{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":43,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":43,"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":"ee4a48787628","filters":{"venue":"ACM Transactions on Database Systems"}},"results":[{"id":"W2740924709","doi":"10.1145/3068335","title":"DBSCAN Revisited, Revisited","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2625,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Alberta","funders":"","keywords":"Computer science; DBSCAN; Data mining; Heuristics; Information retrieval; Algorithm; Artificial intelligence; Cluster analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.03953632886572851,"gpt":0.2875278022523509,"spread":0.2479914733866224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006144177,0.0002252727,0.0002661171,0.0002213446,0.0009985981,0.001539914,0.004366743,0.00005183652,0.00005963134],"category_scores_gemma":[0.00009353485,0.0002058787,0.0001001066,0.0002482905,0.00005747504,0.002527788,0.0001537182,0.000221946,0.0007398337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004367424,"about_ca_system_score_gemma":0.00002565339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002883952,"about_ca_topic_score_gemma":0.000009941318,"domain_scores_codex":[0.9981027,0.00009774519,0.0003376088,0.0006808286,0.0004349471,0.0003461763],"domain_scores_gemma":[0.9919556,0.00007793935,0.0002232246,0.007518143,0.00006713059,0.0001579147],"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":[0.00006677807,0.0008432174,0.0005105551,0.001121147,0.0006515729,0.0006140335,0.0002967126,0.0004647869,0.001302744,0.1313978,0.1103469,0.7523836],"study_design_scores_gemma":[0.001965684,0.0002117781,0.001192581,0.001360079,0.000142762,0.00009623524,0.0001187038,0.07697163,0.001076651,0.0004371409,0.9151763,0.001250455],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001650468,0.0001816538,0.9903804,0.001266618,0.001291853,0.0004778403,0.0007400021,0.0003441889,0.005152375],"genre_scores_gemma":[0.8985859,0.001068342,0.08268696,0.000776584,0.0007595212,0.0002479835,0.0007591086,0.00008249852,0.01503308],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9076934,"threshold_uncertainty_score":0.9994966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171332293","doi":"10.1145/1366102.1366103","title":"Conditional functional dependencies for capturing data inconsistencies","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":458,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Functional dependency; Data integrity; Consistency (knowledge bases); Relational database; SQL; Data mining; Set (abstract data type); Schema (genetic algorithms); Database; Programming language; Theoretical computer science; Algorithm; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5917106512846138,"gpt":0.4156652633131301,"spread":0.1760453879714837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003093297,0.0002136977,0.0003266986,0.0004035097,0.001083693,0.000231642,0.002135647,0.00007091129,0.0005095956],"category_scores_gemma":[0.001780247,0.0001777547,0.0001249815,0.0004236338,0.0002371596,0.001648846,0.0001434835,0.000182569,0.0006297705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007469964,"about_ca_system_score_gemma":0.0001960979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004541447,"about_ca_topic_score_gemma":0.0005062943,"domain_scores_codex":[0.9959337,0.0002293184,0.0008280448,0.0009323349,0.001756935,0.000319692],"domain_scores_gemma":[0.99266,0.002967176,0.0002184519,0.003711031,0.0002912969,0.0001520473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007931147,0.001741999,0.0007502174,0.0004755725,0.001046374,0.0001918663,0.001266063,0.03608345,0.001349926,0.0604348,0.8784931,0.0173735],"study_design_scores_gemma":[0.002182904,0.0001645838,0.002556835,0.0001396222,0.0001632143,0.0005551525,0.01051676,0.01397548,0.0006606838,0.005454475,0.9628404,0.0007898973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002671431,0.0001766919,0.9570127,0.000971684,0.001869707,0.0006627008,0.0357185,0.0001175994,0.0007990051],"genre_scores_gemma":[0.9766784,0.00006541765,0.008499217,0.0005114591,0.0002830176,0.0002859965,0.006512661,0.0000226944,0.007141096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.974007,"threshold_uncertainty_score":0.8334996,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983304353","doi":"10.1145/974750.974757","title":"A normal form for XML documents","year":2004,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":285,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Functional dependency; XML validation; Document Structure Description; XML; Information retrieval; XML database; XML Schema Editor; Relational database; Theoretical computer science; Programming language; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02221699491570806,"gpt":0.2760328890509727,"spread":0.2538158941352646,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003424908,0.0002663985,0.0002872438,0.0001938456,0.0004790036,0.0001241365,0.0008698718,0.00006958968,0.000007994171],"category_scores_gemma":[0.0000434353,0.000238147,0.0001375518,0.0003674102,0.00004355682,0.002190527,0.00004078461,0.0001654078,0.0001885514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00017166,"about_ca_system_score_gemma":0.0001265721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006409155,"about_ca_topic_score_gemma":0.000154684,"domain_scores_codex":[0.9980268,0.00003793475,0.0004645444,0.0005977801,0.0003839135,0.0004890615],"domain_scores_gemma":[0.9973009,0.0001398641,0.0001382642,0.002130935,0.0001006878,0.0001893488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002962564,0.001225312,0.00003085381,0.001317514,0.0004427586,0.0001279368,0.00204528,0.03442099,0.008022746,0.8979825,0.002875641,0.05121215],"study_design_scores_gemma":[0.006950865,0.001130311,0.00003129501,0.001016717,0.00007759828,0.0004568489,0.0007902533,0.006433346,0.02151795,0.002807645,0.9573278,0.001459415],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000675957,0.0001466262,0.993596,0.0003739539,0.001819874,0.0009840283,0.001711735,0.0003106361,0.0003811455],"genre_scores_gemma":[0.5487428,0.00009324779,0.4468435,0.0003675771,0.0003154802,0.001640154,0.0004413833,0.00006469709,0.001491203],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9544521,"threshold_uncertainty_score":0.9711354,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057545667","doi":"10.1145/1508857.1508858","title":"The design of a query monitoring system","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":169,"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; Query optimization; Online aggregation; Joins; Query expansion; Sargable; Query plan; View; Data mining; Database; Query language; Cardinality (data modeling); Web query classification; Information retrieval; Web search query; Search engine; Database design","retraction":null,"screen_n_in":null,"score":{"opus":0.03427797394678277,"gpt":0.266917922125267,"spread":0.2326399481784843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000897679,0.0002292166,0.0003083297,0.0001373608,0.0005864384,0.0001025548,0.001152851,0.00005867906,8.329911e-7],"category_scores_gemma":[0.00006374039,0.0001601361,0.00009449712,0.000507527,0.00005635908,0.0008232024,0.00002343531,0.0002075654,0.00003502559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001133577,"about_ca_system_score_gemma":0.00009106156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001819511,"about_ca_topic_score_gemma":0.000004097476,"domain_scores_codex":[0.9978104,0.000306349,0.0006000795,0.0004262873,0.0004950376,0.0003618484],"domain_scores_gemma":[0.99604,0.0006391392,0.0002391842,0.002839976,0.0001254504,0.0001162619],"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":[0.0003108761,0.0005485391,0.00007380309,0.0008985326,0.0003593489,0.0001917756,0.00145268,0.1010743,0.03651766,0.6661947,0.001423158,0.1909547],"study_design_scores_gemma":[0.007183939,0.004470237,0.00129081,0.01705945,0.0004089946,0.002688042,0.02259827,0.3994166,0.2688852,0.001138729,0.2695045,0.005355233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000237621,0.0009048817,0.9957117,0.0001696337,0.00180763,0.0005636912,0.0001598635,0.0002921224,0.0001528671],"genre_scores_gemma":[0.8958963,0.0001979321,0.1033166,0.00001586597,0.00015766,0.0001368557,0.000008568523,0.00001766918,0.0002526394],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8956586,"threshold_uncertainty_score":0.6530161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2090154982","doi":"10.1145/357775.357778","title":"Emancipating instances from the tyranny of classes in information modeling","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Schema (genetic algorithms); Interoperability; Relational database; Class (philosophy); Semi-structured model; Theoretical computer science; Information schema; Data mining; Information retrieval; Artificial intelligence; Database model; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0253603979568016,"gpt":0.2532512764296321,"spread":0.2278908784728305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003939334,0.0001542196,0.0002343033,0.0001120057,0.0001939445,0.00006741563,0.0006757238,0.00004635015,0.00002892101],"category_scores_gemma":[0.00005311554,0.0001139815,0.00005123316,0.0005093078,0.00003785238,0.003038632,0.00001791622,0.0002003601,0.00004379077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004718163,"about_ca_system_score_gemma":0.00006565318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005100957,"about_ca_topic_score_gemma":0.0009076017,"domain_scores_codex":[0.9984024,0.0001336623,0.0006614886,0.000242564,0.0003502117,0.0002096507],"domain_scores_gemma":[0.9980676,0.000304116,0.000144322,0.001376532,0.00006365553,0.00004373265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009462928,0.000147798,0.0002718998,0.0002246002,0.00006509435,0.000008372151,0.00595067,0.7814463,0.0004318575,0.01825153,0.0001440509,0.1929631],"study_design_scores_gemma":[0.000909591,0.00007284024,0.0001836188,0.001335563,0.00001636693,0.0000146257,0.003518402,0.9565792,0.000892111,0.0002544068,0.03583954,0.0003837497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05213731,0.0003822394,0.9452373,0.0001507476,0.0003713685,0.0003189195,0.0009451286,0.00007860825,0.0003784151],"genre_scores_gemma":[0.9708082,0.0002121221,0.02859749,0.00008528831,0.0000438339,0.0001034667,0.0001132413,0.000007672573,0.00002865628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.918671,"threshold_uncertainty_score":0.7711155,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973115038","doi":"10.1145/937598.937601","title":"Are quorums an alternative for data replication?","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Replication (statistics); Scalability; Overhead (engineering); Replicate; Distributed computing; Consistency (knowledge bases); Eventual consistency; Selection (genetic algorithm); Data access; Data consistency; Consistency model; Database; Programming language; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1108332601636947,"gpt":0.3436451194508417,"spread":0.232811859287147,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001019263,0.0002115714,0.0002701318,0.0001096116,0.0003662662,0.0002860872,0.002940777,0.00006847743,0.000008600126],"category_scores_gemma":[0.0002264319,0.0001978387,0.00005821977,0.0004004269,0.0000319423,0.001570897,0.00003012916,0.0001520894,0.00006759712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000621909,"about_ca_system_score_gemma":0.00007522446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003000261,"about_ca_topic_score_gemma":0.0001027162,"domain_scores_codex":[0.9974681,0.0002114128,0.0004437069,0.001207855,0.0003400608,0.0003289267],"domain_scores_gemma":[0.9898357,0.0002005647,0.000308832,0.009291735,0.0001818246,0.0001813188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002358394,0.005850502,0.0009087333,0.001475437,0.001197891,0.0001539644,0.001832866,0.03085976,0.004745557,0.708931,0.09163543,0.152173],"study_design_scores_gemma":[0.001554626,0.0001926529,0.000128421,0.0003205599,0.00004436214,0.0001406054,0.0006725869,0.32645,0.002342142,0.0006314173,0.6668081,0.0007144853],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000476628,0.000186613,0.9896952,0.0003626711,0.001473604,0.000891305,0.006437166,0.0002152421,0.000261597],"genre_scores_gemma":[0.9465595,0.00003281419,0.05020843,0.0002736149,0.0001567689,0.0007003801,0.00120459,0.00003777323,0.0008261548],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9460828,"threshold_uncertainty_score":0.8067627,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057058417","doi":"10.1145/1132863.1132873","title":"Approximation and streaming algorithms for histogram construction problems","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":127,"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":"Histogram; Computer science; Algorithm; Approximation algorithm; Artificial intelligence; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02572179603381434,"gpt":0.2438775195296402,"spread":0.2181557234958259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003257952,0.0001719808,0.0001653084,0.0002337342,0.0003266283,0.0003559052,0.00045043,0.00004942121,0.000002858158],"category_scores_gemma":[0.00001121009,0.0001676252,0.00004774965,0.0003028538,0.00005349738,0.001253511,0.00002414208,0.00009314338,0.0000100557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005504927,"about_ca_system_score_gemma":0.00001819841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005349753,"about_ca_topic_score_gemma":0.000037662,"domain_scores_codex":[0.9986616,0.00004307375,0.0003151014,0.000501683,0.0002345163,0.0002440513],"domain_scores_gemma":[0.9987986,0.0001018533,0.0001238786,0.0008604085,0.00005872776,0.00005650604],"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":[0.00001291384,0.0003195914,0.00004943895,0.0005670656,0.00007484596,0.000005080026,0.000114559,0.002690375,0.00092593,0.06531347,0.001597979,0.9283288],"study_design_scores_gemma":[0.002109596,0.0002747613,0.0001615306,0.0002851017,0.0001027844,0.0001048039,0.000372088,0.8973469,0.001300105,0.00344912,0.09376732,0.0007258623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004014214,0.0001422532,0.9964413,0.0002278275,0.0008999204,0.0009294755,0.0004267578,0.0002805655,0.0002504644],"genre_scores_gemma":[0.139638,0.0000806913,0.8568093,0.00004423344,0.0002879324,0.0008354313,0.001154732,0.00003623059,0.001113385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9276029,"threshold_uncertainty_score":0.6835557,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130696419","doi":"10.1145/1189769.1189774","title":"Towards multidimensional subspace skyline analysis","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Skyline; Linear subspace; Subspace topology; Computer science; Semantics (computer science); Theoretical computer science; Space (punctuation); Object (grammar); Online analytical processing; Algorithm; Data mining; Mathematics; Artificial intelligence; Pure mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01799995614887762,"gpt":0.2517425082751469,"spread":0.2337425521262693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000442132,0.000218095,0.000277959,0.000581536,0.0002489216,0.0002174444,0.001143695,0.00004820434,0.00006639199],"category_scores_gemma":[0.00001385601,0.0001959469,0.0001778493,0.001811904,0.0000345658,0.0009259198,0.0000625519,0.0001581216,0.0002534667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005408035,"about_ca_system_score_gemma":0.00003568397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002906037,"about_ca_topic_score_gemma":0.0002966779,"domain_scores_codex":[0.9979758,0.0001000853,0.0003542599,0.0006358626,0.000608272,0.000325754],"domain_scores_gemma":[0.9972777,0.0001026223,0.0000992791,0.002343736,0.00007541582,0.0001011834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000150196,0.005940149,0.001520793,0.0005038513,0.006224702,0.0009295337,0.0004159285,0.416884,0.005562076,0.2939969,0.0696414,0.1982305],"study_design_scores_gemma":[0.001350702,0.0001050237,0.002603453,0.00007437368,0.000650168,0.0000260555,0.0001121046,0.8680071,0.002409834,0.00019709,0.1236247,0.0008394453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001200779,0.0001298834,0.9949945,0.0008265504,0.0007773786,0.0002435752,0.0007570244,0.000305299,0.000764971],"genre_scores_gemma":[0.7547597,0.00005672727,0.236852,0.0001851726,0.0002512998,0.0001127214,0.001610635,0.00002807265,0.006143742],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7581426,"threshold_uncertainty_score":0.7990481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1997533292","doi":"10.1145/503099.503102","title":"SchemaSQL","year":2001,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":94,"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; SQL; Data definition language; Relational database; Schema (genetic algorithms); Database schema; Programming language; Database; Conceptual schema; Semi-structured model; Database model; Information retrieval; Database design","retraction":null,"screen_n_in":null,"score":{"opus":0.03070971332297829,"gpt":0.2692929818947709,"spread":0.2385832685717926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003310457,0.0002501868,0.0002709028,0.0002135614,0.0003621707,0.0001043427,0.0009507589,0.00006789153,0.00006069724],"category_scores_gemma":[0.00005162579,0.000222833,0.00009445187,0.0006810019,0.0000516508,0.001463424,0.0000443481,0.0002432903,0.0006899209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007634498,"about_ca_system_score_gemma":0.00006403653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000345515,"about_ca_topic_score_gemma":0.00005030319,"domain_scores_codex":[0.9980167,0.0001068262,0.0004036733,0.000625429,0.0004335359,0.0004138702],"domain_scores_gemma":[0.9962888,0.0001694003,0.0001083085,0.003151397,0.00008124168,0.0002008827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001674145,0.001293159,0.0003282958,0.0005400669,0.0003855712,0.001108257,0.001057095,0.01169125,0.01455998,0.7860388,0.01203114,0.170799],"study_design_scores_gemma":[0.0006591884,0.0001132787,0.00003555637,0.0002532297,0.00001523682,0.0005862983,0.000295655,0.009710787,0.003014636,0.0001300703,0.9846652,0.0005208767],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008409894,0.0003615586,0.9938166,0.0004602707,0.001539845,0.0003441481,0.0003190918,0.000519447,0.001798008],"genre_scores_gemma":[0.6717315,0.0006202548,0.317955,0.0005660715,0.0004834745,0.0005370624,0.0002257368,0.00008302446,0.007797854],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.972634,"threshold_uncertainty_score":0.9086864,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006315879","doi":"10.1145/1093382.1093388","title":"Capturing summarizability with integrity constraints in OLAP","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":93,"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":"Online analytical processing; Computer science; Heuristics; Dimension (graph theory); Theoretical computer science; Set (abstract data type); Data integrity; Aggregate (composite); Intrinsic dimension; Class (philosophy); Space (punctuation); Data mining; Curse of dimensionality; Data warehouse; Database; Artificial intelligence; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02571648555127341,"gpt":0.2608755870518358,"spread":0.2351591015005624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006915124,0.0002889453,0.0003650042,0.0002404868,0.0001956644,0.00009045378,0.0007457053,0.00008462978,0.00003376377],"category_scores_gemma":[0.00006898868,0.0002357822,0.00006016942,0.0005382316,0.0001786434,0.001714895,0.00004245883,0.0006039899,0.00008557451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000260889,"about_ca_system_score_gemma":0.0001608995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001913357,"about_ca_topic_score_gemma":0.003466239,"domain_scores_codex":[0.9976565,0.0002085011,0.0005311031,0.0007557658,0.0004049548,0.0004432112],"domain_scores_gemma":[0.9970111,0.0002865285,0.0001213022,0.002325612,0.00008139173,0.0001740479],"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":[0.0007115612,0.004335192,0.009759254,0.002109495,0.0004900672,0.0008357693,0.007334107,0.07752611,0.005461319,0.3286915,0.001106257,0.5616394],"study_design_scores_gemma":[0.01989117,0.001865299,0.008575709,0.01038187,0.0001981971,0.003654593,0.01396687,0.2138518,0.04510508,0.0008533834,0.6728123,0.008843631],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01181229,0.0001283703,0.9849142,0.0005187187,0.0004514868,0.0005695849,0.0006889716,0.0002506555,0.000665672],"genre_scores_gemma":[0.8872782,0.00001678746,0.1122034,0.00007676168,0.000071509,0.000136723,0.00006103453,0.00001681801,0.0001388063],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8754659,"threshold_uncertainty_score":0.9614917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121433213","doi":"10.1145/1386118.1386119","title":"Probabilistic top- <i>k</i> and ranking-aggregate queries","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ranking (information retrieval); Probabilistic logic; Aggregate (composite); Uncertain data; Semantics (computer science); Tuple; Probabilistic database; Search engine indexing; Materialized view; Dimension (graph theory); Information retrieval; Online aggregation; Data mining; Theoretical computer science; Web search query; Sargable; Search engine; Relational database; Artificial intelligence; View; Database theory; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0273376981472049,"gpt":0.2331527256784324,"spread":0.2058150275312275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002614799,0.0001838085,0.0001959428,0.0001553305,0.0004232176,0.0002012646,0.0008605283,0.00003599748,0.00001258119],"category_scores_gemma":[0.00003435776,0.0001642662,0.0000423391,0.0003728827,0.0001102505,0.001219848,0.00006301071,0.0001451738,0.00008805279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002489872,"about_ca_system_score_gemma":0.00003460166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000245063,"about_ca_topic_score_gemma":0.00002210509,"domain_scores_codex":[0.9985796,0.00008022969,0.0002548651,0.000511805,0.0003075192,0.0002659772],"domain_scores_gemma":[0.9980938,0.00012304,0.00006943008,0.001569252,0.00003872811,0.0001057395],"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":[0.0003199324,0.003091299,0.001654956,0.003694792,0.001254024,0.002816932,0.007839781,0.008262914,0.002776657,0.3346758,0.04701097,0.5866019],"study_design_scores_gemma":[0.006740388,0.001081551,0.001441939,0.001480822,0.0002721767,0.002464352,0.000808921,0.2412082,0.005371025,0.00312376,0.7324467,0.003560237],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00620339,0.0003322276,0.9901506,0.0005983687,0.0009733832,0.0004759999,0.0002528807,0.0003506879,0.0006625082],"genre_scores_gemma":[0.9537305,0.0008514009,0.04111522,0.0003447139,0.0001543849,0.0002386677,0.0001351028,0.00003346149,0.003396518],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9490353,"threshold_uncertainty_score":0.6698579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150433972","doi":"10.1145/958942.958944","title":"Efficient