10.1016/j.ijar.2016.10.010","title":"Long-term forecasting of time series based on linear fuzzy information granules and fuzzy inference system","year":2016,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":107,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Beijing Municipality; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Time series; Data mining; Fuzzy logic; Adaptive neuro fuzzy inference system; Mathematics; Series (stratigraphy); Computer science; Term (time); Artificial intelligence; Autoregressive model; Normalization (sociology); Algorithm; Fuzzy control system; Machine learning; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.05061357592872628,"gpt":0.3459787121040283,"spread":0.295365136175302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005457511,0.0001856652,0.0004186523,0.0007896062,0.0000871985,0.0002309919,0.0007538681,0.00008307496,0.00003540999],"category_scores_gemma":[0.01413698,0.0001130019,0.0001483957,0.000265845,0.0001372313,0.001627597,0.0001532966,0.0001596809,0.00001548976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128738,"about_ca_system_score_gemma":0.0001396618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004925823,"about_ca_topic_score_gemma":0.00000121883,"domain_scores_codex":[0.9960615,0.0002838912,0.001383271,0.0001848078,0.001886127,0.0002003968],"domain_scores_gemma":[0.9918841,0.003608264,0.002191199,0.0002179865,0.001981217,0.0001172136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002280599,0.00008520026,0.1173187,0.0001298946,0.0001970902,0.00009366072,0.0009630492,0.00314571,0.002165577,0.01157796,0.0001156071,0.861927],"study_design_scores_gemma":[0.0130649,0.003152718,0.2430701,0.03458666,0.0002880831,0.006381631,0.002652641,0.6006857,0.04870538,0.04469325,0.0008509799,0.001867967],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8389143,0.00003452604,0.1527797,0.0004059831,0.000706101,0.0001366033,0.00004084657,0.00002894016,0.006953011],"genre_scores_gemma":[0.9277283,0.00001303046,0.07198185,0.0000255773,0.0001795605,0.000002612971,0.00000239796,0.00001210905,0.00005455594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.860059,"threshold_uncertainty_score":0.9941674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996485148","doi":"10.1109/access.2019.2959789","title":"Mixture of Activation Functions With Extended Min-Max Normalization for Forex Market Prediction","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"National Research Foundation of Korea; National IT Industry Promotion Agency; National Natural Science Foundation of China; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Normalization (sociology); Foreign exchange market; Computer science; Foreign exchange; Artificial intelligence; Econometrics; Monetary economics; Mathematics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.07898050297383662,"gpt":0.3912559948429174,"spread":0.3122754918690808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002451101,0.0001632254,0.0002882286,0.0004133428,0.0001386603,0.0001792232,0.0005986736,0.0001344507,0.001066627],"category_scores_gemma":[0.002290966,0.0001180225,0.0001015908,0.001266818,0.00005577558,0.001419546,0.00005597125,0.0001020541,0.00001549934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005239588,"about_ca_system_score_gemma":0.00009860866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001666958,"about_ca_topic_score_gemma":0.00002364008,"domain_scores_codex":[0.9975399,0.000222741,0.0005735193,0.0004910009,0.0009469627,0.0002258437],"domain_scores_gemma":[0.9953761,0.002309258,0.0006137278,0.0006141335,0.001023307,0.00006350796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.005201302,0.0003467994,0.3275692,0.0002296819,0.0001882508,0.000001011935,0.0007724398,0.009837198,0.01768235,0.0005514044,0.372911,0.2647094],"study_design_scores_gemma":[0.003093412,0.0008292111,0.6767707,0.0002291601,0.000128567,0.00002258312,0.000553598,0.2230604,0.05301786,0.01535452,0.02644752,0.0004924535],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2944725,0.000006514691,0.6881557,0.0001205621,0.001010409,0.000865336,0.00007846606,0.00005233987,0.01523816],"genre_scores_gemma":[0.9779498,0.000001421027,0.01285753,0.00007378783,0.0001824686,0.000117748,0.00004069113,0.00002676631,0.008749761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6834773,"threshold_uncertainty_score":0.9998465,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048452064","doi":"10.1145/2628194.2628211","title":"A machine learning approach for stock price prediction","year":2014,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Oracle; Computer science; Machine learning; Artificial intelligence; Support vector machine; Decision tree; Inference; Graph; Decision support system; Data mining; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1349466357588076,"gpt":0.3893020969692675,"spread":0.25435546121046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01396987,0.0001259386,0.0002356193,0.0002182367,0.0002660237,0.000157202,0.0004773584,0.00007984581,0.0002753736],"category_scores_gemma":[0.03256787,0.00008602137,0.0001182198,0.0005688604,0.00003921463,0.0001759783,0.0001191638,0.0001713173,0.00003452714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002750344,"about_ca_system_score_gemma":0.00001914906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001530617,"about_ca_topic_score_gemma":0.000002157687,"domain_scores_codex":[0.997287,0.000641365,0.0004571997,0.0005333431,0.0008087846,0.0002723324],"domain_scores_gemma":[0.9939842,0.005024187,0.0002066249,0.0004153526,0.0002638718,0.0001057292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001340469,0.00006491961,0.03500704,0.00001293151,0.0000160487,1.01683e-7,0.0002706451,0.007311437,0.0003756371,0.005531013,0.009878619,0.9413975],"study_design_scores_gemma":[0.0003757629,0.0001966486,0.008065638,0.000002557571,0.000007727034,0.000008567565,0.00006433099,0.8659797,0.0001029586,0.008932944,0.1161672,0.00009600105],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005217338,0.00001633995,0.8019325,0.00008563275,0.0002348572,0.0003203382,0.00000400864,0.0001587806,0.1920303],"genre_scores_gemma":[0.3588995,7.049217e-7,0.6055276,0.0001133509,0.0002339633,0.00008362289,0.000009482344,0.00002008814,0.03511166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9413016,"threshold_uncertainty_score":0.9755812,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950376465","doi":"10.3390/jrfm12020103","title":"Next-Day Bitcoin Price Forecast","year":2019,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Universitetet i Agder","keywords":"Autoregressive integrated moving average; Econometrics; Sample (material); Autoregressive model; Estimation; Computer science; Statistics; Economics; Time series; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.04551465964877507,"gpt":0.3265935856203653,"spread":0.2810789259715902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01062751,0.0001431956,0.0004040996,0.0005453593,0.0001185986,0.0002205513,0.0005454865,0.00006138568,0.000240323],"category_scores_gemma":[0.003649866,0.00009791974,0.0001783695,0.0007313082,0.00004661826,0.0003978353,0.0002627192,0.0002665666,0.00009949485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003821908,"about_ca_system_score_gemma":0.00003681161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007334296,"about_ca_topic_score_gemma":0.000005610792,"domain_scores_codex":[0.997236,0.0003388735,0.0008426431,0.000262583,0.001068845,0.0002510558],"domain_scores_gemma":[0.9970365,0.001373678,0.0009009022,0.0003189002,0.0002458353,0.0001241569],"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":[0.0001252788,0.00003502383,0.03890941,0.000009679434,0.00001149653,0.00004478168,0.0003621066,0.00008351363,0.00001479242,0.002946533,0.006259335,0.951198],"study_design_scores_gemma":[0.0008074989,0.000261775,0.4233663,0.0000578827,0.00004310035,0.00005204543,0.0004268436,0.000480808,0.00002087508,0.04633525,0.5280041,0.0001435411],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7404205,0.0005990424,0.2323495,0.0001711734,0.002438356,0.0002732053,0.000004963878,0.00001056816,0.02373273],"genre_scores_gemma":[0.9502487,0.0005407294,0.04554534,0.0001942511,0.0003850674,0.000002323405,1.877418e-7,0.00001428145,0.003069113],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9510545,"threshold_uncertainty_score":0.4369494,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167900190","doi":"10.1046/j.0013-0133.2003.172_5.x","title":"Applied Computational Economics and Finance","year":2003,"lang":"en","type":"article","venue":"The Economic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Toolbox; Computational economics; Computer science; MATLAB; Computational finance; Numerical analysis; Process (computing); Theoretical computer science; Algorithm; Computational science; Finance; Mathematical economics; Programming language; Mathematics; Economics; Macroeconomics","retraction":null,"screen_n_in":null,"score":{"opus":0.0775707606853222,"gpt":0.3474639439196236,"spread":0.2698931832343014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008320708,0.00009384379,0.0001892355,0.00009505415,0.0003645367,0.0003600965,0.0004250619,0.00003252731,0.000325534],"category_scores_gemma":[0.0006952644,0.00006187821,0.00005906795,0.0000565991,0.0001376412,0.0001440097,0.0000565203,0.000197603,0.0002257661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001053579,"about_ca_system_score_gemma":0.000221988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001224611,"about_ca_topic_score_gemma":0.000003673849,"domain_scores_codex":[0.9987373,0.0002563629,0.0005096055,0.000207009,0.0001062985,0.0001834012],"domain_scores_gemma":[0.9967405,0.002565792,0.0003787559,0.0002259732,0.00003437852,0.00005457482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005170087,0.000009032724,0.002216897,4.79926e-7,0.00003586474,0.000001851064,0.0005157135,0.3058234,0.000005587456,0.3742255,0.01058259,0.3065314],"study_design_scores_gemma":[0.0003900568,0.00001516947,0.009772997,0.00000165662,0.000005236273,0.0007148688,0.000192679,0.02811031,0.00002793628,0.8635985,0.09707013,0.0001004145],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9338514,0.0001369921,0.01250311,0.0008401502,0.0008836628,0.00007774521,0.000003662491,0.000006262314,0.05169703],"genre_scores_gemma":[0.9671543,0.0001024489,0.03136826,0.000343079,0.0001927953,0.000002597144,1.661751e-7,0.00001027711,0.0008260232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4893731,"threshold_uncertainty_score":0.3564369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2271008577","doi":"10.1145/2838731","title":"A Tensor-Based Information Framework for Predicting the Stock Market","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; National Science Foundation","keywords":"Computer science; Stock market; Stock (firearms); Tensor (intrinsic definition); Curse of dimensionality; Data mining; Dimensionality reduction; Artificial intelligence; Econometrics; Machine learning; Economics; Mathematics; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.08894259654104707,"gpt":0.365239191310019,"spread":0.2762965947689719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008678154,0.00025236,0.0003165551,0.0007394979,0.000879038,0.000832591,0.001264773,0.0002371163,0.0002916415],"category_scores_gemma":[0.02136435,0.000130452,0.0002617506,0.001073096,0.0001054135,0.004029152,0.00001564858,0.0002495856,0.0004724752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001821308,"about_ca_system_score_gemma":0.0001711214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002474928,"about_ca_topic_score_gemma":0.000002872855,"domain_scores_codex":[0.9953747,0.0005310159,0.001782372,0.0002174386,0.001691725,0.0004027485],"domain_scores_gemma":[0.9742163,0.02188191,0.001052464,0.001557351,0.001162129,0.0001298184],"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":[0.0005489946,0.00002674213,0.001057744,0.00007423611,0.00005703279,9.660578e-8,0.001640332,0.009237536,0.000008550917,0.002697607,0.01144161,0.9732095],"study_design_scores_gemma":[0.003507352,0.0006428243,0.01044833,0.0008103907,0.0001076437,0.00005442771,0.007931512,0.1937802,0.000499734,0.01964629,0.7617581,0.0008132334],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002242461,0.000008919202,0.9860278,0.002902179,0.002489877,0.001719692,0.0003711614,0.0002396261,0.00399829],"genre_scores_gemma":[0.935864,0.00000503238,0.06036038,0.001057202,0.0001819433,0.001510084,0.00001214706,0.00002198198,0.0009872629],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9723963,"threshold_uncertainty_score":0.9868791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3208148443","doi":"10.3390/jrfm14110526","title":"Application of Artificial Intelligence in Stock Market Forecasting: A Critique, Review, and Research Agenda","year":2021,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Stock market; Computer science; Artificial intelligence; Artificial neural network; Econometrics; Stock (firearms); Machine learning; Data mining; Economics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1641788009602458,"gpt":0.4504813734288348,"spread":0.286302572468589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0224508,0.00009831989,0.000437425,0.0005863922,0.0001071095,0.00007115917,0.000300836,0.00005399879,0.00005470798],"category_scores_gemma":[0.01889877,0.00008055497,0.0000775471,0.0016069,0.0001324974,0.0001508794,0.0003212138,0.0003708658,0.000001161922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003434027,"about_ca_system_score_gemma":0.00007391382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000219664,"about_ca_topic_score_gemma":0.00006799221,"domain_scores_codex":[0.9963251,0.0009861477,0.001239048,0.0002961656,0.0009442263,0.0002093491],"domain_scores_gemma":[0.9960743,0.002122621,0.0005799106,0.0002655523,0.0008814333,0.00007625236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001108175,0.00006345285,0.004954812,0.0001828424,0.000004955295,0.00006721282,0.0002762321,0.0000126086,0.00001625423,0.002322417,0.002630455,0.9893579],"study_design_scores_gemma":[0.0004940204,0.0005494891,0.2942808,0.001726982,0.0001911983,0.0002626461,0.002834655,0.0103473,0.0004107445,0.5822427,0.1063126,0.0003469696],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1038384,0.0186857,0.8702484,0.0008717406,0.0003106811,0.0006655926,0.00001517078,0.000004860729,0.005359476],"genre_scores_gemma":[0.8392725,0.02550857,0.1342459,0.0002414699,0.0002183288,0.00003115762,7.411032e-7,0.0000177425,0.0004636351],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.989011,"threshold_uncertainty_score":0.9893655,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4223569375","doi":"10.1016/j.knosys.2022.108742","title":"Investigating the informativeness of technical indicators and news sentiment in financial market price prediction","year":2022,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":90,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"New York Institute of Technology","funders":"Ministry of Science Research and Technology","keywords":"Sentiment analysis; Financial market; Computer science; Market sentiment; Financial crisis; Timestamp; Market data; Foreign