{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":2,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"9629b59d971d","filters":{"venue":"ACM / IMS Journal of Data Science"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Lijia Zhou","is_ca":false},{"name":"Frederic Koehler","is_ca":false},{"name":"Danica J. Sutherland","is_ca":true},{"name":"Nathan Srebro","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0531062436633936,"gpt":0.3582758260044411,"spread":0.3051695823410475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02702484,0.003135378,0.002592654,0.0030353,0.001554827,0.004173131,0.005226982,0.003304289,0.005379873],"category_scores_gemma":[0.09292123,0.001441769,0.002736032,0.001924806,0.006600928,0.009626208,0.009719738,0.01101625,0.001381421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002697215,"about_ca_system_score_gemma":0.00209145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001312398,"about_ca_topic_score_gemma":0.0008099982,"domain_scores_codex":[0.9887251,0.005737596,0.0004366834,0.001330976,0.00300019,0.0007694336],"domain_scores_gemma":[0.9365482,0.04790811,0.00415056,0.006307133,0.003672892,0.001413154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001396532,0.0000459381,0.001194962,0.0002433347,0.00007606363,0.0001427677,0.0003008224,0.0858565,0.001260253,0.8897017,0.002208852,0.01882906],"study_design_scores_gemma":[0.00002755958,0.0001636728,0.0003466374,0.0002045939,0.00004155349,0.0001882682,0.00006540381,0.4158763,0.001381079,0.577021,0.004622264,0.00006169802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005180027,0.001258133,0.9876061,0.001021533,0.0001174192,0.00005144137,0.00008188259,0.0001561007,0.004527268],"genre_scores_gemma":[0.5662119,0.007563984,0.4017983,0.003079698,0.002235388,0.001066694,0.0005524984,0.001261314,0.01623026],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02702484,"threshold_uncertainty_score":0.1429228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Alireza Heidari","is_ca":true},{"name":"Ihab F. Ilyas","is_ca":true},{"name":"Theodoros Rekatsinas","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5120775299749007,"gpt":0.5555716160536497,"spread":0.04349408607874894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01136022,0.002045817,0.002861806,0.005840573,0.001401253,0.004045477,0.006431152,0.002550175,0.003121499],"category_scores_gemma":[0.04394877,0.001350543,0.00302881,0.008386554,0.002064916,0.01172472,0.008258821,0.005841135,0.002104602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001753602,"about_ca_system_score_gemma":0.004067641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006720821,"about_ca_topic_score_gemma":0.007839037,"domain_scores_codex":[0.9898854,0.002585058,0.0008387254,0.002932916,0.003308429,0.0004492989],"domain_scores_gemma":[0.9761038,0.01008696,0.00211629,0.0083159,0.003017836,0.0003592208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000764413,0.0006248729,0.01398272,0.0006233287,0.0006596883,0.0003834111,0.001034321,0.1961879,0.007492799,0.03623721,0.01979479,0.7222146],"study_design_scores_gemma":[0.00004992895,0.00009711823,0.001325699,0.00008393019,0.0001459866,0.0002360265,0.0001464086,0.9185882,0.009345485,0.05918368,0.01073118,0.00006645304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005955284,0.0004099309,0.9877331,0.0005256424,0.00009234047,0.0001325693,0.0008212654,0.003461639,0.0008682154],"genre_scores_gemma":[0.1695445,0.0004105394,0.8218092,0.0005150529,0.0002642959,0.0003005081,0.005018301,0.0002717017,0.001865879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01136022,"threshold_uncertainty_score":0.06007928,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}