{"meta":{"query_hash":"62162c5d4f85","filters":{"venue":"Proceedings - International Conference on Data Engineering"},"cohort_total":10,"direct_labels_cover":0,"predictions_cover":10,"exported":10,"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/62162c5d4f85","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+-+International+Conference+on+Data+Engineering"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"","keywords":"Computer science; Categorization; Focus (optics); Information retrieval; Keyword search; Data mining; Contrast (vision); Artificial intelligence","score_opus":0.03711792081511415,"score_gpt":0.2881913891656117,"score_spread":0.25107346835049754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096934584","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":[0.008878313,0.000015296939,0.94610435,0.006281622,0.0012440103,0.00036093956,0.00015855045,0.0007686214,0.036188297],"genre_scores_gemma":[0.9701195,0.00007758944,0.028370557,0.0003596453,0.00010097094,0.000008951977,0.00071925094,0.000006843974,0.00023669457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986648,0.0000020228629,0.00022952752,0.0003321349,0.0005311769,0.00024034835],"domain_scores_gemma":[0.9993153,0.000012707579,0.00006783042,0.00036124274,0.00017239092,0.00007051847],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00027507264,0.00015642514,0.000106460495,0.00032189913,0.000049043123,0.0011404484,0.0030327763,0.000037882786,0.000058192418],"category_scores_gemma":[0.00008518273,0.0001562203,0.000021225615,0.00026562688,0.000009158888,0.0075331368,0.0006778971,0.00019928219,0.00012538444],"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":[0.0000135511145,0.000040616975,0.000035962614,0.000020403175,0.00003563813,0.0000032555797,0.00020262932,0.00026499163,0.0012941223,0.9010595,0.002304897,0.09472444],"study_design_scores_gemma":[0.00030418255,0.000045794422,0.001475805,0.000042150947,0.0000031409636,0.000003819072,0.000024965795,0.9827755,0.00016369314,0.0010399364,0.013935362,0.00018566154],"about_ca_topic_score_codex":0.0000097069415,"about_ca_topic_score_gemma":3.766617e-7,"teacher_disagreement_score":0.9825105,"about_ca_system_score_codex":0.000073233954,"about_ca_system_score_gemma":0.00002619206,"threshold_uncertainty_score":0.99989647},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11157168128214941,"score_gpt":0.34177713795701203,"score_spread":0.23020545667486264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101810678","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":[0.0018775045,0.000015029677,0.945475,0.039507627,0.00088409084,0.000556957,0.0004358993,0.0004266079,0.010821277],"genre_scores_gemma":[0.62867284,0.00017386423,0.36630374,0.002245554,0.00031745087,0.000084070256,0.0013630103,0.000026640326,0.0008128375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879354,0.0000035630767,0.00020827507,0.00045069444,0.00031919056,0.00022475822],"domain_scores_gemma":[0.9991839,0.000071535374,0.00007126602,0.00026988247,0.00031014514,0.000093284274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030408488,0.00014342292,0.00010233293,0.00026333614,0.0000710872,0.0003463846,0.0016652178,0.000040744562,0.00010357836],"category_scores_gemma":[0.00036445263,0.00014226616,0.00002730993,0.0001871018,0.0000075558337,0.0005287891,0.0002247147,0.00015967684,0.00001976869],"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":[0.000026468837,0.00023752189,0.0000026204655,0.00001893164,0.0000208598,7.980512e-7,0.00015126854,0.004284178,0.0005552167,0.9323687,0.014497563,0.047835857],"study_design_scores_gemma":[0.0003478687,0.00012664936,0.0001306037,0.00011371977,0.0000019879183,0.0000027516476,0.000012498786,0.9671756,0.00016011923,0.0013070266,0.030468784,0.00015238354],"about_ca_topic_score_codex":0.0000010288303,"about_ca_topic_score_gemma":3.226184e-7,"teacher_disagreement_score":0.9628914,"about_ca_system_score_codex":0.000068707384,"about_ca_system_score_gemma":0.000030010257,"threshold_uncertainty_score":0.5801445},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08982055515052091,"score_gpt":0.3150799005651456,"score_spread":0.22525934541462472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111984440","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":[0.0048705405,0.000060496342,0.98858184,0.001941278,0.0002549767,0.0003215355,0.00014917634,0.00018617386,0.0036339671],"genre_scores_gemma":[0.7031951,0.000061014805,0.2959006,0.0002511456,0.00018269067,0.00007032599,0.0001928865,0.000013903746,0.0001323333