exchange market; Artificial intelligence; Econometrics; Machine learning; Finance; Economics; Exchange rate","retraction":null,"screen_n_in":null,"score":{"opus":0.05465078483749769,"gpt":0.3446362941369733,"spread":0.2899855092994756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02088043,0.000168524,0.000414806,0.0008071919,0.0003907673,0.00009406869,0.0007095311,0.00008375398,0.00008061913],"category_scores_gemma":[0.009383124,0.0001188266,0.00008225556,0.003081289,0.0002478401,0.0001552624,0.0004904985,0.0004170853,0.000004449208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002600667,"about_ca_system_score_gemma":0.0004687969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008564333,"about_ca_topic_score_gemma":0.00004683373,"domain_scores_codex":[0.9931889,0.003483809,0.001404999,0.0003889003,0.001256498,0.0002769571],"domain_scores_gemma":[0.9929413,0.005460729,0.0008016871,0.0005395569,0.0001578102,0.00009897065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002308545,0.0003346027,0.7868323,0.0003398971,0.00002600279,0.000005344281,0.007992086,0.008764035,0.001362498,0.001434056,0.02002727,0.1726511],"study_design_scores_gemma":[0.002279147,0.0004687153,0.724709,0.0004537879,0.00003462697,0.00006336652,0.006776457,0.1659907,0.0008480247,0.001348579,0.09658585,0.0004418036],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9425312,0.0006855211,0.02562885,0.0001979474,0.001883073,0.001656782,0.00008500534,0.00008103689,0.02725057],"genre_scores_gemma":[0.9983712,9.42678e-7,0.0008190925,0.00003642267,0.00006874885,0.0003512575,0.000003723373,0.0000120867,0.0003365692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1722093,"threshold_uncertainty_score":0.9989613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3158053678","doi":"10.1007/978-3-030-73200-4_47","title":"LSTM Based Sentiment Analysis for Cryptocurrency Prediction","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":90,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Sentiment analysis; Social media; Cryptocurrency; Pipeline (software); Big data; Artificial intelligence; Precision and recall; Volume (thermodynamics); Social media analytics; Analytics; Data science; Natural language processing; Machine learning; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.08994810533514011,"gpt":0.3737289783395337,"spread":0.2837808730043936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009397755,0.0005151196,0.00101089,0.003087079,0.0003733831,0.0008532507,0.002233539,0.0003576497,0.0006781964],"category_scores_gemma":[0.005454663,0.0004260315,0.0007231926,0.00344786,0.0005541763,0.0002597872,0.0006330155,0.0005403609,0.00002136254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003881962,"about_ca_system_score_gemma":0.0008486754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009335289,"about_ca_topic_score_gemma":0.00007817371,"domain_scores_codex":[0.9922428,0.0002079641,0.001247533,0.002458196,0.003215846,0.0006277337],"domain_scores_gemma":[0.9877939,0.00813995,0.0007115374,0.001861177,0.001281554,0.0002118559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002518336,0.00003722823,0.002922123,0.00001873692,0.00008458037,0.00001576631,0.0001528743,0.1549251,0.00005830459,0.0008932056,0.0001732646,0.8406936],"study_design_scores_gemma":[0.0003110639,0.0001489721,0.002388543,0.0001643775,0.000185834,0.00000783433,3.800318e-7,0.8629223,0.0007812763,0.126648,0.005985313,0.0004561539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001454997,0.0002823731,0.9918255,0.0004151489,0.003369217,0.0006527263,0.00008660231,0.00007333763,0.003149639],"genre_scores_gemma":[0.03570705,0.000005580791,0.9599285,0.0007342248,0.0008233364,0.00005554585,0.0000459956,0.00004499758,0.002654756],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8402374,"threshold_uncertainty_score":0.9998192,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963434388","doi":"10.18653/v1/n16-1041","title":"Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks","year":2016,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Word embedding; Stock market; Stock (firearms); Artificial neural network; Embedding; Computer science; Financial market; Market data; Stock price; Econometrics; Artificial intelligence; Finance; Business; Economics; Series (stratigraphy); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09734152973611282,"gpt":0.379394159528915,"spread":0.2820526297928022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003689455,0.000263999,0.0003843339,0.0002955347,0.000264321,0.000292883,0.0006914631,0.0001273843,0.0006691715],"category_scores_gemma":[0.01205129,0.0001589172,0.00009397115,0.0009913758,0.00008166175,0.00054363,0.0007218664,0.0001428921,0.00002494963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001018435,"about_ca_system_score_gemma":0.00005160382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007936874,"about_ca_topic_score_gemma":0.00009017223,"domain_scores_codex":[0.9962499,0.0003749274,0.0007273239,0.0008595452,0.001084037,0.0007042965],"domain_scores_gemma":[0.9957396,0.002789675,0.0002538872,0.0005913936,0.0002236827,0.0004017145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001545213,0.00001913774,0.06806739,0.000001599902,0.000008035902,0.000008549248,0.0002446622,0.001563032,0.0007021929,0.0000651923,0.003459325,0.9257063],"study_design_scores_gemma":[0.001652047,0.0003300027,0.3360336,0.00009171153,0.00002315764,0.00005215059,0.0001589644,0.6369004,0.0002632242,0.008237081,0.01550955,0.0007480417],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4934451,0.00002300685,0.5035382,0.000191787,0.0006156142,0.0002749026,0.000002949391,0.00005038735,0.00185805],"genre_scores_gemma":[0.8895455,0.000003757141,0.1015813,0.001741386,0.0004470499,0.00001913866,3.404344e-7,0.00003297349,0.006628523],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9249583,"threshold_uncertainty_score":0.9962706,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965402578","doi":"10.1002/for.1134","title":"Forecasting volatility with support vector machine‐based GARCH model","year":2009,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":86,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of British Columbia; Fudan University; Kyungpook National University; Deutsche Forschungsgemeinschaft","keywords":"Autoregressive conditional heteroskedasticity; Support vector machine; Volatility (finance); Econometrics; Artificial neural network; Computer science; Normality; Artificial intelligence; Machine learning; Economics; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2387891771350272,"gpt":0.4069124056440709,"spread":0.1681232285090437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01933934,0.0004493998,0.001034356,0.0009453387,0.0004331504,0.0003959191,0.001378824,0.0001605108,0.0002840522],"category_scores_gemma":[0.02479393,0.0002973345,0.0004830889,0.001623247,0.0001528801,0.0009140064,0.000110152,0.001025166,0.00000657823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002068611,"about_ca_system_score_gemma":0.0007983659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007792095,"about_ca_topic_score_gemma":0.00002015069,"domain_scores_codex":[0.9920773,0.0006084535,0.002512677,0.0006150731,0.003338817,0.0008477184],"domain_scores_gemma":[0.9884859,0.005270088,0.002908808,0.0007209308,0.002121758,0.0004924578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001981179,0.0002507416,0.05216986,0.00002936409,0.00006454108,0.0004454714,0.0009535609,0.07932065,0.0007629661,0.0001063333,0.002436998,0.8614783],"study_design_scores_gemma":[0.00130781,0.001524447,0.007347111,0.0002019582,0.00006610491,0.001429692,0.0001156615,0.9761888,0.0007181636,0.01021535,0.0005510881,0.0003337583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5864266,0.0001005901,0.3996862,0.0007172847,0.0003954563,0.0002512194,0.00001547465,0.00004820215,0.01235898],"genre_scores_gemma":[0.7159501,6.16476e-7,0.2831417,0.0002499929,0.0002835245,0.000001824336,0.000001373193,0.00003085509,0.0003400106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8968682,"threshold_uncertainty_score":0.9999479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1997199759","doi":"10.5539/jmr.v2n4p111","title":"Forecasting