{"meta":{"query_hash":"13ca66a5513b","filters":{"venue":"Information and Inference A Journal of the IMA"},"cohort_total":17,"direct_labels_cover":0,"predictions_cover":17,"exported":17,"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/13ca66a5513b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Information+and+Inference+A+Journal+of+the+IMA"},"results":[{"id":"W2471497375","doi":"10.1093/imaiai/iax009","title":"One-bit compressive sensing of dictionary-sparse signals","year":2017,"lang":"en","type":"preprint","venue":"Information and Inference A Journal of the IMA","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; Army Research Office; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Compressed sensing; Computer science; Orthonormal basis; Basis pursuit; Algorithm; Sparse approximation; Sparse matrix; Quantization (signal processing); Basis (linear algebra); Thresholding; Gaussian; Artificial intelligence; Mathematics","score_opus":0.034524037921345015,"score_gpt":0.26906485016661025,"score_spread":0.23454081224526524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471497375","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":[0.85672766,0.0017509437,0.12500614,0.000753025,0.0024432442,0.0004876984,0.000079491,0.00015438418,0.012597424],"genre_scores_gemma":[0.9968982,0.0009179634,0.0020076032,0.00007673738,0.000081633676,6.759615e-7,0.0000034189334,0.000007377227,0.0000064334818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988917,0.000033654567,0.0006518283,0.000043561704,0.00027690703,0.00010235215],"domain_scores_gemma":[0.99789876,0.00006661007,0.0011555783,0.0003221881,0.00050951506,0.000047330133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019286112,0.00014976543,0.00033712207,0.00016295789,0.00009830293,0.00016302009,0.00036559944,0.00014323411,0.000010189265],"category_scores_gemma":[0.00014156196,0.00011570257,0.00012938473,0.000033972752,0.00010803524,0.0007024453,0.00026857894,0.00055879034,0.0000019893887],"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":[0.00024144794,0.00009543647,0.0021225985,0.0011957741,0.0014625727,0.000017209333,0.010476078,0.4521453,0.0279578,0.0018343016,0.020600583,0.4818509],"study_design_scores_gemma":[0.0017676785,0.00027887206,0.034401227,0.019160382,0.00054522976,0.00053491426,0.0006564163,0.58872044,0.2707971,0.0617572,0.020119844,0.0012606679],"about_ca_topic_score_codex":0.00002606231,"about_ca_topic_score_gemma":0.000001619691,"teacher_disagreement_score":0.48059022,"about_ca_system_score_codex":0.000034009085,"about_ca_system_score_gemma":0.00008991444,"threshold_uncertainty_score":0.47182137},"labels":[],"label_agreement":null},{"id":"W2768739050","doi":"10.1093/imaiai/iay019","title":"Near-optimal sample complexity for convex tensor completion","year":2018,"lang":"en","type":"preprint","venue":"Information and Inference A Journal of the IMA","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Tensor (intrinsic definition); Minimax; Combinatorics; Matrix norm; Rank (graph theory); Norm (philosophy); Matrix completion; Regular polygon; Low-rank approximation; Mathematical optimization; Pure mathematics; Physics; Geometry","score_opus":0.049308365212291816,"score_gpt":0.28183863281078586,"score_spread":0.23253026759849404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768739050","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":[0.43481448,0.00011773936,0.5623331,0.00045999972,0.0010647719,0.00038776707,0.00014607774,0.00010866488,0.00056736934],"genre_scores_gemma":[0.9640673,0.00011457031,0.035354186,0.00028529303,0.0001406465,0.000005273741,0.00002169908,0.000008448506,0.000002586812],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991376,0.00002153915,0.00050856767,0.000043870805,0.00016812484,0.000120341785],"domain_scores_gemma":[0.99869925,0.00009817389,0.0004198252,0.00018296116,0.0005539255,0.000045859477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021820453,0.00014395834,0.00026173686,0.00007658268,0.000119636046,0.00024689612,0.00026902676,0.00011624211,0.000026466503],"category_scores_gemma":[0.00020152079,0.00010288211,0.00011546868,0.0000413273,0.00015733557,0.0003997298,0.00014951148,0.0003365971,0.0000036702984],"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":[0.0013158956,0.000209861,0.013911048,0.0031066628,0.0018637769,0.000004550117,0.020543862,0.34905428,0.0033195836,0.020974109,0.38527685,0.20041952],"study_design_scores_gemma":[0.00066078856,0.00018550492,0.013032089,0.0007803503,0.00008142855,0.000081861595,0.0001312095,0.87168425,0.004242289,0.024725012,0.08404806,0.00034716108],"about_ca_topic_score_codex":0.000023470862,"about_ca_topic_score_gemma":0.0000026243179,"teacher_disagreement_score":0.5292528,"about_ca_system_score_codex":0.00004452533,"about_ca_system_score_gemma":0.00006904457,"threshold_uncertainty_score":0.4195411},"labels":[],"label_agreement":null},{"id":"W2806337688","doi":"10.1093/imaiai/iaaa007","title":"On