{"meta":{"query_hash":"323cac591371","filters":{"venue":"ACM SIGMOD Record"},"cohort_total":67,"direct_labels_cover":0,"predictions_cover":67,"exported":67,"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/323cac591371","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+SIGMOD+Record"},"results":[{"id":"W1974306683","doi":"10.1145/335191.335495","title":"An approximate search engine for structural databases","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Parsing; Database; Information retrieval; XML; Set (abstract data type); Subgraph isomorphism problem; Graph database; Graph; Search engine; Heuristic; Data structure; XML database; Data mining; Theoretical computer science; World Wide Web; Programming language; Artificial intelligence","score_opus":0.020294907655088994,"score_gpt":0.28663512953624565,"score_spread":0.26634022188115664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974306683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9830652,0.0002548303,0.01544637,0.00009073723,0.00016656195,0.00032492456,0.00016490922,0.000022377357,0.00046412097],"genre_scores_gemma":[0.9422075,0.0002511277,0.05355887,0.00032216375,0.00073853956,0.000036312777,0.0016862995,0.00003274597,0.0011664318],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919695,0.000018098464,0.00017845194,0.00024366249,0.00006540068,0.00029744618],"domain_scores_gemma":[0.99912816,0.000016418498,0.0000297384,0.0006935118,0.00003727384,0.00009487552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001417562,0.00013337725,0.00011832201,0.000020424399,0.00009940639,0.00003142512,0.00035189016,0.00008455183,0.00019015648],"category_scores_gemma":[0.000019532908,0.00011698518,0.00006335578,0.000042748634,0.00003909939,0.000009282304,0.00007025463,0.0000731979,0.000011115092],"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":[0.00034884785,0.000039041577,0.0005537418,0.00005376433,0.000068625086,0.0000011546695,0.000116202886,0.0012572696,0.038076583,0.00012861722,0.007464588,0.95189154],"study_design_scores_gemma":[0.0039037433,0.0025910542,0.0018346946,0.000045698904,0.00009029431,0.00008480745,0.0002464546,0.26034665,0.116516635,0.0039305277,0.6087737,0.0016357424],"about_ca_topic_score_codex":0.000031174564,"about_ca_topic_score_gemma":0.00003669292,"teacher_disagreement_score":0.9502558,"about_ca_system_score_codex":0.0000062197096,"about_ca_system_score_gemma":0.000030493764,"threshold_uncertainty_score":0.47705173},"labels":[],"label_agreement":null},{"id":"W1975270911","doi":"10.1145/601858.601873","title":"Toward autonomic computing with DB2 universal database","year":2002,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Total cost of ownership; Database; IBM; Unix; Scale (ratio); Software; Operating system","score_opus":0.03708365375936235,"score_gpt":0.23390888169402854,"score_spread":0.1968252279346662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975270911","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":[0.039016552,0.00014576873,0.9565166,0.0007112974,0.00051885616,0.00016537463,0.00002429396,0.00035337315,0.0025478604],"genre_scores_gemma":[0.52954316,0.000036789887,0.46923935,0.00021466492,0.00016898989,0.0000044761796,0.00001627412,0.000020088737,0.0007561778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986475,0.000052407635,0.00022006675,0.00053618796,0.00018003318,0.00036376945],"domain_scores_gemma":[0.9981778,0.0001480503,0.00013605595,0.001360269,0.000049452097,0.00012837075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013072431,0.00019291425,0.00022448429,0.00009197909,0.0001767999,0.000063265354,0.00091967254,0.000039674047,0.00007748746],"category_scores_gemma":[0.00005518551,0.00016109359,0.00004336422,0.00029178458,0.00006826366,0.0011848559,0.00073886535,0.00016846585,0.00017594047],"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":[0.000080027945,0.0003151777,0.006468586,0.00016666889,0.00019495687,0.001069179,0.005463668,0.0018047435,0.002970051,0.34009695,0.02301992,0.6183501],"study_design_scores_gemma":[0.0025015376,0.00069767586,0.0010904119,0.0003715812,0.00003291606,0.0004128532,0.0006659284,0.3724856,0.002176271,0.0008531515,0.61710334,0.0016087024],"about_ca_topic_score_codex":0.00020135168,"about_ca_topic_score_gemma":0.000054091208,"teacher_disagreement_score":0.61674136,"about_ca_system_score_codex":0.00007043947,"about_ca_system_score_gemma":0.00003947754,"threshold_uncertainty_score":0.6569206},"labels":[],"label_agreement":null},{"id":"W1978094234","doi":"10.1145/776985.776996","title":"Peer-to-peer","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Peer-to-peer; World Wide Web; Programming language; Computer network","score_opus":0.026189099824546435,"score_gpt":0.26945035843242077,"score_spread":0.24326125860787434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978094234","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":[0.13278194,0.00016288339,0.70031416,0.121598735,0.0046726507,0.00088002754,0.000007860154,0.0034477357,0.03613403],"genre_scores_gemma":[0.38781473,0.0000074150566,0.57972413,0.003118111,0.00013558047,0.00010251214,0.0000023070115,0.00003742067,0.029057778],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968665,0.000085285035,0.00034246425,0.0009041331,0.0009536826,0.0008479285],"domain_scores_gemma":[0.9958012,0.00026460024,0.00007987284,0.0030792425,0.00047279737,0.0003022706],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00090738264,0.00030814265,0.00032243255,0.00035859144,0.000167433,0.0002594622,0.004381703,0.00019338103,0.00006741784],"category_scores_gemma":[0.004996471,0.00029351155,0.00010718742,0.001681712,0.000046854075,0.0003842218,0.0014088321,0.00034899858,0.0019237046],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007750159,0.00006964633,0.0026072795,0.0000053610042,0.000028442155,0.000056900713,0.00046556015,0.00020845965,0.0010829989,0.034399193,0.5371019,0.4239665],"study_design_scores_gemma":[0.00023156339,0.00026444934,0.0012884401,0.000020542071,0.000006116872,0.000033514552,0.00004769209,0.00062604947,0.007113952,0.038513914,0.9513344,0.0005193346],"about_ca_topic_score_codex":0.000048379585,"about_ca_topic_score_gemma":0.00006995885,"teacher_disagreement_score":0.42344716,"about_ca_system_score_codex":0.000118162505,"about_ca_system_score_gemma":0.00009306836,"threshold_uncertainty_score":0.9999517},"labels":[],"label_agreement":null},{"id":"W1986871321","doi":"10.1145/362084.362142","title":"Knowledge discovery in data warehouses","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Data warehouse; Automatic summarization; Terabyte; Knowledge extraction; Data mining; Process (computing); Data science; Information retrieval; Database","score_opus":0.06937896728329003,"score_gpt":0.3180131510689414,"score_spread":0.24863418378565139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986871321","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":[0.43470162,0.0018580881,0.51306576,0.011804661,0.00165667,0.0009276677,0.00055779016,0.0013208492,0.034106895],"genre_scores_gemma":[0.39759445,0.0009353328,0.5795273,0.00067508174,0.00057294714,0.00012838621,0.0003384858,0.000051412997,0.020176597],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895406,0.000029927396,0.00018350244,0.00052439224,0.00009032308,0.00021779932],"domain_scores_gemma":[0.99674237,0.00016323906,0.000028360306,0.0030039912,0.000012007572,0.000050060007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018545311,0.000097245866,0.00011764176,0.000061995685,0.00006903027,0.00019881573,0.0039517465,0.000036345118,0.000069877395],"category_scores_gemma":[0.000073422845,0.00008785834,0.000019251476,0.00045172023,0.000028748598,0.0015173933,0.0010747908,0.0001110289,0.00045289777],"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":[0.0000013658276,0.000096135685,0.0005452315,0.000002829607,0.0000032679775,0.0000040844593,0.00015028863,0.000004802955,0.000021074446,0.00093237875,0.012524241,0.9857143],"study_design_scores_gemma":[0.00038841012,0.00005029528,0.008430415,0.0000550423,0.0000055415553,0.00001345269,0.000028612194,0.1085044,0.00012344396,0.0050352463,0.87699777,0.00036735606],"about_ca_topic_score_codex":0.00021678487,"about_ca_topic_score_gemma":0.00034793178,"teacher_disagreement_score":0.9853469,"about_ca_system_score_codex":0.000020338215,"about_ca_system_score_gemma":0.00006811039,"threshold_uncertainty_score":0.7343394},"labels":[],"label_agreement":null},{"id":"W1987552238","doi":"10.1145/373626.373697","title":"Constraints