{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"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":"293684bd6cd1","filters":{"venue":"Foundations and Trends in Databases"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Data deduplication; Consistency (knowledge bases); Data consistency; Computer science; Database; Data science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2018429451686717,"gpt":0.3689833687587856,"spread":0.1671404235901139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005498747,0.0001128742,0.000130907,0.0008511615,0.0001079755,0.0001363608,0.003080752,0.00004488813,0.00002088301],"category_scores_gemma":[0.004119711,0.0001159431,0.000008157154,0.00125918,0.000154322,0.002621671,0.01980673,0.0001655999,0.000005283241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005339748,"about_ca_system_score_gemma":0.00004852975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004025544,"about_ca_topic_score_gemma":0.001707214,"domain_scores_codex":[0.9987189,0.00005485475,0.0002842902,0.0005888934,0.0001706793,0.0001823735],"domain_scores_gemma":[0.9957698,0.0002159813,0.00008642102,0.003832095,0.00003613821,0.00005959396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000007713028,0.0001312015,0.0831861,0.000007527317,0.00001149565,0.0000140904,0.0001297092,0.00001829974,0.00001198183,0.1558312,0.07004552,0.6906052],"study_design_scores_gemma":[0.001680598,0.00007316098,0.4506497,0.0001123375,0.0000192148,0.0001016617,0.00025361,0.3981661,0.00002694998,0.08449382,0.0639153,0.0005075329],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2606678,0.00671396,0.5801293,0.1176315,0.001338761,0.0004932336,0.004134353,0.001670219,0.02722087],"genre_scores_gemma":[0.619036,0.0001274161,0.3763247,0.00006919898,0.00002476711,0.00002187645,0.004317646,0.000007336328,0.00007115418],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6900976,"threshold_uncertainty_score":0.9881209,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08973294613584182,"gpt":0.3603261051781024,"spread":0.2705931590422606,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001773422,0.00008812164,0.0001191962,0.0002389907,0.0001536847,0.00009806311,0.0007470366,0.00001700296,0.00006406432],"category_scores_gemma":[0.00004218624,0.00007556283,0.000009328685,0.0005831672,0.0001379886,0.001869096,0.00114123,0.00005970044,0.000007020631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007879818,"about_ca_system_score_gemma":0.00005023447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002798654,"about_ca_topic_score_gemma":0.0003720959,"domain_scores_codex":[0.9990783,0.00002592232,0.0002080626,0.0003965367,0.00014573,0.0001454141],"domain_scores_gemma":[0.9987113,0.00005052882,0.00008820221,0.001054565,0.00005304573,0.00004230321],"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":[0.000003736553,0.0001151649,0.0006080514,0.00001282911,0.000005773638,0.000005376697,0.0001182237,0.000003409516,0.00004895749,0.04173965,0.001881657,0.9554572],"study_design_scores_gemma":[0.001076175,0.0001626854,0.04685558,0.0002551464,0.00002099793,0.00005181508,0.00008413736,0.8302687,0.0003407729,0.006352786,0.1141236,0.0004075699],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002738213,0.0004914058,0.9916591,0.0003081477,0.0001919896,0.00005845571,0.0005049858,0.00005957181,0.003988096],"genre_scores_gemma":[0.5728368,0.00007390756,0.425338,0.00003782213,0.0001291193,0.000006446559,0.001495711,0.000006130645,0.00007614101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9550496,"threshold_uncertainty_score":0.3081363,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Differential privacy; Database; Computer science; Differential (mechanical device); Internet privacy; Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09559784109037046,"gpt":0.3553237568189487,"spread":0.2597259157285783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0001193674,0.0001525894,0.0001810317,0.0003312588,0.0002168666,0.0002270887,0.004212888,0.00003001764,0.0001974262],"category_scores_gemma":[0.007887405,0.0001515162,0.00004053258,0.0007902314,0.0001035997,0.001416566,0.03213705,0.0001239786,0.000006694848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003075519,"about_ca_system_score_gemma":0.00006255072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008791158,"about_ca_topic_score_gemma":0.0004348565,"domain_scores_codex":[0.9985923,0.0000433812,0.0002617321,0.0006511262,0.0001554168,0.0002960085],"domain_scores_gemma":[0.9941754,0.0004191484,0.00006998883,0.005217444,0.00006548513,0.00005251106],"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":[0.00001345534,0.0005254475,0.007352816,0.00006899617,0.00005747882,0.00006023692,0.00005919284,0.000002893268,0.0008358194,0.2565208,0.2208008,0.513702],"study_design_scores_gemma":[0.00337939,0.0001276213,0.04715417,0.0002745666,0.00007991082,0.0001600482,0.0001494017,0.1160404,0.01660254,0.124057,0.6907215,0.001253434],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0243324,0.0003907623,0.9580486,0.01330158,0.0005189963,0.0001220876,0.002441475,0.0003604807,0.0004836288],"genre_scores_gemma":[0.2307553,0.0002919855,0.7618028,0.0001085535,0.00007173402,0.0001101117,0.006626707,0.00001389578,0.0002188959],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5124485,"threshold_uncertainty_score":0.9756908,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Polytechnique Montréal","funders":"","keywords":"Computer science; Graph database; Database; Graph; Information retrieval; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04823954573315253,"gpt":0.3378664988143314,"spread":0.2896269530811789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000243686,0.00013935,0.0001265998,0.0006798436,0.000214403,0.0002847138,0.0002711468,0.00002017443,0.00002845838],"category_scores_gemma":[0.00004169689,0.0001224911,0.00005435057,0.0007831039,0.00008366096,0.001412016,0.0001851693,0.00009844347,0.000001748865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001241117,"about_ca_system_score_gemma":0.00002579514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006825172,"about_ca_topic_score_gemma":0.0002444562,"domain_scores_codex":[0.9990159,0.00003523487,0.0001937854,0.0004544131,0.00009683306,0.0002038345],"domain_scores_gemma":[0.9991927,0.0002573681,0.00002833162,0.0004485812,0.00002545372,0.00004757385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000029,0.00002433701,0.0001163589,0.00003099183,0.00001347519,0.000008800073,0.0001250477,0.000006598559,0.0002039789,0.5055751,0.0006474156,0.493245],"study_design_scores_gemma":[0.0006773347,0.0001558654,0.002300275,0.0006048548,0.00007987611,0.0001553394,0.0001399773,0.2256027,0.008485324,0.4996898,0.2610691,0.001039562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002803258,0.001045566,0.9935753,0.0003757203,0.0003406738,0.0001157464,0.0009845766,0.0003451809,0.0004140258],"genre_scores_gemma":[0.681829,0.0001548573,0.3160277,0.00009023972,0.000101002,0.0001085194,0.001444616,0.00001585351,0.0002281416],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6790258,"threshold_uncertainty_score":0.4995041,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}