{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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":"6ae6e644c581","filters":{"venue":"Knowledge Discovery and Data Mining"}},"results":[{"id":"W62188274","doi":"10.5555/1760894.1760939","title":"Position coded pre-order linked WAP-tree for web log sequential pattern mining","year":2003,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Prefix; Computer science; Tree (set theory); Trie; Fractal tree index; Web log analysis software; Suffix tree; Preorder; Suffix; Node (physics); Segment tree; Binary tree; Tree structure; Data mining; Interval tree; Data structure; Algorithm; Web server; Mathematics; World Wide Web; The Internet; Combinatorics; Discrete mathematics; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.0458814739950354,"gpt":0.3150776749332564,"spread":0.269196200938221,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005677851,0.0002291398,0.0002357067,0.00009745618,0.0004113821,0.000747923,0.001048661,0.00009689187,0.000009227666],"category_scores_gemma":[0.0001803538,0.0002234577,0.00004254017,0.0003102046,0.00007577762,0.002597721,0.0007349769,0.0001097043,0.00001562485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002440603,"about_ca_system_score_gemma":0.000214032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001448355,"about_ca_topic_score_gemma":0.0001183155,"domain_scores_codex":[0.9981216,0.0000776983,0.0003436356,0.00093053,0.0001371524,0.0003894085],"domain_scores_gemma":[0.9981208,0.000289954,0.0001330499,0.001246736,0.00009334587,0.0001160907],"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":[0.00004237843,0.000638014,0.002969009,0.0002481173,0.0001921881,0.00001967996,0.008129,0.00002260011,0.005925454,0.02519174,0.0393478,0.917274],"study_design_scores_gemma":[0.002995464,0.000311984,0.003116003,0.0003780765,0.0001683076,0.0001200084,0.001301016,0.8845803,0.001861209,0.0009784411,0.1030077,0.001181428],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08183807,0.0004857051,0.9131666,0.0001878481,0.0004952222,0.0003215682,0.001069693,0.000111964,0.00232327],"genre_scores_gemma":[0.6774954,0.00005483827,0.3167334,0.0002522583,0.0003659299,0.0001636188,0.003249914,0.00004042601,0.001644131],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9160926,"threshold_uncertainty_score":0.9112341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2805055069","doi":"","title":"Ensemble-Based Anomaly Detetction using Cooperative Learning.","year":2017,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Ensemble learning; Anomaly detection; Artificial intelligence; Anomaly (physics); Machine learning; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.08496144598796657,"gpt":0.3523860738405971,"spread":0.2674246278526305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002715887,0.0001241829,0.0001297011,0.00006543552,0.001459243,0.00110666,0.0009558623,0.00005700512,0.000003376184],"category_scores_gemma":[0.0001137068,0.0001187652,0.00002466553,0.00009974228,0.0001038423,0.002842813,0.0008740136,0.0001246103,0.00001021738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002148246,"about_ca_system_score_gemma":0.0001011014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000458217,"about_ca_topic_score_gemma":0.00005859557,"domain_scores_codex":[0.999057,0.00004845399,0.0001368346,0.0005200126,0.00007156633,0.0001661122],"domain_scores_gemma":[0.9984095,0.0000715748,0.000156403,0.001241514,0.00006173069,0.0000592472],"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":[0.00007540927,0.000434606,0.03677882,0.0001273455,0.0001040009,0.00003263261,0.002406627,0.0004940153,0.04457005,0.04076567,0.003527991,0.8706828],"study_design_scores_gemma":[0.0003683861,0.000125366,0.005713122,0.00007856391,0.00002379236,0.00002277589,0.0001679825,0.9554408,0.01507213,0.0001456595,0.02251055,0.0003308476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1503478,0.0001370512,0.8462742,0.0001345173,0.0001126823,0.0001031747,0.00001506967,0.0001099188,0.00276556],"genre_scores_gemma":[0.9540355,0.00001631275,0.04497621,0.00003255967,0.00008828813,0.00001367756,0.00002996067,0.000008536183,0.0007990067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9549468,"threshold_uncertainty_score":0.9999303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2415000644","doi":"","title":"Learning Nonstationary Models of Normal Network Traffic for Detecting Novel Attacks, Edmonton, Alberta","year":2002,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Computer network; Artificial intelligence; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.05873503901820595,"gpt":0.2885419494280673,"spread":0.2298069104098614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003093383,0.0001301582,0.0001777713,0.00006426597,0.0003904895,0.0001270634,0.0005955388,0.00006043179,0.000004980109],"category_scores_gemma":[0.00007143035,0.0001324631,0.00004493815,0.0002963407,0.00005016511,0.002067546,0.0004704727,0.0001077269,0.000002392746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001171999,"about_ca_system_score_gemma":0.00002650796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001889332,"about_ca_topic_score_gemma":0.00009162656,"domain_scores_codex":[0.9988865,0.0000237643,0.0003144584,0.0004605864,0.00007857617,0.0002361369],"domain_scores_gemma":[0.9987482,0.0004504133,0.0001685377,0.0005157032,0.00006271359,0.00005436871],"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":[0.00004662363,0.0005140578,0.0009387345,0.0002450526,0.0001174841,0.000001571972,0.0101586,0.07103395,0.001563563,0.0527132,0.008106056,0.8545611],"study_design_scores_gemma":[0.0002419022,0.0000992568,0.0001215092,0.00005749292,0.00001563798,0.00001405293,0.0002282768,0.9931043,0.0001777582,0.0001815266,0.005590447,0.0001678392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0375471,0.00059614,0.9586526,0.00006585079,0.00007741287,0.0001966051,0.00003979007,0.00008104001,0.002743475],"genre_scores_gemma":[0.8586611,0.00006091088,0.1400372,0.00002240026,0.0001013972,0.00004759181,0.00006315168,0.00001210432,0.0009941577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9220703,"threshold_uncertainty_score":0.5401689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W73242358","doi":"","title":"Matching