for semistructured data and XML","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Data integrity; XML database; Database; XML; Programming language; World Wide Web","score_opus":0.04716285210807767,"score_gpt":0.3007392847096654,"score_spread":0.2535764326015877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987552238","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":[0.0133720115,0.00019392339,0.984474,0.00058120384,0.00046286537,0.0002053873,0.0001923399,0.00009208006,0.00042619655],"genre_scores_gemma":[0.16608962,0.00012777494,0.8324769,0.0002899592,0.00024334864,0.000023660548,0.00013702847,0.000013276026,0.0005984096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907374,0.000017364986,0.0001617222,0.00045624483,0.00008640323,0.00020450288],"domain_scores_gemma":[0.997985,0.00017453327,0.000070467126,0.0016527238,0.00003980503,0.00007743862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016000032,0.00010694134,0.0001464771,0.000026564308,0.00011362869,0.000047641264,0.0008932583,0.000041271796,0.000017452203],"category_scores_gemma":[0.0003224048,0.000091161084,0.000017743205,0.000094573574,0.000086313725,0.0006185637,0.0008025585,0.000055960703,0.000004209329],"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":[0.000020120622,0.00001265496,0.0016708256,0.000040814335,0.000023717428,0.000022849112,0.00015707129,0.0000025430331,0.0026344098,0.03129234,0.008808781,0.95531386],"study_design_scores_gemma":[0.0007884705,0.000088361994,0.00059269636,0.000046308505,0.000009436899,0.00027923082,0.00009425517,0.016882326,0.0007950322,0.01599602,0.9640759,0.00035195652],"about_ca_topic_score_codex":0.000023654151,"about_ca_topic_score_gemma":0.000048141363,"teacher_disagreement_score":0.95526713,"about_ca_system_score_codex":0.0000085381635,"about_ca_system_score_gemma":0.000039527156,"threshold_uncertainty_score":0.3717441},"labels":[],"label_agreement":null},{"id":"W1998014869","doi":"10.1145/335191.335476","title":"Of XML and databases (panel session)","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Resverlogix (Canada)","funders":"","keywords":"Computer science; XML database; Database; Session (web analytics); XML; XML Schema Editor; Efficient XML Interchange; World Wide Web; XML Base; Streaming XML; XML validation; Information retrieval; XML Encryption","score_opus":0.04303868654853697,"score_gpt":0.2752964978959816,"score_spread":0.2322578113474446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998014869","genre_codex":"empirical","genre_gemma":"methods","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":[0.54597163,0.0007999311,0.44872898,0.00075408776,0.0004663701,0.00023030207,0.000112913105,0.00018438953,0.0027514275],"genre_scores_gemma":[0.39584893,0.0005617414,0.6003938,0.00026409962,0.00013029865,0.000019164432,0.000032235108,0.000016938036,0.0027328252],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916226,0.000037846756,0.0002099843,0.00029576628,0.00013365224,0.00016048716],"domain_scores_gemma":[0.9986909,0.00015230836,0.00007024675,0.0009882521,0.000029688033,0.000068589055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110588895,0.00010252079,0.00017754607,0.00004226887,0.000074812866,0.000013805471,0.00037405212,0.000022906752,0.00015903461],"category_scores_gemma":[0.00008782345,0.00008146845,0.000025924985,0.00016022746,0.000059363665,0.0008041476,0.00031582918,0.00006322525,0.00002465311],"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":[0.000019318184,0.000045337973,0.0028015666,0.00005437764,0.000012284873,0.000018190409,0.00022403442,0.000010681924,0.00228853,0.039479624,0.0024967557,0.9525493],"study_design_scores_gemma":[0.00060791353,0.00018211764,0.0065406803,0.00020310686,0.000010376887,0.00009140115,0.000100414574,0.0029813976,0.008143352,0.0028426445,0.9778678,0.00042881246],"about_ca_topic_score_codex":0.00021598044,"about_ca_topic_score_gemma":0.000039736846,"teacher_disagreement_score":0.975371,"about_ca_system_score_codex":0.000005648557,"about_ca_system_score_gemma":0.00002660713,"threshold_uncertainty_score":0.33221874},"labels":[],"label_agreement":null},{"id":"W2008481019","doi":"10.1145/1107499.1107509","title":"In memoriam Alberto Oscar Mendelzon","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TD Bank Group","funders":"","keywords":"Tribute; Battle; Friendship; Computer science; Intellect; Art history; Art; History; Ancient history; Theology; Philosophy; Sociology","score_opus":0.16446583863983466,"score_gpt":0.4286982494735129,"score_spread":0.26423241083367827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008481019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5237374,0.0004581445,0.013273696,0.15876247,0.016922496,0.0015316092,0.00008343689,0.0002719222,0.28495887],"genre_scores_gemma":[0.8595002,0.00019660035,0.027527913,0.011340105,0.0024609314,0.00008043199,0.000027038945,0.00003744171,0.09882929],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972386,0.00023834435,0.00068518944,0.0005895479,0.00091052207,0.0003378247],"domain_scores_gemma":[0.9969689,0.0010784346,0.00014816877,0.0016385588,0.00006128623,0.00010459941],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0032842155,0.00014297321,0.00027783867,0.00030521664,0.000070037386,0.00017470265,0.001866507,0.00007488275,0.002879581],"category_scores_gemma":[0.003424542,0.00011259849,0.00008851728,0.00065866724,0.00004482466,0.0009826097,0.0007641051,0.00014754558,0.003971934],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035687724,0.00010968984,0.0008977993,0.0000028553186,0.000010210921,0.0000117112,0.00046291156,0.0000607022,0.000076066346,0.005448979,0.5537364,0.43914703],"study_design_scores_gemma":[0.00039308664,0.00004822501,0.001051275,0.000006660832,0.0000053719505,0.0000017678811,0.00039772035,0.0005730619,0.00025355245,0.05977349,0.9373393,0.00015650145],"about_ca_topic_score_codex":0.0005045992,"about_ca_topic_score_gemma":0.0047735707,"teacher_disagreement_score":0.4389905,"about_ca_system_score_codex":0.000072871364,"about_ca_system_score_gemma":0.000029102654,"threshold_uncertainty_score":0.9980319},"labels":[],"label_agreement":null},{"id":"W2018758714","doi":"10.1145/945721.945733","title":"The hyperion project","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":189,"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 Ottawa; University of Toronto","funders":"","keywords":"Computer science; Schema (genetic algorithms); Database; Distributed database; Database schema; Key (lock); Information retrieval; Database design; Computer security","score_opus":0.026853933392331445,"score_gpt":0.2671210670957384,"score_spread":0.24026713370340697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018758714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39571923,0.0016038027,0.4801357,0.047223058,0.008819721,0.0023258042,0.000002814886,0.0054138335,0.058756035],"genre_scores_gemma":[0.66545916,0.00024174046,0.32956716,0.0006666312,0.00011524201,0.00018193088,5.6068683e-7,0.000024587096,0.0037429698],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987538,0.00008082329,0.00016324656,0.00037258622,0.00021856678,0.00041098596],"domain_scores_gemma":[0.9977266,0.00030588455,0.000054167613,0.0018254016,0.00004478331,0.00004311676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043126557,0.00013230636,0.000113806724,0.000083521445,0.00027410136,0.00019248996,0.0026987765,0.00007701667,0.000003146087],"category_scores_gemma":[0.0010808568,0.000088933426,0.000052549032,0.0007650167,0.00005252393,0.00019503657,0.00064692425,0.00018121928,0.00015229556],"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":[0.0000037563727,0.000018646253,0.0011682634,0.0000018064029,0.00001043231,0.000005361605,0.00012572538,0.000012788973,0.0004096623,0.04042483,0.043620404,0.91419834],"study_design_scores_gemma":[0.000109905246,0.00016486234,0.0007573931,0.000009431468,0.0000024650612,0.000018088242,0.000037428228,0.0010184556,0.0029267939,0.048637755,0.9461141,0.00020327885],"about_ca_topic_score_codex":0.0000327131,"about_ca_topic_score_gemma":0.00011353283,"teacher_disagreement_score":0.913995,"about_ca_system_score_codex":0.000048077058,"about_ca_system_score_gemma":0.0000743813,"threshold_uncertainty_score":0.5015043},"labels":[],"label_agreement":null},{"id":"W2020463925","doi":"10.1145/1462571.1462581","title":"Paper