Exchange Rate in India: An Application of Artificial Neural Network Model","year":2010,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Mean absolute percentage error; Mean squared error; Artificial neural network; Mean absolute error; Absolute deviation; Mathematics; Exchange rate; Statistics; Us dollar; Econometrics; Pound (networking); Foreign exchange; Approximation error; Artificial intelligence; Computer science; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.4487515755731387,"gpt":0.5227797922347571,"spread":0.07402821666161846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08802678,0.0001178599,0.0004942646,0.001093871,0.0001369693,0.0001639597,0.001309444,0.0001478064,0.00007035968],"category_scores_gemma":[0.02690818,0.0000860372,0.0001176634,0.001772038,0.0001945358,0.0003995108,0.0002561528,0.001354907,0.000007331181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004388608,"about_ca_system_score_gemma":0.0002180198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008621567,"about_ca_topic_score_gemma":0.00009957212,"domain_scores_codex":[0.9934667,0.001183528,0.001866896,0.0002453151,0.002739039,0.0004985589],"domain_scores_gemma":[0.9873957,0.008903529,0.0011706,0.0005898509,0.001751736,0.0001885839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004503392,0.001176084,0.0137269,0.0002102268,0.0000349494,0.00007260546,0.009539807,0.09394088,0.05891956,0.01215094,0.001942674,0.807835],"study_design_scores_gemma":[0.0001509932,0.0001218221,0.002343626,0.00003648598,0.000003606037,0.00004454462,0.0004488728,0.7316176,0.0006283029,0.2645144,0.00003480588,0.00005489357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9052588,0.00002381554,0.09266008,0.0001300729,0.0002276952,0.0002610543,0.000002372092,0.000004305821,0.001431765],"genre_scores_gemma":[0.8054125,0.000003020587,0.1940914,0.000008452607,0.0003832988,0.000009166773,3.189132e-7,0.00001856351,0.00007327369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8077801,"threshold_uncertainty_score":0.9812886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2910330388","doi":"10.1109/icmla.2018.00242","title":"Token-Based Adaptive Time-Series Prediction by Ensembling Linear and Non-linear Estimators: A Machine Learning Approach for Predictive Analytics on big Stock Data","year":2018,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Big data; Kalman filter; Estimator; Time series; Machine learning; Artificial neural network; Data mining; Artificial intelligence; Ensemble learning; Predictive analytics; Algorithm; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1776362040593276,"gpt":0.3897161042609912,"spread":0.2120799002016637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007531669,0.0003949078,0.0006075466,0.0005047597,0.0006738838,0.0002278474,0.0009256843,0.0002140697,0.00007923243],"category_scores_gemma":[0.01815585,0.0002990045,0.0000958801,0.00102453,0.000432443,0.0005235538,0.0004674518,0.0004047671,0.00002730384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007552827,"about_ca_system_score_gemma":0.0001917445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006259565,"about_ca_topic_score_gemma":0.00001314093,"domain_scores_codex":[0.9954767,0.0005337627,0.0008318368,0.001437131,0.00123516,0.0004854008],"domain_scores_gemma":[0.9922225,0.005096596,0.0004801455,0.001164475,0.0007896603,0.0002466128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02543651,0.001552387,0.06870349,0.0001759981,0.00102575,0.00001273578,0.003359677,0.2689308,0.004104343,0.000194492,0.1061512,0.5203526],"study_design_scores_gemma":[0.001105502,0.002860676,0.0005164866,0.00004821402,0.00009181647,0.000008365415,0.0002655056,0.9882597,0.001801401,0.0002346587,0.004525429,0.0002822976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01889983,0.00004276985,0.9749075,0.000117659,0.0002773927,0.0009366181,0.0009189532,0.0002190829,0.003680247],"genre_scores_gemma":[0.2272924,0.000004462285,0.7674062,0.0001494522,0.0007297553,0.00006632816,0.0004591194,0.00007353775,0.003818673],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7193289,"threshold_uncertainty_score":0.9999462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2910159406","doi":"10.3390/jrfm12010017","title":"Trend Prediction Classification for High Frequency Bitcoin Time Series with Deep Learning","year":2019,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Time series; Series (stratigraphy); Machine learning; Cryptocurrency; Deep learning; Baseline (sea); Classifier (UML); Profit (economics); Econometrics; Odds; Mathematics; Logistic regression; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.02576748199051209,"gpt":0.2906265897207604,"spread":0.2648591077302483,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003618092,0.000104322,0.0002575573,0.0003553719,0.0001663444,0.0001160213,0.0001877821,0.00005020606,0.00005956316],"category_scores_gemma":[0.001086525,0.0000695945,0.00006831178,0.0003854152,0.00004062065,0.0003860506,0.00003974009,0.000163544,0.00001199068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003810495,"about_ca_system_score_gemma":0.00001813829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003668165,"about_ca_topic_score_gemma":0.00001256215,"domain_scores_codex":[0.9983582,0.0001820109,0.0005399007,0.0002117369,0.000563285,0.0001448011],"domain_scores_gemma":[0.998295,0.0005481173,0.0007891182,0.0001528225,0.0001622812,0.0000526751],"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":[0.0005663825,0.00002900643,0.095002,0.00001539204,0.00001928742,0.000005582784,0.0003248886,0.0003490609,0.0000880452,0.004093918,0.0004830321,0.8990234],"study_design_scores_gemma":[0.00130865,0.001311288,0.9082066,0.00007149792,0.0001107043,0.00003446279,0.0006172932,0.001519963,0.00003637839,0.03753253,0.0491186,0.000132037],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6733208,0.0001389643,0.323496,0.0001437235,0.0005795601,0.0002993817,0.00001126629,0.00001472056,0.001995691],"genre_scores_gemma":[0.8957728,0.0001606575,0.1015313,0.00001829029,0.0002316237,0.00000962021,0.000002872742,0.00001220712,0.002260583],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8988914,"threshold_uncertainty_score":0.2837981,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2899037356","doi":"10.5539/mas.v12n11p309","title":"ARIMA Model in Predicting Banking Stock Market Data","year":2018,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Autoregressive integrated moving average; Econometrics; Stock market; Autoregressive model; Time series; Stock (firearms); Computer science; Moving average; Economics; Machine