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884784,0.0000017602567,0.00023276237,0.00046780315,0.00023679115,0.00021305878],"domain_scores_gemma":[0.99936354,0.000035981848,0.00008358289,0.0002955596,0.00016831834,0.00005302306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023095695,0.0001582308,0.00015955584,0.0001820093,0.00003175596,0.00015796424,0.0011018823,0.000032596923,0.0000067605315],"category_scores_gemma":[0.00016854408,0.00013619527,0.00001641708,0.00017378807,0.000010978687,0.0020873474,0.00017666633,0.00013354326,0.000005895133],"study_design_candidate":"theoretical_or_conceptual","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":[0.00002350837,0.000029540895,0.00012743889,0.00002830236,0.000009439111,0.0000037201287,0.00012523243,0.00022685032,0.002976588,0.98990715,0.00041694657,0.006125288],"study_design_scores_gemma":[0.00074160093,0.00027337158,0.0013363451,0.00080983853,0.0000040698524,0.000038317667,0.00011713724,0.88727975,0.0024094037,0.0022392634,0.10426514,0.00048578865],"about_ca_topic_score_codex":0.000008548103,"about_ca_topic_score_gemma":0.000008521176,"teacher_disagreement_score":0.98766786,"about_ca_system_score_codex":0.00004856135,"about_ca_system_score_gemma":0.000034927336,"threshold_uncertainty_score":0.5553882},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.11409841460705344,"score_gpt":0.32357743779976694,"score_spread":0.2094790231927135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116316066","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":[0.22663376,0.00018941531,0.74560666,0.005199494,0.0009576742,0.00047455446,0.011158626,0.00046577537,0.009314049],"genre_scores_gemma":[0.79145855,0.00004378315,0.2065696,0.000034673598,0.00008130471,0.0000035766582,0.0017895567,0.000006549237,0.000012388691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998585,0.0000021921246,0.0003484276,0.0005380947,0.00038447566,0.00014183635],"domain_scores_gemma":[0.99851274,0.000059291266,0.00020540995,0.0009251884,0.00023768489,0.000059654252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021835105,0.00013559197,0.0001736374,0.00013260554,0.000023622053,0.00013649657,0.0053352294,0.00004037316,0.000026320375],"category_scores_gemma":[0.00026700858,0.00013698384,0.000015088962,0.0002320955,0.000020392321,0.0012901856,0.0009767872,0.00011191596,0.000004402943],"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":[0.000013447665,0.00033644793,0.0009901737,0.00004731476,0.00018026562,0.000005034928,0.00075092673,0.00039924655,0.06095259,0.5792189,0.0054360777,0.35166952],"study_design_scores_gemma":[0.00017290835,0.000046021432,0.0015241649,0.00024421632,0.00000877063,0.0000031783823,0.000076406504,0.99060076,0.0048277494,0.00062351726,0.0017266215,0.0001457091],"about_ca_topic_score_codex":0.00011839109,"about_ca_topic_score_gemma":0.0000014079203,"teacher_disagreement_score":0.9902015,"about_ca_system_score_codex":0.000024017958,"about_ca_system_score_gemma":0.000050868035,"threshold_uncertainty_score":0.99142724},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05346340745751707,"score_gpt":0.3007754703162046,"score_spread":0.24731206285868754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142712680","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":[0.0035219984,0.000045360906,0.9889884,0.0014274785,0.00042208892,0.00013349477,0.0001294005,0.00037507957,0.004956675],"genre_scores_gemma":[0.9359511,0.000041606476,0.06321417,0.0001895199,0.00016938744,0.00000924769,0.00024544186,0.000012297135,0.00016724603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855125,0.0000028376583,0.00028025216,0.0005344482,0.0003963268,0.00023490108],"domain_scores_gemma":[0.99921256,0.000030800413,0.000111773996,0.00037904902,0.00018289514,0.00008289118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020941549,0.0001889697,0.0001479003,0.00014615197,0.00006639676,0.0002708272,0.0012499634,0.000046422032,0.000028866381],"category_scores_gemma":[0.00025471539,0.00019247856,0.000022066646,0.0001810036,0.00001041879,0.0028849181,0.00035195012,0.00018596834,0.000029103701],"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":[0.000012363074,0.00004517967,0.00003983301,0.000022354856,0.00002307742,0.000004444288,0.00016461026,0.0061107846,0.031895265,0.9381466,0.0027731329,0.020762382],"study_design_scores_gemma":[0.0001733408,0.000049094604,0.00014998564,0.00013002851,0.0000019937124,0.000008085899,0.000024587833,0.93335235,0.002480694,0.00052403484,0.062873624,0.00023219391],"about_ca_topic_score_codex":0.0000074616437,"about_ca_topic_score_gemma":5.2915397e-7,"teacher_disagreement_score":0.93762255,"about_ca_system_score_codex":0.00006294692,"about_ca_system_score_gemma":0.000021765443,"threshold_uncertainty_score":0.7849048},"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,"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; 