and proposal reviews","year":2008,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Term (time); Data science; Panel discussion; World Wide Web; Engineering ethics; Engineering","score_opus":0.10000165082144481,"score_gpt":0.28754345874430165,"score_spread":0.18754180792285685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020463925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8958776,0.008115756,0.0029388964,0.01355726,0.003715599,0.0017712015,0.000008742963,0.00062613934,0.073388785],"genre_scores_gemma":[0.95919997,0.008140757,0.00924353,0.011275185,0.0051538716,0.000108475084,0.00009189703,0.00008344474,0.006702859],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907774,0.000007831441,0.0002483187,0.00030603897,0.0001346856,0.00022536064],"domain_scores_gemma":[0.9992723,0.000029910045,0.00012236087,0.0004889394,0.000073658804,0.000012871969],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000196097,0.00016252723,0.00021950706,0.00008872276,0.00020663896,0.00009348288,0.00038293467,0.00006566343,0.0011706494],"category_scores_gemma":[0.00042145344,0.00012257171,0.000047127345,0.000300517,0.00010526113,0.0014268275,0.00036563032,0.00011910418,0.0010833228],"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":[0.000059618895,0.00011877256,0.0776791,0.00040519118,0.000020264626,0.00004876361,0.000056547105,7.855676e-7,0.0017343734,0.007663428,0.2864353,0.62577784],"study_design_scores_gemma":[0.00012462765,0.000007689414,0.01053027,0.000058172933,0.000019903475,0.000021805292,0.000010922639,0.00009063802,0.00006019198,0.005091659,0.98376495,0.00021916686],"about_ca_topic_score_codex":0.00033113698,"about_ca_topic_score_gemma":0.0001028826,"teacher_disagreement_score":0.69732964,"about_ca_system_score_codex":0.0000068684203,"about_ca_system_score_gemma":0.000015545766,"threshold_uncertainty_score":0.9997424},"labels":[],"label_agreement":null},{"id":"W2026730210","doi":"10.1145/362084.362104","title":"Generating spatiotemporal datasets on the WWW","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":54,"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 Alberta","funders":"Financiadora de Estudos e Projetos; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Search engine indexing; Data mining; Information retrieval; Interface (matter); Database; Operating system","score_opus":0.031612334944660654,"score_gpt":0.2537045766043308,"score_spread":0.22209224165967018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026730210","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6059836,0.00026455254,0.25837797,0.07071173,0.004541916,0.0018851178,0.0004608115,0.0014699408,0.056304358],"genre_scores_gemma":[0.37618166,0.00037332275,0.5552338,0.02823809,0.0029261555,0.00016355033,0.0015394377,0.00008677708,0.035257228],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901193,0.00006371942,0.00015205459,0.00034054279,0.00021687098,0.00021489784],"domain_scores_gemma":[0.9981888,0.00012281457,0.000047916463,0.0015897664,0.000009720684,0.000040980147],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030221412,0.00011273538,0.00008337827,0.000036172398,0.000211668,0.00032137387,0.0021140622,0.000024456613,0.00056916295],"category_scores_gemma":[0.0000628488,0.00007496291,0.000033996206,0.00021609833,0.000021926679,0.0005853166,0.0004157474,0.000115622424,0.0010797435],"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":[0.0000021187648,0.00002351102,0.00008806538,0.0000015979722,0.000008268771,0.000011191894,0.000029123536,0.00004800066,0.000027271935,0.0034747103,0.12628557,0.8700006],"study_design_scores_gemma":[0.00022281228,0.00012639769,0.00052592636,0.000019379951,0.0000057424327,0.0000029459195,0.000009292813,0.22672668,0.00043956467,0.0039631105,0.76770097,0.0002571773],"about_ca_topic_score_codex":0.000087961365,"about_ca_topic_score_gemma":0.000023945599,"teacher_disagreement_score":0.8697434,"about_ca_system_score_codex":0.000011691271,"about_ca_system_score_gemma":0.000012681424,"threshold_uncertainty_score":0.99969804},"labels":[],"label_agreement":null},{"id":"W2033301070","doi":"10.1145/1107499.1107519","title":"Christos Faloutsos speaks out","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Very large database; Computer science; Library science; Database; Information retrieval","score_opus":0.02296878735220468,"score_gpt":0.24348310670995268,"score_spread":0.220514319357748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033301070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12144428,0.0008627436,0.79638135,0.011704838,0.0017126376,0.00035639908,0.0000057580405,0.00090571254,0.06662625],"genre_scores_gemma":[0.8464334,0.00003427576,0.14539425,0.00060151634,0.00067891006,0.000009021901,0.000003285718,0.000017942486,0.006827367],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99860483,0.000033461463,0.0003106479,0.0004433507,0.00023248316,0.00037523592],"domain_scores_gemma":[0.9984251,0.000080064994,0.00013185403,0.0011803502,0.0000610626,0.00012156005],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021583037,0.00016568006,0.00022946659,0.00009609454,0.00016242034,0.00017340979,0.0015253307,0.0000671437,0.00026948279],"category_scores_gemma":[0.00012924972,0.00014475588,0.00016187741,0.00027642582,0.000032983622,0.0005487937,0.00056456967,0.00016214032,0.0008717024],"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":[0.000004163061,0.000038476064,0.0010909096,0.0000041376134,0.000030326066,0.000009129928,0.0007289101,0.000114280454,0.0005369437,0.00195514,0.0072387736,0.9882488],"study_design_scores_gemma":[0.0004576549,0.00017914173,0.0016363944,0.000029375631,0.000030118224,0.000027198761,0.00008479002,0.15449938,0.0020187867,0.0030553387,0.8373469,0.00063493865],"about_ca_topic_score_codex":0.00008852494,"about_ca_topic_score_gemma":0.00025013424,"teacher_disagreement_score":0.98761386,"about_ca_system_score_codex":0.000047141028,"about_ca_system_score_gemma":0.00003174552,"threshold_uncertainty_score":0.99990624},"labels":[],"label_agreement":null},{"id":"W2041835352","doi":"10.1145/945721.945722","title":"Analysis of SIGMOD's co-authorship graph","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Information retrieval; Theoretical computer science","score_opus":0.02584356087544954,"score_gpt":0.30262111552378207,"score_spread":0.27677755464833254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041835352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8880239,0.00010269029,0.073970474,0.00006381906,0.00009474787,0.00022682772,0.00003774348,0.00012350993,0.037356306],"genre_scores_gemma":[0.99181455,0.000008360932,0.0073526045,0.00002800807,0.00008361217,0.000032476684,0.00008838088,0.000024528139,0.0005674459],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982873,0.00021872603,0.00049721793,0.0004100666,0.00024214336,0.00034453964],"domain_scores_gemma":[0.9979818,0.00031329962,0.0002983851,0.0011766267,0.00011451304,0.000115407376],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048074944,0.00023076311,0.00065783306,0.0005937535,0.000095679345,0.00003366883,0.0005299647,0.00007084545,0.0031163301],"category_scores_gemma":[0.000056813267,0.00022283122,0.00074602925,0.0022110417,0.00007841563,0.00009280713,0.00007264839,0.0002051523,0.000019391426],"study_design_candidate":"observational","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":[0.000019132056,0.00024247843,0.9166691,0.0000073910974,0.0035004339,0.0000014751664,0.00018214119,0.00042298634,0.0013053943,0.033667807,0.0037638398,0.04021783],"study_design_scores_gemma":[0.0016900591,0.00056232914,0.1053426,0.00010079462,0.014525928,0.0000015943954,0.000791322,0.0122365095,0.062495317,0.7069401,0.09244139,0.0028720368],"about_ca_topic_score_codex":0.00042674545,"about_ca_topic_score_gemma":0.0000724631,"teacher_disagreement_score":0.8113265,"about_ca_system_score_codex":0.0000203622,"about_ca_system_score_gemma":0.00003568141,"threshold_uncertainty_score":0.997795},"labels":[],"label_agreement":null},{"id":"W2042832124","doi":"10.1145/1361348.1361361","title":"Report