{"meta":{"query_hash":"55a6ee9ff08d","filters":{"venue":"ACM/IMS Transactions on Data Science"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/55a6ee9ff08d","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM%2FIMS+Transactions+on+Data+Science"},"results":[{"id":"W3033527224","doi":"10.1145/3385188","title":"Asterisk","year":2020,"lang":"en","type":"article","venue":"ACM/IMS Transactions on Data Science","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Computer science; Heuristics; Quality (philosophy); Machine learning; Preprocessor; Process (computing); Artificial intelligence; Annotation; IBM; Data mining","score_opus":0.076600776069982,"score_gpt":0.3117897892712219,"score_spread":0.23518901320123992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033527224","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004295618,0.0018842784,0.17439349,0.017029164,0.023043796,0.0012999568,0.110674284,0.06868587,0.5986935],"genre_scores_gemma":[0.03417986,0.0031727282,0.19867161,0.007877329,0.0034366213,0.0011054715,0.19108659,0.023088822,0.537381],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99593604,0.00076771964,0.00062904577,0.0010279006,0.0012997191,0.00033964112],"domain_scores_gemma":[0.9803602,0.004138392,0.0017003835,0.007390639,0.005592095,0.00081822043],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032665827,0.0015406132,0.0012865087,0.0035188727,0.0027294739,0.008265748,0.004449442,0.0037806232,0.5137476],"category_scores_gemma":[0.0220295,0.0009966356,0.0011019119,0.005846728,0.0014770945,0.007292263,0.005289281,0.0032071567,0.49635264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021891748,0.000046453926,0.0005737723,0.00043449752,0.000015363987,0.00026431005,0.0001568375,0.00039634467,0.0015307885,0.017956857,0.8848882,0.09351762],"study_design_scores_gemma":[0.000022894212,0.000013718455,0.00026984402,0.00011697911,0.0000051461725,0.00021227275,0.00009658119,0.00065734045,0.001319498,0.0064296466,0.9908386,0.000017402686],"about_ca_topic_score_codex":0.0023308806,"about_ca_topic_score_gemma":0.0023886508,"teacher_disagreement_score":0.48625243,"about_ca_system_score_codex":0.0017308844,"about_ca_system_score_gemma":0.0035721855,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W3041355115","doi":"10.1145/3385191","title":"Interval-based Queries over Lossy IoT Event Streams","year":2020,"lang":"en","type":"article","venue":"ACM/IMS Transactions on Data Science","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":6,"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":"Deutsche Forschungsgemeinschaft; Alexander von Humboldt-Stiftung","keywords":"Computer science; Event (particle physics); Timestamp; Probabilistic logic; Interval (graph theory); Sequence (biology); Data mining; Theoretical computer science; Real-time computing; Artificial intelligence; Mathematics","score_opus":0.06056157224516586,"score_gpt":0.318393266819087,"score_spread":0.25783169457392113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041355115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08135834,0.00042199506,0.91102934,0.00034746813,0.000054933887,0.00023937911,0.0015045169,0.0034238482,0.0016202632],"genre_scores_gemma":[0.75749254,0.0003050052,0.23782955,0.00014429895,0.00010876094,0.00021501299,0.0025831352,0.00031963203,0.001002144],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99435437,0.0011046131,0.00059791066,0.0009768705,0.0026898705,0.00027638234],"domain_scores_gemma":[0.98772556,0.008600642,0.0010512929,0.00094936,0.001289405,0.00038374757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031908748,0.0010695832,0.0012645797,0.0017898951,0.00063155603,0.0027949682,0.0022181314,0.00095087674,0.0020644541],"category_scores_gemma":[0.021865811,0.0005214424,0.00096558343,0.0020905798,0.00075055746,0.004255876,0.0022058568,0.001213748,0.00043420543],"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":[0.0012413841,0.00028361107,0.010980384,0.00041133663,0.00021598967,0.0007507073,0.00066925195,0.76868516,0.009431635,0.038255177,0.0056197937,0.16345559],"study_design_scores_gemma":[0.00001651553,0.000028854462,0.0003067041,0.000008586156,0.000008382253,0.000075823125,0.000068165464,0.98041534,0.0018553529,0.016437588,0.0007707669,0.000007852275],"about_ca_topic_score_codex":0.0037139636,"about_ca_topic_score_gemma":0.0035147353,"teacher_disagreement_score":0.0037139636,"about_ca_system_score_codex":0.0012801363,"about_ca_system_score_gemma":0.0010867774,"threshold_uncertainty_score":0.016875148},"labels":[],"label_agreement":null},{"id":"W3161168558","doi":"10.1145/3447541","title":"TabReformer: Unsupervised Representation Learning for Erroneous Data Detection","year":2021,"lang":"en","type":"article","venue":"ACM/IMS Transactions on Data Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","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":"IBM (Canada); University of Alberta","funders":"","keywords":"Computer science; Pipeline (software); Range (aeronautics); Representation (politics); Encoder; Probabilistic logic; Artificial intelligence; Tuple; Machine learning; External Data Representation; Mixture model; Task (project management); Data mining; Mathematics","score_opus":0.13343075932399806,"score_gpt":0.3654867943384096,"score_spread":0.23205603501441152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161168558","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":[0.020806821,0.0006514707,0.94931966,0.00037381533,0.00015160059,0.00017342696,0.0015846869,0.02579315,0.0011453611],"genre_scores_gemma":[0.32504967,0.0005654745,0.65673697,0.000762548,0.00012552374,0.00055526197,0.008846264,0.0014776643,0.005880588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862874,0.00031451677,0.00009495452,0.0004146288,0.0004180984,0.00012905305],"domain_scores_gemma":[0.9965827,0.0011898055,0.00030773255,0.001176867,0.00066213554,0.00008089797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026911101,0.0013382625,0.0010843812,0.0016517643,0.00044101092,0.0014698999,0.0034129138,0.0013909228,0.0036452697],"category_scores_gemma":[0.01049024,0.0004717833,0.0010411676,0.0016601486,0.00069633086,0.0032311694,0.002346288,0.0021021452,0.0025206818],"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":[0.00036647858,0.0002451871,0.0040917727,0.00025887685,0.00010697773,0.00015938874,0.0002345342,0.06896214,0.008176684,0.0057964493,0.029298896,0.88230264],"study_design_scores_gemma":[0.000023798615,0.00009487145,0.0005705663,0.000042975484,0.000026842457,0.00011119843,0.000055466735,0.9718132,0.012833421,0.0094053745,0.0049972385,0.000024971578],"about_ca_topic_score_codex":0.0037366147,"about_ca_topic_score_gemma":0.005197323,"teacher_disagreement_score":0.0037366147,"about_ca_system_score_codex":0.0008966124,"about_ca_system_score_gemma":0.0015350503,"threshold_uncertainty_score":0.014232099},"labels":[],"label_agreement":null},{"id":"W4211105203","doi":"10.1145/3491255","title":"Quantized Tensor Neural Network","year":2021,"lang":"en","type":"article","venue":"ACM/IMS Transactions on Data Science","topic":"Tensor decomposition and applications","field":"Mathematics","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":"St. Francis Xavier University","funders":"National Natural Science Foundation of China","keywords":"Tensor (intrinsic definition); Artificial neural network; Computer science; Artificial intelligence; Deep learning; Machine learning; Mathematics","score_opus":0.1596832134277979,"score_gpt":0.39083364715414226,"score_spread":0.23115043372634436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211105203","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":[0.009297315,0.0012076832,0.98386765,0.00045701864,0.00029099255,0.000047797377,0.0004946831,0.0010220476,0.0033147929],"genre_scores_gemma":[0.5405702,0.0034014543,0.44286257,0.00045974317,0.00038038337,0.00021475414,0.0019687458,0.0002874761,0.00985472],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922,0.00019544455,0.000060318132,0.00018427536,0.00024069911,0.000099201694],"domain_scores_gemma":[0.99892443,0.00026568767,0.00014008864,0.00018483924,0.00042130423,0.00006364147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094149803,0.0010017658,0.0010369853,0.00091528497,0.00052752893,0.0015424129,0.0014705467,0.00080618693,0.0033696042],"category_scores_gemma":[0.0037811908,0.0003702943,0.00076421705,0.0015984046,0.0009785201,0.0027991654,0.0010160819,0.0015908895,0.00090910966],"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":[0.00023680336,0.0000666228,0.0020293342,0.00042114698,0.00014008883,0.00017701964,0.000115741655,0.6294147,0.008666501,0.12858653,0.01451589,0.21562962],"study_design_scores_gemma":[0.0000046014165,0.000016350896,0.0001522731,0.000011243596,0.0000100073585,0.000027474702,0.000009223749,0.9774968,0.0009005675,0.019013932,0.002346766,0.000010798011],"about_ca_topic_score_codex":0.01081475,"about_ca_topic_score_gemma":0.009619813,"teacher_disagreement_score":0.01081475,"about_ca_system_score_codex":0.0015184358,"about_ca_system_score_gemma":0.0015851823,"threshold_uncertainty_score":0.021503627},"labels":[],"label_agreement":null}]}