dynamic mining of constrained frequent sets","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; University of British Columbia","funders":"","keywords":"Computer science; Context (archaeology); Computation; Exploit; Process (computing); Set (abstract data type); Data mining; Function (biology); Component (thermodynamics); Association rule learning; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02206422575661429,"gpt":0.269716471572934,"spread":0.2476522458163198,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004322259,0.0001584158,0.0002086651,0.000171405,0.0001847505,0.00006880292,0.0007939843,0.0000469855,0.00002288717],"category_scores_gemma":[0.00005486202,0.0001510834,0.00006799591,0.0005164462,0.00007300417,0.0001220858,0.00001560397,0.0001256515,0.00004884077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005292186,"about_ca_system_score_gemma":0.0001140909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001034017,"about_ca_topic_score_gemma":0.00001089123,"domain_scores_codex":[0.9985104,0.0001024397,0.000400055,0.0004386788,0.0003018392,0.0002466442],"domain_scores_gemma":[0.9976213,0.0002250335,0.0001366243,0.001829352,0.00007089886,0.000116813],"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":[0.00004183201,0.005740967,0.0001210315,0.001101676,0.000890603,0.0001555559,0.005209444,0.2385602,0.06855043,0.3096522,0.003375816,0.3666002],"study_design_scores_gemma":[0.0009237067,0.0001460918,0.00005301883,0.0003385312,0.00004754161,0.0001888647,0.0009531404,0.9841938,0.005024651,0.0000798514,0.00760716,0.0004436333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01539448,0.0001006681,0.9817111,0.0001643064,0.0005305423,0.0003058216,0.001104766,0.0001240205,0.0005642615],"genre_scores_gemma":[0.7912593,0.00001054389,0.2084568,0.00002550976,0.000005340512,0.00008721164,0.00005373254,0.00001064074,0.00009091013],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7758648,"threshold_uncertainty_score":0.6161003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4256119157","doi":"10.1145/1189769.1189778","title":"Peer data exchange","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":69,"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; Data exchange; Tuple; Peer-to-peer; Schema (genetic algorithms); Data sharing; Generalization; Data source; Theoretical computer science; Information retrieval; Distributed computing; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0697215860345619,"gpt":0.2892360718961638,"spread":0.2195144858616019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005387742,0.0001604394,0.0001821687,0.0001478942,0.0002008666,0.000213933,0.002952375,0.00006037406,0.00003778918],"category_scores_gemma":[0.00006090681,0.0001379667,0.00004094982,0.0003326766,0.00003942095,0.0009320771,0.0001007164,0.0001494488,0.0003578354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003005582,"about_ca_system_score_gemma":0.00004478833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002977729,"about_ca_topic_score_gemma":0.000450932,"domain_scores_codex":[0.9982386,0.00008967936,0.0002613627,0.0005947225,0.0005194093,0.0002962067],"domain_scores_gemma":[0.9946458,0.0002039429,0.00006333311,0.004943543,0.00008133407,0.00006198424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006604196,0.001999972,0.0008095505,0.0007583306,0.0003130113,0.0006518948,0.0008153832,0.004337924,0.003678022,0.08136776,0.7225571,0.182645],"study_design_scores_gemma":[0.0010997,0.0001183415,0.0009351831,0.0001748253,0.0000641161,0.0002673595,0.0003964993,0.08375075,0.002452761,0.0006909032,0.9092853,0.0007642432],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005300246,0.0006093375,0.9907727,0.002572579,0.00180007,0.0002292313,0.0006614061,0.0004270511,0.00239763],"genre_scores_gemma":[0.9329497,0.00008065848,0.05508913,0.0002477592,0.0004102825,0.0000893196,0.0006456998,0.00002729778,0.0104602],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9356835,"threshold_uncertainty_score":0.5626119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2553567329","doi":"10.1145/3004295","title":"Smart Meter Data Analytics","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":67,"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":"Computer science; Data analysis; Analytics; Smart meter; Big data; Data science; Data mining; Smart grid; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09289352135828077,"gpt":0.2750155793791962,"spread":0.1821220580209155,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005697055,0.0001714684,0.0002367216,0.0001865957,0.0002192093,0.0001887553,0.002628636,0.00004723188,0.0001137846],"category_scores_gemma":[0.00007928043,0.000110633,0.00008588134,0.0005172396,0.0000426709,0.001324282,0.000133607,0.0001055584,0.0003835325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004240837,"about_ca_system_score_gemma":0.00004443786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002707799,"about_ca_topic_score_gemma":0.000101991,"domain_scores_codex":[0.9982066,0.00009476695,0.0003734519,0.000659561,0.0003603356,0.0003053502],"domain_scores_gemma":[0.9939816,0.0002722472,0.000111737,0.005429799,0.00006633112,0.0001382933],"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":[0.0000709379,0.0006914103,0.0006766364,0.0001971984,0.001559205,0.0001632647,0.0003050104,0.002308672,0.01126798,0.02187157,0.02421414,0.936674],"study_design_scores_gemma":[0.001525545,0.0002804157,0.0002409517,0.0006426423,0.0003676093,0.0002031356,0.0002330248,0.5039417,0.003748482,0.0002647902,0.4873213,0.001230415],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000291823,0.00009117746,0.9963562,0.001015862,0.000627715,0.0001161458,0.0008728725,0.000154044,0.0004741462],"genre_scores_gemma":[0.9443691,0.000110609,0.05168378,0.0001392655,0.0001462817,0.00002446976,0.0001161368,0.00002676311,0.003383645],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9446725,"threshold_uncertainty_score":0.4929662,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054655669","doi":"10.1145/383891.383892","title":"Querying ATSQL databases with temporal logic","year":2001,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":66,"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":"Computer science; SQL; Temporal logic; Expressive power; Temporal database; Extension (predicate logic); Database; Translation (biology); Programming language; Representation (politics); Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05051783123629092,"gpt":0.2832165114231688,"spread":0.2326986801868779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004637012,0.0004424177,0.0004585469,0.0003168459,0.0006112725,0.0001595031,0.001083293,0.00006306586,0.00005807579],"category_scores_gemma":[0.00005404414,0.000342736,0.00009441422,0.0009763244,0.0001196116,0.002679967,0.00007553676,0.0003623097,0.0002616735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001155907,"about_ca_system_score_gemma":0.0001430313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001924893,"about_ca_topic_score_gemma":0.0006468459,"domain_scores_codex":[0.996909,0.0002059758,0.0005650618,0.001016207,0.0006709408,0.0006327672],"domain_scores_gemma":[0.9951604,0.0002945526,0.0002255802,0.003909136,0.0001301148,0.0002802348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001321575,0.003430482,0.006888615,0.00191666,0.001213961,0.007067352,0.002041735,0.0532531,0.008963967,0.7929184,0.01107181,0.1099123],"study_design_scores_gemma":[0.002517856,0.0007072717,0.0001905113,0.00162627,0.00009034803,0.003417806,0.002001602,0.0163961,0.002736453,0.0001283226,0.9682288,0.001958648],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001529873,0.0004525893,0.9933615,0.0004382894,0.00093397,0.000614967,0.00107492,0.0006721002,0.0009217391],"genre_scores_gemma":[0.6327109,0.0003503442,0.362985,0.0004710231,0.0003036441,0.000455109,0.0007520039,0.00008498662,0.001886979],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.957157,"threshold_uncertainty_score":0.9999025,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112527958","doi":"10.1145/1538909.1538913","title":"Snapshot isolation and integrity constraints in replicated databases","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Seventh Framework Programme; Federación Española de Enfermedades Raras","keywords":"Computer science; Serializability; Correctness; Replica; Data integrity; Snapshot (computer storage); Database; Isolation (microbiology); Distributed computing; Rollback; Concurrency control; Two-phase locking; Distributed database; Fault tolerance; Database transaction; Distributed transaction; Transaction processing; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04464981699830389,"gpt":0.2969985777953138,"spread":0.2523487607970099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005919423,0.000205803,0.0002865211,0.0002152847,0.0001503346,0.000165014,0.0005911699,0.00007451172,0.00002006991],"category_scores_gemma":[0.00007990286,0.0001935257,0.00004022391,0.0006236123,0.00006644613,0.0009343825,0.00001643077,0.0003703104,0.00002410201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006525768,"about_ca_system_score_gemma":0.00005943361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006153391,"about_ca_topic_score_gemma":0.00009857579,"domain_scores_codex":[0.9981222,0.0001621661,0.0004981329,0.000664896,0.0002611463,0.0002915091],"domain_scores_gemma":[0.9978519,0.0001560503,0.0001164689,0.001672389,0.00006724177,0.000135925],"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":[0.000428589,0.004380023,0.004930387,0.0008123831,0.0002625578,0.0006441264,0.002499885,0.005710429,0.0490873,0.2707289,0.01185858,0.6486568],"study_design_scores_gemma":[0.01295401,0.001678945,0.05668557,0.00657548,0.0001401917,0.002595461,0.002579472,0.8087973,0.01193406,0.002152595,0.08901589,0.004891015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01262687,0.0002612675,0.9837021,0.0008128177,0.0004070742,0.0004929023,0.0009301907,0.0001610168,0.000605815],"genre_scores_gemma":[0.9915928,0.00006154989,0.007766127,0.0001551718,0.00002769209,0.00004173311,0.0003123543,0.00000614226,0.00003648481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9789659,"threshold_uncertainty_score":0.789175,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967155922","doi":"10.1145/1670243.1670250","title":"Automatic virtual machine configuration for database workloads","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); University of Waterloo","funders":"","keywords":"Computer science; Online transaction