Unstructured Offers to Structured Product Descriptions","year":2011,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":3,"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":"","keywords":"Computer science; Matching (statistics); Product (mathematics); Component (thermodynamics); Function (biology); Information retrieval; Database; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07683517453153065,"gpt":0.2881091713015354,"spread":0.2112739967700047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003780527,0.0002220395,0.0002546254,0.0002225789,0.0003229533,0.0005174833,0.001884041,0.00004553107,0.00001898127],"category_scores_gemma":[0.0001237906,0.0001921887,0.00003891542,0.000599579,0.00006383879,0.003305271,0.001951104,0.0001365467,0.00002884658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001770317,"about_ca_system_score_gemma":0.00009439328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001181102,"about_ca_topic_score_gemma":0.0002800536,"domain_scores_codex":[0.9981526,0.00007862105,0.0002726692,0.001000485,0.0001469177,0.0003487131],"domain_scores_gemma":[0.9977233,0.00005170414,0.00007864634,0.00191999,0.00004553462,0.000180815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001147247,0.0003791022,0.02291909,0.0002598912,0.000690161,0.0001173982,0.1458265,0.00005910094,0.02089812,0.09169064,0.02383902,0.6932063],"study_design_scores_gemma":[0.007165175,0.0014281,0.5754727,0.002983667,0.002246215,0.00136768,0.05753015,0.1035003,0.05840624,0.05436594,0.1221121,0.01342175],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6565318,0.0005209907,0.3371572,0.0001377994,0.000887422,0.0001633123,0.0003851075,0.0001940633,0.004022263],"genre_scores_gemma":[0.8717101,0.00001205579,0.1273927,0.000098333,0.0001304719,0.000005910787,0.000220527,0.00001278772,0.0004171359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6797845,"threshold_uncertainty_score":0.7837229,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3003238448","doi":"","title":"Towards a Benchmark for Knowledge Base Exchange.","year":2019,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Knowledge base; Base (topology); Artificial intelligence; Mathematics; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.06517942266695431,"gpt":0.3206417762695815,"spread":0.2554623536026271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007208461,0.0002050278,0.0002943584,0.0001125449,0.0001512757,0.0004078182,0.001516925,0.00008315215,0.00002611383],"category_scores_gemma":[0.0003035695,0.0001724583,0.00005414365,0.0002300087,0.00005892259,0.002455958,0.002036369,0.00008170996,0.00007628827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001979108,"about_ca_system_score_gemma":0.000194593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001337586,"about_ca_topic_score_gemma":0.0001063483,"domain_scores_codex":[0.9983631,0.00005485685,0.0002260779,0.000831961,0.00009597868,0.0004280029],"domain_scores_gemma":[0.9978231,0.0005453934,0.00007022358,0.001402694,0.00006018202,0.00009839171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008845452,0.0004216845,0.008537241,0.001129224,0.000125575,0.00001968133,0.01496991,0.000002163156,0.0007222385,0.08154622,0.07734869,0.8150889],"study_design_scores_gemma":[0.00540668,0.00104866,0.02348133,0.0009780242,0.0001668535,0.0001118931,0.006300933,0.3310945,0.003490946,0.006376818,0.6192675,0.002275936],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.394911,0.02876454,0.4653501,0.0007845408,0.005552466,0.001206063,0.0005166355,0.0004004933,0.1025142],"genre_scores_gemma":[0.9438825,0.000201714,0.04887032,0.0001921127,0.00042551,0.00005433085,0.0003094113,0.00002347078,0.006040652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.812813,"threshold_uncertainty_score":0.7032644,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3004067286","doi":"","title":"Detecting and Correcting Typing Errors in DBpedia.","year":2019,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Typing; Information retrieval; Artificial intelligence; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.03783106692397872,"gpt":0.3066728428562663,"spread":0.2688417759322875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008268494,0.000113747,0.0001505637,0.0001756632,0.00008151837,0.0003139915,0.0005846683,0.00004641257,0.000002661113],"category_scores_gemma":[0.00127165,0.0001151145,0.000009378013,0.0003694487,0.00002416372,0.002102339,0.001803347,0.0002166069,0.00001572855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002404074,"about_ca_system_score_gemma":0.00005510086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003020689,"about_ca_topic_score_gemma":0.00006945085,"domain_scores_codex":[0.9988452,0.00004307349,0.0001596898,0.0005628274,0.00008657113,0.0003027011],"domain_scores_gemma":[0.9979375,0.001343907,0.00003408291,0.0006056248,0.00001703018,0.0000618288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009167121,0.00002440853,0.7026823,0.0001816407,0.00001233423,0.00001761841,0.006503529,0.00006988645,0.0006371384,0.0003122235,0.00009346298,0.2894562],"study_design_scores_gemma":[0.001435766,0.0001553369,0.2915037,0.0012637,0.00001135326,0.0001978839,0.004576309,0.6968045,0.001305279,0.0001516712,0.001645913,0.0009486561],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9733345,0.001279513,0.02414845,0.00001942867,0.0005237958,0.00009326876,0.000004118319,0.00007806467,0.0005188858],"genre_scores_gemma":[0.9929383,0.00002083619,0.006782884,0.00001106833,0.00005967588,0.000003476531,0.000007187615,0.00001111313,0.0001654907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6967345,"threshold_uncertainty_score":0.4694235,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}