{"meta":{"query_hash":"48d19ed0378d","filters":{"venue":"Journal of Machine Learning Research"},"cohort_total":12,"direct_labels_cover":0,"predictions_cover":12,"exported":12,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/48d19ed0378d","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Machine+Learning+Research"},"results":[{"id":"W2126046032","doi":"","title":"SPMF: a Java open-source pattern mining library","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":417,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Java; Source code; License; Interface (matter); MIT License; Open source; Documentation; Database transaction; Implementation; Data mining; Database; Programming language; Information retrieval; World Wide Web; Operating system; Software","score_opus":0.05115801282898343,"score_gpt":0.35700697144061744,"score_spread":0.305848958611634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126046032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09662678,0.00047233404,0.8714099,0.018650813,0.0002279282,0.00020037896,0.000004058285,0.00012008423,0.012287746],"genre_scores_gemma":[0.799513,0.00011947403,0.18957403,0.0004894206,0.00078910746,0.000010798018,0.000009761105,0.000054794644,0.009439611],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973193,0.00073221355,0.0004276059,0.00028515566,0.0008231597,0.00041258085],"domain_scores_gemma":[0.9977609,0.0009889345,0.00028560197,0.0005058801,0.00021174285,0.000246937],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005018271,0.00011459298,0.0002462483,0.00039199536,0.000451391,0.0013781327,0.0037381058,0.0000542594,0.00010446294],"category_scores_gemma":[0.00079925545,0.00009259699,0.00007156381,0.0007593492,0.000067893605,0.0013610139,0.002111179,0.0013944047,0.00010071363],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010617446,0.00009738193,0.0127011305,0.000013945912,0.000021477019,0.00003078669,0.00086781225,0.00039873898,0.00024456772,0.001093274,0.014796326,0.96972394],"study_design_scores_gemma":[0.00060019916,0.0006044717,0.005083202,0.00013870826,0.000003883837,0.0002117979,0.00013030581,0.42267525,0.0002204645,0.00062298885,0.56956464,0.0001440724],"about_ca_topic_score_codex":0.0000921299,"about_ca_topic_score_gemma":0.000002911434,"teacher_disagreement_score":0.9695799,"about_ca_system_score_codex":0.000025971634,"about_ca_system_score_gemma":0.00015350823,"threshold_uncertainty_score":0.9996585},"labels":[],"label_agreement":null},{"id":"W2146250995","doi":"10.5555/2627435.2697064","title":"Recursive teaching dimension, VC-dimension and sample compression","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of Alberta","funders":"","keywords":"Dimension (graph theory); VC dimension; Intersection (aeronautics); Mathematics; Matching (statistics); Concept class; Class (philosophy); Bounded function; Sample (material); Theoretical computer science; Discrete mathematics; Computer science; Algorithm; Combinatorics; Artificial intelligence","score_opus":0.026932607691139716,"score_gpt":0.345164434175636,"score_spread":0.3182318264844963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146250995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5955049,0.0017299502,0.38992906,0.009969783,0.000737942,0.0002095333,0.0000012590002,0.000147422,0.0017701982],"genre_scores_gemma":[0.9018227,0.00011714257,0.09698966,0.00012293668,0.00039226352,0.0000013052916,0.0000022245958,0.000025302905,0.00052647496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939112,0.0032679576,0.00051722693,0.0003900715,0.0013753792,0.0005381677],"domain_scores_gemma":[0.9941788,0.0041129747,0.0004136602,0.0003822812,0.00056687795,0.00034542746],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011154839,0.00019679498,0.00040067747,0.00065611856,0.0010830633,0.0003269939,0.0008330618,0.00010527714,0.000027803471],"category_scores_gemma":[0.006953037,0.00014597859,0.00010272461,0.0003838959,0.00011500514,0.00046902135,0.0007943188,0.004100969,0.000020890764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024092376,0.00037474572,0.05462037,0.00013301229,0.00010193191,0.00016870002,0.007592945,0.0144733675,0.01606786,0.020864788,0.0068280557,0.8785333],"study_design_scores_gemma":[0.0018670213,0.002812125,0.012080247,0.00064155326,0.000016040462,0.0006498626,0.00023728357,0.8718269,0.00082828454,0.014027052,0.09462915,0.00038446733],"about_ca_topic_score_codex":0.0003491336,"about_ca_topic_score_gemma":0.000004333811,"teacher_disagreement_score":0.87814885,"about_ca_system_score_codex":0.000060788116,"about_ca_system_score_gemma":0.0000738665,"threshold_uncertainty_score":0.9981966},"labels":[],"label_agreement":null},{"id":"W2159136633","doi":"10.5555/2627435.2750354","title":"Efficient