{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":10,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":10,"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":"62162c5d4f85","filters":{"venue":"Proceedings - International Conference on Data Engineering"}},"results":[{"id":"W2116316066","doi":"10.1109/icde.2009.157","title":"Mining of Frequent Itemsets from Streams of Uncertain Data","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data stream mining; Data mining; Database transaction; Uncertain data; Flood myth; Tree (set theory); Transaction data; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1140984146070534,"gpt":0.3235774377997669,"spread":0.2094790231927135,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002183511,0.000135592,0.0001736374,0.0001326055,0.00002362205,0.0001364966,0.005335229,0.00004037316,0.00002632037],"category_scores_gemma":[0.0002670086,0.0001369838,0.00001508896,0.0002320955,0.00002039232,0.001290186,0.0009767872,0.000111916,0.000004402943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002401796,"about_ca_system_score_gemma":0.00005086804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001183911,"about_ca_topic_score_gemma":0.00000140792,"domain_scores_codex":[0.998585,0.000002192125,0.0003484276,0.0005380947,0.0003844757,0.0001418364],"domain_scores_gemma":[0.9985127,0.00005929127,0.0002054099,0.0009251884,0.0002376849,0.00005965425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001344766,0.0003364479,0.0009901737,0.00004731476,0.0001802656,0.000005034928,0.0007509267,0.0003992465,0.06095259,0.5792189,0.005436078,0.3516695],"study_design_scores_gemma":[0.0001729083,0.00004602143,0.001524165,0.0002442163,0.00000877063,0.000003178382,0.0000764065,0.9906008,0.004827749,0.0006235173,0.001726622,0.0001457091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2266338,0.0001894153,0.7456067,0.005199494,0.0009576742,0.0004745545,0.01115863,0.0004657754,0.009314049],"genre_scores_gemma":[0.7914585,0.00004378315,0.2065696,0.0000346736,0.00008130471,0.000003576658,0.001789557,0.000006549237,0.00001238869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9902015,"threshold_uncertainty_score":0.9914272,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170896764","doi":"10.1109/icde.2009.102","title":"Ranking with Uncertain Scores","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Computer science; Rank (graph theory); Data mining; Set (abstract data type); Uncertain data; Probabilistic logic; Learning to rank; Semantics (computer science); Information retrieval; Ranking SVM; Sampling (signal processing); Machine learning; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05920357991017572,"gpt":0.2793436375045019,"spread":0.2201400575943261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000203226,0.0001638946,0.0001084189,0.000204727,0.00004960925,0.0008419645,0.003157002,0.00002416885,0.00002798452],"category_scores_gemma":[0.00006593875,0.0001413128,0.00001425951,0.0002358431,0.00001205738,0.002664714,0.0004543117,0.0001533823,0.0000267147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003528153,"about_ca_system_score_gemma":0.00002086217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000615178,"about_ca_topic_score_gemma":6.575959e-7,"domain_scores_codex":[0.9986663,0.000001505633,0.0001506278,0.0004987636,0.0004578409,0.0002249264],"domain_scores_gemma":[0.9993753,0.00001480722,0.00006634299,0.0003546912,0.0001288861,0.00005997881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001416134,0.00004062847,0.000177861,0.00001269598,0.00004020184,0.00001675956,0.00009544526,0.0003385227,0.0009174052,0.9563231,0.001559122,0.04046408],"study_design_scores_gemma":[0.0003420239,0.0001117978,0.001146712,0.0001975963,0.000005966166,0.00001404872,0.00002699741,0.9878616,0.000475989,0.001624706,0.007923328,0.0002691812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008208024,0.00003667396,0.9368629,0.008066685,0.0007172441,0.0003218945,0.000075157,0.0009013112,0.04481014],"genre_scores_gemma":[0.9219407,0.0000373894,0.07716163,0.000325385,0.000181561,0.000008337062,0.0001506308,0.000009374357,0.000185035],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9875231,"threshold_uncertainty_score":0.8119083,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169872697","doi":"10.1109/icde.2009.70","title":"Online