{"meta":{"query_hash":"293684bd6cd1","filters":{"venue":"Foundations and Trends in Databases"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/293684bd6cd1","api":"https://metacan.xera.ac/api/v1/cohort?venue=Foundations+and+Trends+in+Databases"},"results":[{"id":"W2791946429","doi":"10.1561/1900000055","title":"Algorithmic Aspects of Parallel Data Processing","year":2018,"lang":"en","type":"article","venue":"Foundations and Trends in Databases","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data processing; Massively parallel; SPARK (programming language); Parallel processing; Sorting; Joins; Data processing system; Scope (computer science); Computation; Parallel computing; Distributed computing; Theoretical computer science; Algorithm; Database","score_opus":0.08973294613584182,"score_gpt":0.36032610517810243,"score_spread":0.2705931590422606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791946429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027382132,0.00049140584,0.9916591,0.0003081477,0.00019198959,0.000058455706,0.0005049858,0.00005957181,0.003988096],"genre_scores_gemma":[0.57283676,0.00007390756,0.42533797,0.000037822127,0.00012911929,0.0000064465594,0.0014957113,0.000006130645,0.00007614101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907833,0.000025922322,0.0002080626,0.00039653666,0.00014573004,0.0001454141],"domain_scores_gemma":[0.99871135,0.00005052882,0.00008820221,0.0010545654,0.000053045726,0.000042303214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017734224,0.00008812164,0.000119196186,0.00023899066,0.00015368471,0.00009806311,0.0007470366,0.00001700296,0.00006406432],"category_scores_gemma":[0.000042186242,0.00007556283,0.000009328685,0.00058316725,0.00013798858,0.0018690962,0.0011412302,0.000059700436,0.000007020631],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037365528,0.000115164876,0.0006080514,0.000012829109,0.0000057736383,0.000005376697,0.000118223725,0.0000034095165,0.000048957492,0.041739646,0.0018816572,0.95545715],"study_design_scores_gemma":[0.0010761749,0.00016268542,0.04685558,0.00025514644,0.000020997932,0.00005181508,0.00008413736,0.83026874,0.00034077294,0.0063527864,0.11412361,0.0004075699],"about_ca_topic_score_codex":0.00027986543,"about_ca_topic_score_gemma":0.00037209588,"teacher_disagreement_score":0.95504963,"about_ca_system_score_codex":0.000007879818,"about_ca_system_score_gemma":0.00005023447,"threshold_uncertainty_score":0.30813628},"labels":[],"label_agreement":null},{"id":"W4285522518","doi":"10.1561/1900000066","title":"Differential Privacy for Databases","year":2021,"lang":"en","type":"article","venue":"Foundations and Trends in Databases","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Differential privacy; Database; Computer science; Differential (mechanical device); Internet privacy; Data mining; Engineering","score_opus":0.09559784109037046,"score_gpt":0.35532375681894873,"score_spread":0.2597259157285783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285522518","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024332402,0.00039076232,0.9580486,0.01330158,0.00051899627,0.00012208756,0.0024414747,0.00036048068,0.00048362883],"genre_scores_gemma":[0.23075531,0.0002919855,0.7618028,0.00010855354,0.000071734015,0.00011011167,0.006626707,0.000013895776,0.00021889586],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985923,0.000043381202,0.0002617321,0.0006511262,0.0001554168,0.00029600854],"domain_scores_gemma":[0.99417543,0.0004191484,0.000069988826,0.005217444,0.00006548513,0.00005251106],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0001193674,0.00015258936,0.00018103166,0.0003312588,0.00021686658,0.00022708875,0.0042128884,0.000030017638,0.00019742624],"category_scores_gemma":[0.007887405,0.00015151623,0.00004053258,0.0007902314,0.00010359967,0.0014165657,0.032137055,0.00012397859,0.000006694848],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013455343,0.00052544754,0.0073528164,0.000068996174,0.000057478825,0.00006023692,0.000059192836,0.000002893268,0.0008358194,0.25652084,0.22080083,0.513702],"study_design_scores_gemma":[0.00337939,0.00012762133,0.04715417,0.0002745666,0.000079910824,0.0001600482,0.00014940169,0.11604039,0.016602537,0.124056995,0.6907215,0.0012534336],"about_ca_topic_score_codex":0.000087911576,"about_ca_topic_score_gemma":0.00043485648,"teacher_disagreement_score":0.51244855,"about_ca_system_score_codex":0.000030755185,"about_ca_system_score_gemma":0.00006255072,"threshold_uncertainty_score":0.97569084},"labels":[],"label_agreement":null},{"id":"W4293582904","doi":"10.1561/1900000045","title":"Trends