learning and planning with compressed predictive states","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Observable; A priori and a posteriori; Dimensionality reduction; Machine learning; Curse of dimensionality","score_opus":0.0249183959460578,"score_gpt":0.331304983517485,"score_spread":0.30638658757142717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159136633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18937214,0.0003850899,0.80815166,0.00047339028,0.00008708872,0.000105578954,1.394694e-7,0.000062026964,0.0013628802],"genre_scores_gemma":[0.9846391,0.000052986285,0.014525572,0.000024906052,0.00014870182,0.000002234473,0.0000015108037,0.000025651465,0.0005793448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957034,0.001343142,0.00044258544,0.00029488566,0.0016455492,0.000570457],"domain_scores_gemma":[0.9959605,0.0022366897,0.00045583717,0.00021064423,0.00088193244,0.00025442013],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0058949534,0.00018196643,0.00034164297,0.0006333191,0.00062055833,0.0004457496,0.00073786924,0.00006792065,0.000013938108],"category_scores_gemma":[0.0021851074,0.00013327216,0.00005125783,0.00058615755,0.00020476486,0.00022323005,0.00047032477,0.0031186072,0.000009896463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013151037,0.000027168242,0.056979213,0.0000376587,0.0000519098,0.00005595272,0.0025308647,0.9361988,0.00026034296,0.00047113342,0.00006811733,0.0031873756],"study_design_scores_gemma":[0.0010115352,0.0029844635,0.007667805,0.0002789267,0.00000966031,0.00015179154,0.00046110046,0.9808924,0.0001317663,0.00008085598,0.0061861984,0.00014349236],"about_ca_topic_score_codex":0.000022216396,"about_ca_topic_score_gemma":4.2095107e-7,"teacher_disagreement_score":0.795267,"about_ca_system_score_codex":0.000080681,"about_ca_system_score_gemma":0.00010767062,"threshold_uncertainty_score":0.9991812},"labels":[],"label_agreement":null},{"id":"W2185184584","doi":"","title":"A characterization of linkage-based hierarchical clustering","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Linkage (software); Hierarchical clustering of networks; Hierarchical clustering; Computer science; Class (philosophy); Cluster analysis; Complete linkage; Locality; Hierarchical database model; Mathematics; Artificial intelligence; Algorithm; Data mining; Canopy clustering algorithm; Correlation clustering","score_opus":0.04192133453023034,"score_gpt":0.3573990556538818,"score_spread":0.31547772112365147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185184584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21194491,0.00006394974,0.78357786,0.0040692952,0.000116147734,0.00009692478,0.0000018956398,0.000029375036,0.00009963896],"genre_scores_gemma":[0.9575171,0.00010857504,0.041386675,0.000022706112,0.00021264331,0.000004225592,0.0000010153889,0.000025472938,0.00072159275],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955961,0.0011174718,0.00063685124,0.0002640732,0.0018398977,0.00054556684],"domain_scores_gemma":[0.99632674,0.0014913881,0.00037424781,0.00041085258,0.0011566627,0.0002401183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005287281,0.00012969661,0.0003198446,0.0010326977,0.00018597177,0.00010631195,0.0014750268,0.000090248315,0.000050257826],"category_scores_gemma":[0.0026816074,0.00008555382,0.00012683873,0.0009162197,0.00020102915,0.0006055057,0.00065356283,0.0014144495,0.000020342703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020559455,0.00012101756,0.00348348,0.000092199836,0.000028421302,0.00013946946,0.00029935784,0.002284849,0.66111326,0.00028286845,0.000011061367,0.33193845],"study_design_scores_gemma":[0.004362864,0.0038728095,0.024978997,0.0015202075,0.0000074678314,0.00035736876,0.000028709967,0.8356362,0.11714706,0.001535756,0.010155603,0.0003969591],"about_ca_topic_score_codex":0.000011197745,"about_ca_topic_score_gemma":0.0000021050867,"teacher_disagreement_score":0.8333514,"about_ca_system_score_codex":0.00017164726,"about_ca_system_score_gemma":0.0003522251,"threshold_uncertainty_score":0.61451584},"labels":[],"label_agreement":null},{"id":"W2397184916","doi":"","title":"Hybrid