Interval Skyline Queries on Time Series","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"SFU Community Trust Endowment Fund; Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Skyline; Interval (graph theory); Computer science; Series (stratigraphy); Set (abstract data type); Time series; Data mining; Time complexity; On the fly; Space (punctuation); Algorithm; Mathematics; Combinatorics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.04585186737646731,"gpt":0.2792407797789533,"spread":0.233388912402486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001960988,0.0002319796,0.0001694652,0.0002493519,0.00005094468,0.0007352244,0.003336387,0.00004077916,0.0001013955],"category_scores_gemma":[0.0001774757,0.0002214169,0.00003084951,0.000201342,0.00001991082,0.003317351,0.0008027328,0.0002269263,0.0001517117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004753359,"about_ca_system_score_gemma":0.00001881437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003071342,"about_ca_topic_score_gemma":6.473442e-7,"domain_scores_codex":[0.9984556,0.000002732284,0.0002549331,0.0005814181,0.0004546459,0.0002507058],"domain_scores_gemma":[0.999217,0.00001834121,0.00008729415,0.0004432165,0.0001560456,0.00007810669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003815358,0.0002323664,0.00002100116,0.00001837821,0.00006164824,0.00001704347,0.000120434,0.0001394988,0.002316966,0.9375855,0.009277109,0.05017196],"study_design_scores_gemma":[0.0003427207,0.0004115638,0.001087688,0.000264232,0.000008037688,0.00001676236,0.00004427692,0.937379,0.001531809,0.002206058,0.05627252,0.0004353478],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06378961,0.0001712387,0.6219607,0.1362882,0.008054355,0.001659531,0.003636619,0.006628421,0.1578113],"genre_scores_gemma":[0.8342899,0.0002694006,0.15449,0.002066482,0.001284842,0.00002120921,0.002752522,0.00004441157,0.004781205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9372395,"threshold_uncertainty_score":0.9029119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170138277","doi":"10.1109/icde.2009.59","title":"GuruMine: A Pattern Mining System for Discovering Leaders and Tribes","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Set (abstract data type); Social media; Process (computing); Social network (sociolinguistics); Interface (matter); World Wide Web; Graphical user interface; Data science; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.0736423980785224,"gpt":0.2996072730270575,"spread":0.2259648749485351,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001910335,0.0001567378,0.0001351832,0.0001336183,0.00007706338,0.0005979704,0.001461393,0.0000364277,0.000001839361],"category_scores_gemma":[0.0001007801,0.0001566972,0.00001988677,0.0001155185,0.00001542365,0.001280625,0.0002962007,0.00009384803,0.000003466038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004382565,"about_ca_system_score_gemma":0.0000213195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007722309,"about_ca_topic_score_gemma":5.576928e-7,"domain_scores_codex":[0.9988492,0.000001161104,0.0002077273,0.0005210758,0.0002080529,0.0002127555],"domain_scores_gemma":[0.9994373,0.00004306808,0.00007695958,0.0002637806,0.0001039327,0.000074936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001485581,0.00007196212,0.0002240239,0.0001712617,0.00008332184,0.000004381774,0.001191705,0.0001309473,0.01108793,0.5751743,0.001974336,0.409871],"study_design_scores_gemma":[0.0002760118,0.00006549383,0.0004258951,0.0002676689,0.000006982954,0.00002251402,0.0004476088,0.9944843,0.0008338366,0.00008456377,0.002889308,0.0001957957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02002226,0.00003468871,0.9745314,0.003098116,0.0003144551,0.0002375817,0.0002816512,0.0003224209,0.001157442],"genre_scores_gemma":[0.9195196,0.00002065299,0.07995949,0.00008602838,0.0001697368,0.00004772105,0.0001442716,0.0000105777,0.00004193612],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9943534,"threshold_uncertainty_score":0.6389927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101810678","doi":"10.1109/icde.2009.105","title":"On