{"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":"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":[0.0015667009,0.000019525358,0.9815032,0.014978017,0.00044970537,0.00008196936,0.00006852633,0.00031668326,0.0010157088],"genre_scores_gemma":[0.82085353,0.00002922191,0.17612761,0.0027293717,0.000088257046,0.000005708147,0.000008238918,0.000008787587,0.00014924616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790466,0.000041746007,0.00016938036,0.0009480175,0.00059358444,0.0003426038],"domain_scores_gemma":[0.9969416,0.00008832551,0.00005133266,0.002580889,0.000049357997,0.0002884732],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00048969314,0.00013063359,0.000116203875,0.00011453369,0.0005602127,0.00043341037,0.008285082,0.000027698394,0.00009263845],"category_scores_gemma":[0.00020173735,0.00011486581,0.000031061132,0.0017021392,0.00023172732,0.002588109,0.00025711037,0.00032833632,0.0004901678],"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":[0.000009362915,0.000120090175,0.000070815666,0.000012159994,0.000011159513,0.000021624182,0.0012124529,0.0036941788,0.0036151474,0.0020578995,0.0014568279,0.9877183],"study_design_scores_gemma":[0.00028594915,0.00026294272,0.00090382405,0.000016465565,0.000008369916,0.000027398697,0.00007487123,0.934579,0.0032957112,0.0002829031,0.05994931,0.0003132114],"about_ca_topic_score_codex":0.00003478943,"about_ca_topic_score_gemma":0.000004819406,"teacher_disagreement_score":0.98740506,"about_ca_system_score_codex":0.00001851924,"about_ca_system_score_gemma":0.00016669523,"threshold_uncertainty_score":0.99708056},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060676867,0.000056229335,0.98702824,0.0047790403,0.0005923597,0.00023197559,0.0008203324,0.0002912243,0.00013290584],"genre_scores_gemma":[0.82037336,0.000034568726,0.17713118,0.0022065975,0.00007670352,0.000030337842,0.000056274064,0.000017310587,0.000073698444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996933,0.00005867896,0.00038232372,0.0012982003,0.00083763315,0.0004901963],"domain_scores_gemma":[0.9954671,0.00015790308,0.00012709243,0.0037848684,0.00010702091,0.00035597236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049432274,0.00025378074,0.00024232146,0.00015948179,0.00062299607,0.00025847368,0.0049279463,0.000045838242,0.00013281695],"category_scores_gemma":[0.0002006868,0.00021902753,0.000070694696,0.0016359142,0.0006298501,0.0040361667,0.00025001145,0.0002755843,0.00015130905],"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":[0.0003349907,0.0014581298,0.0007763621,0.00040693374,0.0001422212,0.0002365388,0.0062771896,0.044442303,0.043046515,0.09870577,0.00855376,0.7956193],"study_design_scores_gemma":[0.0014133789,0.0009559705,0.0014295559,0.00032028434,0.00003832893,0.000041294563,0.00062207703,0.5841052,0.06841784,0.00047156113,0.3408477,0.0013368007],"about_ca_topic_score_codex":0.00017150787,"about_ca_topic_score_gemma":0.00012765148,"teacher_disagreement_score":0.81430566,"about_ca_system_score_codex":0.00008090776,"about_ca_system_score_gemma":0.00041252805,"threshold_uncertainty_score":0.91574323},"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":"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":[0.00079823984,0.000033790096,0.9952773,0.0017535045,0.0005526813,0.00037411024,0.00043726765,0.00056662183,0.00020647621],"genre_scores_gemma":[0.6590311,0.00022560952,0.33872512,0.00028761476,0.00005390662,0.00009201417,0.0012742889,0.000019498151,0.00029084747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964529,0.00009665756,0.00038544595,0.0018902415,0.00072262355,0.0004520883],"domain_scores_gemma":[0.98963106,0.0003339193,0.0001586782,0.009361732,0.00037634253,0.00013824906],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0013516021,0.00018178522,0.00017546129,0.00029683992,0.0011809055,0.0006239695,0.008993422,0.00007802892,0.00003853769],"category_scores_gemma":[0.0013161858,0.00018547862,0.00003765209,0.002412387,0.00026690884,0.008841366,0.00057282473,0.00032228744,0.000052257124],"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":[0.000020939677,0.00018454305,0.000030885687,0.000020816673,0.000017151058,0.0000062174495,0.00018518824,0.00083744846,0.14071345,0.0009871443,0.000536599,0.8564596],"study_design_scores_gemma":[0.0004304949,0.00012974953,0.0007790657,0.000031485033,0.00002658232,0.000096183816,0.0002450694,0.6219256,0.34209043,0.0009421242,0.032948174,0.00035508245],"about_ca_topic_score_codex":0.00007904704,"about_ca_topic_score_gemma":0.00013005068,"teacher_disagreement_score":0.85610455,"about_ca_system_score_codex":0.00014561441,"about_ca_system_score_gemma":0.0004934566,"threshold_uncertainty_score":0.9963684},"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":"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":[0.18273325,0.000121396166,0.78608876,0.02135972,0.0014389982,0.0007860752,0.0012220311,0.0009082753,0.005341474],"genre_scores_gemma":[0.8434577,0.000058937123,0.1542929,0.0010092111,0.0000926651,0.000036739566,0.00007923273,0.000021575897,0.0009510147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981957,0.000050476658,0.00028123535,0.00066163065,0.00044142196,0.00036954615],"domain_scores_gemma":[0.9961671,0.000442264,0.00007261415,0.0029858781,0.00017165179,0.00016048615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044295954,0.00013676025,0.00017172398,0.00008167191,0.00083866913,0.00018221243,0.001658244,0.000044359218,0.00059394736],"category_scores_gemma":[0.00026445437,0.00012719128,0.0000596504,0.0014457499,0.00031803423,0.00069683575,0.00006594269,0.00023518315,0.0002070199],"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":[0.00023393882,0.0059555904,0.0005730638,0.00017681018,0.00028160168,0.00019159047,0.0012466179,0.012709961,0.16986403,0.50246054,0.13697018,0.16933605],"study_design_scores_gemma":[0.006704404,0.0004699184,0.017142273,0.00047137783,0.0009437872,0.001681905,0.0029313446,0.2705031,0.09456358,0.3235555,0.2770638,0.003969017],"about_ca_topic_score_codex":0.000010285869,"about_ca_topic_score_gemma":0.000051925817,"teacher_disagreement_score":0.66072446,"about_ca_system_score_codex":0.000034411336,"about_ca_system_score_gemma":0.0001547013,"threshold_uncertainty_score":0.65033066},"labels":[],"label_agreement":null}]}