orthogonal projection and estimation (HOPE): a new framework to learn neural networks","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"MNIST database; Computer science; Artificial intelligence; TIMIT; Unsupervised learning; Projection (relational algebra); Artificial neural network; Machine learning; Feature (linguistics); Generative model; Pattern recognition (psychology); Generative grammar; Hidden Markov model; Algorithm","score_opus":0.048229047213752776,"score_gpt":0.353960200129276,"score_spread":0.3057311529155232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397184916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17960778,0.00017394213,0.80757844,0.012135012,0.00018786153,0.000109913286,3.0171546e-7,0.000035999117,0.00017077063],"genre_scores_gemma":[0.90351737,0.00011961072,0.09455599,0.0001594739,0.00045961133,0.0000046472874,3.500604e-7,0.000015179118,0.0011677518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976577,0.00063029985,0.00032600682,0.00022828099,0.0008154119,0.00034229094],"domain_scores_gemma":[0.9977841,0.0012637709,0.0001633901,0.00015824354,0.00030552008,0.00032496834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003099784,0.00010440782,0.0001831749,0.0005684133,0.00025900992,0.00031091383,0.00040549246,0.00006214664,0.00012108652],"category_scores_gemma":[0.0042818994,0.00006797117,0.000070155256,0.00049054716,0.000044152952,0.00054664415,0.00019840454,0.0010505798,0.000042785323],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009675166,0.000025054318,0.004252437,0.0000044027965,0.000014815485,0.000049470786,0.00014786016,0.0013498395,0.00023601219,0.00040233255,0.0011907243,0.9922303],"study_design_scores_gemma":[0.000784846,0.001424884,0.01575617,0.00039422774,0.000008919439,0.0013373055,0.000032471802,0.9597686,0.0006181842,0.006664558,0.012990078,0.00021979169],"about_ca_topic_score_codex":0.000034229317,"about_ca_topic_score_gemma":0.00000563678,"teacher_disagreement_score":0.99201053,"about_ca_system_score_codex":0.00007364948,"about_ca_system_score_gemma":0.00013007024,"threshold_uncertainty_score":0.51261425},"labels":[],"label_agreement":null},{"id":"W2465040775","doi":"10.5555/3122009.3122040","title":"Preference-based teaching","year":2017,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Class (philosophy); Mathematics; Dimension (graph theory); Closure (psychology); Preference; Operator (biology); Euclidean geometry; Discrete mathematics; Concept class; Algebra over a field; Combinatorics; Pure mathematics; Computer science; Artificial intelligence","score_opus":0.12414997380127998,"score_gpt":0.40135681010946644,"score_spread":0.27720683630818643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465040775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27701744,0.0014304048,0.61576766,0.04416674,0.0019636468,0.00034730192,0.000002263964,0.0002837362,0.059020817],"genre_scores_gemma":[0.9611134,0.000029585939,0.03518218,0.000055532582,0.00052510784,0.0000020762934,7.2749884e-7,0.000019679557,0.0030717272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99554825,0.0015045695,0.00045394414,0.0003008446,0.0016161031,0.0005762952],"domain_scores_gemma":[0.99662757,0.0008566614,0.0007083597,0.00092950027,0.00060143723,0.00027649518],"candidate_categories":["sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01212998,0.00016540854,0.00032549803,0.0005902577,0.0025161493,0.0015502122,0.0040072077,0.00009070366,0.00005967609],"category_scores_gemma":[0.007962771,0.00012596145,0.00017758775,0.00015875012,0.00015970111,0.0008243326,0.0006986922,0.005379361,0.00006701217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001174501,0.00034252513,0.14647599,0.000086119864,0.00008734466,0.0005943952,0.0012710048,0.010390099,0.0017796484,0.0104533415,0.004313689,0.8240884],"study_design_scores_gemma":[0.0018543168,0.0016787228,0.05339543,0.00035670365,0.000009866111,0.00022025585,0.00005218337,0.81298286,0.0006642715,0.0028015268,0.12566148,0.00032240144],"about_ca_topic_score_codex":0.00029545958,"about_ca_topic_score_gemma":0.000007688515,"teacher_disagreement_score":0.823766,"about_ca_system_score_codex":0.00008097903,"about_ca_system_score_gemma":0.00034352965,"threshold_uncertainty_score":0.99948627},"labels":[],"label_agreement":null},{"id":"W2490023472","doi":"10.5555/2946645.3007063","title":"Are