{"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005955284,0.00040993094,0.9877331,0.0005256424,0.000092340466,0.00013256929,0.0008212654,0.003461639,0.0008682154],"genre_scores_gemma":[0.1695445,0.00041053945,0.82180923,0.00051505293,0.00026429587,0.00030050808,0.005018301,0.00027170166,0.0018658794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98988545,0.002585058,0.0008387254,0.0029329164,0.0033084294,0.00044929885],"domain_scores_gemma":[0.97610384,0.010086962,0.00211629,0.0083159,0.0030178358,0.00035922084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011360215,0.0020458165,0.002861806,0.0058405725,0.0014012527,0.004045477,0.006431152,0.002550175,0.0031214992],"category_scores_gemma":[0.043948773,0.0013505425,0.0030288096,0.008386554,0.0020649158,0.011724715,0.0082588205,0.0058411346,0.0021046023],"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":[0.00076441304,0.00062487286,0.01398272,0.00062332867,0.0006596883,0.00038341107,0.0010343213,0.19618787,0.007492799,0.036237206,0.019794794,0.72221464],"study_design_scores_gemma":[0.000049928953,0.00009711823,0.0013256987,0.000083930194,0.00014598665,0.00023602646,0.00014640855,0.9185882,0.009345485,0.05918368,0.0107311765,0.00006645304],"about_ca_topic_score_codex":0.0067208214,"about_ca_topic_score_gemma":0.007839037,"teacher_disagreement_score":0.011360215,"about_ca_system_score_codex":0.0017536016,"about_ca_system_score_gemma":0.004067641,"threshold_uncertainty_score":0.060079277},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051800273,0.0012581327,0.9876061,0.0010215333,0.00011741921,0.000051441366,0.000081882594,0.00015610071,0.004527268],"genre_scores_gemma":[0.5662119,0.0075639836,0.4017983,0.0030796984,0.0022353882,0.0010666936,0.00055249844,0.0012613144,0.01623026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9887251,0.005737596,0.0004366834,0.0013309761,0.0030001905,0.00076943357],"domain_scores_gemma":[0.93654823,0.04790811,0.00415056,0.006307133,0.003672892,0.0014131538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027024845,0.0031353782,0.0025926544,0.0030353002,0.0015548274,0.0041731307,0.005226982,0.003304289,0.0053798733],"category_scores_gemma":[0.09292123,0.0014417692,0.0027360325,0.0019248064,0.0066009285,0.009626208,0.009719738,0.011016246,0.0013814212],"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":[0.00013965316,0.000045938104,0.0011949618,0.00024333471,0.00007606363,0.00014276766,0.00030082243,0.0858565,0.001260253,0.8897017,0.0022088524,0.018829055],"study_design_scores_gemma":[0.000027559581,0.00016367277,0.00034663742,0.0002045939,0.000041553485,0.00018826821,0.00006540381,0.41587627,0.0013810787,0.577021,0.004622264,0.00006169802],"about_ca_topic_score_codex":0.0013123975,"about_ca_topic_score_gemma":0.0008099982,"teacher_disagreement_score":0.027024845,"about_ca_system_score_codex":0.0026972152,"about_ca_system_score_gemma":0.0020914497,"threshold_uncertainty_score":0.14292276},"labels":[],"label_agreement":null}]}