on the First International Workshop on Ranking in Databases (DBRank'07)","year":2007,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":1,"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":"Conjunction (astronomy); Ranking (information retrieval); Computer science; Database; World Wide Web; Information retrieval","score_opus":0.047223779236043414,"score_gpt":0.3079342729547288,"score_spread":0.2607104937186854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042832124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08901243,0.000078756406,0.88896084,0.008580266,0.003655876,0.00037727042,0.000022139106,0.00017199843,0.0091404095],"genre_scores_gemma":[0.919357,0.00009075432,0.07447849,0.0035421976,0.0009264928,0.00006303233,0.0000858291,0.000034791745,0.0014214371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983657,0.000037000136,0.00040942914,0.0005005529,0.0003937024,0.00029363364],"domain_scores_gemma":[0.99679476,0.0013311538,0.00018069801,0.0016001173,0.000046950645,0.000046328878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010929063,0.00016073983,0.00015789768,0.00015135227,0.00016246668,0.000055012133,0.0010383248,0.00003837749,0.000061827464],"category_scores_gemma":[0.0012637445,0.000111479276,0.000055993947,0.00032515958,0.000045698656,0.00055282953,0.0005029353,0.00026113636,0.00008666124],"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":[0.00034913994,0.00038559496,0.034834743,0.000031666248,0.00007866987,0.0030463394,0.0010131723,0.0006521854,0.00029325858,0.5194373,0.025641397,0.41423655],"study_design_scores_gemma":[0.00045624314,0.00006265964,0.010288054,0.0005155718,0.0000026373575,0.00011243303,0.00014016902,0.0015901576,0.0016628484,0.0016410473,0.9831972,0.0003309644],"about_ca_topic_score_codex":0.0001606284,"about_ca_topic_score_gemma":0.0010924357,"teacher_disagreement_score":0.95755583,"about_ca_system_score_codex":0.00008059531,"about_ca_system_score_gemma":0.000030378613,"threshold_uncertainty_score":0.4545993},"labels":[],"label_agreement":null},{"id":"W2044936152","doi":"10.1145/2094114.2094118","title":"Parallel data processing with MapReduce","year":2012,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":555,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Abstraction; Data science; Big data; Volume (thermodynamics); Data processing; Simple (philosophy); Node (physics); Parallel processing; Database; Parallel computing; Data mining","score_opus":0.05152052286016848,"score_gpt":0.2733963681575956,"score_spread":0.22187584529742713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044936152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27888808,0.0009860436,0.7055041,0.0040827096,0.00081287214,0.0003006311,0.0000014717343,0.00068524934,0.008738832],"genre_scores_gemma":[0.74946284,0.0000038976777,0.24857785,0.00031072888,0.00036433266,0.0000074930513,0.000003848704,0.000013956399,0.0012550728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986069,0.000046936904,0.00015816194,0.00045520012,0.00026756834,0.00046518742],"domain_scores_gemma":[0.9972955,0.000069891365,0.00009860076,0.0023759203,0.000030227233,0.00012983286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000403816,0.00014832016,0.00013794638,0.000061368846,0.00017913675,0.00016481652,0.003304876,0.000036949757,0.000007931911],"category_scores_gemma":[0.000051533287,0.000107998436,0.000022029993,0.0003200393,0.00003425208,0.00019192565,0.002609532,0.00014006965,0.000068894304],"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":[0.000011298843,0.00014464786,0.0073213624,0.000038565548,0.000031291926,0.00000961901,0.0008456981,0.0005030078,0.000029808283,0.00096494483,0.009056501,0.9810433],"study_design_scores_gemma":[0.0013558621,0.00032461563,0.019835014,0.00029809427,0.00007284473,0.00015360363,0.00035230184,0.56608033,0.00019825659,0.0021747497,0.40785277,0.0013015474],"about_ca_topic_score_codex":0.000040181378,"about_ca_topic_score_gemma":0.0000054164625,"teacher_disagreement_score":0.9797417,"about_ca_system_score_codex":0.000022031394,"about_ca_system_score_gemma":0.000034731205,"threshold_uncertainty_score":0.61413366},"labels":[],"label_agreement":null},{"id":"W2046769817","doi":"10.1145/1147376.1147391","title":"Consistent query answering in databases","year":2006,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Database; Set (abstract data type); Query optimization; Query language; View; Sargable; Data integrity; Information retrieval; Distributed database; Web search query; Database design; Programming language; Search engine","score_opus":0.02901131692479943,"score_gpt":0.2536003828049169,"score_spread":0.22458906588011748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046769817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7790526,0.0017216785,0.15680657,0.0009188441,0.0022965798,0.00034673532,0.0000069676603,0.00052845664,0.05832152],"genre_scores_gemma":[0.9621798,0.000043253116,0.036395397,0.00014907894,0.00018143245,0.000017764489,0.000007820392,0.000009839302,0.0010156259],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988182,0.00005718988,0.00024266895,0.00041236417,0.00013716244,0.00033238117],"domain_scores_gemma":[0.99872136,0.00023645346,0.00006797305,0.00088045397,0.000037839898,0.000055938763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022528188,0.00013854401,0.00018486966,0.00011643701,0.000070757254,0.000079913705,0.00085366453,0.00004252582,0.000027398319],"category_scores_gemma":[0.00018930084,0.00012327003,0.00006114512,0.00030630882,0.00003950408,0.00039201014,0.0005188677,0.0001275874,0.00009381381],"study_design_candidate":"observational","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":[0.000031381205,0.0006769823,0.42508617,0.000092952796,0.000032715772,0.00053590036,0.00079332193,0.00019447808,0.0052652606,0.19599418,0.027927138,0.34336954],"study_design_scores_gemma":[0.0039649666,0.00053766917,0.36889312,0.00054652157,0.000039531715,0.00027097602,0.00026227857,0.0528937,0.019789511,0.07754246,0.4724321,0.0028271817],"about_ca_topic_score_codex":0.0013344428,"about_ca_topic_score_gemma":0.0021626814,"teacher_disagreement_score":0.44450495,"about_ca_system_score_codex":0.000054867527,"about_ca_system_score_gemma":0.00006349735,"threshold_uncertainty_score":0.5026806},"labels":[],"label_agreement":null},{"id":"W2064853889","doi":"10.1145/335191.335372","title":"Mining frequent patterns without candidate generation","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6360,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Scalability; Set (abstract data type); Tree (set theory); GSP Algorithm; Trie; Apriori algorithm; Association rule learning; Database transaction; Data