processing; Workload; Database; Software deployment; Virtual machine; Virtualization; Temporal isolation among virtual machines; Distributed computing; Hypervisor; Operating system; Cloud computing; Transaction processing; Database transaction","retraction":null,"screen_n_in":null,"score":{"opus":0.03302318292325333,"gpt":0.2566651177257133,"spread":0.22364193480246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004996076,0.0002444762,0.0002623443,0.0002504422,0.0007159286,0.0001251014,0.001149155,0.00005769289,0.00002791695],"category_scores_gemma":[0.00006170596,0.0002198787,0.0001205767,0.0004536187,0.00005416566,0.0001007305,0.00004889086,0.0001977414,0.000145736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007644699,"about_ca_system_score_gemma":0.00006438995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002179831,"about_ca_topic_score_gemma":0.0000160286,"domain_scores_codex":[0.9980049,0.0001425056,0.0004585648,0.0005954639,0.0004441447,0.0003544666],"domain_scores_gemma":[0.9971172,0.0004258294,0.0001405415,0.002098234,0.00007045714,0.0001477995],"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":[0.0002091562,0.002950878,0.00008596054,0.001282437,0.0009075251,0.0003787524,0.003865057,0.3230456,0.005244107,0.04091509,0.03477176,0.5863436],"study_design_scores_gemma":[0.0009951721,0.0002150682,0.00003684181,0.0002225457,0.00003401243,0.0001170859,0.0001173125,0.9816348,0.0007927602,0.00002220066,0.01549507,0.0003171466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02444104,0.00016163,0.9714692,0.0006465008,0.001352841,0.0008215113,0.0002899499,0.0005787486,0.0002386161],"genre_scores_gemma":[0.9739885,0.00001792338,0.02351877,0.0002201174,0.000153496,0.0002282514,0.0001445684,0.00002503458,0.001703343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9495475,"threshold_uncertainty_score":0.8966393,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118265701","doi":"10.1145/1189769.1189772","title":"Adaptive rank-aware query optimization in relational databases","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":56,"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":"Computer science; Query optimization; Query plan; Ranking (information retrieval); Rank (graph theory); Cardinality (data modeling); Key (lock); Query language; Relational database; Join (topology); Operator (biology); Sargable; Theoretical computer science; Database; Data mining; Information retrieval; Web search query; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.03803229702306821,"gpt":0.2493029119004517,"spread":0.2112706148773835,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004005503,0.0002005901,0.0001899484,0.0004532937,0.0001930692,0.0001488692,0.0008048548,0.0000437803,0.00005168119],"category_scores_gemma":[0.00002117737,0.0002017094,0.0000532522,0.0008227048,0.00003540338,0.002598456,0.00005280482,0.0001984426,0.0001104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009749365,"about_ca_system_score_gemma":0.00005691511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002186456,"about_ca_topic_score_gemma":0.000300732,"domain_scores_codex":[0.9981118,0.0001484953,0.0004282731,0.0005855631,0.0004467619,0.0002790712],"domain_scores_gemma":[0.9981123,0.0002149879,0.0001114411,0.001446099,0.00005759816,0.00005758848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003330093,0.0004385584,0.0001853345,0.00005436694,0.00003695118,0.00007391315,0.00004323764,0.9410409,0.00002530454,0.04748416,0.004152541,0.006431443],"study_design_scores_gemma":[0.0009108643,0.00004338362,0.000403984,0.000197957,0.00001876389,0.00001648086,0.0001152852,0.9884306,0.00009600836,0.0001169516,0.009310028,0.0003397274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001044263,0.0001143791,0.9960285,0.0003234512,0.0007311543,0.0004320179,0.001235761,0.0002102179,0.0008200286],"genre_scores_gemma":[0.520306,0.0001571016,0.4695767,0.0002039517,0.0003474657,0.0003705197,0.006279065,0.00005494582,0.002704282],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5264519,"threshold_uncertainty_score":0.8225468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993831977","doi":"10.1145/1242524.1242529","title":"Estimating the selectivity of approximate string queries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"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":"Substring; String (physics); Estimator; Approximate string matching; Computer science; Inverse; String searching algorithm; String metric; Algorithm; String kernel; Data structure; Mathematics; Statistics; Pattern matching; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0257870433612683,"gpt":0.2745853299599472,"spread":0.2487982865986789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108473,0.0001271105,0.0001619928,0.0001010573,0.0003724879,0.00009327244,0.0009795231,0.00003743953,0.000004320801],"category_scores_gemma":[0.00005615739,0.00008790805,0.00004792118,0.0004505019,0.00005093674,0.0006701408,0.00005683245,0.0002077368,0.000007032083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003277867,"about_ca_system_score_gemma":0.00004186483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006743145,"about_ca_topic_score_gemma":0.00004156485,"domain_scores_codex":[0.9987236,0.0000849596,0.0003156314,0.0003000883,0.0003362077,0.000239461],"domain_scores_gemma":[0.9977694,0.0004218685,0.0001455933,0.001538795,0.00006458361,0.00005981061],"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":[0.0001611612,0.001163655,0.000674953,0.001105537,0.0003122696,0.00007373625,0.003617494,0.1168229,0.03319674,0.05399875,0.0009992147,0.7878736],"study_design_scores_gemma":[0.0004520912,0.000124118,0.0005994808,0.0004399066,0.00002627779,0.0001076512,0.0003918915,0.9549856,0.03957935,0.0003621578,0.002603059,0.0003284636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00885549,0.00009512026,0.9896277,0.00006814308,0.0007449384,0.0002371702,0.0001272055,0.0001291744,0.0001150633],"genre_scores_gemma":[0.8386069,0.000005119525,0.1612456,0.00001450302,0.00005704597,0.00001831186,0.0000121939,0.000007923099,0.00003234365],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8381626,"threshold_uncertainty_score":0.3584787,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3166524313","doi":"10.1145/3446980","title":"Optimizing One-time and Continuous Subgraph Queries using Worst-case Optimal Joins","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":39,"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":"Computer science; Joins; Query plan; Query optimization; Spatial query; Vertex (graph theory); Computation; Theoretical computer science; Graph; Sargable; Algorithm; Database; Web search query; Search engine; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.03081097010833498,"gpt":0.24837275789465,"spread":0.2175617877863151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004732419,0.0002602813,0.000370788,0.0002523635,0.0006795399,0.0004642126,0.0004497603,0.00008633082,0.00003807849],"category_scores_gemma":[0.00004116816,0.0002724144,0.0001200168,0.0007171771,0.0001235585,0.001039213,0.00006351592,0.0002886171,0.000024964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003210181,"about_ca_system_score_gemma":0.00008976243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000240856,"about_ca_topic_score_gemma":0.00003325362,"domain_scores_codex":[0.9979767,0.000316329,0.000380164,0.0006708245,0.0002630822,0.0003929675],"domain_scores_gemma":[0.9978201,0.0002771641,0.0001061714,0.001468987,0.0001176569,0.0002099128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005752323,0.005947342,0.0002917442,0.002166299,0.004043487,0.06125147,0.02337314,0.2723568,0.3333147,0.1556837,0.0005319668,0.1404641],"study_design_scores_gemma":[0.003964395,0.0005440626,0.00004352154,0.002016632,0.000514105,0.04488315,0.006862178,0.8578889,0.07536444,0.0008695278,0.004284169,0.002764938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1083148,0.0007696188,0.8892211,0.0001462504,0.0006534746,0.0002280399,0.0003627335,0.0002247377,0.00007923393],"genre_scores_gemma":[0.7129565,0.00009525957,0.2863628,0.00009397152,0.00007702625,0.00003515057,0.00004128905,0.00003188268,0.0003060794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6046417,"threshold_uncertainty_score":0.9999728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042315498","doi":"10.1145/581751.581752","title":"Searching for dependencies at multiple abstraction levels","year":2002,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":38,"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; Functional dependency; Dependency (UML); Tuple; Online analytical processing; Dependency theory (database theory); Generalization; Abstraction; Scope (computer science); Data mining; Extension (predicate logic); Theoretical computer science; Database; Data warehouse; Relational database; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.09694704259971397,"gpt":0.2879969122087368,"spread":0.1910498696090228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004537154,0.0002640716,0.0002796368,0.0002205943,0.0008953732,0.0001276028,0.0006824078,0.00008174354,0.00005852391],"category_scores_gemma":[0.0001607037,0.0002453422,0.0001350841,0.0002888596,0.0000498614,0.001759655,0.0000510284,0.0002037979,0.0002591049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002099556,"about_ca_system_score_gemma":0.00002598001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004298564,"about_ca_topic_score_gemma":0.0006068511,"domain_scores_codex":[0.9977934,0.0001099709,0.0004641685,0.0006811984,0.0004704962,0.0004807751],"domain_scores_gemma":[0.9968196,0.0008098679,0.000162133,0.001920209,0.0001085617,0.0001796491],"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":[0.0004734446,0.002656349,0.0005323783,0.004088048,0.001076546,0.0003375979,0.007764148,0.150105,0.1976909,0.1709131,0.02488816,0.4394743],"study_design_scores_gemma":[0.00236962,0.0003227882,0.0002215298,0.0005045617,0.00004686559,0.0005155481,0.0008952114,0.3263606,0.0311365,0.0001533935,0.6363226,0.001150741],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002785537,0.0003029949,0.9915824,0.0002811724,0.001543015,0.0008352023,0.001993155,0.000362182,0.0003143602],"genre_scores_gemma":[0.8708889,0.00007693413,0.1249821,0.00007769648,0.0001831742,0.0005166975,0.0001176885,0.00004031917,0.003116393],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8681034,"threshold_uncertainty_score":0.9999999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1984237017","doi":"10.1145/1735886.1735887","title":"Transparent anonymization","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":34,"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":"Nanyang Technological University; Glaucoma Research Foundation","keywords":"Computer science; Data publishing; Adversary; Exploit; Guard (computer science); Generalization; Data anonymization; Privacy protection; Computer security; Adversary model; Information privacy; Data