oracle-type local recovery guarantees in compressed sensing","year":2020,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Compressed sensing; Minification; Sampling (signal processing); Nyquist–Shannon sampling theorem; Coherence (philosophical gambling strategy); Wavelet; Oracle; Dimension (graph theory); Haar wavelet; SIGNAL (programming language)","score_opus":0.015683203423382395,"score_gpt":0.2246411339346488,"score_spread":0.2089579305112664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806337688","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":[0.8860576,0.00014395925,0.11072077,0.00085466297,0.0002830262,0.00007364589,0.0000014212089,0.000058127116,0.001806786],"genre_scores_gemma":[0.9982836,0.00012818491,0.0005660492,0.0009984609,0.000019653422,6.510359e-8,3.191283e-7,0.0000029915955,6.803744e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953127,0.000017325257,0.00026212574,0.000020135214,0.00010445603,0.00006469403],"domain_scores_gemma":[0.99969304,0.00005213837,0.00009430317,0.000055361346,0.00007709548,0.000028085737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006752421,0.000060922244,0.00010576563,0.00006240111,0.000023084422,0.000055459324,0.00008854461,0.000030890995,0.0000064450564],"category_scores_gemma":[0.00010219556,0.0000421944,0.000026170394,0.00011541331,0.000023858966,0.0005285309,0.000021164517,0.00019757515,0.0000056066046],"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":[0.0005367932,0.000022384169,0.00082364876,0.00009446893,0.00007137439,0.00002163757,0.0053895954,0.48112252,0.0102697015,0.0015547955,0.01227299,0.4878201],"study_design_scores_gemma":[0.0007041219,0.00028031002,0.0043662875,0.0007043953,0.000011651588,0.00008182755,0.00042480038,0.9465808,0.03716482,0.0026299497,0.0068654725,0.00018554744],"about_ca_topic_score_codex":0.000006430977,"about_ca_topic_score_gemma":0.000001750185,"teacher_disagreement_score":0.48763454,"about_ca_system_score_codex":0.000017511324,"about_ca_system_score_gemma":0.000018456967,"threshold_uncertainty_score":0.17206377},"labels":[],"label_agreement":null},{"id":"W2962684393","doi":"10.1093/imaiai/iav001","title":"Graph connection Laplacian and random matrices with random blocks","year":2015,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Random Matrices and Applications","field":"Mathematics","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":"University of Toronto","funders":"","keywords":"Connection (principal bundle); Random graph; Mathematics; Laplacian matrix; Graph; Combinatorics; Computer science; Geometry","score_opus":0.024046796891924953,"score_gpt":0.28013923201228547,"score_spread":0.2560924351203605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962684393","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":[0.9640243,0.00034494328,0.03011735,0.0014967638,0.00015856778,0.00035812025,0.000005843514,0.000018816896,0.0034752972],"genre_scores_gemma":[0.99787533,0.0003060875,0.0015514559,0.0001610618,0.000054556684,0.000006301576,6.8417916e-7,0.0000032759124,0.000041245217],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99921685,0.00003926808,0.00040616645,0.000034867597,0.0002213701,0.000081494305],"domain_scores_gemma":[0.99851215,0.0002586537,0.0006006297,0.00009457509,0.00044704683,0.00008694563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006198059,0.00008440594,0.00018992252,0.00011012776,0.00012721357,0.00016385532,0.000108231776,0.000037306087,0.0000098987775],"category_scores_gemma":[0.00050752866,0.000043856468,0.00004135174,0.00017992004,0.000064530264,0.0009848269,0.000026191898,0.00012914595,0.000002093913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03798148,0.0009905276,0.11280169,0.0017749737,0.0020331652,0.00001621055,0.090113774,0.0036622386,0.00064774335,0.28589106,0.16478378,0.29930338],"study_design_scores_gemma":[0.17861195,0.0020555519,0.0131416125,0.0014165031,0.0014934725,0.0033164406,0.025647057,0.016760465,0.0028538788,0.52966285,0.22356285,0.0014773421],"about_ca_topic_score_codex":0.000016372902,"about_ca_topic_score_gemma":0.000010054113,"teacher_disagreement_score":0.29782602,"about_ca_system_score_codex":0.0000121811345,"about_ca_system_score_gemma":0.000065807995,"threshold_uncertainty_score":0.17884149},"labels":[],"label_agreement":null},{"id":"W3078707548","doi":"10.1093/imaiai/iaaa014","title":"Sensitivity of ℓ1 minimization to parameter choice","year":2020,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Pacific Institute for the Mathematical Sciences","keywords":"Lasso (programming language); Minimax; Regularization (linguistics); Stability (learning theory); Minification; Computer science; Sensitivity (control systems); Value (mathematics); Mathematical optimization; Algorithm; Mathematics; Applied