random forests truly the best classifiers","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics; University of Toronto","funders":"","keywords":"Random forest; Support vector machine; Random subspace method; Artificial intelligence; Machine learning; Computer science; Classifier (UML); Artificial neural network; Pattern recognition (psychology); Data mining","score_opus":0.08091568562646898,"score_gpt":0.37147970277836134,"score_spread":0.2905640171518924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490023472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24702424,0.0028308132,0.56105477,0.18177529,0.0010155776,0.00044868494,0.0000066870066,0.00015379647,0.0056901365],"genre_scores_gemma":[0.99373513,0.00031644502,0.0012418138,0.00009478956,0.00038783002,0.0000061359615,9.166591e-7,0.000018598286,0.0041983156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950869,0.0021231894,0.00051665306,0.00028543404,0.0014877634,0.0005000231],"domain_scores_gemma":[0.9945799,0.0030918678,0.00076108595,0.0006452409,0.00071030686,0.00021156885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009731015,0.00014750316,0.00027251072,0.00047092236,0.0006662366,0.0003689397,0.0021730466,0.000087710694,0.00005798731],"category_scores_gemma":[0.008756197,0.00006847439,0.00016108903,0.0007111454,0.00022837555,0.0006363401,0.00036904513,0.0019067033,0.00020663849],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045575906,0.0001871516,0.42674804,0.000035232257,0.00010180802,0.00018527395,0.00070252345,0.0007787752,0.0033136802,0.007901537,0.012763452,0.5468268],"study_design_scores_gemma":[0.006458111,0.0014441638,0.35885665,0.0006174521,0.000030177001,0.0007393955,0.0006161663,0.0545474,0.0005055121,0.0067100474,0.56905216,0.00042275796],"about_ca_topic_score_codex":0.000047924495,"about_ca_topic_score_gemma":0.00004838485,"teacher_disagreement_score":0.7467109,"about_ca_system_score_codex":0.00011571961,"about_ca_system_score_gemma":0.0001851734,"threshold_uncertainty_score":0.9995935},"labels":[],"label_agreement":null},{"id":"W2586119848","doi":"","title":"Blending learning and inference in conditional random fields","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Conditional random field; Conditional probability distribution; Approximate inference; Artificial intelligence; Computer science; Machine learning; Random variable; Structured prediction; Set (abstract data type); Mathematics; Conditional probability; Exponential family; Algorithm; Statistics","score_opus":0.04452678542633241,"score_gpt":0.41504741736400536,"score_spread":0.37052063193767293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586119848","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06858215,0.00093209796,0.9273162,0.002493783,0.000041228766,0.00006912098,3.350304e-7,0.000033980647,0.0005311274],"genre_scores_gemma":[0.9888924,0.0016238918,0.008705841,0.000022641765,0.00007299629,0.0000021331994,2.7088225e-7,0.000006782934,0.00067308993],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997995,0.0006022983,0.00033045263,0.0001715598,0.0005994784,0.0003012074],"domain_scores_gemma":[0.9956856,0.0036366957,0.00016625566,0.00009201479,0.00031717497,0.000102302954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004025817,0.00008444914,0.00020580638,0.00058683887,0.00017442409,0.00011498046,0.00040836193,0.00006142072,0.00005418157],"category_scores_gemma":[0.007135104,0.000054681605,0.000045461496,0.00041704578,0.000100808575,0.0008432222,0.0002879553,0.0014520199,0.0000066907232],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034563587,0.00008318608,0.26211807,0.000046598692,0.000030093532,0.00050133374,0.00077547965,0.00057012076,0.024344556,0.010505659,0.00021725934,0.700462],"study_design_scores_gemma":[0.029299611,0.0125953145,0.13152418,0.005412842,0.000026605227,0.002226527,0.00066942273,0.10972839,0.11457518,0.40681505,0.1852461,0.0018807906],"about_ca_topic_score_codex":0.000013665228,"about_ca_topic_score_gemma":0.0000033811202,"teacher_disagreement_score":0.9203102,"about_ca_system_score_codex":0.00006676032,"about_ca_system_score_gemma":0.00009794442,"threshold_uncertainty_score":0.8541902},"labels":[],"label_agreement":null},{"id":"W2946302343","doi":"","title":"Robust