learning; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.256433715932613,"gpt":0.4345700944942127,"spread":0.1781363785615996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03834428,0.0002671819,0.0003952615,0.000902763,0.0008055664,0.0007504321,0.007910218,0.0001032432,0.0003012687],"category_scores_gemma":[0.0109282,0.0002234948,0.00003958985,0.003854482,0.001575325,0.001220306,0.003982006,0.0003809912,0.00009658844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001888952,"about_ca_system_score_gemma":0.0006526641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003629445,"about_ca_topic_score_gemma":0.000145896,"domain_scores_codex":[0.9917744,0.0001904447,0.0009382279,0.002351001,0.003714067,0.001031794],"domain_scores_gemma":[0.9934325,0.001928679,0.0003860901,0.003642191,0.0003565074,0.0002540302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000222619,0.0001077337,0.02853832,0.000008681107,0.000005979602,0.000007807948,0.004208702,0.005404133,0.07542037,0.00275567,0.004750113,0.8785698],"study_design_scores_gemma":[0.0002470117,0.00001954494,0.01247493,0.00001710983,0.000003979835,0.000008025604,0.0001128956,0.860113,0.0006163508,0.1259157,0.0002498608,0.000221607],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1387337,0.00001333783,0.6485626,0.000101054,0.0003269266,0.0003060396,0.00001703028,0.00009474494,0.2118446],"genre_scores_gemma":[0.8269151,6.816264e-7,0.1719237,0.0002268924,0.0001434207,0.00002038868,0.000001398251,0.00002043654,0.0007479627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8783482,"threshold_uncertainty_score":0.9974574,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890227220","doi":"10.1142/s021962201841002x","title":"A New Approach for Stock Price Analysis and Prediction Based on SSA and SVM","year":2018,"lang":"en","type":"article","venue":"International Journal of Information Technology & Decision Making","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"National Natural Science Foundation of China","keywords":"Adaptive neuro fuzzy inference system; Support vector machine; Singular spectrum analysis; Hilbert–Huang transform; Computer science; Econometrics; Stock price; Stock (firearms); Artificial intelligence; Stock market; Time series; Data mining; Pattern recognition (psychology); Machine learning; Fuzzy logic; Series (stratigraphy); Economics; Singular value decomposition; Fuzzy control system; White noise; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04804812834144129,"gpt":0.4002494417166428,"spread":0.3522013133752016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005478853,0.0001443933,0.0003325692,0.005884266,0.0001697494,0.0003931045,0.0008352368,0.0001995286,0.0001092078],"category_scores_gemma":[0.01938417,0.0001093993,0.0001461571,0.001658462,0.0001177343,0.001122337,0.0001773419,0.0002408452,0.000007869235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001026749,"about_ca_system_score_gemma":0.0001171133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001567418,"about_ca_topic_score_gemma":0.00000185503,"domain_scores_codex":[0.9966711,0.00008101722,0.001359826,0.0002255934,0.001505551,0.0001568754],"domain_scores_gemma":[0.9928542,0.002762752,0.001582367,0.0002843319,0.002433266,0.00008303641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000743703,0.00001817334,0.0155773,0.000001869314,0.0001484462,0.000001072331,0.0001748717,0.001661507,0.0000350168,0.001528868,0.002469806,0.9776394],"study_design_scores_gemma":[0.002178598,0.0007220365,0.0628745,0.0001450383,0.0001649532,0.0002927895,0.0005959711,0.8392707,0.0004888694,0.0784023,0.01467265,0.0001915953],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05424567,0.00002251282,0.9426658,0.0007104726,0.000561962,0.0001758941,0.00001742724,0.00003404992,0.00156623],"genre_scores_gemma":[0.5104447,0.000004012989,0.4891563,0.0002408972,0.0001143401,0.000004260485,0.000002211095,0.00000405006,0.00002919595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9774477,"threshold_uncertainty_score":0.988876,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104024060","doi":"","title":"IS STOCK RETURN PREDICTABILITY SPURIOUS","year":2003,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Spurious relationship; Predictability; Econometrics; Stock (firearms); Dividend yield; Dividend; Regression; Regression analysis; Variable (mathematics); Stock market; Computer science; Economics; Statistics; Mathematics; Machine learning; Finance; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.068509761971321,"gpt":0.3830834612397569,"spread":0.3145736992684359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05205953,0.0002767218,0.0004519895,0.000338813,0.0005173445,0.0003065105,0.001252213,0.0001712515,0.001285493],"category_scores_gemma":[0.02526763,0.0002039821,0.0003742496,0.001143095,0.0001524748,0.0003848071,0.00009538611,0.002980218,0.0001708387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116377,"about_ca_system_score_gemma":0.00391274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002211443,"about_ca_topic_score_gemma":0.0002123786,"domain_scores_codex":[0.9903013,0.002310905,0.001122237,0.0007043703,0.002244528,0.00331663],"domain_scores_gemma":[0.9955313,0.002038469,0.0005935921,0.0009840273,0.0005643886,0.0002882291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002875568,0.000241874,0.4458572,0.000005484963,0.0002425658,0.0000203354,0.001194205,0.00004264629,0.0004172461,0.06114873,0.01238557,0.4781566],"study_design_scores_gemma":[0.0006646689,0.0003905036,0.01271427,0.000009703495,0.00002833613,0.00195789,0.0009672962,0.0003094567,0.000284135,0.949883,0.03254066,0.0002500429],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8468168,0.002832554,0.1170708,0.001323167,0.001597926,0.0003453149,0.000006947974,0.00009039983,0.02991604],"genre_scores_gemma":[0.9817837,0.0002094885,0.004654015,0.000264412,0.0002751481,0.0000067074,3.424907e-7,0.00003369405,0.01277245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8887343,"threshold_uncertainty_score":0.9996275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399381752","doi":"10.1016/j.knosys.2024.112026","title":"Forecasting bitcoin: Decomposition aided long short-term memory based time series modeling and its explanation with Shapley values","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Science Fund of the Republic of Serbia","keywords":"Term (time); Series (stratigraphy); Decomposition; Computer science; Chemistry; Geology; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1206324377903339,"gpt":0.3751820788323812,"spread":0.2545496410420474,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008786244,0.000488023,0.0007095772,0.001204866,0.000522389,0.001416976,0.0004856494,0.0002083926,0.00009304597],"category_scores_gemma":[0.00187704,0.0003707651,0.000163447,0.001457425,0.00009975276,0.001019769,0.0001016923,0.0002987152,0.0001271169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002410735,"about_ca_system_score_gemma":0.0004196682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002245839,"about_ca_topic_score_gemma":0.00008526933,"domain_scores_codex":[0.9942994,0.001393439,0.001220523,0.001215446,0.001330823,0.000540401],"domain_scores_gemma":[0.9931383,0.004853924,0.0002376902,0.0005750162,0.0009348329,0.0002602767],"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":[0.002547442,0.0004631385,0.02230134,0.005498581,0.0005411014,0.0009443709,0.008317328,0.7116844,0.02906414,0.0009203933,0.004462382,0.2132554],"study_design_scores_gemma":[0.0004951109,0.0002429348,0.0002766564,0.002283737,0.00008475479,0.0001763477,0.0003374309,0.9914782,0.003806348,0.0002711831,0.00007918758,0.0004680843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6240763,0.003649343,0.3651165,0.0001174972,0.001408957,0.0009659627,0.00004308435,0.0005026289,0.004119698],"genre_scores_gemma":[0.9913821,0.000002188638,0.006613838,0.00001915572,0.0004650266,0.0001703957,0.00005740081,0.00009214781,0.001197702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3673058,"threshold_uncertainty_score":0.9998744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2007398915","doi":"10.1016/j.jbankfin.2012.09.012","title":"Fuzzy