mathematics; Machine learning; Artificial intelligence","score_opus":0.020331169196309222,"score_gpt":0.24109894219256156,"score_spread":0.22076777299625233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3078707548","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":[0.8619165,0.00002820684,0.13635646,0.0009398913,0.000101852966,0.00006513991,0.0000030480664,0.00002677826,0.0005621261],"genre_scores_gemma":[0.99722457,0.000024885769,0.0019313786,0.00079559773,0.000020741974,1.9842741e-7,2.7367378e-7,0.0000017005423,6.5504696e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963117,0.000016967666,0.00021049293,0.000013390954,0.000088952605,0.00003902271],"domain_scores_gemma":[0.99962395,0.00006420632,0.00010574046,0.000046495774,0.00012421944,0.00003539792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000735903,0.000039780363,0.00008066281,0.00003684669,0.000014559868,0.000025419564,0.000052888823,0.000019594632,0.000004316263],"category_scores_gemma":[0.00031408996,0.000027559117,0.000025312092,0.00008810022,0.0000121214,0.00044862635,0.000022158205,0.000069958085,0.0000018929663],"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":[0.0002053357,0.00003881452,0.018895563,0.0002676985,0.00020885978,0.0000037270202,0.02831067,0.2836555,0.09197748,0.001822054,0.035521578,0.5390927],"study_design_scores_gemma":[0.0005467779,0.00023194824,0.049651176,0.00037399324,0.000041429706,0.000054152562,0.00039695375,0.55924696,0.36366022,0.00045570548,0.025111426,0.00022929204],"about_ca_topic_score_codex":0.000004991217,"about_ca_topic_score_gemma":6.266028e-7,"teacher_disagreement_score":0.5388634,"about_ca_system_score_codex":0.0000062635777,"about_ca_system_score_gemma":0.000010603175,"threshold_uncertainty_score":0.11238282},"labels":[],"label_agreement":null},{"id":"W3088799486","doi":"10.1093/imaiai/iaab027","title":"Strong replica symmetry for high-dimensional disordered log-concave Gibbs measures","year":2021,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":8,"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":"Replica; Mathematics; Inference; Gibbs measure; Regular polygon; Decoupling (probability); Gibbs sampling; Applied mathematics; Statistical physics; Mathematical analysis; Statistics; Computer science; Bayesian probability; Physics; Geometry; Artificial intelligence","score_opus":0.05467278135402242,"score_gpt":0.3396268383534964,"score_spread":0.28495405699947396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088799486","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":[0.65546423,0.0005716071,0.3332343,0.0060567744,0.0011079484,0.00043634733,0.00006227015,0.000024009025,0.0030424793],"genre_scores_gemma":[0.9586877,0.000071795526,0.04025767,0.00070459174,0.00007974022,0.0000056325634,0.0000034387176,0.0000062450863,0.00018318085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885774,0.00009157296,0.00059132284,0.000055251156,0.0002745393,0.00012958515],"domain_scores_gemma":[0.9979542,0.0004953264,0.0005600002,0.00019688852,0.00072626414,0.000067333305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009010771,0.000100695775,0.00022811725,0.000064642554,0.00013096817,0.000093380215,0.00014505009,0.00006311387,0.000021583635],"category_scores_gemma":[0.0032510583,0.00006328666,0.00012522744,0.000098868375,0.00004534407,0.0005539687,0.000079957106,0.0001772596,1.11091325e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004751728,0.00019515913,0.0021780585,0.0004980999,0.00041239438,0.0000062245545,0.003809121,0.00013087661,0.0046043447,0.6330291,0.02436369,0.33029774],"study_design_scores_gemma":[0.017733786,0.001476995,0.010480611,0.002137593,0.00086032925,0.001749573,0.012678971,0.022148855,0.08735434,0.67684156,0.16483098,0.0017063934],"about_ca_topic_score_codex":0.0000047366,"about_ca_topic_score_gemma":0.0000076789265,"teacher_disagreement_score":0.32859135,"about_ca_system_score_codex":0.00003213566,"about_ca_system_score_gemma":0.00020899042,"threshold_uncertainty_score":0.38920552},"labels":[],"label_agreement":null},{"id":"W3151137625","doi":"10.1093/imaiai/iaab002","title":"A model of double descent for high-dimensional binary linear classification","year":2021,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":78,"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 British Columbia","funders":"","keywords":"Kappa; Gradient descent; Mathematics; Support vector machine; Binary classification; Binary number; Linear classifier; Linear regression; Gaussian; Logistic regression; Applied mathematics; Artificial intelligence; Pattern recognition (psychology); Statistics; Computer science; Physics; Geometry; Artificial neural