{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"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"},"query_hash":"55a6ee9ff08d","filters":{"venue":"ACM/IMS 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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.076600776069982,"gpt":0.3117897892712219,"spread":0.2351890132012399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004896931,0.0001306336,0.0001162039,0.0001145337,0.0005602127,0.0004334104,0.008285082,0.00002769839,0.00009263845],"category_scores_gemma":[0.0002017373,0.0001148658,0.00003106113,0.001702139,0.0002317273,0.002588109,0.0002571104,0.0003283363,0.0004901678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001851924,"about_ca_system_score_gemma":0.0001666952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003478943,"about_ca_topic_score_gemma":0.000004819406,"domain_scores_codex":[0.9979047,0.00004174601,0.0001693804,0.0009480175,0.0005935844,0.0003426038],"domain_scores_gemma":[0.9969416,0.00008832551,0.00005133266,0.002580889,0.000049358,0.0002884732],"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":[0.000009362915,0.0001200902,0.00007081567,0.00001215999,0.00001115951,0.00002162418,0.001212453,0.003694179,0.003615147,0.002057899,0.001456828,0.9877183],"study_design_scores_gemma":[0.0002859492,0.0002629427,0.0009038241,0.00001646556,0.000008369916,0.0000273987,0.00007487123,0.934579,0.003295711,0.0002829031,0.05994931,0.0003132114],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001566701,0.00001952536,0.9815032,0.01497802,0.0004497054,0.00008196936,0.00006852633,0.0003166833,0.001015709],"genre_scores_gemma":[0.8208535,0.00002922191,0.1761276,0.002729372,0.00008825705,0.000005708147,0.000008238918,0.000008787587,0.0001492462],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9874051,"threshold_uncertainty_score":0.9970806,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1334307593239981,"gpt":0.3654867943384096,"spread":0.2320560350144115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001351602,0.0001817852,0.0001754613,0.0002968399,0.001180905,0.0006239695,0.008993422,0.00007802892,0.00003853769],"category_scores_gemma":[0.001316186,0.0001854786,0.00003765209,0.002412387,0.0002669088,0.008841366,0.0005728247,0.0003222874,0.00005225712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001456144,"about_ca_system_score_gemma":0.0004934566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007904704,"about_ca_topic_score_gemma":0.0001300507,"domain_scores_codex":[0.9964529,0.00009665756,0.000385446,0.001890242,0.0007226235,0.0004520883],"domain_scores_gemma":[0.9896311,0.0003339193,0.0001586782,0.009361732,0.0003763425,0.0001382491],"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":[0.00002093968,0.0001845431,0.00003088569,0.00002081667,0.00001715106,0.000006217449,0.0001851882,0.0008374485,0.1407135,0.0009871443,0.000536599,0.8564596],"study_design_scores_gemma":[0.0004304949,0.0001297495,0.0007790657,0.00003148503,0.00002658232,0.00009618382,0.0002450694,0.6219256,0.3420904,0.0009421242,0.03294817,0.0003550824],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007982398,0.0000337901,0.9952773,0.001753505,0.0005526813,0.0003741102,0.0004372676,0.0005666218,0.0002064762],"genre_scores_gemma":[0.6590311,0.0002256095,0.3387251,0.0002876148,0.00005390662,0.00009201417,0.001274289,0.00001949815,0.0002908475],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8561046,"threshold_uncertainty_score":0.9963684,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06056157224516586,"gpt":0.318393266819087,"spread":0.2578316945739211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004943227,0.0002537807,0.0002423215,0.0001594818,0.0006229961,0.0002584737,0.004927946,0.00004583824,0.0001328169],"category_scores_gemma":[0.0002006868,0.0002190275,0.0000706947,0.001635914,0.0006298501,0.004036167,0.0002500114,0.0002755843,0.0001513091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008090776,"about_ca_system_score_gemma":0.0004125281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001715079,"about_ca_topic_score_gemma":0.0001276515,"domain_scores_codex":[0.996933,0.00005867896,0.0003823237,0.0012982,0.0008376332,0.0004901963],"domain_scores_gemma":[0.9954671,0.0001579031,0.0001270924,0.003784868,0.0001070209,0.0003559724],"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":[0.0003349907,0.00145813,0.0007763621,0.0004069337,0.0001422212,0.0002365388,0.00627719,0.0444423,0.04304652,0.09870577,0.00855376,0.7956193],"study_design_scores_gemma":[0.001413379,0.0009559705,0.001429556,0.0003202843,0.00003832893,0.00004129456,0.000622077,0.5841052,0.06841784,0.0004715611,0.3408477,0.001336801],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006067687,0.00005622934,0.9870282,0.00477904,0.0005923597,0.0002319756,0.0008203324,0.0002912243,0.0001329058],"genre_scores_gemma":[0.8203734,0.00003456873,0.1771312,0.002206597,0.00007670352,0.00003033784,0.00005627406,0.00001731059,0.00007369844],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8143057,"threshold_uncertainty_score":0.9157432,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1596832134277979,"gpt":0.3908336471541423,"spread":0.2311504337263444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004429595,0.0001367603,0.000171724,0.00008167191,0.0008386691,0.0001822124,0.001658244,0.00004435922,0.0005939474],"category_scores_gemma":[0.0002644544,0.0001271913,0.0000596504,0.00144575,0.0003180342,0.0006968357,0.00006594269,0.0002351831,0.0002070199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003441134,"about_ca_system_score_gemma":0.0001547013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001028587,"about_ca_topic_score_gemma":0.00005192582,"domain_scores_codex":[0.9981957,0.00005047666,0.0002812353,0.0006616306,0.000441422,0.0003695461],"domain_scores_gemma":[0.9961671,0.000442264,0.00007261415,0.002985878,0.0001716518,0.0001604861],"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":[0.0002339388,0.00595559,0.0005730638,0.0001768102,0.0002816017,0.0001915905,0.001246618,0.01270996,0.169864,0.5024605,0.1369702,0.1693361],"study_design_scores_gemma":[0.006704404,0.0004699184,0.01714227,0.0004713778,0.0009437872,0.001681905,0.002931345,0.2705031,0.09456358,0.3235555,0.2770638,0.003969017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1827333,0.0001213962,0.7860888,0.02135972,0.001438998,0.0007860752,0.001222031,0.0009082753,0.005341474],"genre_scores_gemma":[0.8434577,0.00005893712,0.1542929,0.001009211,0.0000926651,0.00003673957,0.00007923273,0.0000215759,0.0009510147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6607245,"threshold_uncertainty_score":0.6503307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}