structure; Database; Mathematics","score_opus":0.02961243143666664,"score_gpt":0.2688342363591712,"score_spread":0.23922180492250456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064853889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6896045,0.000032956486,0.30711597,0.0013411596,0.0002875429,0.0001334093,0.000022108952,0.00018356844,0.0012787537],"genre_scores_gemma":[0.61931324,0.00010506283,0.37640244,0.00069368235,0.00044217455,0.00009794698,0.000100548634,0.000017819668,0.0028270532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989803,0.000030291929,0.00019902976,0.00040919226,0.00015403325,0.00022714857],"domain_scores_gemma":[0.9987328,0.000033455995,0.00005686031,0.001060004,0.00002970633,0.00008713994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013474518,0.00011607864,0.00011255265,0.00004543518,0.00017097693,0.00020534584,0.0009652141,0.00004245195,0.00023793364],"category_scores_gemma":[0.000019658053,0.00010761141,0.000034411893,0.00017630044,0.0000151309405,0.0004159127,0.00013660324,0.00007983806,0.00018090845],"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":[9.213145e-7,0.00002687723,0.0035855346,0.0000020625841,0.000008742509,0.0000038066444,0.00028930217,0.000028365346,0.00074799557,0.00037522844,0.0048564244,0.99007475],"study_design_scores_gemma":[0.0008090095,0.00023111899,0.011326788,0.000070521855,0.00002738519,0.000061190796,0.00005418539,0.75206536,0.00656089,0.0016767756,0.2262554,0.0008614005],"about_ca_topic_score_codex":0.0005004618,"about_ca_topic_score_gemma":0.00019154405,"teacher_disagreement_score":0.98921335,"about_ca_system_score_codex":0.000029781557,"about_ca_system_score_gemma":0.00003698879,"threshold_uncertainty_score":0.4388266},"labels":[],"label_agreement":null},{"id":"W2066407644","doi":"10.1145/1041410.1041416","title":"Kanata","year":2004,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Metadata; Focus (optics); World Wide Web; Database; Software engineering","score_opus":0.02648632253714379,"score_gpt":0.25709268722599943,"score_spread":0.23060636468885565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066407644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28333813,0.00045635938,0.6836505,0.01568586,0.0022849075,0.00016598162,8.6839947e-7,0.00079830503,0.013619129],"genre_scores_gemma":[0.8234584,0.000034857014,0.17539735,0.0007209857,0.00008654345,0.000006017621,6.3104096e-7,0.0000051451416,0.00029009755],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99924356,0.000014424201,0.00011822255,0.00026964548,0.0001311171,0.00022300803],"domain_scores_gemma":[0.9987579,0.00008386968,0.00003648735,0.0010442719,0.000026659181,0.000050801893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000101132384,0.00008541979,0.00010921515,0.00005325372,0.000067962814,0.00007287011,0.0016562322,0.00004845936,0.000020185853],"category_scores_gemma":[0.00022691363,0.00007036249,0.00004713308,0.000195277,0.000029576862,0.0002983532,0.00044934903,0.00008092262,0.00026518968],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008149751,0.00011288876,0.006222796,0.00001556872,0.00003530404,0.00017103403,0.0007721638,0.00007775901,0.001192287,0.22385575,0.008499435,0.75903684],"study_design_scores_gemma":[0.0014737215,0.0003679643,0.032409575,0.00005628132,0.00001374527,0.000114852395,0.00013479599,0.0015049366,0.015280756,0.8800371,0.067916624,0.0006896029],"about_ca_topic_score_codex":0.00021374803,"about_ca_topic_score_gemma":0.00008871741,"teacher_disagreement_score":0.7583473,"about_ca_system_score_codex":0.000026491784,"about_ca_system_score_gemma":0.000053016618,"threshold_uncertainty_score":0.34085655},"labels":[],"label_agreement":null},{"id":"W2070556972","doi":"10.1145/2380776.2380784","title":"dbTrento","year":2012,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universidad de Zaragoza; University of Alberta","keywords":"Citation; Computer science; Library science; Database; World Wide Web","score_opus":0.03247796109390363,"score_gpt":0.278870893944344,"score_spread":0.24639293285044037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070556972","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":[0.032557297,0.0006155676,0.9596804,0.0014468569,0.001426168,0.000111143876,0.0000031520228,0.0015204841,0.00263893],"genre_scores_gemma":[0.5277145,0.000041403986,0.47145095,0.00020394017,0.00011051829,0.000019409943,0.0000026393327,0.000009039448,0.00044760207],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990487,0.000019346198,0.00012913048,0.0002453569,0.00014860506,0.000408875],"domain_scores_gemma":[0.9978678,0.0001201627,0.00006235661,0.0018474592,0.000022369846,0.00007981791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013146353,0.00011390893,0.000113935406,0.000089388646,0.00006987113,0.000040764713,0.0021956232,0.00006665328,0.000031921925],"category_scores_gemma":[0.0004337749,0.00010005806,0.000036752008,0.0003239031,0.000044538105,0.0014925397,0.001495388,0.00013543582,0.0004585843],"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":[0.0000019352458,0.00005243778,0.0066821836,0.000004127714,0.0000081654225,0.000005910725,0.00016021018,0.0000020797254,0.0011553337,0.0539113,0.013431847,0.92458445],"study_design_scores_gemma":[0.0004480944,0.00017349339,0.007207872,0.000023720691,0.000010352983,0.00006237875,0.00011594495,0.0013346218,0.023461582,0.14047252,0.82588947,0.000799939],"about_ca_topic_score_codex":0.000014811184,"about_ca_topic_score_gemma":0.000005737323,"teacher_disagreement_score":0.92378455,"about_ca_system_score_codex":0.000046002133,"about_ca_system_score_gemma":0.000012019312,"threshold_uncertainty_score":0.58943266},"labels":[],"label_agreement":null},{"id":"W2078181649","doi":"10.1145/507338.507366","title":"Report on the 18 <sup>th</sup> British National Conference on Databases (BNCOD)","year":2002,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Terabyte; Library science; Session (web analytics); Presentation (obstetrics); Database; Service (business); Computer science; World Wide Web; Medicine","score_opus":0.14909883946530322,"score_gpt":0.32737886912988584,"score_spread":0.17828002966458262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078181649","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13892967,0.00007925396,0.00006993894,0.0129625015,0.00079430215,0.00062881183,0.00008607267,0.00019962741,0.8462498],"genre_scores_gemma":[0.9832311,0.00032809755,0.00021056957,0.0013356573,0.00046007833,0.00010063171,0.000025182715,0.000009794205,0.014298833],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99767137,0.00017125098,0.0004287982,0.00028321188,0.0011118087,0.00033353767],"domain_scores_gemma":[0.9978414,0.00087196456,0.0002543063,0.00049160654,0.00046497694,0.00007570488],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012745571,0.00013705035,0.00018487927,0.00010140986,0.001230243,0.00020423632,0.00056087924,0.000070868584,0.003098196],"category_scores_gemma":[0.0039751963,0.00011715863,0.00009357412,0.0004066325,0.00032457546,0.0003596537,0.00012378467,0.00020803283,0.00068234326],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000155324,0.00016082815,0.022073068,0.000018675177,0.000115610936,0.00007401283,0.010242337,0.000051956387,0.0000029844102,0.15399309,0.7840679,0.029183986],"study_design_scores_gemma":[0.0003230672,0.000101091915,0.011697102,0.00020003661,0.000014308091,0.00005283834,0.010324831,0.00056304294,0.000009917615,0.0076839835,0.96865034,0.00037946235],"about_ca_topic_score_codex":0.0049263765,"about_ca_topic_score_gemma":0.0040644747,"teacher_disagreement_score":0.8443015,"about_ca_system_score_codex":0.00007852506,"about_ca_system_score_gemma":0.00007841594,"threshold_uncertainty_score":0.9978131},"labels":[],"label_agreement":null},{"id":"W2079337221","doi":"10.1145/603867.603886","title":"Career-enhancing services at SIGMOD online","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Database; Architecture","score_opus":0.15690084962122752,"score_gpt":0.37431087168082067,"score_spread":0.21741002205959314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079337221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798462,0.00016259974,0.005944975,0.0027051647,0.0034427107,0.00020938444,0.0000429699,0.00021748003,0.0074285255],"genre_scores_gemma":[0.95187265,0.000041221025,0.007800606,0.0011999424,0.0005426935,0.0000082440265,0.00008867124,0.000024649193,0.038421344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953741,0.00016457688,0.00084571994,0.001338402,0.0016984501,0.00057875767],"domain_scores_gemma":[0.9943148,0.0013906151,0.00032077677,0.003455217,0.00029464552,0.00022394885],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0031894245,0.00024225951,0.00036176134,0.00040124013,0.00047380177,0.0005949261,0.0035035345,0.00008496513,0.0017876705],"category_scores_gemma":[0.0021079287,0.00018592636,0.00016595103,0.0015343435,0.00007094828,0.00048729143,0.0029936896,0.00016624312,0.0023331249],"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":[0.00007695945,0.00018587279,0.057487905,0.0000184547,0.000038304686,0.00009251794,0.00095604354,0.00057609,0.0015333659,0.00011167158,0.10448315,0.83443964],"study_design_scores_gemma":[0.0005650249,0.00012208092,0.024818178,0.000069921276,0.0000297054,0.00003053709,0.00222739,0.020817632,0.00047758457,0.011951151,0.9384108,0.00047997566],"about_ca_topic_score_codex":0.0005964625,"about_ca_topic_score_gemma":0.007496543,"teacher_disagreement_score":0.8339597,"about_ca_system_score_codex":0.000109248955,"about_ca_system_score_gemma":0.000038259706,"threshold_uncertainty_score":0.9991248},"labels":[],"label_agreement":null},{"id":"W2083283415","doi":"10.1145/2694413.2694425","title":"Report