network","score_opus":0.051562028037794805,"score_gpt":0.268477240208541,"score_spread":0.21691521217074622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151137625","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":[0.897475,0.00010301331,0.10160633,0.0003736203,0.00014344229,0.00006990161,0.000006620044,0.000017277942,0.00020480069],"genre_scores_gemma":[0.9900454,0.00008922053,0.009745208,0.00009235827,0.000014950382,0.0000012331507,0.0000027155183,0.0000023157907,0.0000065900444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995719,0.000005507432,0.00026434084,0.000016893855,0.00009575136,0.000045601457],"domain_scores_gemma":[0.99940115,0.000020378764,0.00013925547,0.00007228661,0.00034838432,0.000018571927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008015913,0.00004202777,0.00008029911,0.000044757515,0.000029619132,0.000017643337,0.000060892533,0.00002865917,0.0000033580945],"category_scores_gemma":[0.00003065666,0.000029528914,0.000036409874,0.000052684747,0.000017400838,0.00039463432,0.000019689869,0.00006833565,4.5995364e-7],"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":[0.00027663165,0.00007493633,0.00051449565,0.00016986363,0.00011327975,9.665292e-7,0.0012665186,0.6469796,0.2814553,0.024365082,0.00732774,0.037455622],"study_design_scores_gemma":[0.00038754815,0.000028775425,0.0011016222,0.00011383393,0.000012532432,0.000017272292,0.00004234055,0.8531578,0.14276743,0.0019267668,0.00040325103,0.00004078657],"about_ca_topic_score_codex":0.0000014387367,"about_ca_topic_score_gemma":4.669126e-7,"teacher_disagreement_score":0.20617826,"about_ca_system_score_codex":0.00001475373,"about_ca_system_score_gemma":0.000059859885,"threshold_uncertainty_score":0.12041542},"labels":[],"label_agreement":null},{"id":"W3160701863","doi":"10.1093/imaiai/iaab007","title":"Distributed information-theoretic clustering","year":2021,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"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 Montréal","funders":"Vienna Science and Technology Fund; Arizona State University","keywords":"Information bottleneck method; Mutual information; Constraint (computer-aided design); Cluster analysis; Encoder; Bottleneck; Computer science; Binary number; Combinatorics; Information theory; Characterization (materials science); Cardinality (data modeling); Independence (probability theory); Mathematics; Discrete mathematics; Algorithm; Data mining; Artificial intelligence; Statistics; Physics","score_opus":0.008085186106822037,"score_gpt":0.232273134839672,"score_spread":0.22418794873284995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160701863","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":[0.008774438,0.000056701105,0.988194,0.0018306327,0.0003908204,0.000031711654,0.000011163745,0.000010300564,0.0007002353],"genre_scores_gemma":[0.98286897,0.00016822826,0.015446886,0.0014630377,0.00003073605,9.3766283e-7,0.0000108260265,0.0000010876406,0.000009278445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922085,0.00003120487,0.0004053779,0.00002608002,0.00023111187,0.0000853896],"domain_scores_gemma":[0.9989418,0.000050992207,0.0003647153,0.00019753246,0.00039040908,0.000054599303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002202672,0.000057756384,0.00008483026,0.000055184762,0.00012715919,0.000491697,0.00041963026,0.000026956885,0.00001886381],"category_scores_gemma":[0.00028771316,0.000035435052,0.000039724415,0.0001987215,0.000030288731,0.0074540367,0.0003624482,0.0001332901,0.000013163587],"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":[0.000037183996,0.000045936256,0.0021858427,0.00012707015,0.000051228733,0.000008759132,0.007213858,0.0043327175,0.00020967427,0.1511543,0.008534767,0.8260987],"study_design_scores_gemma":[0.0018095894,0.00013576806,0.031480156,0.00048188894,0.000021793852,0.0014863254,0.000996935,0.69702315,0.003805692,0.019855086,0.24255852,0.0003450738],"about_ca_topic_score_codex":0.0000028283519,"about_ca_topic_score_gemma":5.581011e-7,"teacher_disagreement_score":0.97409457,"about_ca_system_score_codex":0.000018902376,"about_ca_system_score_gemma":0.00014384669,"threshold_uncertainty_score":0.5403997},"labels":[],"label_agreement":null},{"id":"W3182878663","doi":"10.1093/imaiai/iaaf019","title":"Performance of Bayesian linear regression in a model with mismatch","year":2025,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Control Systems and Identification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Bayesian linear regression; Bayesian multivariate linear regression; Bayesian probability; Linear regression; Proper linear model; Regression; Statistics; Linear model; Regression analysis; Econometrics; General linear model; Computer science; Mathematics; Bayesian