{"meta":{"query_hash":"6ae6e644c581","filters":{"venue":"Knowledge Discovery and Data Mining"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"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/6ae6e644c581","api":"https://metacan.xera.ac/api/v1/cohort?venue=Knowledge+Discovery+and+Data+Mining"},"results":[{"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Computer network; Artificial intelligence; Computer security","score_opus":0.058735039018205946,"score_gpt":0.2885419494280673,"score_spread":0.22980691040986137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2415000644","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":[0.037547104,0.00059614,0.95865256,0.000065850785,0.00007741287,0.0001966051,0.00003979007,0.00008104001,0.0027434747],"genre_scores_gemma":[0.8586611,0.000060910883,0.14003716,0.000022400258,0.000101397185,0.00004759181,0.00006315168,0.000012104325,0.0009941577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888647,0.000023764296,0.00031445842,0.0004605864,0.000078576166,0.00023613691],"domain_scores_gemma":[0.99874824,0.0004504133,0.0001685377,0.0005157032,0.00006271359,0.000054368713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030933833,0.00013015821,0.0001777713,0.000064265965,0.0003904895,0.00012706337,0.00059553876,0.000060431794,0.000004980109],"category_scores_gemma":[0.000071430346,0.00013246312,0.00004493815,0.0002963407,0.00005016511,0.0020675461,0.00047047267,0.00010772689,0.0000023927464],"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":[0.000046623627,0.0005140578,0.0009387345,0.00024505256,0.00011748409,0.0000015719718,0.0101585975,0.07103395,0.001563563,0.052713204,0.008106056,0.8545611],"study_design_scores_gemma":[0.00024190223,0.0000992568,0.000121509234,0.000057492918,0.000015637985,0.000014052928,0.0002282768,0.9931043,0.0001777582,0.00018152663,0.0055904468,0.00016783923],"about_ca_topic_score_codex":0.000018893319,"about_ca_topic_score_gemma":0.00009162656,"teacher_disagreement_score":0.9220703,"about_ca_system_score_codex":0.000011719989,"about_ca_system_score_gemma":0.00002650796,"threshold_uncertainty_score":0.54016894},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Ensemble learning; Anomaly detection; Artificial intelligence; Anomaly (physics); Machine learning; Physics","score_opus":0.08496144598796657,"score_gpt":0.35238607384059706,"score_spread":0.2674246278526305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805055069","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":[0.1503478,0.00013705117,0.8462742,0.00013451734,0.000112682275,0.000103174694,0.000015069673,0.00010991879,0.00276556],"genre_scores_gemma":[0.95403546,0.000016312753,0.044976212,0.000032559674,0.00008828813,0.000013677561,0.000029960673,0.0000085361835,0.0007990067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999057,0.000048453992,0.00013683461,0.0005200126,0.000071566334,0.00016611218],"domain_scores_gemma":[0.9984095,0.000071574796,0.000156403,0.0012415143,0.00006173069,0.000059247202],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00027158868,0.00012418295,0.00012970113,0.00006543552,0.0014592428,0.0011066602,0.0009558623,0.000057005123,0.000003376184],"category_scores_gemma":[0.00011370678,0.00011876519,0.000024665535,0.00009974228,0.000103842336,0.0028428128,0.00087401364,0.00012461028,0.0000102173835],"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":[0.00007540927,0.00043460602,0.03677882,0.00012734554,0.000104000916,0.00003263261,0.0024066274,0.00049401534,0.04457005,0.040765665,0.0035279905,0.87068284],"study_design_scores_gemma":[0.0003683861,0.000125366,0.0057131224,0.00007856391,0.000023792361,0.000022775888,0.00016798249,0.9554408,0.015072134,0.00014565955,0.022510545,0.0003308476],"about_ca_topic_score_codex":0.000045821696,"about_ca_topic_score_gemma":0.000058595568,"teacher_disagreement_score":0.9549468,"about_ca_system_score_codex":0.000021482463,"about_ca_system_score_gemma":0.00010110144,"threshold_uncertainty_score":0.99993026},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Knowledge base; Base (topology); Artificial intelligence; Mathematics; Geology","score_opus":0.06517942266695431,"score_gpt":0.32064177626958146,"score_spread":0.25546235360262715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003238448","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":[0.39491102,0.028764537,0.46535006,0.00078454084,0.0055524665,0.0012060627,0.0005166355,0.0004004933,0.10251417],"genre_scores_gemma":[0.94388247,0.00020171404,0.04887032,0.00019211265,0.00042551,0.00005433085,0.00030941135,0.000023470777,0.0060406523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836314,0.000054856853,0.00022607786,0.000831961,0.00009597868,0.00042800294],"domain_scores_gemma":[0.9978231,0.0005453934,0.00007022358,0.0014026943,0.000060182025,0.000098391705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007208461,0.00020502784,0.0002943584,0.00011254489,0.0001512757,0.00040781815,0.001516925,0.000083152154,0.000026113834],"category_scores_gemma":[0.00030356948,0.00017245825,0.000054143653,0.00023000866,0.00005892259,0.0024559584,0.0020363687,0.00008170996,0.00007628827],"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":[0.000088454515,0.00042168447,0.008537241,0.0011292244,0.00012557495,0.00001968133,0.0149699105,0.000002163156,0.0007222385,0.081546225,0.07734869,0.8150889],"study_design_scores_gemma":[0.0054066796,0.0010486597,0.023481328,0.0009780242,0.0001668535,0.000111893074,0.0063009327,0.33109447,0.0034909458,0.0063768183,0.61926746,0.0022759358],"about_ca_topic_score_codex":0.000013375859,"about_ca_topic_score_gemma":0.00010634828,"teacher_disagreement_score":0.812813,"about_ca_system_score_codex":0.000019791078,"about_ca_system_score_gemma":0.00019459301,"threshold_uncertainty_score":0.70326436},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Typing; Information