on the First International Workshop on Exploratory Search in Databases and the Web (ExploreDB 2014)","year":2014,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management 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 British Columbia","funders":"","keywords":"Computer science; Database; World Wide Web; Information retrieval","score_opus":0.0560095100511173,"score_gpt":0.2822348339987544,"score_spread":0.22622532394763706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083283415","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38329232,0.0003046912,0.15598188,0.41234556,0.009444051,0.0022549187,0.000050104576,0.00052571937,0.035800762],"genre_scores_gemma":[0.97966295,0.0011950673,0.007211869,0.007940677,0.0009294991,0.00025762353,0.00008346357,0.000033143344,0.0026857255],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986126,0.00014582169,0.000212692,0.0004454289,0.0003836838,0.00019977633],"domain_scores_gemma":[0.99697125,0.0012977133,0.00007792749,0.0015860461,0.000031105494,0.00003594085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017390589,0.00012628344,0.00012062626,0.00012362421,0.00015652923,0.00028024477,0.0019693163,0.000021570739,0.00003665454],"category_scores_gemma":[0.00066054275,0.00006990211,0.000034150355,0.00021184783,0.00011249287,0.0006259451,0.0013841422,0.00024255841,0.000115869196],"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":[0.00019037859,0.00022962187,0.010639605,0.000015584988,0.0000793345,0.00016255374,0.00094886,0.00014735003,0.000011952353,0.20567569,0.283235,0.49866405],"study_design_scores_gemma":[0.0018403925,0.000120879326,0.006468059,0.00020757804,0.000008950099,0.000014940207,0.00032853993,0.15495947,0.00015248818,0.008227973,0.82729846,0.0003722734],"about_ca_topic_score_codex":0.00004719088,"about_ca_topic_score_gemma":0.00015288465,"teacher_disagreement_score":0.59637064,"about_ca_system_score_codex":0.000022449272,"about_ca_system_score_gemma":0.00001911973,"threshold_uncertainty_score":0.36595124},"labels":[],"label_agreement":null},{"id":"W2094817912","doi":"10.1145/1084805.1084825","title":"Exchange, integration, and consistency of data","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"IBM (Canada); University of Victoria; York University; Carleton University","funders":"","keywords":"Computer science; IBM; Data exchange; Consistency (knowledge bases); Data consistency; Data integration; Database; Operating system; Programming language","score_opus":0.057434164822293146,"score_gpt":0.30152373536708393,"score_spread":0.2440895705447908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094817912","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":[0.008073254,0.0013278953,0.9874422,0.0013482401,0.00022096888,0.00011967687,0.000059470654,0.00006078065,0.0013474966],"genre_scores_gemma":[0.1315757,0.00033542424,0.8671762,0.00017864349,0.00013747164,0.0000075085654,0.000037454673,0.000006287975,0.00054530357],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99926454,0.00002889974,0.00021150727,0.0002898276,0.000098889774,0.000106321655],"domain_scores_gemma":[0.99809265,0.000112985326,0.00009806172,0.001591723,0.000062228624,0.000042322194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019482116,0.00007643927,0.00013777407,0.000046518107,0.0000520489,0.000016793667,0.0006850846,0.000026757136,0.000019820864],"category_scores_gemma":[0.00020855718,0.00006215675,0.000012727842,0.00012670056,0.000056834946,0.0013137381,0.00090659055,0.000051009723,0.000009350702],"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":[0.0000032510197,0.000017945695,0.00038454626,0.000021585962,0.0000073281644,0.0000016062552,0.00029107372,7.077479e-7,0.00084379385,0.044735257,0.0052067344,0.94848615],"study_design_scores_gemma":[0.00042329784,0.00012642954,0.0011647909,0.00010993752,0.000009941606,0.00004418799,0.00016531235,0.013547566,0.0034913563,0.0038464495,0.97678936,0.0002813477],"about_ca_topic_score_codex":0.00009642479,"about_ca_topic_score_gemma":0.00041936096,"teacher_disagreement_score":0.97158265,"about_ca_system_score_codex":0.000006927945,"about_ca_system_score_gemma":0.000030153053,"threshold_uncertainty_score":0.25346786},"labels":[],"label_agreement":null},{"id":"W2098416578","doi":"10.1145/335191.335419","title":"Efficient and extensible algorithms for multi query optimization","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":409,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Query optimization; Heuristics; Benchmark (surveying); Overhead (engineering); Greedy algorithm; Heuristic; Algorithm; Data mining; Artificial intelligence","score_opus":0.04290867931345283,"score_gpt":0.2807725920124819,"score_spread":0.23786391269902907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098416578","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":[0.005635933,0.00012403553,0.99223095,0.00060048973,0.00039472536,0.0003865989,0.00000934215,0.00017184236,0.00044606614],"genre_scores_gemma":[0.0034817134,0.00014085535,0.99237776,0.00032895614,0.000111507215,0.000048655354,0.000024832274,0.000014284878,0.0034714506],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989354,0.000022953245,0.00017895068,0.00046491512,0.00013308275,0.0002647201],"domain_scores_gemma":[0.99908435,0.00008123619,0.000047967085,0.0006637301,0.00004995728,0.0000727315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022950128,0.00013147427,0.00013648764,0.00008989274,0.00015228581,0.00021201979,0.00067268,0.00004419554,0.000058516864],"category_scores_gemma":[0.00005787947,0.00012077585,0.000042884094,0.00023136864,0.000029447563,0.0003262915,0.00026213398,0.000053674725,0.000031219453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008155907,0.00007509506,0.000051519222,0.000013215318,0.000012906102,0.000004346927,0.00008119923,0.015832525,0.000016696551,0.00067434326,0.0019857374,0.98124427],"study_design_scores_gemma":[0.0005906847,0.00008373343,0.00023803237,0.00001304947,0.000008778405,0.0000035593707,0.0000106881835,0.9842018,0.00007027005,0.00041765004,0.014185641,0.00017611048],"about_ca_topic_score_codex":0.000037220212,"about_ca_topic_score_gemma":0.0000043044242,"teacher_disagreement_score":0.98106813,"about_ca_system_score_codex":0.000015553167,"about_ca_system_score_gemma":0.000014301328,"threshold_uncertainty_score":0.4925096},"labels":[],"label_agreement":null},{"id":"W2099464320","doi":"10.1145/1107499.1107507","title":"An apples-to-apples comparison of two database journals","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Database; Information retrieval; World Wide