logic, trading uncertainty and technical trading","year":2012,"lang":"en","type":"article","venue":"Journal of Banking & Finance","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Technical analysis; Pairs trade; Trading strategy; Imperfect; Economics; Fuzzy logic; Volatility (finance); Algorithmic trading; Order (exchange); Alternative trading system; Econometrics; Liberian dollar; Moving average; High-frequency trading; Financial economics; Computer science; Finance; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1255683456633481,"gpt":0.3933363138234955,"spread":0.2677679681601474,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01658189,0.0001827399,0.0005591655,0.0003689798,0.0002345946,0.0001676435,0.0006834679,0.0001258547,0.00009751747],"category_scores_gemma":[0.009179825,0.000129907,0.0002047605,0.0007583196,0.0001585194,0.0007619574,0.0001081793,0.0005798784,0.000005351396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001230246,"about_ca_system_score_gemma":0.00007288433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002891502,"about_ca_topic_score_gemma":0.000001349163,"domain_scores_codex":[0.9966056,0.0003966508,0.001123914,0.0002532549,0.001139072,0.0004815411],"domain_scores_gemma":[0.994234,0.003923504,0.001158533,0.0003036898,0.0002319491,0.0001483256],"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":[0.000274235,0.0001533186,0.1148233,0.00001838632,0.00003680723,0.00008594273,0.001692873,0.0003179697,0.008061412,0.02648892,0.01169366,0.8363532],"study_design_scores_gemma":[0.001155574,0.0005019973,0.5176359,0.0005325009,0.00008138567,0.006363825,0.0003198305,0.003209281,0.0009872131,0.4252218,0.04341023,0.0005803995],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9357601,0.002948606,0.0390652,0.0007326023,0.001554138,0.00009856986,0.000001937659,0.00002483732,0.01981399],"genre_scores_gemma":[0.9075299,0.00005441886,0.09157113,0.0001458106,0.0005636479,0.000001475026,7.267023e-8,0.00001387293,0.0001196876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8357728,"threshold_uncertainty_score":0.9991663,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062482216","doi":"10.14778/1920841.1921029","title":"Efficient event processing through reconfigurable hardware for algorithmic trading","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Complex event processing; Computer science; Field-programmable gate array; Event (particle physics); Reconfigurable computing; Latency (audio); Predicate (mathematical logic); Computer architecture; Embedded system; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08710940498047279,"gpt":0.380379721870738,"spread":0.2932703168902653,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006991785,0.0002866516,0.0004857981,0.0001823237,0.0005332524,0.0002957467,0.001740688,0.0001207295,0.0001613202],"category_scores_gemma":[0.008377729,0.0001777554,0.000382592,0.0009107735,0.0001886788,0.0002266975,0.0002118499,0.0003796339,0.000009192263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001005258,"about_ca_system_score_gemma":0.0001184116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002506956,"about_ca_topic_score_gemma":0.000004025419,"domain_scores_codex":[0.9960667,0.00003215148,0.001047879,0.0007528258,0.001527404,0.0005729718],"domain_scores_gemma":[0.9964527,0.0009868324,0.001052014,0.0003644038,0.001029176,0.0001148304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002470939,0.0003696104,0.003053224,0.0002868286,0.00007476748,5.139414e-7,0.005903652,0.0004612123,0.3290238,0.009108699,0.01542735,0.6360433],"study_design_scores_gemma":[0.001969511,0.0002890014,0.002422636,0.0004802834,0.0001354803,0.0000873399,0.003023704,0.1204725,0.6546086,0.146158,0.06965794,0.0006950006],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986805,0.0002393785,0.01875936,0.00348266,0.004084335,0.003586687,0.00005026119,0.0001749992,0.07094179],"genre_scores_gemma":[0.9048616,0.000001888772,0.0926347,0.0001091174,0.0002545849,0.000265779,5.057509e-7,0.00003756405,0.001834302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6353483,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2896262751","doi":"10.1109/fuzz-ieee.2018.8491523","title":"Fuzzy Logic-Based Data Analytics on Predicting the Effect of Hurricanes on the Stock Market","year":2018,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stock market; Big data; Stock exchange; Profit (economics); Stock (firearms); Market maker; Stock market bubble; Computer science; Analytics; Fuzzy logic; Business; Financial economics; Data science; Economics; Finance; Data mining; Artificial intelligence; Microeconomics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2509882350628654,"gpt":0.4415236796144294,"spread":0.190535444551564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03641781,0.000237335,0.0003845093,0.0001997322,0.0004426951,0.0001755425,0.003996569,0.0000811756,0.001576489],"category_scores_gemma":[0.09553882,0.00008609432,0.0001316135,0.001417936,0.0006094417,0.00009141802,0.0006509669,0.0002912072,0.0001044786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002831483,"about_ca_system_score_gemma":0.00007158114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005177491,"about_ca_topic_score_gemma":0.00004067621,"domain_scores_codex":[0.9926301,0.003630181,0.0006565187,0.0007088197,0.002032608,0.0003418345],"domain_scores_gemma":[0.9120055,0.08337034,0.0004940607,0.003798826,0.0002588962,0.00007241307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00199447,0.0001158203,0.1309292,0.00002074069,0.0001273055,0.00000632768,0.0002051461,0.0007884607,0.0001800178,0.003103471,0.5147167,0.3478124],"study_design_scores_gemma":[0.001470843,0.009166431,0.1388135,0.0002192729,0.0002490588,0.00001604849,0.0007782676,0.7916812,0.009802802,0.01922376,0.02799538,0.0005834259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4092289,0.00002789689,0.01348637,0.004681519,0.001099366,0.00113122,0.0001005619,0.0001216959,0.5701225],"genre_scores_gemma":[0.9917184,8.622808e-7,0.004000086,0.001116065,0.0003126289,0.0000147656,0.000003101567,0.0000188189,0.002815339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7908928,"threshold_uncertainty_score":0.9993362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3007471723","doi":"10.1109/bigdata47090.2019.9006554","title":"KryptoOracle: A Real-Time Cryptocurrency Price Prediction Platform Using Twitter Sentiments","year":2019,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cryptocurrency; Computer science; Sentiment analysis; SPARK (programming language); Big data; Social media; Volume (thermodynamics); Database transaction; Variety (cybernetics); Machine learning; Data science; Data mining; Artificial intelligence; Computer