inference","score_opus":0.005053991288399349,"score_gpt":0.21409594950855465,"score_spread":0.2090419582201553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182878663","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":[0.97978526,0.00007764145,0.018639171,0.0001863009,0.000071808216,0.00005986413,8.6707416e-7,0.00000381654,0.0011752665],"genre_scores_gemma":[0.9995449,0.00011300201,0.00027741556,0.000021276766,0.000004726559,0.0000012189953,2.7292197e-7,0.0000010905567,0.00003610313],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995257,0.0000067396577,0.00032816254,0.000013207666,0.0000852375,0.000040945375],"domain_scores_gemma":[0.99967283,0.000010632919,0.00013978682,0.00006536645,0.000099829456,0.000011571915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015365271,0.000038927523,0.00008876596,0.00011032411,0.000020403784,0.000018903273,0.00007619801,0.000022368911,0.0000016863444],"category_scores_gemma":[0.000022887709,0.000021973126,0.00001593056,0.00012060971,0.000012080185,0.000675877,0.000009032358,0.00008227006,4.3427528e-7],"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":[0.00026000617,0.000029823728,0.065274514,0.0008871458,0.000054192275,3.3126662e-7,0.005675185,0.794784,0.00780409,0.0012343191,0.0009359789,0.12306041],"study_design_scores_gemma":[0.00039079733,0.000018216166,0.021694612,0.00060769636,0.00000501606,0.0000051159363,0.00011806879,0.9753881,0.0014038435,0.00006446052,0.00027700185,0.000027035016],"about_ca_topic_score_codex":0.000007663307,"about_ca_topic_score_gemma":0.000007422649,"teacher_disagreement_score":0.18060413,"about_ca_system_score_codex":0.00001788776,"about_ca_system_score_gemma":0.000041295792,"threshold_uncertainty_score":0.08960381},"labels":[],"label_agreement":null},{"id":"W4213048988","doi":"10.1093/imaiai/iaac004","title":"An analysis of classical multidimensional scaling with applications to clustering","year":2022,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Dental and Craniofacial Research; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Cluster analysis; Scaling; Multidimensional scaling; Statistical physics; Scaling law; Econometrics; Computer science; Physics; Economics; Mathematics; Artificial intelligence; Machine learning; Geometry","score_opus":0.014548756245397169,"score_gpt":0.27289479637366815,"score_spread":0.258346040128271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213048988","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":[0.33026826,0.0000047696462,0.6688711,0.00070784026,0.000032553697,0.000055300123,0.000004709265,0.0000041758326,0.000051273888],"genre_scores_gemma":[0.9780912,0.0000031004477,0.021317989,0.0005693389,0.0000058450064,0.00000702376,0.0000019893166,7.5388084e-7,0.00000277094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931407,0.000038190614,0.00027137288,0.000038209837,0.00028372,0.00005441386],"domain_scores_gemma":[0.99932045,0.000041832773,0.0002744405,0.0001288308,0.00017909089,0.000055378252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024595985,0.000038503338,0.00009369996,0.00023931878,0.00016308363,0.000052541087,0.00027718744,0.000010038681,0.000018341076],"category_scores_gemma":[0.00001861558,0.0000238746,0.00003908794,0.00053572963,0.000017302811,0.0010445844,0.00014659326,0.00009973517,0.0000010684535],"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":[0.00015254146,0.00016061495,0.008777921,0.00002080753,0.00019422118,9.3536516e-7,0.009171712,0.7187393,0.007047275,0.008471499,0.00026045795,0.24700275],"study_design_scores_gemma":[0.00035643572,0.00022682395,0.028752198,0.00003424959,0.000064645596,0.000041558582,0.0011463827,0.9630241,0.0014900282,0.00019071955,0.0045862375,0.00008664236],"about_ca_topic_score_codex":0.000006786111,"about_ca_topic_score_gemma":0.0000031983366,"teacher_disagreement_score":0.6478229,"about_ca_system_score_codex":0.000018310026,"about_ca_system_score_gemma":0.000057973055,"threshold_uncertainty_score":0.1254324},"labels":[],"label_agreement":null},{"id":"W4226000139","doi":"10.1093/imaiai/iaae002","title":"PACMAN: PAC-style bounds accounting for the Mismatch between Accuracy and Negative log-loss","year":2024,"lang":"en","type":"preprint","venue":"Information and Inference A Journal of the IMA","topic":"Machine Learning and Data Classification","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":"École de Technologie Supérieure; McGill University","funders":"Universidad de Buenos Aires; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Generalization; Computer science; Algorithm; Function (biology); Metric (unit); Generalization error; Cross entropy; Mathematics; Artificial intelligence; Artificial neural network; Pattern recognition (psychology)","score_opus":0.026705443778082257,"score_gpt":0.3117600080436237,"score_spread":0.28505456426554143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226000139","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":[0.19257168,0.0018786482,0.7051216,0.09500757,0.0024551759,0.0010878409,0.00016357398,0.00009786532,0.0016160387],"genre_scores_gemma":[0.99520266,0.0004816519,0.0035232652,0.00052718,0.00019714105,0.0000122800275,0.000009889551,0.000004668977,0.000041276915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875975,0.00007255931,0.00061493996,0.000114808514,0.00029532192,0.0001426276],"domain_scores_gemma":[0.9969359,0.0010725709,0.0011998432,0.00038334468,0.00035487063,0.000053447897],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012863532,0.0001596465,0.00021152655,0.00012486301,0.00033783563,0.0020837022,0.0009936307,0.00010718326,0.0000032509417],"category_scores_gemma":[0.0014771756,0.00008496188,0.00009527427,0.00014856615,0.00010146217,0.0016509163,0.0011872188,0.0008733403,0.000006018836],"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":[0.000028068336,0.000011984262,0.008036128,0.00055120984,0.00018975807,7.0001175e-7,0.017363044,0.0003704412,0.000019882995,0.020334823,0.004864736,0.94822925],"study_design_scores_gemma":[0.0014402467,0.00024306982,0.21717726,0.0023121997,0.00034314237,0.00024485055,0.002304819,0.43693444,0.00038523113,0.20108849,0.13677357,0.0007526881],"about_ca_topic_score_codex":0.00004521676,"about_ca_topic_score_gemma":0.0000042846823,"teacher_disagreement_score":0.9474765,"about_ca_system_score_codex":0.000036296715,"about_ca_system_score_gemma":0.00026211777,"threshold_uncertainty_score":0.9989522},"labels":[],"label_agreement":null},{"id":"W4366682198","doi":"10.1093/imaiai/iaad007","title":"Third-order moment varieties of linear non-Gaussian graphical models","year":2023,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":5,"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 British Columbia","funders":"European Research Council","keywords":"Algebraic number; Gaussian; Mathematics; Graph; Graphical model; Polytope; Moment (physics); Ideal (ethics); Order (exchange); Discrete mathematics; Mathematical analysis","score_opus":0.02198218244826054,"score_gpt":0.26393061856571126,"score_spread":0.24194843611745073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366682198","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":[0.046143845,0.000035988556,0.94888264,0.003480593,0.00026361202,0.000059764185,0.0000023762677,0.000023138728,0.0011080416],"genre_scores_gemma":[0.99259937,0.00028304814,0.0066130287,0.00044448744,0.000020485671,0.0000016850993,6.0088183e-7,0.0000020335542,0.000035283854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879974,0.000035586436,0.0005704061,0.000054411466,0.00039598384,0.00014384178],"domain_scores_gemma":[0.9988144,0.00005626336,0.000409148,0.0002147042,0.0004301569,0.000075303695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057515956,0.00009209473,0.00016693378,0.0002070076,0.00011549852,0.00012874568,0.0006076981,0.000060532886,0.000004096879],"category_scores_gemma":[0.000077026314,0.00005685167,0.00007328567,0.00056674884,0.00008417181,0.0021371332,0.00020185995,0.00023705015,0.000009784514],"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":[0.00006667327,0.000088789224,0.0014365449,0.00015738036,0.000109733905,0.00000400199,0.023082899,0.09429998,0.0004944821,0.77463675,0.0035986213,0.10202413],"study_design_scores_gemma":[0.00031088514,0.00012988145,0.0024024835,0.000106850806,0.00000810323,0.000032023036,0.00022787566,0.9173911,0.00055969285,0.078042366,0.0006921885,0.00009651222],"about_ca_topic_score_codex":0.000016164358,"about_ca_topic_score_gemma":9.912934e-7,"teacher_disagreement_score":0.9464555,"about_ca_system_score_codex":0.000010574763,"about_ca_system_score_gemma":0.00018547276,"threshold_uncertainty_score":0.23183438},"labels":[],"label_agreement":null},{"id":"W4382811464","doi":"10.1093/imaiai/iaad024","title":"Multivariate super-resolution without separation","year":2023,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Measure (data warehouse); Point spread function; Point (geometry); Gaussian; Generalization; Function (biology); Point process; Mathematics; Image (mathematics); Resolution (logic); Algorithm; Regular polygon; Applied mathematics; Computer science; Mathematical optimization; Mathematical analysis; Artificial intelligence; Physics; Statistics; Geometry","score_opus":0.01995799000048502,"score_gpt":0.2832194905943124,"score_spread":0.26326150059382736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382811464","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":[0.9566459,0.000044885073,0.040574457,0.0003570521,0.00040424484,0.000078523684,0.0000024192582,0.00015274827,0.0017397555],"genre_scores_gemma":[0.9993083,0.00011615868,0.00045044912,0.0000792407,0.000028295604,8.155868e-7,0.00000139375,0.000002384557,0.000012983885],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995925,0.000013254245,0.00021067714,0.000014493542,0.000105374085,0.00006372725],"domain_scores_gemma":[0.9997163,0.00001883621,0.000081980295,0.000061653605,0.00010072226,0.00002054322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013305452,0.000046939564