retrieval; Artificial intelligence; Speech recognition","score_opus":0.03783106692397872,"score_gpt":0.3066728428562663,"score_spread":0.26884177593228753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004067286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733345,0.0012795127,0.024148447,0.000019428668,0.0005237958,0.00009326876,0.0000041183193,0.00007806467,0.0005188858],"genre_scores_gemma":[0.9929383,0.000020836194,0.0067828842,0.00001106833,0.00005967588,0.0000034765314,0.0000071876148,0.0000111131285,0.00016549072],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884516,0.000043073494,0.00015968976,0.0005628274,0.00008657113,0.0003027011],"domain_scores_gemma":[0.9979375,0.0013439066,0.000034082914,0.0006056248,0.000017030181,0.0000618288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008268494,0.000113747046,0.00015056373,0.00017566321,0.00008151837,0.0003139915,0.0005846683,0.00004641257,0.0000026611133],"category_scores_gemma":[0.0012716503,0.00011511455,0.000009378013,0.00036944874,0.000024163719,0.0021023392,0.0018033467,0.00021660687,0.000015728549],"study_design_candidate":"observational","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":[0.000009167121,0.000024408528,0.7026823,0.00018164073,0.000012334231,0.000017618408,0.0065035294,0.000069886446,0.0006371384,0.0003122235,0.00009346298,0.28945625],"study_design_scores_gemma":[0.0014357656,0.0001553369,0.29150367,0.0012637003,0.000011353257,0.00019788393,0.004576309,0.69680446,0.0013052787,0.00015167121,0.0016459132,0.00094865606],"about_ca_topic_score_codex":0.000030206891,"about_ca_topic_score_gemma":0.00006945085,"teacher_disagreement_score":0.69673455,"about_ca_system_score_codex":0.000024040737,"about_ca_system_score_gemma":0.000055100863,"threshold_uncertainty_score":0.4694235},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0458814739950354,"score_gpt":0.3150776749332564,"score_spread":0.269196200938221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W62188274","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":[0.08183807,0.00048570512,0.91316664,0.00018784807,0.0004952222,0.00032156822,0.0010696929,0.00011196397,0.00232327],"genre_scores_gemma":[0.6774954,0.000054838274,0.31673345,0.00025225827,0.00036592985,0.00016361877,0.0032499137,0.000040426006,0.0016441314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812156,0.0000776983,0.0003436356,0.00093053,0.00013715237,0.00038940847],"domain_scores_gemma":[0.99812084,0.000289954,0.00013304988,0.0012467358,0.000093345865,0.00011609072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056778506,0.00022913975,0.00023570674,0.00009745618,0.00041138215,0.000747923,0.0010486611,0.00009689187,0.000009227666],"category_scores_gemma":[0.0001803538,0.00022345771,0.000042540174,0.0003102046,0.00007577762,0.002597721,0.0007349769,0.00010970427,0.000015624852],"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":[0.000042378426,0.000638014,0.002969009,0.00024811734,0.00019218812,0.000019679961,0.008129,0.000022600114,0.0059254537,0.025191743,0.0393478,0.917274],"study_design_scores_gemma":[0.0029954636,0.00031198395,0.0031160028,0.0003780765,0.00016830763,0.000120008415,0.0013010158,0.8845803,0.0018612089,0.0009784411,0.103007734,0.0011814277],"about_ca_topic_score_codex":0.000014483548,"about_ca_topic_score_gemma":0.00011831549,"teacher_disagreement_score":0.9160926,"about_ca_system_score_codex":0.000024406027,"about_ca_system_score_gemma":0.00021403204,"threshold_uncertainty_score":0.91123414},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07683517453153065,"score_gpt":0.2881091713015354,"score_spread":0.21127399677000475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W73242358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65653175,0.0005209907,0.33715725,0.00013779939,0.000887422,0.00016331232,0.00038510753,0.00019406334,0.0040222625],"genre_scores_gemma":[0.87171006,0.000012055793,0.12739274,0.000098333,0.0001304719,0.0000059107874,0.000220527,0.0000127877165,0.00041713595],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981526,0.00007862105,0.00027266922,0.0010004855,0.00014691774,0.00034871313],"domain_scores_gemma":[0.9977233,0.000051704144,0.000078646335,0.0019199903,0.00004553462,0.000180815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003780527,0.00022203953,0.00025462543,0.00022257888,0.00032295327,0.00051748333,0.0018840405,0.00004553107,0.00001898127],"category_scores_gemma":[0.0001237906,0.00019218873,0.000038915423,0.00059957895,0.00006383879,0.0033052706,0.001951104,0.00013654667,0.000028846578],"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":[0.00011472469,0.00037910216,0.022919087,0.0002598912,0.000690161,0.000117398165,0.1458265,0.00005910094,0.020898119,0.09169064,0.023839017,0.69320625],"study_design_scores_gemma":[0.007165175,0.0014281004,0.5754727,0.002983667,0.0022462152,0.0013676805,0.05753015,0.10350034,0.058406238,0.054365944,0.12211205,0.013421751],"about_ca_topic_score_codex":0.000118110205,"about_ca_topic_score_gemma":0.0002800536,"teacher_disagreement_score":0.67978454,"about_ca_system_score_codex":0.000017703169,"about_ca_system_score_gemma":0.000094393276,"threshold_uncertainty_score":0.7837229},"labels":[],"label_agreement":null}]}