Efficient Recommendations for Online Exchange Markets","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Popularity; Database transaction; Focus (optics); Social network (sociolinguistics); Probabilistic logic; Value (mathematics); User modeling; World Wide Web; Class (philosophy); Recommender system; User interface; Social media; Database; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1115716812821494,"gpt":0.341777137957012,"spread":0.2302054566748626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003040849,0.0001434229,0.0001023329,0.0002633361,0.0000710872,0.0003463846,0.001665218,0.00004074456,0.0001035784],"category_scores_gemma":[0.0003644526,0.0001422662,0.00002730993,0.0001871018,0.000007555834,0.0005287891,0.0002247147,0.0001596768,0.00001976869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006870738,"about_ca_system_score_gemma":0.00003001026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000102883,"about_ca_topic_score_gemma":3.226184e-7,"domain_scores_codex":[0.9987935,0.000003563077,0.0002082751,0.0004506944,0.0003191906,0.0002247582],"domain_scores_gemma":[0.9991839,0.00007153537,0.00007126602,0.0002698825,0.0003101451,0.00009328427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002646884,0.0002375219,0.000002620465,0.00001893164,0.0000208598,7.980512e-7,0.0001512685,0.004284178,0.0005552167,0.9323687,0.01449756,0.04783586],"study_design_scores_gemma":[0.0003478687,0.0001266494,0.0001306037,0.0001137198,0.000001987918,0.000002751648,0.00001249879,0.9671756,0.0001601192,0.001307027,0.03046878,0.0001523835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001877505,0.00001502968,0.945475,0.03950763,0.0008840908,0.000556957,0.0004358993,0.0004266079,0.01082128],"genre_scores_gemma":[0.6286728,0.0001738642,0.3663037,0.002245554,0.0003174509,0.00008407026,0.00136301,0.00002664033,0.0008128375],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9628914,"threshold_uncertainty_score":0.5801445,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111984440","doi":"10.1109/icde.2009.131","title":"Query Rewrites with Views for XML in DB2","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); Microsoft (Canada); York University","funders":"","keywords":"Computer science; XML database; Streaming XML; XQuery; Efficient XML Interchange; XML validation; XML Schema Editor; XML Encryption; Information retrieval; Document Structure Description; Database; XML; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.08982055515052091,"gpt":0.3150799005651456,"spread":0.2252593454146247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000230957,0.0001582308,0.0001595558,0.0001820093,0.00003175596,0.0001579642,0.001101882,0.00003259692,0.000006760532],"category_scores_gemma":[0.0001685441,0.0001361953,0.00001641708,0.0001737881,0.00001097869,0.002087347,0.0001766663,0.0001335433,0.000005895133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004856135,"about_ca_system_score_gemma":0.00003492734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008548103,"about_ca_topic_score_gemma":0.000008521176,"domain_scores_codex":[0.9988478,0.000001760257,0.0002327624,0.0004678032,0.0002367912,0.0002130588],"domain_scores_gemma":[0.9993635,0.00003598185,0.00008358289,0.0002955596,0.0001683183,0.00005302306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002350837,0.0000295409,0.0001274389,0.00002830236,0.000009439111,0.000003720129,0.0001252324,0.0002268503,0.002976588,0.9899071,0.0004169466,0.006125288],"study_design_scores_gemma":[0.0007416009,0.0002733716,0.001336345,0.0008098385,0.000004069852,0.00003831767,0.0001171372,0.8872797,0.002409404,0.002239263,0.1042651,0.0004857887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00487054,0.00006049634,0.9885818,0.001941278,0.0002549767,0.0003215355,0.0001491763,0.0001861739,0.003633967],"genre_scores_gemma":[0.7031951,0.00006101481,0.2959006,0.0002511456,0.0001826907,0.00007032599,0.0001928865,0.00001390375,0.0001323333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9876679,"threshold_uncertainty_score":0.5553882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096934584","doi":"10.1109/icde.2009.91","title":"Keyword