mining; Publishing","retraction":null,"screen_n_in":null,"score":{"opus":0.04600808504767626,"gpt":0.2870118829402188,"spread":0.2410037978925426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004301431,0.0002078105,0.0001932725,0.00027973,0.0002613746,0.0002121111,0.02049874,0.0001504986,0.00006448062],"category_scores_gemma":[0.001831554,0.0001972073,0.00006403113,0.0006727477,0.00007735948,0.001076164,0.001256523,0.0005939155,0.0002122406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004373892,"about_ca_system_score_gemma":0.0000657661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000187522,"about_ca_topic_score_gemma":0.0001206833,"domain_scores_codex":[0.9981528,0.00007929972,0.0003482485,0.0006493779,0.0004303296,0.000339935],"domain_scores_gemma":[0.9828835,0.0002049916,0.00009243881,0.01664094,0.0000673316,0.0001108512],"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":[0.000111786,0.002721023,0.0007323801,0.0007580377,0.0004855051,0.0002529097,0.0005748806,0.006607456,0.1716464,0.05826668,0.250581,0.507262],"study_design_scores_gemma":[0.002184952,0.0003369953,0.0005500658,0.0003834698,0.00008843339,0.0003720433,0.0001801646,0.7370209,0.09398346,0.0196188,0.1435202,0.001760529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001983718,0.00004971215,0.9857735,0.006637586,0.0029459,0.0003601294,0.0005101888,0.001371907,0.0003673399],"genre_scores_gemma":[0.7360292,0.00006628558,0.2633832,0.00008669206,0.00006232577,0.0001362243,0.0001243552,0.00002202916,0.00008970593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7340454,"threshold_uncertainty_score":0.9848008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971604907","doi":"10.1145/1189769.1189770","title":"Expressive power of an algebra for data mining","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":34,"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; Tuple; Relational algebra; Data mining; Data model (GIS); Relational database; Information retrieval; Theoretical computer science; Algebra over a field; Artificial intelligence; Mathematics; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04314760138777388,"gpt":0.2949769826758806,"spread":0.2518293812881067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003591967,0.0001404445,0.0001894599,0.0001261665,0.0002046735,0.0001267275,0.002605393,0.00004701279,0.000009120196],"category_scores_gemma":[0.00003186288,0.000134139,0.00004006085,0.0002954049,0.00004150104,0.001256143,0.00006890023,0.00007757649,0.0000126746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001590152,"about_ca_system_score_gemma":0.00006219418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006514125,"about_ca_topic_score_gemma":0.00004110582,"domain_scores_codex":[0.9985142,0.00004759452,0.0003683181,0.0006161127,0.0002363205,0.0002174215],"domain_scores_gemma":[0.9948097,0.000276077,0.0001555416,0.004597069,0.00008547681,0.00007614528],"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":[0.0001548535,0.006476794,0.00008766302,0.0008400878,0.00054158,0.00005567795,0.0027321,0.009246011,0.04703939,0.1130869,0.1001784,0.7195606],"study_design_scores_gemma":[0.001605773,0.000411531,0.0001456563,0.0003625962,0.00009316498,0.00008052662,0.001110057,0.8852735,0.01609745,0.0005072441,0.09357873,0.0007337999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004055239,0.00008250077,0.9862648,0.0001490926,0.0003580807,0.0004036647,0.008426124,0.0001220808,0.0001384395],"genre_scores_gemma":[0.33108,0.000005790021,0.6659688,0.00003637202,0.00009165509,0.0002497769,0.002330715,0.00002191763,0.0002150109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8760275,"threshold_uncertainty_score":0.5470028,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3212747350","doi":"10.1145/3483940","title":"On Directed Densest Subgraph Discovery","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"University of Hong Kong; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Scalability; Induced subgraph isomorphism problem; Enhanced Data Rates for GSM Evolution; Core (optical fiber); Graph; Directed graph; Subgraph isomorphism problem; Efficient algorithm; Theoretical computer science; Algorithm; Artificial intelligence; Database; Line graph","retraction":null,"screen_n_in":null,"score":{"opus":0.01990446779099111,"gpt":0.2521827545106705,"spread":0.2322782867196793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000135104,0.0002703728,0.0002730285,0.0002173799,0.000321721,0.0002921078,0.0009613929,0.00008023818,0.00002140156],"category_scores_gemma":[0.00008309139,0.0002527359,0.0001580375,0.001446432,0.00005215285,0.001091856,0.00003713881,0.0004112317,0.0001539652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000604772,"about_ca_system_score_gemma":0.00007412403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005961852,"about_ca_topic_score_gemma":0.00009766273,"domain_scores_codex":[0.9977165,0.0002418779,0.0003384375,0.0008226992,0.0004673103,0.0004131305],"domain_scores_gemma":[0.9959985,0.0007171803,0.000094783,0.002922626,0.0001005935,0.0001663333],"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":[0.000665136,0.005987893,0.0008496029,0.0008463941,0.001439275,0.007877939,0.000962532,0.3689574,0.05521684,0.3702691,0.0332395,0.1536884],"study_design_scores_gemma":[0.01629252,0.003550137,0.007492193,0.009009319,0.0007463642,0.006353679,0.00149073,0.44467,0.3023508,0.02766387,0.1675467,0.01283359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01205493,0.0003647961,0.9830376,0.0004625204,0.002549055,0.000261556,0.0003129155,0.0006407591,0.0003158986],"genre_scores_gemma":[0.985059,0.0002131761,0.01248608,0.0004591162,0.00009013635,0.0001046336,0.00011672,0.00003516102,0.001435976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9730041,"threshold_uncertainty_score":0.9999925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139000699","doi":"10.1145/2338626.2338633","title":"Reordering rows for better compression","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speedup; Lexicographical order; Row; Sorting; Compression (physics); Algorithm; Data compression; Heuristic; Heuristics; Huffman coding; Compression ratio; Encoding (memory); Parallel computing; Mathematics; Combinatorics; Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04066127576892296,"gpt":0.289049769394661,"spread":0.248388493625738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004722758,0.0002371075,0.0002726967,0.0001542237,0.0004377103,0.00007377272,0.0006301859,0.00006882168,0.00001767138],"category_scores_gemma":[0.00004469308,0.0002044488,0.0001031192,0.0002472866,0.00003286566,0.002033568,0.00004848178,0.0001769014,0.000117284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006316912,"about_ca_system_score_gemma":0.00002581417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001104774,"about_ca_topic_score_gemma":0.00001256705,"domain_scores_codex":[0.9982471,0.0001012953,0.0003955039,0.000430374,0.0002965519,0.0005291668],"domain_scores_gemma":[0.9972442,0.0003068764,0.0001280144,0.002045617,0.00006650452,0.0002088077],"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":[0.0004505993,0.002755681,0.00102,0.003893941,0.0007478192,0.00005142975,0.005046713,0.01662073,0.08558463,0.4106841,0.0618893,0.411255],"study_design_scores_gemma":[0.0008524553,0.0001007479,0.00006792793,0.0004419422,0.0000265961,0.00008866107,0.0002477753,0.01235291,0.01169595,0.00006860908,0.9735073,0.0005491019],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001124852,0.0005091833,0.9932705,0.0002775919,0.002815309,0.0006810279,0.0007584566,0.0003009638,0.0002620797],"genre_scores_gemma":[0.520099,0.00005060507,0.476923,0.0003228357,0.0006335341,0.0008706806,0.0002444571,0.00005681237,0.0007990473],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.911618,"threshold_uncertainty_score":0.8337182,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010916971","doi":"10.1145/1132863.1132868","title":"Integrating XML data sources using approximate joins","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28,"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; Joins; XML validation; XML; Efficient XML Interchange; Document Structure Description; XML Schema (W3C); XML database; Information retrieval; Streaming XML; Data mining; Set (abstract data type); Tree (set theory); XML Encryption; Database; Programming language; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.06748389564404962,"gpt":0.2828255905583581,"spread":0.2153416949143085,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006450247,0.0002356194,0.0002258399,0.0002625086,0.0004441542,0.0007688176,0.003412124,0.00004464581,0.00001553283],"category_scores_gemma":[0.00002580177,0.0002090692,0.00005082696,0.0006086887,0.00004508615,0.002746512,0.0002513643,0.0002173363,0.00006603077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004848087,"about_ca_system_score_gemma":0.00004260462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002600541,"about_ca_topic_score_gemma":0.0001590475,"domain_scores_codex":[0.9978706,0.0001120941,0.0004257681,0.0007860456,0.0004300545,0.0003754994],"domain_scores_gemma":[0.9952618,0.0001096217,0.0001502299,0.004366148,0.00003814234,0.00007399989],"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":[0.0001025569,0.005205174,0.001317388,0.003004951,0.001396839,0.000913572,0.001599835,0.1140444,0.02703342,0.2612251,0.04833811,0.5358188],"study_design_scores_gemma":[0.0003427732,0.00002752211,0.00001754675,0.0002035477,0.00004436975,0.00004203835,0.0003099292,0.9748998,0.0006996151,0.000152731,0.02291302,0.0003471658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001312555,0.0001553828,0.9946947,0.000175082,0.001001512,0.0003352186,0.001369839,0.0003665092,0.0005892667],"genre_scores_gemma":[0.4233841,0.00004943761,0.5715017,0.0001571371,0.0006029073,0.00006935373,0.002692138,0.0000648788,0.001478331],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8608554,"threshold_uncertainty_score":0.8525596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971512992","doi":"10.1145/1005566.1005570","title":"A compressed accessibility map for XML","year":2004,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Access Control and Trust","field":"Social Sciences","cited_by":28,"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; Efficient XML Interchange; XML validation; XML Schema (W3C); XML database; XML; Streaming XML; XML framework; XML Encryption; Simple API for XML; Database; Document Structure Description; XML Schema Editor; XML Signature; Information retrieval; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.05599528690366123,"gpt":0.3495931178292262,"spread":0.293597830925565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006328559,0.0001440473,0.0002318654,0.00008795118,0.001029217,0.0001847956,0.0006838304,0.00009784161,0.0001193233],"category_scores_gemma":[0.0001301589,0.0001310485,0.0001248019,0.0002284968,0.0001517162,0.0005905725,0.00000770482,0.0001524934,0.0001026067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001536534,"about_ca_system_score_gemma":0.0002189167,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01072342,"about_ca_topic_score_gemma":0.003779888,"domain_scores_codex":[0.9984678,0.0001364767,0.0002957026,0.0003809837,0.0003592315,0.000359798],"domain_scores_gemma":[0.9984637,0.0003466358,0.00009508024,0.0008033956,0.0001192387,0.0001719599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004975177,0.01391937,0.004026407,0.005238665,0.002672077,0.000176199,0.03557788,0.07392809,0.009219999,0.6264123,0.01550098,0.2083529],"study_design_scores_gemma":[0.01678665,0.0004892228,0.001844135,0.0009839437,0.0005595184,0.00001032619,0.01777449,0.002575349,0.00366572,0.01524468,0.938062,0.002004012],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009226237,0.0003328051,0.9766003,0.003690745,0.002493529,0.002141303,0.002136396,0.0003637431,0.003014896],"genre_scores_gemma":[0.9968306,0.00002751225,0.001550824,0.0001248981,0.0002742641,0.0004369396,0.00007490009,0.00001614365,0.0006639049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9876044,"threshold_uncertainty_score":0.9958643,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2053495332","doi":"10.1145/2487259.2487260","title":"Analysis