Web","score_opus":0.06868933506628278,"score_gpt":0.39365361095319384,"score_spread":0.32496427588691107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099464320","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":[0.11838296,0.00014486202,0.8786974,0.0019670487,0.00014167503,0.00019307584,0.00010885849,0.00011294782,0.000251169],"genre_scores_gemma":[0.36692134,0.000018619663,0.63250214,0.00020632123,0.00021765105,0.000028094051,0.000036114525,0.0000094174075,0.00006034442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854267,0.000048458354,0.00042831193,0.00043159473,0.00028019585,0.00026877184],"domain_scores_gemma":[0.99739283,0.00015473718,0.00018895144,0.0019453746,0.000092387876,0.00022574094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042162059,0.00013819474,0.0002557992,0.00014250986,0.0001372546,0.00015212657,0.002636224,0.000034620058,0.00006769428],"category_scores_gemma":[0.00008013789,0.00012810246,0.000049391914,0.0004885262,0.000034356766,0.00073726074,0.0005249441,0.00015559816,0.00013797829],"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":[0.0000030474573,0.0003000172,0.0038122218,0.0000059683352,0.000013748337,0.0000011661521,0.0004431227,0.00035437892,0.023466172,0.0043025557,0.019812029,0.94748557],"study_design_scores_gemma":[0.0012907767,0.0005956946,0.011781091,0.00017732683,0.000049674032,0.000042757787,0.00036045405,0.53893304,0.07373147,0.002934264,0.36907297,0.0010305021],"about_ca_topic_score_codex":0.00016541446,"about_ca_topic_score_gemma":0.0001346712,"teacher_disagreement_score":0.94645506,"about_ca_system_score_codex":0.000021947257,"about_ca_system_score_gemma":0.000053388292,"threshold_uncertainty_score":0.52238667},"labels":[],"label_agreement":null},{"id":"W2116493296","doi":"10.1145/335191.335409","title":"XTRACT","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; XML validation; Document Structure Description; Document type definition; RELAX NG; XML Schema Editor; Well-formed document; XML Schema (W3C); Streaming XML; XML; Information retrieval; Programming language; Simple API for XML; Efficient XML Interchange; XML database; XML Signature; World Wide Web","score_opus":0.010340759165822527,"score_gpt":0.24748946711200087,"score_spread":0.23714870794617834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116493296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5872807,0.00036488366,0.22584279,0.014160382,0.0022065013,0.00026316274,0.000002473473,0.0018479119,0.1680312],"genre_scores_gemma":[0.726635,0.00008602018,0.23174208,0.0012611422,0.0005659762,0.0000127019675,0.0000031984819,0.000020591058,0.03967332],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999175,0.000049873495,0.000121479134,0.00028335128,0.00014525451,0.00022505618],"domain_scores_gemma":[0.99897176,0.00010279351,0.000029265051,0.0008043212,0.0000151350305,0.00007670466],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015247548,0.00009424842,0.00010075266,0.00004037277,0.00009885225,0.00009605048,0.0011493164,0.000041270807,0.0010449879],"category_scores_gemma":[0.00006729605,0.00008052059,0.00005641572,0.00020579276,0.000014439763,0.00023458673,0.0001086314,0.00019028303,0.0012209893],"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":[0.0000018303455,0.00002219204,0.00081648683,0.0000016313224,0.0000042080105,0.000013720786,0.00009363781,0.00005610891,0.00004851586,0.00053781085,0.0031812005,0.9952226],"study_design_scores_gemma":[0.00040376722,0.00021909576,0.011263884,0.000020306117,0.000004797553,0.000061003546,0.0000052174387,0.1182701,0.00036189397,0.015029644,0.8539644,0.00039589088],"about_ca_topic_score_codex":0.00012403574,"about_ca_topic_score_gemma":0.0000045363704,"teacher_disagreement_score":0.9948268,"about_ca_system_score_codex":0.000010090779,"about_ca_system_score_gemma":0.000020570396,"threshold_uncertainty_score":0.9998682},"labels":[],"label_agreement":null},{"id":"W2123331342","doi":"10.1145/335191.336589","title":"DISIMA","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"","field":"","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; Database","score_opus":0.01982543029966458,"score_gpt":0.2650928007484224,"score_spread":0.24526737044875782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123331342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9095379,0.00009000667,0.000015485493,0.0004236864,0.00020580649,0.00015300952,0.000026626787,0.0004349667,0.0891125],"genre_scores_gemma":[0.9701171,0.00004316908,0.0035935089,0.00029941995,0.0003272935,0.00002835275,0.000022150356,0.000119639626,0.025449395],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987794,0.00006140978,0.00020283867,0.0003385115,0.00022322948,0.0003945949],"domain_scores_gemma":[0.99856347,0.000121896715,0.000042169326,0.0011153367,0.00002882734,0.00012827679],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015507282,0.00016416254,0.00017663918,0.00006754362,0.000089410525,0.000041141957,0.000619781,0.00007385339,0.022495616],"category_scores_gemma":[0.00019809756,0.00015031894,0.000093119845,0.000331133,0.00005981172,0.00021658649,0.00007878291,0.00015612412,0.08877561],"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":[0.00013978072,0.00011870631,0.01294884,0.0000054162283,0.000032868174,0.000030508563,0.00015919183,0.000018793686,0.004186702,0.00012752891,0.1278132,0.85441846],"study_design_scores_gemma":[0.00071108365,0.00012796621,0.020559484,0.000019995385,0.00002757189,0.000020487723,0.000023430517,0.00034501648,0.0017964334,0.008491694,0.9674779,0.00039889716],"about_ca_topic_score_codex":0.00016009768,"about_ca_topic_score_gemma":0.00009455004,"teacher_disagreement_score":0.8540196,"about_ca_system_score_codex":0.000062506595,"about_ca_system_score_gemma":0.000025742285,"threshold_uncertainty_score":0.97839797},"labels":[],"label_agreement":null},{"id":"W2126321570","doi":"10.1145/335191.335393","title":"How to roll a join","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":91,"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; Materialized view; Asynchronous communication; Process (computing); Join (topology); Point (geometry); Refresh rate; Distributed computing; Database; Operating system; Computer hardware; Computer network; View","score_opus":0.016190014463895588,"score_gpt":0.23275630997701277,"score_spread":0.21656629551311718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126321570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31436136,0.00035950297,0.6019365,0.03938935,0.002156476,0.00085252564,0.0000388073,0.0008793681,0.040026076],"genre_scores_gemma":[0.9336844,0.000017048616,0.03818214,0.0013565893,0.00026709225,0.00005324936,0.0000035671817,0.000014003399,0.0264219],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877745,0.000042833984,0.00017399098,0.00043760234,0.00022249747,0.00034564678],"domain_scores_gemma":[0.9984578,0.0000487023,0.00004015068,0.0012281972,0.000049235477,0.00017591417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015164563,0.00014005009,0.00019738289,0.000052108313,0.00009039453,0.0003618472,0.0015186999,0.000062545514,0.00010092689],"category_scores_gemma":[0.00007471314,0.00012301258,0.000075667216,0.00047052038,0.000011734475,0.00041839576,0.00016190701,0.000100138204,0.00069387315],"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":[0.000010002804,0.00003944375,0.00036527784,0.000006566218,0.0000108402255,0.000028058987,0.00024312585,0.000047033434,0.00039569684,0.0018340347,0.051855437,0.9451645],"study_design_scores_gemma":[0.00032053847,0.00014672552,0.0017598136,0.00003440782,0.0000024131368,0.000021205964,0.000014064563,0.0052855937,0.0004175111,0.0025203023,0.98920584,0.00027157713],"about_ca_topic_score_codex":0.00010315411,"about_ca_topic_score_gemma":0.000046846548,"teacher_disagreement_score":0.9448929,"about_ca_system_score_codex":0.000029756065,"about_ca_system_score_gemma":0.000030189822,"threshold_uncertainty_score":0.8918567},"labels":[],"label_agreement":null},{"id":"W2128114397","doi":"10.1145/1228268.1228284","title":"Normalization theory for XML","year":2006,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Computer science; Relational database; Normalization (sociology); XML; XML database; Database; Relational model; Information retrieval; Simple (philosophy); World Wide