{"meta":{"query_hash":"9629b59d971d","filters":{"venue":"ACM / IMS Journal of Data Science"},"cohort_total":2,"direct_labels_cover":0,"predictions_cover":2,"exported":2,"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/9629b59d971d","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+%2F+IMS+Journal+of+Data+Science"},"results":[{"id":"W4391018115","doi":"10.1145/3593579","title":"Record Fusion via Inference and Data Augmentation","year":2024,"lang":"en","type":"article","venue":"ACM / IMS Journal of Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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 Waterloo","funders":"","keywords":"Computer science; Inference; Probabilistic logic; Sensor fusion; Data mining; Fusion; Data source; Artificial intelligence; Machine learning","score_opus":0.5120775299749007,"score_gpt":0.5555716160536497,"score_spread":0.04349408607874894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391018115","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":[0.32441798,0.0029277839,0.638906,0.023143008,0.0070650117,0.00038969438,0.001602311,0.00006096902,0.0014872738],"genre_scores_gemma":[0.9360951,0.0016236736,0.06111645,0.0005506846,0.00023564689,5.995909e-7,0.00012070581,0.000006784798,0.00025034454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956779,0.00013254953,0.0008170487,0.00078008126,0.0023717186,0.00022072987],"domain_scores_gemma":[0.9937635,0.0014162299,0.00039194658,0.003944189,0.00028853441,0.000195585],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.023029098,0.00009981575,0.00018500177,0.00052378944,0.000249898,0.0021482504,0.013045885,0.000024412657,0.00021986366],"category_scores_gemma":[0.013065709,0.000066036926,0.000018409373,0.001635967,0.0004944185,0.020372694,0.011141012,0.00019807312,0.00013622841],"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":[0.0000150459155,0.000024639925,0.0007443671,0.000010812121,0.000008265724,0.000034559365,0.00024307918,0.000003262378,0.0035319233,0.0012052095,0.035587765,0.95859104],"study_design_scores_gemma":[0.00059464935,0.00043091175,0.025150346,0.0004010677,0.0001107794,0.00033672794,0.0029948768,0.0630696,0.0007013286,0.11329627,0.7924813,0.00043213659],"about_ca_topic_score_codex":0.00007799401,"about_ca_topic_score_gemma":0.00009017748,"teacher_disagreement_score":0.9581589,"about_ca_system_score_codex":0.00003375756,"about_ca_system_score_gemma":0.00032350203,"threshold_uncertainty_score":0.9988876},"labels":[],"label_agreement":null},{"id":"W4391131725","doi":"10.1145/3594234","title":"Optimistic Rates: A Unifying Theory for Interpolation Learning and Regularization in Linear Regression","year":2024,"lang":"en","type":"article","venue":"ACM / IMS Journal of Data Science","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","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":"University of British Columbia","funders":"","keywords":"Regularization (linguistics); Linear regression; Mathematics; Interpolation (computer graphics); Econometrics; Applied mathematics; Linear interpolation; Bayesian multivariate linear regression; Regression; Proper linear model; Statistics; Linear model; Computer science; Artificial intelligence; Mathematical analysis","score_opus":0.0531062436633936,"score_gpt":0.3582758260044411,"score_spread":0.30516958234104746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391131725","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":[0.11076812,0.0023353025,0.8861553,0.000085014646,0.00038544144,0.00008699364,0.0000041456287,0.00008454073,0.00009515696],"genre_scores_gemma":[0.9222077,0.00034034447,0.07735966,0.000005483902,0.000055949877,4.5443858e-7,0.0000058353708,0.000008355361,0.000016196198],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994588,0.000024502571,0.0001814929,0.00011859699,0.00012045005,0.000096152515],"domain_scores_gemma":[0.99945575,0.00021516369,0.00004978144,0.00018171746,0.000068040645,0.000029541668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012766245,0.00005625731,0.00008063069,0.0002458734,0.000060158858,0.00012623868,0.0003726121,0.000027204665,0.000001959795],"category_scores_gemma":[0.0010340664,0.000044170316,0.000010296212,0.00030072758,0.00007057285,0.0012436735,0.00014938215,0.00017885401,2.760326e-7],"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":[0.000094384144,0.000022007776,0.0014979885,0.00022950725,0.000036152524,0.000080868725,0.0021743518,0.029908625,0.65924937,0.0048885117,0.0008161146,0.30100212],"study_design_scores_gemma":[0.00008700705,0.00006058814,0.0001480287,0.001268158,0.000011776492,0.000070628375,0.00017860548,0.9802243,0.010257504,0.007019254,0.0006064164,0.00006772687],"about_ca_topic_score_codex":7.6519484e-7,"about_ca_topic_score_gemma":4.7090043e-7,"teacher_disagreement_score":0.95031565,"about_ca_system_score_codex":0.00002738729,"about_ca_system_score_gemma":0.000041700132,"threshold_uncertainty_score":0.18012132},"labels":[],"label_agreement":null}]}