Estimation of Derivatives Using Locally Weighted Least Absolute Deviation Regression","year":2019,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Least absolute deviations; Mathematics; Absolute deviation; Mean absolute error; Regression; Estimation; Robust regression; Statistics; Standard deviation; Linear regression; Computer science; Mean squared error; Economics","score_opus":0.2541103090533701,"score_gpt":0.500195041705714,"score_spread":0.24608473265234393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946302343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3696548,0.00013405173,0.6297181,0.0001283998,0.00004749868,0.000115222036,0.0000016326576,0.000006611367,0.00019366574],"genre_scores_gemma":[0.50465125,0.000032467236,0.4950263,0.000002915766,0.000041715168,5.7118433e-7,0.0000014876588,0.000018388906,0.00022491187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693656,0.0009987768,0.00067184994,0.00014809793,0.0009830536,0.0002616499],"domain_scores_gemma":[0.9954461,0.0026071768,0.0007214977,0.00015380947,0.00097267015,0.00009875064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043761875,0.00011767648,0.0003977948,0.00036086587,0.00014264707,0.000030295956,0.00018867254,0.00008623613,0.00013488691],"category_scores_gemma":[0.0066520786,0.00008465416,0.00008319756,0.0003565545,0.00008444099,0.00029128097,0.00009188566,0.0010869788,0.0000056978038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016742562,0.0005633013,0.007355062,0.0015392449,0.00021982826,0.000061000002,0.0026019476,0.560499,0.112660564,0.05390102,0.0002168315,0.2587079],"study_design_scores_gemma":[0.0007300103,0.00052370486,0.0014354164,0.00092994765,0.000021367303,0.000040827505,0.00018925432,0.899099,0.0020653806,0.094773285,0.00009447465,0.00009734698],"about_ca_topic_score_codex":0.000015960597,"about_ca_topic_score_gemma":0.0000016395995,"teacher_disagreement_score":0.33859995,"about_ca_system_score_codex":0.00011410117,"about_ca_system_score_gemma":0.00013317048,"threshold_uncertainty_score":0.79636395},"labels":[],"label_agreement":null},{"id":"W2964112145","doi":"","title":"Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Iterated function; Convergence (economics); Markov decision process; Markov chain; Mathematics; Weak convergence; Constant (computer programming); Ergodic theory; Applied mathematics; Divergence (linguistics); Rate of convergence; Limit (mathematics); Stochastic approximation; Markov process; Mathematical optimization; Computer science; Key (lock); Mathematical analysis; Statistics","score_opus":0.05478746984954716,"score_gpt":0.3014922333272734,"score_spread":0.2467047634777262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964112145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69054276,0.000757149,0.30555472,0.002142891,0.000109910296,0.00023133893,6.4584566e-7,0.000051407376,0.00060919643],"genre_scores_gemma":[0.9850425,0.00043837895,0.012296807,0.0000148091,0.000042517713,0.0000034412085,3.225768e-7,0.000024214987,0.002136998],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99523056,0.0011840545,0.0008706066,0.0003528706,0.0017658345,0.00059607066],"domain_scores_gemma":[0.9955349,0.0017377362,0.0009328045,0.00033032702,0.0012044797,0.00025975928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050131464,0.00023945441,0.00054553576,0.00050901575,0.00038245955,0.00027813637,0.0010531949,0.00008988054,0.000042245767],"category_scores_gemma":[0.0044634882,0.00013643964,0.000079184094,0.0005774282,0.0009105948,0.0007533361,0.00047755562,0.0014907024,0.000007703147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000763562,0.00013542733,0.71450895,0.00060884183,0.00033055226,0.00027410136,0.0057651857,0.035680708,0.19205506,0.007446728,0.000059059596,0.042371817],"study_design_scores_gemma":[0.01358927,0.021732457,0.046880536,0.018067723,0.00013328822,0.003037219,0.0051865545,0.8441844,0.039583556,0.00095232506,0.004825151,0.0018275253],"about_ca_topic_score_codex":0.000069538764,"about_ca_topic_score_gemma":0.0000053935437,"teacher_disagreement_score":0.8085037,"about_ca_system_score_codex":0.00009295855,"about_ca_system_score_gemma":0.0005817413,"threshold_uncertainty_score":0.6476443},"labels":[],"label_agreement":null},{"id":"W3008911943","doi":"","title":"Distributed