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","score_opus":0.032577268319563535,"score_gpt":0.26186568050244985,"score_spread":0.22928841218288631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159957898","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":[0.040849388,0.000018442033,0.95739645,0.00016719414,0.00016656218,0.00019843495,0.000061353116,0.00009750846,0.0010446787],"genre_scores_gemma":[0.9678015,0.0000081433855,0.032013748,0.00001815417,0.000056781788,0.000007399323,0.00007374626,0.0000072748285,0.000013259914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998907,0.000008088726,0.00018701851,0.000354307,0.0004006046,0.00014297645],"domain_scores_gemma":[0.999068,0.000077944576,0.00012968939,0.00035832403,0.00033050613,0.000035542675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005577034,0.00013643307,0.00013084157,0.000076772914,0.000048620524,0.00012055272,0.0011755596,0.000029917615,0.0000019828854],"category_scores_gemma":[0.0001340789,0.000094913245,0.000016614684,0.00019953374,0.000022644575,0.002540085,0.00025360892,0.00015919608,0.0000016684363],"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":[0.00007466702,0.00001641728,0.00003840221,0.00005155586,0.000018197014,0.0000015409921,0.00007886902,0.0030792684,0.033395365,0.96195114,0.0000092872,0.0012852672],"study_design_scores_gemma":[0.00027617865,0.00013594075,0.0005999241,0.00057790556,0.0000058187316,0.000024386938,0.00004881349,0.97414035,0.022154769,0.0014940252,0.00037347534,0.0001684265],"about_ca_topic_score_codex":0.000014098517,"about_ca_topic_score_gemma":3.157702e-7,"teacher_disagreement_score":0.97106105,"about_ca_system_score_codex":0.000041105166,"about_ca_system_score_gemma":0.000038535556,"threshold_uncertainty_score":0.38704497},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07268246504518185,"score_gpt":0.33779392153745974,"score_spread":0.2651114564922779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168592511","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":[0.01511923,0.000035485285,0.9778453,0.0031105403,0.00027588036,0.00038695382,0.00015595522,0.00009401456,0.002976651],"genre_scores_gemma":[0.9731305,0.000014358501,0.02659903,0.00008057327,0.000051945237,0.00003161499,0.000079084224,0.0000036054846,0.000009281474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987546,0.000008848311,0.0003073213,0.00034053408,0.00042931247,0.0001593404],"domain_scores_gemma":[0.999123,0.00009227498,0.00014460883,0.0004136484,0.00019569932,0.0000307921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055068376,0.00013076559,0.00016496413,0.00013243618,0.000029933804,0.00019557709,0.0024475302,0.000030022777,0.0000060325724],"category_scores_gemma":[0.0006655439,0.00010209566,0.000022924269,0.0002614881,0.000020082369,0.00264524,0.00031380725,0.00015783453,0.0000021452522],"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":[0.000015307063,0.00004406835,0.00024147445,0.00002901658,0.000012194328,0.0000035559683,0.00029276917,0.0036563338,0.0020665945,0.98632807,0.00025615672,0.007054488],"study_design_scores_gemma":[0.00025805394,0.000049708684,0.005268841,0.00018765379,0.0000030517617,0.000014769403,0.000050717103,0.9891661,0.0007233713,0.0027166288,0.0014324533,0.00012868668],"about_ca_topic_score_codex":0.000039758794,"about_ca_topic_score_gemma":0.0000042163038,"teacher_disagreement_score":0.98550975,"about_ca_system_score_codex":0.000028797913,"about_ca_system_score_gemma":0.000031701602,"threshold_uncertainty_score":0.45481607},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04585186737646731,"score_gpt":0.27924077977895334,"score_spread":0.23338891240248602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169872697","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":[0.06378961,0.00017123869,0.6219607,0.13628821,0.008054355,0.0016595314,0.0036366193,0.006628421,0.1578113],"genre_scores_gemma":[0.8342899,0.0002694006,0.15449002,0.002066482,0.0012848421,0.000021209207,0.002752522,0.00004441157,0.0047812047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984556,0.0000027322844,0.00025493314,0.0005814181,0.0004546459,0.0002507058],"domain_scores_gemma":[0.999217,0.000018341207,0.000087294145,0.0004432165,0.00015604556,0.00007810669