and optimization for boolean expression indexing","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28,"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; Regular expression; Theoretical computer science; Search engine indexing; Boolean expression; Tree (set theory); Matching (statistics); Search tree; Data structure; Tree structure; String searching algorithm; Data mining; Algorithm; Pattern matching; Boolean function; Binary tree; Search algorithm; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02055275887691247,"gpt":0.2477562282413695,"spread":0.227203469364457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002216614,0.0001164764,0.0001504704,0.0003700835,0.0002389589,0.0004355764,0.0005470418,0.00003344342,0.00003475912],"category_scores_gemma":[0.00001812183,0.0001030558,0.00005584994,0.0005670465,0.00001554575,0.001703434,0.00003776483,0.00006387971,0.00001791181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001726513,"about_ca_system_score_gemma":0.000007827476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002257366,"about_ca_topic_score_gemma":0.000009032257,"domain_scores_codex":[0.9990009,0.00004518239,0.0002056804,0.0003959926,0.0001792238,0.0001730142],"domain_scores_gemma":[0.9986489,0.0001106167,0.00007370613,0.001035832,0.0000507396,0.00008023167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003034396,0.0005047765,0.0005412012,0.0005427334,0.001233785,0.000008495736,0.0006319066,0.5774015,0.002565795,0.005465928,0.005843409,0.4052301],"study_design_scores_gemma":[0.0002947629,0.00003408885,0.00007666843,0.00004643125,0.00009254835,0.000001383851,0.0001057553,0.9966292,0.000662424,0.00003787465,0.00186855,0.0001503076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003914545,0.00004158241,0.9981969,0.0002273063,0.000262177,0.000530267,0.0001502839,0.0001270983,0.00007290731],"genre_scores_gemma":[0.3874102,0.00008587718,0.610346,0.0001328909,0.00007654499,0.0005278687,0.0005072822,0.00001933894,0.0008940978],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4192277,"threshold_uncertainty_score":0.4202495,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104120015","doi":"10.1145/1538909.1538910","title":"Anonymization-based attacks in privacy-preserving data publishing","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Research Grants Council, University Grants Committee","keywords":"Computer science; Adversary; Data publishing; Overhead (engineering); Confidentiality; Computer security; Information loss; k-anonymity; Information sensitivity; Publishing; Information privacy; Internet privacy; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.07597995798891426,"gpt":0.3100199144698071,"spread":0.2340399564808928,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001834779,0.0003641723,0.0003909403,0.0009261411,0.0003174168,0.001603547,0.08681242,0.000246255,0.0000386491],"category_scores_gemma":[0.02297696,0.0003754716,0.00005839012,0.002397655,0.00006300142,0.009644433,0.01042143,0.0009059467,0.00006136835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002381044,"about_ca_system_score_gemma":0.0002660881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007617353,"about_ca_topic_score_gemma":0.0001806129,"domain_scores_codex":[0.9957877,0.0003162991,0.000777892,0.001542839,0.0008656658,0.0007096135],"domain_scores_gemma":[0.9515556,0.0007805563,0.0002336292,0.04715066,0.0001199496,0.0001596148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001445512,0.002659242,0.002971973,0.0006108684,0.0001803974,0.0005499058,0.0003443302,0.05164092,0.003405142,0.004916076,0.6869829,0.2455937],"study_design_scores_gemma":[0.001033299,0.00008540906,0.0005281625,0.0005647682,0.00001489112,0.00002512239,0.000072413,0.978999,0.001114222,0.00431578,0.01270685,0.0005400992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008987007,0.0002623285,0.9539698,0.04032479,0.0008539879,0.0006420161,0.001192678,0.001383194,0.0004724576],"genre_scores_gemma":[0.6262185,0.00007419529,0.3715016,0.0006651515,0.00007683741,0.00006830577,0.001316673,0.00003264089,0.00004611646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.927358,"threshold_uncertainty_score":0.9998697,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1998597078","doi":"10.1145/1670243.1670248","title":"An information-theoretic analysis of worst-case redundancy in database design","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":25,"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":"Seventh Framework Programme; Engineering and Physical Sciences Research Council","keywords":"Computer science; Redundancy (engineering); Schema (genetic algorithms); Functional dependency; Database schema; Theoretical computer science; Data integrity; Relational database; Data mining; Database design; Information retrieval; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.03518479320693964,"gpt":0.275027395432391,"spread":0.2398426022254513,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009919658,0.0003148786,0.0006242088,0.001704416,0.0003461944,0.0000622431,0.0009734325,0.00008703383,0.00004458877],"category_scores_gemma":[0.0001311117,0.0002967949,0.0001462591,0.003512766,0.0001699501,0.005274704,0.00004229934,0.0002793641,0.00004675517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001071764,"about_ca_system_score_gemma":0.0001853559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00230234,"about_ca_topic_score_gemma":0.0003577521,"domain_scores_codex":[0.9968585,0.0005061816,0.001117669,0.0005644325,0.0005468594,0.0004063369],"domain_scores_gemma":[0.9946991,0.0004707822,0.0003570997,0.004064915,0.000176656,0.0002314862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004529611,0.002147634,0.0009720215,0.0009529034,0.001479815,0.004161713,0.01190788,0.8090082,0.002775057,0.1492956,0.0006947381,0.01615145],"study_design_scores_gemma":[0.002771359,0.0006807006,0.0005085507,0.0008077925,0.000634247,0.003970108,0.003683454,0.9704953,0.006467935,0.0001429388,0.008164986,0.001672591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01178142,0.0001537483,0.9843577,0.00004038466,0.0004133509,0.0006364483,0.002379375,0.0001608745,0.0000766585],"genre_scores_gemma":[0.8550411,0.0001582552,0.1438545,0.00005012932,0.00002294237,0.0001772202,0.0006477304,0.0000162984,0.00003182571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8432597,"threshold_uncertainty_score":0.9999484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051445745","doi":"10.1145/507234.507237","title":"A logical foundation for deductive object-oriented databases","year":2002,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Programming language; Deductive database; Syntax; Semantics (computer science); Class (philosophy); Object (grammar); Well-founded semantics; Logic programming; Inheritance (genetic algorithm); Operational semantics; Database; Natural language processing; Artificial intelligence; Denotational semantics","retraction":null,"screen_n_in":null,"score":{"opus":0.07233550198391613,"gpt":0.2909125887188853,"spread":0.2185770867349692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003629344,0.0002606291,0.0002822916,0.0002133833,0.0005309876,0.0001680192,0.000859645,0.0000709223,0.0001358759],"category_scores_gemma":[0.0002699666,0.0002222522,0.000139101,0.0005790183,0.00007601231,0.001075429,0.00003717018,0.0002019961,0.0004611655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001243935,"about_ca_system_score_gemma":0.00004667906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001510831,"about_ca_topic_score_gemma":0.00006467963,"domain_scores_codex":[0.9979281,0.00016627,0.0003684002,0.0007753781,0.0003354666,0.0004264227],"domain_scores_gemma":[0.9972386,0.0005636734,0.0001314156,0.001699302,0.0001898839,0.0001771335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003497008,0.006668591,0.0002646906,0.0008658628,0.0008095978,0.0001289856,0.006140235,0.0028707,0.005544625,0.6957039,0.03762867,0.2430245],"study_design_scores_gemma":[0.004924118,0.001402671,0.0002209147,0.0005039286,0.0002341042,0.0004764496,0.001408645,0.4107793,0.007911345,0.001078979,0.5692325,0.001827042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001062777,0.0002907686,0.9930258,0.0002730195,0.002089054,0.0008660089,0.0004319747,0.0003682502,0.001592279],"genre_scores_gemma":[0.9390233,0.0001197201,0.05722579,0.0001402235,0.0003379863,0.0007038194,0.0003458615,0.00002977639,0.002073493],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9379606,"threshold_uncertainty_score":0.9063183,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4245823248","doi":"10.1145/1114244.1114250","title":"Optimization of query streams using semantic prefetching","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":20,"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":"Computer science; Latency (audio); Context (archaeology); Server; Query optimization; STREAMS; Data mining; Information retrieval; Database; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.03100413104897517,"gpt":0.2743439780064526,"spread":0.2433398469574774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003586616,0.0002205491,0.0003170143,0.0002617272,0.000240428,0.00005678791,0.0005715459,0.00006488009,0.00001949445],"category_scores_gemma":[0.00004167211,0.0002058556,0.00008649836,0.0004736237,0.00004489777,0.001947989,0.0000400881,0.0001710344,0.00001973159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001055091,"about_ca_system_score_gemma":0.00009011477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008427167,"about_ca_topic_score_gemma":0.00008003106,"domain_scores_codex":[0.9981174,0.0001482074,0.0005933121,0.0004689063,0.0003900004,0.0002821474],"domain_scores_gemma":[0.9974688,0.0001516804,0.0002625944,0.001907613,0.0001037512,0.0001055718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001159804,0.0001301152,0.00002452559,0.000170634,0.00004264633,0.000005240195,0.0002501649,0.978129,0.002674367,0.005745394,0.00002974633,0.01278663],"study_design_scores_gemma":[0.0004287248,0.00006001836,0.000007439775,0.0006041995,0.00003165713,0.00009179618,0.0002835589,0.9860477,0.007423284,0.00001180707,0.004711067,0.000298771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005187922,0.0002388055,0.992754,0.00008781331,0.000634576,0.0003730972,0.0004226894,0.0001840118,0.0001170184],"genre_scores_gemma":[0.5395878,0.00005879476,0.4600142,0.00002725171,0.0001004866,0.00002803558,0.00006343139,0.00002188362,0.00009808865],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5343999,"threshold_uncertainty_score":0.8394548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002932370","doi":"10.1145/1061318.1061324","title":"Concise