Search over Dynamic Categorized Information","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Data Management and Algorithms","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":"ASTER","funders":"","keywords":"Computer science; Categorization; Focus (optics); Information retrieval; Keyword search; Data mining; Contrast (vision); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03711792081511415,"gpt":0.2881913891656117,"spread":0.2510734683504975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002750726,0.0001564251,0.0001064605,0.0003218991,0.00004904312,0.001140448,0.003032776,0.00003788279,0.00005819242],"category_scores_gemma":[0.00008518273,0.0001562203,0.00002122561,0.0002656269,0.000009158888,0.007533137,0.0006778971,0.0001992822,0.0001253844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007323395,"about_ca_system_score_gemma":0.00002619206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009706941,"about_ca_topic_score_gemma":3.766617e-7,"domain_scores_codex":[0.9986648,0.000002022863,0.0002295275,0.0003321349,0.0005311769,0.0002403484],"domain_scores_gemma":[0.9993153,0.00001270758,0.00006783042,0.0003612427,0.0001723909,0.00007051847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001355111,0.00004061697,0.00003596261,0.00002040317,0.00003563813,0.00000325558,0.0002026293,0.0002649916,0.001294122,0.9010595,0.002304897,0.09472444],"study_design_scores_gemma":[0.0003041826,0.00004579442,0.001475805,0.00004215095,0.000003140964,0.000003819072,0.0000249658,0.9827755,0.0001636931,0.001039936,0.01393536,0.0001856615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008878313,0.00001529694,0.9461043,0.006281622,0.00124401,0.0003609396,0.0001585505,0.0007686214,0.0361883],"genre_scores_gemma":[0.9701195,0.00007758944,0.02837056,0.0003596453,0.0001009709,0.000008951977,0.0007192509,0.000006843974,0.0002366946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9825105,"threshold_uncertainty_score":0.9998965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168592511","doi":"10.1109/icde.2009.39","title":"PSALM: Cardinality Estimation in the Presence of Fine-Grained Access Controls","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Tuple; Cardinality (data modeling); Computer science; Exploit; Access control; Process (computing); Data access; Database; Information retrieval; Data mining; Theoretical computer science; Computer security; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.07268246504518185,"gpt":0.3377939215374597,"spread":0.2651114564922779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005506838,0.0001307656,0.0001649641,0.0001324362,0.0000299338,0.0001955771,0.00244753,0.00003002278,0.000006032572],"category_scores_gemma":[0.0006655439,0.0001020957,0.00002292427,0.0002614881,0.00002008237,0.00264524,0.0003138072,0.0001578345,0.000002145252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002879791,"about_ca_system_score_gemma":0.0000317016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003975879,"about_ca_topic_score_gemma":0.000004216304,"domain_scores_codex":[0.9987546,0.000008848311,0.0003073213,0.0003405341,0.0004293125,0.0001593404],"domain_scores_gemma":[0.999123,0.00009227498,0.0001446088,0.0004136484,0.0001956993,0.0000307921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001530706,0.00004406835,0.0002414745,0.00002901658,0.00001219433,0.000003555968,0.0002927692,0.003656334,0.002066595,0.9863281,0.0002561567,0.007054488],"study_design_scores_gemma":[0.0002580539,0.00004970868,0.005268841,0.0001876538,0.000003051762,0.0000147694,0.0000507171,0.9891661,0.0007233713,0.002716629,0.001432453,0.0001286867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01511923,0.00003548529,0.9778453,0.00311054,0.0002758804,0.0003869538,0.0001559552,0.00009401456,0.002976651],"genre_scores_gemma":[0.9731305,0.0000143585,0.02659903,0.00008057327,0.00005194524,0.00003161499,0.00007908422,0.000003605485,0.000009281474],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9855098,"threshold_uncertainty_score":0.4548161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142712680","doi":"10.1109/icde.2009.124","title":"Join