in Cleaning Relational Data: Consistency and Deduplication","year":2015,"lang":"en","type":"article","venue":"Foundations and Trends in Databases","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data deduplication; Consistency (knowledge bases); Data consistency; Computer science; Database; Data science; Artificial intelligence","score_opus":0.20184294516867166,"score_gpt":0.36898336875878557,"score_spread":0.1671404235901139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293582904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26066777,0.00671396,0.5801293,0.117631495,0.0013387612,0.00049323356,0.0041343533,0.0016702189,0.027220873],"genre_scores_gemma":[0.61903596,0.00012741615,0.37632468,0.00006919898,0.000024767105,0.000021876454,0.0043176464,0.000007336328,0.00007115418],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987189,0.000054854754,0.0002842902,0.00058889337,0.00017067928,0.00018237346],"domain_scores_gemma":[0.9957698,0.00021598127,0.000086421016,0.0038320946,0.000036138208,0.000059593964],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005498747,0.00011287422,0.00013090704,0.00085116155,0.00010797551,0.00013636077,0.0030807522,0.000044888133,0.000020883012],"category_scores_gemma":[0.0041197105,0.00011594308,0.000008157154,0.0012591799,0.00015432201,0.002621671,0.01980673,0.00016559991,0.000005283241],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007713028,0.00013120148,0.083186105,0.0000075273174,0.000011495652,0.000014090402,0.00012970915,0.000018299741,0.000011981825,0.15583122,0.070045516,0.69060516],"study_design_scores_gemma":[0.0016805977,0.000073160976,0.4506497,0.00011233745,0.0000192148,0.00010166166,0.00025361,0.3981661,0.00002694998,0.08449382,0.0639153,0.0005075329],"about_ca_topic_score_codex":0.0004025544,"about_ca_topic_score_gemma":0.0017072142,"teacher_disagreement_score":0.69009763,"about_ca_system_score_codex":0.000053397478,"about_ca_system_score_gemma":0.000048529746,"threshold_uncertainty_score":0.9881209},"labels":[],"label_agreement":null},{"id":"W4403690984","doi":"10.1561/1900000090","title":"Modern Techniques For Querying Graph-structured Databases","year":2024,"lang":"en","type":"article","venue":"Foundations and Trends in Databases","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Polytechnique Montréal","funders":"","keywords":"Computer science; Graph database; Database; Graph; Information retrieval; Theoretical computer science","score_opus":0.048239545733152527,"score_gpt":0.3378664988143314,"score_spread":0.28962695308117886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403690984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028032577,0.0010455664,0.9935753,0.00037572026,0.00034067375,0.00011574641,0.0009845766,0.00034518092,0.00041402577],"genre_scores_gemma":[0.68182904,0.00015485732,0.31602773,0.00009023972,0.00010100205,0.000108519394,0.0014446161,0.000015853506,0.00022814162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990159,0.000035234872,0.00019378542,0.0004544131,0.000096833064,0.00020383445],"domain_scores_gemma":[0.9991927,0.00025736808,0.000028331624,0.00044858115,0.000025453715,0.000047573852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024368602,0.00013935001,0.00012659981,0.0006798436,0.00021440301,0.0002847138,0.0002711468,0.000020174433,0.000028458384],"category_scores_gemma":[0.00004169689,0.00012249107,0.00005435057,0.00078310387,0.00008366096,0.0014120158,0.0001851693,0.000098443474,0.0000017488651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029000003,0.000024337009,0.00011635892,0.000030991832,0.0000134751945,0.000008800073,0.00012504769,0.0000065985587,0.00020397885,0.5055751,0.00064741564,0.49324498],"study_design_scores_gemma":[0.00067733467,0.00015586542,0.0023002746,0.00060485484,0.00007987611,0.00015533937,0.00013997727,0.2256027,0.008485324,0.49968982,0.2610691,0.0010395618],"about_ca_topic_score_codex":0.00006825172,"about_ca_topic_score_gemma":0.00024445617,"teacher_disagreement_score":0.67902577,"about_ca_system_score_codex":0.0000124111675,"about_ca_system_score_gemma":0.000025795141,"threshold_uncertainty_score":0.4995041},"labels":[],"label_agreement":null}]}