feature screening via componentwise debiasing","year":2020,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; Computer science; Feature (linguistics); Statistic; Component (thermodynamics); Range (aeronautics); Measure (data warehouse); Convergence (economics); Distributive property; Function (biology); Algorithm; Big data; Data mining; Mathematics; Mathematical optimization; Statistics","score_opus":0.26335867222648546,"score_gpt":0.47108318881866357,"score_spread":0.2077245165921781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008911943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086398125,0.0004170723,0.90177494,0.01074327,0.00006368812,0.00011180209,0.000013497655,0.0000352489,0.0004423281],"genre_scores_gemma":[0.67934024,0.000027336955,0.32011378,0.00008865773,0.00032155492,8.329815e-7,0.000004566801,0.000027197226,0.00007583371],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996443,0.0014302814,0.00045986735,0.00016504944,0.0010981209,0.0004037084],"domain_scores_gemma":[0.9936718,0.0048672883,0.00029232082,0.000119227196,0.00066305377,0.00038632963],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0038918937,0.00013346455,0.0004078096,0.00014815561,0.00028704037,0.000118680175,0.00038328886,0.00008936533,0.00026558986],"category_scores_gemma":[0.029393878,0.000101178666,0.00012401304,0.00052756915,0.00010563579,0.00009754055,0.00018425414,0.003241934,0.000014792827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041930266,0.00084431074,0.1272923,0.0014526895,0.00080385513,0.003101089,0.0065680807,0.0031114947,0.08409219,0.033022802,0.05419161,0.68132657],"study_design_scores_gemma":[0.0054500145,0.0051181414,0.03957131,0.0016423825,0.00020843679,0.0009836288,0.0015806677,0.72930145,0.0046137455,0.14387049,0.06669187,0.00096788706],"about_ca_topic_score_codex":0.000020971505,"about_ca_topic_score_gemma":0.0000012145423,"teacher_disagreement_score":0.7261899,"about_ca_system_score_codex":0.000049221762,"about_ca_system_score_gemma":0.000063060106,"threshold_uncertainty_score":0.99905765},"labels":[],"label_agreement":null},{"id":"W3037218554","doi":"","title":"Statistical guarantees for local graph clustering","year":2020,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"PageRank; Cluster analysis; Computer science; Graph; Theoretical computer science; Cluster (spacecraft); Clustering coefficient; Path (computing); Mathematics; Algorithm; Artificial intelligence","score_opus":0.07959760419103978,"score_gpt":0.4021193523576084,"score_spread":0.3225217481665686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037218554","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023426155,0.00049003714,0.98907197,0.007599811,0.00012221595,0.00018786664,0.0000046303244,0.00005220953,0.00012861966],"genre_scores_gemma":[0.7185916,0.00010919443,0.28050554,0.00014071002,0.00042574923,0.000009695871,0.0000020032003,0.000036253612,0.00017932542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961278,0.00061822054,0.0005413266,0.00034768612,0.0016235613,0.0007413942],"domain_scores_gemma":[0.9960088,0.0021850578,0.0001704242,0.00023122304,0.0009485182,0.00045598313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00375259,0.00014983413,0.0003534206,0.00041406925,0.0003721083,0.00029015177,0.0016497961,0.00007167174,0.00003420198],"category_scores_gemma":[0.0040797396,0.00012585426,0.00013514938,0.00083494704,0.00021198622,0.0004775063,0.0008077099,0.002264995,0.000021033942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011692832,0.00017355938,0.0013998282,0.0004959559,0.0001563398,0.0010041578,0.003039659,0.25597695,0.0056812344,0.0060587954,0.002874413,0.72196984],"study_design_scores_gemma":[0.0011230628,0.002350006,0.00038552357,0.0000642637,0.000003707228,0.00018755144,0.00018372356,0.9766591,0.00048494784,0.002508081,0.015911222,0.00013881845],"about_ca_topic_score_codex":0.000018913453,"about_ca_topic_score_gemma":0.0000041312346,"teacher_disagreement_score":0.721831,"about_ca_system_score_codex":0.00011370927,"about_ca_system_score_gemma":0.00023123213,"threshold_uncertainty_score":0.9840402},"labels":[],"label_agreement":null}]}