,0.000063390464,0.00009227758,0.000051925756,0.00006095354,0.00007396863,0.000028791055,0.0000049594514],"category_scores_gemma":[0.000062710926,0.0000311122,0.000026030362,0.00012287432,0.000018067762,0.00087971566,0.000020588297,0.00009580516,0.000016615164],"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":[0.0001894149,0.00003894396,0.018904934,0.00015024473,0.00026300593,0.0000070420037,0.018966105,0.42083114,0.11378403,0.010465582,0.08900037,0.3273992],"study_design_scores_gemma":[0.00043028226,0.000052484924,0.05129426,0.00018175747,0.000016750275,0.00006676511,0.00022032588,0.9025952,0.020216918,0.0025233787,0.022273796,0.00012806348],"about_ca_topic_score_codex":0.000006436344,"about_ca_topic_score_gemma":0.0000012785706,"teacher_disagreement_score":0.48176408,"about_ca_system_score_codex":0.000015699374,"about_ca_system_score_gemma":0.000014780875,"threshold_uncertainty_score":0.12687187},"labels":[],"label_agreement":null},{"id":"W4391592471","doi":"10.1093/imaiai/iaad056","title":"Statistical inference with regularized optimal transport","year":2024,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Estimator; Consistency (knowledge bases); Statistical inference; Inference; Flexibility (engineering); Limit (mathematics); Mathematical optimization; Computer science; Smoothing; Mathematics; Probability distribution; Algorithm; Applied mathematics; Artificial intelligence; Statistics","score_opus":0.03608366168691175,"score_gpt":0.35146102116916816,"score_spread":0.3153773594822564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391592471","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":[0.1061409,0.000054066164,0.89090276,0.0007480453,0.00021377818,0.00012403502,0.000042423257,0.000024939625,0.0017490728],"genre_scores_gemma":[0.80392414,0.000056843113,0.19573632,0.00018381228,0.000036341735,0.0000034759478,0.0000015184133,0.0000064532583,0.00005110708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998584,0.00007825353,0.00068005826,0.00006985905,0.0004198789,0.00016795362],"domain_scores_gemma":[0.9979554,0.0012332819,0.00024830617,0.00015081684,0.00029716926,0.00011504019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069782144,0.00014221416,0.000258059,0.00010539185,0.0000868185,0.00019508526,0.00022106148,0.000061452745,0.00023359926],"category_scores_gemma":[0.0016456288,0.000073364994,0.000057020443,0.0002067916,0.00020567917,0.0009368355,0.000034580848,0.00039606597,0.000009765364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016799445,0.000030841205,0.0012511628,0.00026508755,0.00007866999,0.000018159095,0.0019227974,0.00003810667,0.000116615185,0.90893036,0.0007441555,0.08643608],"study_design_scores_gemma":[0.0027777117,0.0017540931,0.052762624,0.0031820298,0.0005467326,0.0014923285,0.0014201923,0.053490262,0.0016893788,0.8535266,0.026499966,0.00085811067],"about_ca_topic_score_codex":0.000008182167,"about_ca_topic_score_gemma":0.0000023990933,"teacher_disagreement_score":0.69778323,"about_ca_system_score_codex":0.000027930908,"about_ca_system_score_gemma":0.00030523943,"threshold_uncertainty_score":0.29917377},"labels":[],"label_agreement":null},{"id":"W4403162617","doi":"10.1093/imaiai/iaae023","title":"Statistical inference for sketching algorithms","year":2024,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Sketch; Inference; Computer science; Algorithm; Set (abstract data type); Data set; Sampling (signal processing); Statistical inference; Mathematics; Statistics; Artificial intelligence","score_opus":0.019625975934582,"score_gpt":0.32757539395024937,"score_spread":0.3079494180156674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403162617","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000931181,0.0001880639,0.9955833,0.0020407704,0.0006572054,0.00007892795,0.000007897384,0.00001632401,0.0004963221],"genre_scores_gemma":[0.45379207,0.000095982505,0.54526156,0.0007456988,0.00007012228,0.0000030405984,5.779596e-7,0.0000023168268,0.000028640403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922293,0.000043430093,0.00037718966,0.000053728036,0.00018638266,0.00011633763],"domain_scores_gemma":[0.99908453,0.00040452028,0.0001487779,0.00012218826,0.00017406259,0.00006589973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073635334,0.00007455929,0.0001127511,0.00009758327,0.00009352503,0.0006111894,0.00039675197,0.000036273977,0.000006425302],"category_scores_gemma":[0.00041492863,0.000042836407,0.000057128203,0.00013984814,0.000036618374,0.002643498,0.000096150776,0.00019729312,0.0000041101825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031502482,0.0000030027145,0.000022531178,0.00003049931,0.0000086060545,7.3326913e-7,0.0010589954,0.000015893833,0.000030044754,0.3730684,0.00059320254,0.6251649],"study_design_scores_gemma":[0.00032886036,0.00016476886,0.0012915242,0.00027220833,0.000019184568,0.00020045348,0.000049614806,0.56181914,0.0005041946,0.39610875,0.039096266,0.0001450375],"about_ca_topic_score_codex":0.0000034101106,"about_ca_topic_score_gemma":4.590918e-7,"teacher_disagreement_score":0.6250199,"about_ca_system_score_codex":0.000018908471,"about_ca_system_score_gemma":0.00020141616,"threshold_uncertainty_score":0.5893714},"labels":[],"label_agreement":null},{"id":"W4403585525","doi":"10.1093/imaiai/iaae028","title":"Hitting