Reordering by Join Simulation","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":5,"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":"Join (topology); Computer science; Pipeline (software); Pipeline transport; Cardinality (data modeling); Parallel computing; Path (computing); Distributed computing; Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05346340745751707,"gpt":0.3007754703162046,"spread":0.2473120628586875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002094155,0.0001889697,0.0001479003,0.000146152,0.00006639676,0.0002708272,0.001249963,0.00004642203,0.00002886638],"category_scores_gemma":[0.0002547154,0.0001924786,0.00002206665,0.0001810036,0.00001041879,0.002884918,0.0003519501,0.0001859683,0.0000291037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006294692,"about_ca_system_score_gemma":0.00002176544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007461644,"about_ca_topic_score_gemma":5.29154e-7,"domain_scores_codex":[0.9985512,0.000002837658,0.0002802522,0.0005344482,0.0003963268,0.0002349011],"domain_scores_gemma":[0.9992126,0.00003080041,0.000111774,0.000379049,0.0001828951,0.00008289118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001236307,0.00004517967,0.00003983301,0.00002235486,0.00002307742,0.000004444288,0.0001646103,0.006110785,0.03189526,0.9381466,0.002773133,0.02076238],"study_design_scores_gemma":[0.0001733408,0.0000490946,0.0001499856,0.0001300285,0.000001993712,0.000008085899,0.00002458783,0.9333524,0.002480694,0.0005240348,0.06287362,0.0002321939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003521998,0.00004536091,0.9889884,0.001427479,0.0004220889,0.0001334948,0.0001294005,0.0003750796,0.004956675],"genre_scores_gemma":[0.9359511,0.00004160648,0.06321417,0.0001895199,0.0001693874,0.00000924769,0.0002454419,0.00001229714,0.000167246],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9376225,"threshold_uncertainty_score":0.7849048,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159957898","doi":"10.1109/icde.2009.173","title":"Improving the Effectiveness of XML Retrieval with User Navigation Models","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"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; Information retrieval; XML; Ranking (information retrieval); Markup language; XML Schema (W3C); Document Structure Description; XML database; XML framework; Relevance (law); Search engine; XML validation; Key (lock); Data mining; Database; XML Signature; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03257726831956353,"gpt":0.2618656805024498,"spread":0.2292884121828863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005577034,0.0001364331,0.0001308416,0.00007677291,0.00004862052,0.0001205527,0.00117556,0.00002991762,0.000001982885],"category_scores_gemma":[0.0001340789,0.00009491324,0.00001661468,0.0001995337,0.00002264458,0.002540085,0.0002536089,0.0001591961,0.000001668436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004110517,"about_ca_system_score_gemma":0.00003853556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001409852,"about_ca_topic_score_gemma":3.157702e-7,"domain_scores_codex":[0.998907,0.000008088726,0.0001870185,0.000354307,0.0004006046,0.0001429765],"domain_scores_gemma":[0.999068,0.00007794458,0.0001296894,0.000358324,0.0003305061,0.00003554267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007466702,0.00001641728,0.00003840221,0.00005155586,0.00001819701,0.000001540992,0.00007886902,0.003079268,0.03339536,0.9619511,0.0000092872,0.001285267],"study_design_scores_gemma":[0.0002761786,0.0001359407,0.0005999241,0.0005779056,0.000005818732,0.00002438694,0.00004881349,0.9741403,0.02215477,0.001494025,0.0003734753,0.0001684265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04084939,0.00001844203,0.9573964,0.0001671941,0.0001665622,0.000198435,0.00006135312,0.00009750846,0.001044679],"genre_scores_gemma":[0.9678015,0.000008143385,0.03201375,0.00001815417,0.00005678179,0.000007399323,0.00007374626,0.000007274828,0.00001325991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9710611,"threshold_uncertainty_score":0.387045,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}