security; Database; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1319082240168736,"gpt":0.4060884385136096,"spread":0.274180214496736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005335307,0.0002667721,0.0004170419,0.0004894017,0.0001796564,0.0003502158,0.000735405,0.0001596403,0.01667043],"category_scores_gemma":[0.00184963,0.000198932,0.0001729143,0.00137026,0.00005795402,0.001016544,0.0003744591,0.000213574,0.005617153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001568105,"about_ca_system_score_gemma":0.0001015583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006871639,"about_ca_topic_score_gemma":8.438379e-7,"domain_scores_codex":[0.9953429,0.00022179,0.0009757536,0.0008706436,0.002050484,0.0005384383],"domain_scores_gemma":[0.996169,0.001750249,0.0004606326,0.001040896,0.0003875468,0.0001916501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005354476,0.0004903174,0.492806,0.00005311092,0.0002026071,0.00001682221,0.002194203,0.00115302,0.165059,0.001308742,0.1025173,0.2336634],"study_design_scores_gemma":[0.003306888,0.0005806692,0.313923,0.0002399301,0.0001109268,0.0001335241,0.0008950229,0.5900697,0.01217984,0.05068928,0.02644622,0.00142495],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8073025,0.000006901349,0.02744764,0.00005018084,0.001386624,0.0005447572,0.000009958775,0.000185497,0.163066],"genre_scores_gemma":[0.6580227,0.000007055349,0.2622108,0.0003363,0.0004895899,0.00003046205,0.00001761161,0.00009259681,0.07879293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5889167,"threshold_uncertainty_score":0.9951571,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4289225573","doi":"10.1007/s40745-022-00432-6","title":"Forecasting Directional Movement of Stock Prices using Deep Learning","year":2022,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Stock market; Computer science; Deep learning; Artificial intelligence; Stock market prediction; Word2vec; Machine learning; Stock (firearms); Sentiment analysis; Binary classification; Econometrics; Support vector machine; Economics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.609124789376396,"gpt":0.5163442024371268,"spread":0.09278058693926927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03551867,0.0001206024,0.0003049671,0.0007205129,0.001002682,0.0001090875,0.004279354,0.00001793784,0.0005330131],"category_scores_gemma":[0.02415333,0.000106064,0.00007007003,0.00429244,0.000600697,0.001832032,0.00497979,0.0002221691,0.000001511491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003906317,"about_ca_system_score_gemma":0.000359566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001911508,"about_ca_topic_score_gemma":0.00001134747,"domain_scores_codex":[0.9931129,0.000461034,0.0009026147,0.0008662941,0.004237912,0.0004193028],"domain_scores_gemma":[0.9937217,0.002974151,0.001217216,0.00117126,0.0008049736,0.0001106664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001108544,0.0002014642,0.08964239,0.00002107399,0.0000291141,0.000005521533,0.001320243,0.07717986,0.0357974,0.0009731023,0.0008432002,0.7938758],"study_design_scores_gemma":[0.0001568708,0.000297523,0.03190312,0.00003288119,0.00001124485,0.00002858115,0.002036156,0.9414012,0.0116208,0.006838891,0.005456664,0.0002160582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9467461,0.0002603604,0.04678619,0.0001753328,0.0005572816,0.000199832,0.0001319504,0.00002266609,0.005120267],"genre_scores_gemma":[0.8796946,0.000005660424,0.1200111,0.0001022207,0.00004042004,0.000005549203,0.000007139396,0.000008339839,0.0001249926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8642213,"threshold_uncertainty_score":0.9931365,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224302811","doi":"10.3390/jrfm15050188","title":"Forecasting a Stock Trend Using Genetic Algorithm and Random Forest","year":2022,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Random forest; Stock (firearms); Stock market index; Classifier (UML); Computer science; Econometrics; Artificial intelligence; Data mining; Stock market; Economics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.07355580097656854,"gpt":0.3339804228058774,"spread":0.2604246218293088,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006705356,0.000146843,0.0004122952,0.0006214817,0.0006652137,0.0001605662,0.0003240249,0.00002877826,0.00004671866],"category_scores_gemma":[0.001633478,0.0001161299,0.0001310715,0.0006361938,0.00007092973,0.0001477587,0.0005760097,0.0002995381,2.578452e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005732651,"about_ca_system_score_gemma":0.00003538327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002729722,"about_ca_topic_score_gemma":0.00001264176,"domain_scores_codex":[0.9971139,0.0005097868,0.0008380789,0.0002724988,0.001018746,0.0002470114],"domain_scores_gemma":[0.9976186,0.001099438,0.0008969309,0.0001762501,0.000092029,0.0001167513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002402297,0.0000286778,0.02174662,0.000005902709,0.00001500816,0.0001721175,0.0005054155,0.003647978,0.000001540577,0.00005227072,0.0003975735,0.9731867],"study_design_scores_gemma":[0.007747726,0.001081976,0.3646296,0.00008720684,0.000424064,0.001959056,0.002602037,0.4089616,0.000004549308,0.08666068,0.1253619,0.000479558],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5065076,0.001077923,0.4913512,0.00002190326,0.0005933017,0.0001516388,0.00001291097,0.000004011148,0.0002795011],"genre_scores_gemma":[0.5770715,0.000253544,0.4220151,0.00007124439,0.000350859,0.000009270513,3.522916e-7,0.00001853102,0.0002096409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9727071,"threshold_uncertainty_score":0.5116353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098806386","doi":"10.1002/for.986","title":"Non‐linear, non‐parametric, non‐fundamental exchange rate forecasting","year":2006,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Bank of Canada; Lakehead University","funders":"University of British Columbia; Lakehead University","keywords":"Random walk; Mean squared error; Linear model; Exchange rate; Parametric statistics; Mathematics; Econometrics; Statistics; Computer science; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.1667260819266446,"gpt":0.3864074929030265,"spread":0.2196814109763819,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02667341,0.0006524907,0.001481877,0.002433702,0.0007098903,0.000721356,0.001842867,0.0002912585,0.0005062389],"category_scores_gemma":[0.02098538,0.0005072031,0.0009304675,0.004173057,0.000232982,0.001400331,0.0005711314,0.00118745,0.00009783766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003947689,"about_ca_system_score_gemma":0.0003362256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001359122,"about_ca_topic_score_gemma":0.00006148523,"domain_scores_codex":[0.9901366,0.0005997885,0.003995101,0.0008328951,0.003128791,0.001306779],"domain_scores_gemma":[0.9829635,0.008981432,0.005091217,0.0007471831,0.001739373,0.0004773199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001061748,0.0005811527,0.1774347,0.0001540902,0.0002401697,0.001793469,0.001770049,0.03327526,0.008517159,0.00004038524,0.04559403,0.7295378],"study_design_scores_gemma":[0.00496105,0.001729014,0.06294987,0.0009344164,0.0002388367,0.005227418,0.001734445,0.8886695,0.008722804,0.01051473,0.01298265,0.001335267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8722522,0.000267112,0.1016999,0.0002150826,0.003093243,0.0004248553,0.00001764686,0.00004053879,0.02198941],"genre_scores_gemma":[0.8496812,0.000007799463,0.1448139,0.0001516654,0.002668124,0.00001019538,0.000003699902,0.00009255012,0.002570919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8553942,"threshold_uncertainty_score":0.999738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3096794928","doi":"10.1002/spe.2915","title":"A graph‐based convolutional neural network stock price prediction with leading indicators","year":2020,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Stock market; Convolutional neural network; Stock (firearms); Artificial neural network; Futures contract; Trading strategy; Machine learning; Artificial