the High-dimensional notes: an ODE for SGD learning dynamics on GLMs and multi-index models","year":2024,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Israel Science Foundation; Canadian Institute for Advanced Research","keywords":"Ode; Index (typography); Dynamics (music); Econometrics; Artificial intelligence; Statistical physics; Computer science; Mathematics; Physics; Applied mathematics","score_opus":0.023443340076124308,"score_gpt":0.2753627054817372,"score_spread":0.2519193654056129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403585525","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":[0.02430227,0.00004489804,0.9731233,0.0021143842,0.00021503078,0.00012587827,0.0000027719977,0.000038194783,0.00003323584],"genre_scores_gemma":[0.94417584,0.0000223542,0.055236667,0.0005256226,0.000020660636,0.0000041960534,0.0000014282316,0.0000031568563,0.000010060857],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992843,0.000033457443,0.00031225703,0.0000621962,0.00021198689,0.0000957725],"domain_scores_gemma":[0.9990926,0.00031805923,0.00022924723,0.000111188325,0.00020629633,0.000042622458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005365976,0.000079564896,0.00008382168,0.00012244993,0.00022333341,0.00046028927,0.00029264743,0.00003546322,0.0000011136848],"category_scores_gemma":[0.00030979534,0.0000436908,0.000035113473,0.00013223718,0.00004605,0.0023268561,0.00009709486,0.00021686174,6.440462e-7],"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":[0.000027338003,0.000019709576,0.00022394945,0.000036474932,0.000025090509,6.1962567e-7,0.005048189,0.40954608,0.000036403246,0.3292534,0.000078011835,0.25570473],"study_design_scores_gemma":[0.00019885488,0.00014363974,0.0003671776,0.00014179641,0.000005909438,0.00005145239,0.00010744004,0.9851687,0.00010200033,0.013589063,0.00006676791,0.000057182773],"about_ca_topic_score_codex":0.000009701519,"about_ca_topic_score_gemma":0.0000021598123,"teacher_disagreement_score":0.9198736,"about_ca_system_score_codex":0.000035802306,"about_ca_system_score_gemma":0.000074572294,"threshold_uncertainty_score":0.443858},"labels":[],"label_agreement":null},{"id":"W4406502827","doi":"10.1093/imaiai/iaae034","title":"Differentially private low-dimensional synthetic data from high-dimensional datasets","year":2025,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Curse of dimensionality; Principal component analysis; Synthetic data; Intrinsic dimension; Covariance; Computer science; Clustering high-dimensional data; Key (lock); Dimension (graph theory); Algorithm; Covariance matrix; Data mining; Artificial intelligence; Mathematics; Statistics","score_opus":0.020406553467568554,"score_gpt":0.272225933458451,"score_spread":0.25181937999088244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406502827","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":[0.5529721,0.00038097304,0.38520902,0.05693039,0.0025690922,0.00026245654,0.0013574203,0.00013161967,0.00018693857],"genre_scores_gemma":[0.93099993,0.00007841933,0.06696172,0.0017345983,0.000024411067,0.0000014207067,0.00019042777,0.000002722766,0.0000063374946],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984773,0.00007376762,0.0006382503,0.00016057646,0.00048048998,0.00016963287],"domain_scores_gemma":[0.9944418,0.00031908453,0.0005514479,0.00444941,0.0001822997,0.000055927314],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00051163085,0.00013703975,0.00019620772,0.00019148742,0.00017669363,0.00040453774,0.017647186,0.000078023964,0.00004623055],"category_scores_gemma":[0.009698443,0.000087662476,0.00003665397,0.00027701733,0.00013953767,0.005286952,0.051996633,0.00036006275,0.00002484388],"study_design_candidate":"not_applicable","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":[0.00015619614,0.00021204122,0.0025921997,0.00008939655,0.0003363181,0.000016354908,0.00014951728,0.00033645658,0.0033247825,0.026030121,0.747763,0.21899362],"study_design_scores_gemma":[0.0016436597,0.000078348945,0.052465897,0.0010591395,0.00006490562,0.0000985048,0.000020684298,0.59166074,0.0077565955,0.32957044,0.015237619,0.00034347855],"about_ca_topic_score_codex":0.000040909432,"about_ca_topic_score_gemma":0.0000050346875,"teacher_disagreement_score":0.7325254,"about_ca_system_score_codex":0.000037750604,"about_ca_system_score_gemma":0.00025316505,"threshold_uncertainty_score":0.9986433},"labels":[],"label_agreement":null}]}