descriptions of subsets of structured sets","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":19,"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; Automatic summarization; Theoretical computer science; Set (abstract data type); Minimum description length; Online analytical processing; Hierarchy; Cover (algebra); Context (archaeology); Representation (politics); Data mining; Algorithm; Artificial intelligence; Data warehouse","retraction":null,"screen_n_in":null,"score":{"opus":0.0319806076430219,"gpt":0.2639264952448165,"spread":0.2319458876017946,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002589322,0.0001438858,0.0002386991,0.0002566489,0.00009024883,0.00005214967,0.001250279,0.00004169544,0.00005542114],"category_scores_gemma":[0.00002067352,0.0001340711,0.00008135671,0.0004759157,0.00005867845,0.001021411,0.00004034056,0.0001115126,0.00004463801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003035391,"about_ca_system_score_gemma":0.00003956522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001868103,"about_ca_topic_score_gemma":0.00007351698,"domain_scores_codex":[0.9986135,0.00007531949,0.0004374945,0.0003142164,0.0003656296,0.000193843],"domain_scores_gemma":[0.9977255,0.00008150355,0.0001683279,0.001856845,0.00008732885,0.00008051918],"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":[0.0001520326,0.002649009,0.000401355,0.001704478,0.001111698,0.00006369471,0.002844628,0.03404836,0.05311339,0.1042902,0.03320691,0.7664143],"study_design_scores_gemma":[0.009017816,0.0009330284,0.003582539,0.001729766,0.0006193956,0.0002020332,0.001961514,0.5726355,0.1795072,0.00119883,0.2260464,0.002566045],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007239223,0.0001776432,0.988696,0.0002694101,0.0007559824,0.0003559746,0.002066163,0.0001017754,0.0003378238],"genre_scores_gemma":[0.9371369,0.000054775,0.06227939,0.00004152769,0.00003382045,0.00002640478,0.0001421772,0.00001002765,0.000274936],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9298977,"threshold_uncertainty_score":0.5467262,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3172623769","doi":"10.1145/3451159","title":"Graph Indexing for Efficient Evaluation of Label-constrained Reachability Queries","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reachability; Computer science; Vertex (graph theory); Search engine indexing; Transitive closure; Combinatorics; Graph; Theoretical computer science; Discrete mathematics; Mathematics; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.06869570056074788,"gpt":0.3123199311397553,"spread":0.2436242305790074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020408,0.0001357737,0.0002071955,0.0001702385,0.0001807735,0.0001136395,0.0005996138,0.00004077315,0.00001779901],"category_scores_gemma":[0.0001896492,0.0001332598,0.00008556974,0.0006016582,0.00006142744,0.000454196,0.00003910171,0.00009076017,0.000005651945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005802691,"about_ca_system_score_gemma":0.0001591413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001316686,"about_ca_topic_score_gemma":0.00005381612,"domain_scores_codex":[0.9980745,0.0002352748,0.0003884325,0.0004942946,0.0006048257,0.0002027081],"domain_scores_gemma":[0.9974092,0.0002692099,0.0001258492,0.001737981,0.0004003355,0.00005740086],"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":[0.0001000797,0.002955456,0.0001141564,0.00200018,0.0006857818,0.00001973552,0.001820588,0.06124807,0.01467163,0.1490546,0.0009092907,0.7664204],"study_design_scores_gemma":[0.003114942,0.0001890191,0.0001752371,0.0004258941,0.0002522222,0.00002119481,0.001511416,0.9653699,0.02225854,0.001721802,0.004492366,0.0004674848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008771741,0.0001458807,0.9876969,0.0003031282,0.0009872316,0.0007476862,0.0009864005,0.00009535594,0.0002656474],"genre_scores_gemma":[0.9251003,0.00001788003,0.07392434,0.00003331338,0.00004246864,0.0003211238,0.0003813956,0.00001202029,0.0001671775],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9163285,"threshold_uncertainty_score":0.5434178,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080555007","doi":"10.1145/1806907.1806909","title":"Continuous online index tuning in moving object databases","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Media Development Authority - Singapore","keywords":"Computer science; Granularity; B-tree; Overhead (engineering); Search engine indexing; Tree (set theory); Grid; Data mining; Workload; Set (abstract data type); Object (grammar); Database; Binary tree; Information retrieval; Algorithm; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02813362435550357,"gpt":0.2745241931610565,"spread":0.2463905688055529,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006626886,0.0002460809,0.0002844383,0.0005483517,0.0001997293,0.0003113437,0.001887804,0.00005427772,0.00004220869],"category_scores_gemma":[0.0001151465,0.0002385513,0.00006025504,0.0008076304,0.00004824142,0.002097528,0.0001385292,0.0006470979,0.00008572257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003500802,"about_ca_system_score_gemma":0.00006131239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002611039,"about_ca_topic_score_gemma":0.002281161,"domain_scores_codex":[0.9979141,0.0001053232,0.0004442433,0.0006881533,0.0004162808,0.0004319249],"domain_scores_gemma":[0.9966849,0.0002652427,0.0001163541,0.002760135,0.0000448376,0.0001284982],"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":[0.000131113,0.004838792,0.01082829,0.000864495,0.000425751,0.001712182,0.001355733,0.008771725,0.0320848,0.04095716,0.006051922,0.891978],"study_design_scores_gemma":[0.003738289,0.0002094551,0.005206101,0.001022248,0.00007083258,0.000217102,0.001764723,0.8333502,0.002093875,0.0001466791,0.1503901,0.001790398],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0195941,0.00006175797,0.9753745,0.0002885505,0.00238569,0.0004255073,0.001164809,0.0003261243,0.0003789094],"genre_scores_gemma":[0.9424059,0.00005133276,0.05584538,0.0001727026,0.0001817105,0.00007571498,0.0006269836,0.00002855332,0.0006117696],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9228117,"threshold_uncertainty_score":0.9727841,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766916843","doi":"10.1145/3110214","title":"Blazes","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Debugging; Consistency (knowledge bases); Scalability; Distributed computing; Programming language; Database; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03784811562260383,"gpt":0.288350591027029,"spread":0.2505024754044252,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000344005,0.0001801174,0.0002295065,0.00008164046,0.001027365,0.0009159747,0.003049734,0.00006728541,0.00001710329],"category_scores_gemma":[0.00005870729,0.0001596472,0.00009152583,0.000108093,0.00006226372,0.001177188,0.00004545047,0.000187436,0.0005120052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003888809,"about_ca_system_score_gemma":0.00004956889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007692372,"about_ca_topic_score_gemma":0.00005450941,"domain_scores_codex":[0.9984897,0.00006487535,0.0002932953,0.0004945883,0.0003541876,0.0003033427],"domain_scores_gemma":[0.9941479,0.00007443516,0.0001834387,0.005371301,0.0000735334,0.0001493977],"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":[0.0001476657,0.002373741,0.001240975,0.001176487,0.0009199376,0.000967527,0.001696343,0.01034099,0.01064476,0.3487652,0.06897842,0.552748],"study_design_scores_gemma":[0.002814064,0.0002890659,0.002876331,0.001193675,0.00005860898,0.0003626321,0.0003091431,0.1048558,0.005530099,0.0005801246,0.8795756,0.001554863],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001134541,0.0001610415,0.9904814,0.0008971845,0.002815214,0.0002774923,0.000586703,0.0002389956,0.003407433],"genre_scores_gemma":[0.9933432,0.00003498705,0.004463505,0.00006468382,0.000119437,0.00009498274,0.00002196831,0.00001276154,0.001844488],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9922087,"threshold_uncertainty_score":0.8832765,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036787492","doi":"10.1145/2560796","title":"Sharing across Multiple MapReduce Jobs","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cloud computing; Merge (version control); Key (lock); Batch processing; Database; Distributed computing; Context (archaeology); Parallel computing; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02870516225659378,"gpt":0.265099848590538,"spread":0.2363946863339443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000758142,0.0002019565,0.000204624,0.0001110773,0.0005337259,0.0003316919,0.001998407,0.00005377473,0.000006572799],"category_scores_gemma":[0.00006396704,0.000184924,0.00009997468,0.0003827963,0.00003338352,0.00005925992,0.0001585537,0.0002439852,0.0002819893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005943513,"about_ca_system_score_gemma":0.00001175058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005751841,"about_ca_topic_score_gemma":0.00004105191,"domain_scores_codex":[0.9980518,0.0001117708,0.0003186164,0.0006970163,0.0003734172,0.000447442],"domain_scores_gemma":[0.9966807,0.0002675963,0.0000894425,0.002773061,0.00004140717,0.0001477664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003796702,0.0007830719,0.001031987,0.0005185667,0.00026316,0.00005068516,0.003175437,0.6682317,0.002060867,0.01120902,0.002562339,0.3100752],"study_design_scores_gemma":[0.0006706298,0.0000751398,0.0004024284,0.0002116357,0.00001266424,0.00003613405,0.0002530572,0.9493737,0.0009071147,0.00006702697,0.04765357,0.0003368569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1074758,0.0000523099,0.8890007,0.000433416,0.001585061,0.0002467592,0.0000424051,0.0005187322,0.000644923],"genre_scores_gemma":[0.9895576,0.000002580316,0.008496407,0.0001456997,0.0001672729,0.0000509314,0.000008037788,0.00001922568,0.0015523],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8820818,"threshold_uncertainty_score":0.7540982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309617049","doi":"10.1145/3571281","title":"Efficiently Cleaning Structured Event Logs: A Graph Repair Approach","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Beijing National Research Center For Information Science And Technology; National Natural Science Foundation of China","keywords":"Computer science; Workflow; Event (particle physics); Pruning; Data mining; Graph; Profiling (computer programming); Information retrieval; Theoretical computer