intelligence; Finance; Economics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09107486337675993,"gpt":0.3796336706920618,"spread":0.2885588073153018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001871951,0.0002138022,0.0002768647,0.0001564537,0.0005702609,0.0003403191,0.0004525761,0.00009151799,0.0001437628],"category_scores_gemma":[0.03007995,0.0001630485,0.00005787144,0.002300198,0.0003621223,0.001694572,0.0001525276,0.0003753505,0.00002268507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000335616,"about_ca_system_score_gemma":0.0001558564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001720582,"about_ca_topic_score_gemma":0.000002344764,"domain_scores_codex":[0.9963185,0.0005936966,0.000468708,0.0008032617,0.001398834,0.0004169738],"domain_scores_gemma":[0.9912012,0.007294611,0.0005140873,0.0003314906,0.0002982399,0.000360421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002970744,0.0001318786,0.7584493,0.00003425706,0.00007058409,0.0001093861,0.02553181,0.01126096,0.0001950444,0.0006663799,0.01260362,0.1879761],"study_design_scores_gemma":[0.005031643,0.004998395,0.3792056,0.0003279022,0.0003260639,0.001114434,0.04184399,0.1764671,0.0007027278,0.004729214,0.382724,0.002529002],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4249216,0.0005656321,0.5688404,0.003228837,0.0004729793,0.0004164385,0.00001461792,0.0003152494,0.001224233],"genre_scores_gemma":[0.8627651,0.00000746182,0.1336658,0.003172585,0.0002357399,0.00007218265,0.000003622011,0.00001847469,0.00005903678],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4378434,"threshold_uncertainty_score":0.9780901,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2898909450","doi":"10.5539/mas.v12n11p181","title":"Predicting Closed Price Time Series Data Using ARIMA Model","year":2018,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Autoregressive integrated moving average; Econometrics; Time series; Autoregressive model; Computer science; Series (stratigraphy); Stock exchange; Moving average; Economics; Finance; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.2569002962247076,"gpt":0.4284299615374034,"spread":0.1715296653126959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.02103082,0.0002833082,0.0003970468,0.0004863599,0.001604246,0.0009981352,0.006742373,0.0001009847,0.0001505356],"category_scores_gemma":[0.008487377,0.0002308982,0.00004578879,0.003070611,0.00242735,0.001976602,0.003788867,0.0002548136,0.000311767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001540476,"about_ca_system_score_gemma":0.0008993955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002063136,"about_ca_topic_score_gemma":0.00001128545,"domain_scores_codex":[0.9924819,0.0001411649,0.0007871386,0.002094212,0.003566351,0.0009292001],"domain_scores_gemma":[0.9939548,0.001024698,0.0004899435,0.003573869,0.0006431155,0.0003136197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001474794,0.00005325233,0.001251483,0.000005223293,0.00000838415,0.00000295777,0.002541183,0.007374226,0.8879799,0.00172024,0.0007819014,0.09813382],"study_design_scores_gemma":[0.000167885,0.00002821119,0.0007187141,0.00001161598,0.00001045466,0.00002261941,0.00009757781,0.9195244,0.008091648,0.07077775,0.0002938692,0.0002552358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2284914,0.000009903705,0.7024089,0.00008095682,0.0002774899,0.0002775191,0.00002977294,0.0001615392,0.06826253],"genre_scores_gemma":[0.6444548,3.367265e-7,0.354162,0.0001486505,0.0001893397,0.00000576445,0.000001934701,0.00002108958,0.001015979],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9121502,"threshold_uncertainty_score":0.9998646,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3006726006","doi":"10.1109/bigdata47090.2019.9006342","title":"Stock Prediction using Deep Learning and Sentiment Analysis","year":2019,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Stock market; Computer science; Sentiment analysis; Stock (firearms); Stock market prediction; Econometrics; Artificial intelligence; Deep learning; Predictive power; Machine learning; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.09282569742488601,"gpt":0.4124607944035287,"spread":0.3196350969786427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00467136,0.00009618813,0.0002566561,0.000559143,0.0001361594,0.0001984442,0.0001493697,0.00005263929,0.002945646],"category_scores_gemma":[0.001543185,0.00007092231,0.0001111269,0.001587533,0.00002866811,0.0001976345,0.0001661688,0.0001141634,0.00008017469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003878046,"about_ca_system_score_gemma":0.00001296936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003998171,"about_ca_topic_score_gemma":0.00001194761,"domain_scores_codex":[0.9976705,0.0004643649,0.0003779559,0.0004602136,0.0008468002,0.000180188],"domain_scores_gemma":[0.997937,0.001385118,0.0001732545,0.0002793494,0.0001427805,0.00008250371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000120941,0.000007273406,0.8920739,0.000001185946,0.00009261542,5.411836e-7,0.0001537415,0.009204973,0.001074252,0.00004284396,0.00003489719,0.09730168],"study_design_scores_gemma":[0.0001421813,0.00004049472,0.2299165,0.000003092439,0.0001280816,0.000006133022,0.000425519,0.7667966,0.0001783412,0.0005637489,0.001721015,0.00007827277],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.729431,0.00003731509,0.257399,0.00002104053,0.0001821633,0.0001049988,6.222905e-7,0.00004324764,0.01278061],"genre_scores_gemma":[0.9322116,0.000001520207,0.05729145,0.00002332675,0.00003081694,0.000001660964,9.064528e-7,0.000006845632,0.01043182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7575916,"threshold_uncertainty_score":0.9979658,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367693552","doi":"10.1093/jcde/qwad039","title":"Hybrid neural network-based metaheuristics for prediction of financial markets: a case study on global gold market","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Design and Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Metaheuristic; Firefly algorithm; Artificial neural network; Computer science; Hyperparameter; Novelty; Artificial intelligence; Machine learning; Convolutional neural network; Particle swarm optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.09818076663270471,"gpt":0.3518817096107613,"spread":0.2537009429780566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007978516,0.0001368316,0.0003520286,0.0003204384,0.00007093391,0.00007216656,0.0001701848,0.00003476553,0.000006347536],"category_scores_gemma":[0.006729967,0.0001133588,0.0001326378,0.0006237518,0.00002213609,0.0001125934,0.00003082472,0.0001267427,4.516183e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004395278,"about_ca_system_score_gemma":0.0001154556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.533329e-7,"about_ca_topic_score_gemma":1.536436e-7,"domain_scores_codex":[0.9976453,0.0003316688,0.0008559775,0.0001705043,0.0008130971,0.0001834669],"domain_scores_gemma":[0.9891748,0.009716234,0.0004030994,0.00009708541,0.0005060104,0.0001027019],"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":[0.0005202452,0.00004868225,0.002053237,0.00001461754,0.00003835107,0.0003504929,0.00003530125,0.9652987,0.000008123339,0.00006117992,0.01166734,0.01990378],"study_design_scores_gemma":[0.0009674609,0.000699633,0.1335715,0.00004062333,0.00004738176,0.0008032637,0.00003335557,0.8580883,0.000004875164,0.005529225,0.0001441806,0.00007027613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3714685,0.00003086991,0.6275567,0.00003657947,0.0006385874,0.0001968773,0.0000400555,0.00001649219,0.00001538884],"genre_scores_gemma":[0.8628194,0.000001015028,0.1368846,0.00002398416,0.0002340717,0.000006819261,0.000001621151,0.00001052619,0.00001789738],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.491351,"threshold_uncertainty_score":0.8056886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}