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019609879,0.0002319796,0.00016946519,0.0002493519,0.000050944676,0.0007352244,0.003336387,0.00004077916,0.00010139549],"category_scores_gemma":[0.00017747574,0.0002214169,0.00003084951,0.00020134203,0.000019910824,0.003317351,0.00080273283,0.00022692628,0.00015171168],"study_design_candidate":"theoretical_or_conceptual","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":[0.000038153583,0.00023236642,0.000021001164,0.000018378207,0.000061648236,0.000017043465,0.00012043403,0.0001394988,0.0023169662,0.9375855,0.009277109,0.050171956],"study_design_scores_gemma":[0.00034272068,0.00041156381,0.0010876877,0.00026423202,0.000008037688,0.00001676236,0.000044276923,0.937379,0.0015318088,0.0022060585,0.056272518,0.00043534784],"about_ca_topic_score_codex":0.0000030713422,"about_ca_topic_score_gemma":6.473442e-7,"teacher_disagreement_score":0.93723947,"about_ca_system_score_codex":0.000047533595,"about_ca_system_score_gemma":0.00001881437,"threshold_uncertainty_score":0.9029119},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0736423980785224,"score_gpt":0.29960727302705753,"score_spread":0.22596487494853512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170138277","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":[0.02002226,0.000034688714,0.9745314,0.0030981163,0.00031445513,0.00023758167,0.00028165116,0.0003224209,0.0011574423],"genre_scores_gemma":[0.9195196,0.000020652988,0.07995949,0.00008602838,0.00016973683,0.000047721052,0.00014427156,0.0000105777035,0.000041936117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988492,0.0000011611038,0.00020772727,0.0005210758,0.00020805285,0.00021275549],"domain_scores_gemma":[0.99943733,0.000043068085,0.00007695958,0.0002637806,0.0001039327,0.000074936004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019103345,0.00015673778,0.00013518316,0.00013361832,0.00007706338,0.00059797044,0.0014613926,0.000036427704,0.0000018393606],"category_scores_gemma":[0.000100780104,0.00015669722,0.000019886771,0.00011551854,0.000015423646,0.0012806252,0.0002962007,0.00009384803,0.0000034660377],"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":[0.0000148558065,0.000071962124,0.00022402394,0.00017126166,0.000083321844,0.000004381774,0.0011917049,0.00013094733,0.011087928,0.5751743,0.0019743356,0.409871],"study_design_scores_gemma":[0.0002760118,0.000065493834,0.00042589512,0.00026766895,0.0000069829543,0.000022514025,0.00044760876,0.9944843,0.00083383656,0.00008456377,0.0028893077,0.0001957957],"about_ca_topic_score_codex":0.0000077223085,"about_ca_topic_score_gemma":5.5769283e-7,"teacher_disagreement_score":0.99435335,"about_ca_system_score_codex":0.000043825654,"about_ca_system_score_gemma":0.000021319502,"threshold_uncertainty_score":0.6389927},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05920357991017572,"score_gpt":0.27934363750450186,"score_spread":0.22014005759432614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170896764","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":[0.008208024,0.00003667396,0.9368629,0.008066685,0.00071724405,0.00032189448,0.000075157004,0.0009013112,0.04481014],"genre_scores_gemma":[0.9219407,0.000037389404,0.077161625,0.00032538496,0.00018156104,0.000008337062,0.00015063079,0.000009374357,0.000185035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866635,0.0000015056335,0.00015062783,0.0004987636,0.0004578409,0.00022492642],"domain_scores_gemma":[0.9993753,0.000014807223,0.00006634299,0.00035469123,0.0001288861,0.000059978815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020322595,0.00016389464,0.0001084189,0.00020472695,0.000049609254,0.0008419645,0.0031570017,0.000024168854,0.000027984524],"category_scores_gemma":[0.00006593875,0.0001413128,0.000014259505,0.00023584312,0.000012057377,0.0026647141,0.0004543117,0.00015338227,0.000026714699],"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":[0.000014161341,0.000040628474,0.00017786102,0.000012695985,0.00004020184,0.000016759563,0.00009544526,0.00033852275,0.0009174052,0.9563231,0.0015591221,0.04046408],"study_design_scores_gemma":[0.00034202388,0.00011179779,0.0011467118,0.00019759625,0.0000059661656,0.000014048724,0.00002699741,0.98786163,0.00047598904,0.0016247057,0.007923328,0.00026918118],"about_ca_topic_score_codex":0.00000615178,"about_ca_topic_score_gemma":6.575959e-7,"teacher_disagreement_score":0.98752314,"about_ca_system_score_codex":0.000035281526,"about_ca_system_score_gemma":0.000020862171,"threshold_uncertainty_score":0.8119083},"labels":[],"label_agreement":null}]}