science; Database; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1167959570941646,"gpt":0.3589782289255208,"spread":0.2421822718313563,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006514168,0.0002537365,0.0003957864,0.0007524402,0.001307311,0.0002765772,0.002230303,0.00004586341,0.0008134438],"category_scores_gemma":[0.0004147896,0.0002175674,0.0003174985,0.001873257,0.00008820976,0.0004223358,0.0002148386,0.0004936128,0.0001945438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001570881,"about_ca_system_score_gemma":0.00006976764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005676133,"about_ca_topic_score_gemma":0.00006747658,"domain_scores_codex":[0.9933639,0.001330328,0.001024144,0.001126115,0.002727783,0.0004277746],"domain_scores_gemma":[0.9949101,0.0006978599,0.0003144542,0.003807829,0.00009119069,0.0001786087],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000536886,0.002511915,0.0001251514,0.0002631,0.0005690636,0.000121829,0.003413769,0.7770706,0.000477668,0.02937876,0.1383023,0.04722892],"study_design_scores_gemma":[0.001962923,0.0005214039,0.0003274187,0.00006897005,0.0001956384,0.0001732986,0.06328368,0.05944963,0.0001504641,0.002055759,0.8708953,0.0009154814],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009426407,0.000256942,0.9766492,0.0004024369,0.003217915,0.001273625,0.006329013,0.000424474,0.002019937],"genre_scores_gemma":[0.9913121,0.00001361327,0.004396016,0.0004283733,0.00006508816,0.0004227625,0.0005775493,0.00002897143,0.002755507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9818857,"threshold_uncertainty_score":0.9999928,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410830018","doi":"10.1145/3736756","title":"Efficient Parallel Boolean Expression Matching","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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":"Science and Technology Commission of Shanghai Municipality","keywords":"Computer science; Boolean expression; Expression (computer science); Matching (statistics); Regular expression; Theoretical computer science; Boolean function; Algorithm; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01736739543533445,"gpt":0.2672524681699296,"spread":0.2498850727345952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003399167,0.0002076448,0.0002142177,0.0002632496,0.0005152252,0.0002396397,0.001488136,0.00007260138,0.00001956693],"category_scores_gemma":[0.00001935355,0.0001719517,0.00008207322,0.0004451232,0.00002647063,0.0003212595,0.0001235213,0.0002776355,0.0001253704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006608829,"about_ca_system_score_gemma":0.00007072005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002835616,"about_ca_topic_score_gemma":0.000006081199,"domain_scores_codex":[0.9982031,0.0001398595,0.0003548158,0.0006114786,0.000384871,0.0003058587],"domain_scores_gemma":[0.9970183,0.0002057562,0.0000833636,0.002528648,0.00004761345,0.0001163088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000162085,0.001798464,0.00003429665,0.0006424569,0.0001731244,0.0001413491,0.001141529,0.7311589,0.030494,0.06144535,0.02155403,0.1512544],"study_design_scores_gemma":[0.001686516,0.00009962344,0.000150056,0.002411858,0.00003964049,0.00004698714,0.0005207708,0.9275442,0.008398479,0.0009625379,0.0574308,0.000708504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001694051,0.0003177871,0.9941649,0.0003621166,0.001882065,0.0003397745,0.0001778627,0.0003343157,0.0007270937],"genre_scores_gemma":[0.8214864,0.00005934491,0.1761206,0.0003174818,0.00009013052,0.000179313,0.00009734052,0.00002227909,0.001627156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8197923,"threshold_uncertainty_score":0.7011988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7117687674","doi":"10.1145/3786785","title":"Finding Smallest Witnesses for Conjunctive Queries","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","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 Waterloo","funders":"","keywords":"Conjunctive query; Rewriting; Property (philosophy); Logarithm; Class (philosophy); Time complexity; Polynomial; Constant (computer programming)","retraction":null,"screen_n_in":null,"score":{"opus":0.03221601730685047,"gpt":0.2997566851307163,"spread":0.2675406678238658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000372403,0.0002903189,0.0003833721,0.0003200767,0.0006745776,0.0001492846,0.0007913326,0.00008149658,0.000009746082],"category_scores_gemma":[0.0001834291,0.0002626801,0.0001179562,0.0006269781,0.0001039119,0.0009509432,0.00005283052,0.0001790843,0.00003068877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001146645,"about_ca_system_score_gemma":0.0002031161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003876212,"about_ca_topic_score_gemma":0.0002191484,"domain_scores_codex":[0.9981236,0.00009608636,0.0004631116,0.0006946517,0.0002328862,0.0003896591],"domain_scores_gemma":[0.996816,0.0008066518,0.0001410551,0.001954442,0.0001868083,0.00009503296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001440982,0.0001845422,0.00008755943,0.0006409598,0.0002569256,0.00001914127,0.0004249484,0.003223401,0.001988749,0.9771493,0.005219542,0.0106608],"study_design_scores_gemma":[0.002901043,0.0004085596,0.0001385615,0.001855978,0.0001309741,0.00008457099,0.004092677,0.01448976,0.02398592,0.002146157,0.9484943,0.001271522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004767091,0.0005986854,0.9917354,0.00057208,0.002858462,0.0009822942,0.00170517,0.0003126702,0.0007585476],"genre_scores_gemma":[0.7676578,0.0001767618,0.2222365,0.0004674863,0.0001986453,0.002371817,0.0003909647,0.00004934243,0.006450644],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9750032,"threshold_uncertainty_score":0.9999825,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417496854","doi":"10.1145/3785662","title":"Semi-Oblivious Chase Termination for Linear Existential Rules and Beyond: An Experimental Analysis","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Existentialism; Chase; Set (abstract data type); Generalization; Linearization; Class (philosophy); Focus (optics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02356188656044739,"gpt":0.3092196439563378,"spread":0.2856577573958904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003309369,0.0001725102,0.0002250047,0.0006605075,0.0003428095,0.0003591552,0.0007350048,0.00004736115,0.000009650723],"category_scores_gemma":[0.00001296269,0.0001694143,0.00009862363,0.0006345482,0.00003852648,0.001323696,0.00005379794,0.00007860427,0.00000837367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004048368,"about_ca_system_score_gemma":0.0000237743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001666604,"about_ca_topic_score_gemma":0.00004062989,"domain_scores_codex":[0.9986295,0.00007388175,0.0002819572,0.0005856705,0.0002186179,0.0002104406],"domain_scores_gemma":[0.9984316,0.0000911571,0.00007519678,0.001266483,0.00004958918,0.00008603382],"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":[0.0005553265,0.009360514,0.0003579161,0.002015998,0.007024628,0.0002014063,0.004680427,0.01067497,0.02854654,0.1696426,0.009514221,0.7574254],"study_design_scores_gemma":[0.001610913,0.0003032633,0.0001148923,0.0000802726,0.000608713,0.000009322295,0.0009705128,0.9753913,0.007508501,0.0001594969,0.01280314,0.0004396963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009767524,0.0001743463,0.9870277,0.0002196304,0.0007089726,0.0005413606,0.001196571,0.0001606454,0.0002032727],"genre_scores_gemma":[0.9324806,0.00004830645,0.06326842,0.0001886226,0.0001059133,0.0004041313,0.001724005,0.00001539915,0.001764557],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9647163,"threshold_uncertainty_score":0.6908516,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392139269","doi":"10.1145/3649133","title":"Sharing Queries with Nonequivalent User-defined Aggregate Functions","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","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 Waterloo","funders":"","keywords":"Rewriting; Computer science; Aggregate (composite); Class (philosophy); Query language; Function (biology); Materialized view; Extension (predicate logic); Theoretical computer science; Database query; Reuse; Programming language; Information retrieval; Artificial intelligence; View","retraction":null,"screen_n_in":null,"score":{"opus":0.02668953795672124,"gpt":0.2596981473377908,"spread":0.2330086093810696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000339451,0.0004029423,0.0003626755,0.0004079307,0.0004947246,0.000514912,0.0008564417,0.00007569491,0.00005830354],"category_scores_gemma":[0.00003012173,0.000315906,0.0001249126,0.00107224,0.0001022232,0.002652616,0.00008316986,0.0004080884,0.0005402532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001607921,"about_ca_system_score_gemma":0.0001368613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009955425,"about_ca_topic_score_gemma":0.0003425584,"domain_scores_codex":[0.997222,0.00008591094,0.0005085885,0.001103855,0.0005621549,0.0005174787],"domain_scores_gemma":[0.9963498,0.0002446292,0.00009933066,0.002984535,0.0001012021,0.0002204941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002707918,0.0006107063,0.0001692359,0.003315804,0.001257241,0.00149072,0.002133451,0.04249815,0.00746313,0.890094,0.006339103,0.04435763],"study_design_scores_gemma":[0.0008613006,0.0005219868,0.00004554172,0.003799129,0.0001407849,0.001067528,0.001051944,0.04227437,0.004984148,0.0001667974,0.9438603,0.001226182],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001703856,0.001452737,0.9894316,0.0005756618,0.002864486,0.0005531106,0.001475787,0.001372248,0.0005705667],"genre_scores_gemma":[0.8289388,0.000545865,0.146542,0.0001984185,0.0005924389,0.001536036,0.0006412209,0.0002028715,0.0208023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9375212,"threshold_uncertainty_score":0.9999293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415991463","doi":"10.1145/3774322","title":"Proof-of-Execution: Low-Latency Consensus via Speculative Execution","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","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":"McMaster University","funders":"","keywords":"Protocol (science); Latency (audio); Key (lock); Distributed transaction; Transaction processing; Two-phase commit protocol; Database transaction","retraction":null,"screen_n_in":null,"score":{"opus":0.01594775058131951,"gpt":0.2646067206446487,"spread":0.2486589700633292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004363617,0.0002682578,0.0004166359,0.0002932533,0.0002814489,0.00009927675,0.0009331523,0.0001294902,0.00001546091],"category_scores_gemma":[0.00004776638,0.0002530699,0.0001490041,0.001234227,0.000107108,0.0003615067,0.00003401712,0.0002578794,0.00005325044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001386735,"about_ca_system_score_gemma":0.0001854149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005130736,"about_ca_topic_score_gemma":0.00002813104,"domain_scores_codex":[0.9976292,0.000219563,0.0007508259,0.0006407265,0.0004231583,0.0003365418],"domain_scores_gemma":[0.9971964,0.0001872461,0.0002454628,0.001974835,0.0002884039,0.0001075913],"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":[0.0007942349,0.00649616,0.0005189294,0.006581675,0.00239251,0.0005400547,0.003190848,0.1072317,0.05633717,0.5325409,0.02796134,0.2554145],"study_design_scores_gemma":[0.007679367,0.0009605011,0.001595665,0.00967422,0.0003722738,0.0005209135,0.001643621,0.7254943,0.1580576,0.004589951,0.08665077,0.002760835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002652278,0.0004951142,0.990003,0.0005185842,0.002417105,0.000874739,0.000675356,0.0001857125,0.002178104],"genre_scores_gemma":[0.9938766,0.00001557804,0.004797615,0.00005215321,0.00004592785,0.0001382325,0.00008583268,0.00001085533,0.0009772062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9912243,"threshold_uncertainty_score":0.9999921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}