Web","score_opus":0.012011270581554807,"score_gpt":0.24309843180001883,"score_spread":0.23108716121846404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128114397","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":[0.00341222,0.00011611368,0.9937985,0.00019467773,0.00057653146,0.00019509069,0.00001409419,0.0001474706,0.0015453184],"genre_scores_gemma":[0.1368319,0.000016733338,0.857011,0.000327451,0.0006089603,0.00013804405,0.0000888606,0.000022813292,0.0049542324],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992929,0.000033206208,0.00017182546,0.0002330834,0.00008949971,0.0001794542],"domain_scores_gemma":[0.99902016,0.00017236572,0.000079528276,0.0006371126,0.00006472581,0.000026119913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021089232,0.00008611705,0.000101232,0.00004461816,0.0001201793,0.000032323263,0.00037845722,0.00003434943,0.000010717883],"category_scores_gemma":[0.00011584834,0.00007365647,0.00004466417,0.00014105496,0.000019740797,0.0006162221,0.00015131898,0.000032160722,0.000021701186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009587953,0.000016485988,0.00036680623,0.0000164859,0.0000037169045,0.0000015228359,0.000045670346,0.00010860606,0.00070984743,0.92000973,0.004751886,0.073959656],"study_design_scores_gemma":[0.00042288334,0.00010532923,0.0006753214,0.00002687268,0.000005543459,0.00001052571,0.000021855785,0.010073201,0.0051466166,0.22083902,0.7623949,0.0002779247],"about_ca_topic_score_codex":0.000069193695,"about_ca_topic_score_gemma":0.00006587836,"teacher_disagreement_score":0.757643,"about_ca_system_score_codex":0.000016662387,"about_ca_system_score_gemma":0.000022256974,"threshold_uncertainty_score":0.30036238},"labels":[],"label_agreement":null},{"id":"W2132851185","doi":"10.1145/776985.776986","title":"Issues in data stream management","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":916,"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; Timestamp; Data stream mining; Database; Query language; Streaming data; Data stream; Data management; Data science; Data mining; Computer security","score_opus":0.04335612978330646,"score_gpt":0.30557491160712486,"score_spread":0.2622187818238184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132851185","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":[0.010826367,0.0011570955,0.9682918,0.0012233502,0.0013494481,0.00044437396,0.00003905268,0.00023012246,0.016438361],"genre_scores_gemma":[0.040006507,0.00049059774,0.95476747,0.00018900109,0.00006723812,0.00003094146,0.000043363863,0.000014228779,0.004390629],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883723,0.0000667561,0.00020721529,0.00049672544,0.00015259275,0.00023946598],"domain_scores_gemma":[0.9968245,0.000058572412,0.000053050982,0.003002434,0.0000148335985,0.000046619065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029699376,0.00011184419,0.00014477737,0.00008254938,0.000048741927,0.000038516846,0.0013818573,0.0000270342,0.000031556316],"category_scores_gemma":[0.00012094316,0.00009910932,0.000016022477,0.000291468,0.000018926361,0.00095891656,0.001069485,0.00007531655,0.00008110548],"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":[0.0000058403807,0.00011845783,0.005661293,0.0000608452,0.000027143788,0.00018202043,0.0002537628,0.000033822802,0.00007387413,0.5717079,0.021108668,0.40076634],"study_design_scores_gemma":[0.00025624197,0.000026241552,0.00071736594,0.00004839499,0.000002333813,0.000008071451,0.00013128911,0.0010245821,0.00030549522,0.007734839,0.98955804,0.00018710221],"about_ca_topic_score_codex":0.00016376557,"about_ca_topic_score_gemma":0.0003568002,"teacher_disagreement_score":0.96844935,"about_ca_system_score_codex":0.000021743464,"about_ca_system_score_gemma":0.00001634025,"threshold_uncertainty_score":0.4041561},"labels":[],"label_agreement":null},{"id":"W2139422684","doi":"10.1145/335191.336572","title":"Towards data mining benchmarking","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Benchmarking; Data stream mining; Database transaction; Association rule learning; Apriori algorithm; Set (abstract data type); GSP Algorithm; Database; Relational database","score_opus":0.05942132737752803,"score_gpt":0.2999806763587709,"score_spread":0.24055934898124287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139422684","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":[0.12581748,0.00037734292,0.8064063,0.008276653,0.0014482513,0.00041684706,0.00019450365,0.0010368844,0.056025755],"genre_scores_gemma":[0.02542416,0.00010801186,0.9722846,0.00044181422,0.00037773195,0.000021402731,0.00014146308,0.0000128495585,0.0011879791],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869657,0.000024990297,0.00020154372,0.0006202683,0.00018631175,0.00027032607],"domain_scores_gemma":[0.99633056,0.00011081171,0.000050524417,0.003395619,0.000023200999,0.00008928599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002983463,0.0001156648,0.0001246802,0.00004763048,0.00017945927,0.00022622042,0.004721919,0.00004527917,0.0003829614],"category_scores_gemma":[0.00007526581,0.00010989355,0.000026938056,0.00037813734,0.000027578484,0.0008260771,0.00126645,0.00010460275,0.00020959118],"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":[7.7045013e-7,0.000020914445,0.00013698003,0.0000018373041,0.0000069688267,0.000004271962,0.00013061162,0.000003140197,0.00002846158,0.0004282969,0.01703158,0.98220617],"study_design_scores_gemma":[0.0001946442,0.00006460295,0.0023621083,0.000034499546,0.000010050672,0.000027285672,0.000025004632,0.36935508,0.00011190287,0.0022323502,0.6252734,0.0003090695],"about_ca_topic_score_codex":0.00017282034,"about_ca_topic_score_gemma":0.000021494448,"teacher_disagreement_score":0.9818971,"about_ca_system_score_codex":0.000015657452,"about_ca_system_score_gemma":0.000062531704,"threshold_uncertainty_score":0.8774579},"labels":[],"label_agreement":null},{"id":"W2144182447","doi":"10.1145/335191.335388","title":"LOF","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":5181,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Local outlier factor; Computer science; Object (grammar); Anomaly detection; Degree (music); Data mining; Property (philosophy); Binary number; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.012959734804963171,"score_gpt":0.24427321013530048,"score_spread":0.2313134753303373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144182447","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":[0.051220167,0.000041619143,0.8993725,0.0025405057,0.00011671523,0.00017801233,0.0000011654089,0.0010153602,0.045513913],"genre_scores_gemma":[0.7039994,0.00012917821,0.27095243,0.0009854356,0.00012937495,0.000096807,0.0000013275637,0.00001114469,0.023694886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994681,0.000011960719,0.000107241445,0.00021277429,0.00007423,0.00012572341],"domain_scores_gemma":[0.99906695,0.000028951557,0.00002400522,0.0008137341,0.000018985565,0.000047368685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000038045364,0.000060359966,0.00006145999,0.0000322863,0.00009083017,0.00004875777,0.0008472514,0.000038775674,0.0005769607],"category_scores_gemma":[0.000009114733,0.00005594824,0.0000438223,0.00024839863,0.00001657201,0.00017773302,0.00009139064,0.00006965944,0.0006258794],"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":[9.1335613e-7,0.0000172974,0.00010742597,7.3080275e-7,0.0000019325485,7.9034965e-7,0.000016281067,0.000002387615,0.00040851478,0.0052488013,0.00884214,0.9853528],"study_design_scores_gemma":[0.000095799005,0.00009326492,0.0015497927,0.0000046520486,0.000002373166,0.000017899063,0.0000036858446,0.0042837546,0.0070996243,0.056204032,0.93046886,0.00017627934],"about_ca_topic_score_codex":0.00004216504,"about_ca_topic_score_gemma":0.0000057202133,"teacher_disagreement_score":0.9851765,"about_ca_system_score_codex":0.000013217473,"about_ca_system_score_gemma":0.0000122415695,"threshold_uncertainty_score":0.8044622},"labels":[],"label_agreement":null},{"id":"W2161694107","doi":"10.1145/2034863.2034873","title":"Repeatability and workability evaluation of SIGMOD 2011","year":2011,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Repeatability; Executable; Computer science; Process (computing); Statistics; Operating system; Mathematics","score_opus":0.5113276891992731,"score_gpt":0.42903251205096915,"score_spread":0.08229517714830392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161694107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9848324,0.00011721587,0.0040142643,0.00018996703,0.0010465027,0.0003876138,0.000014273005,0.000040724302,0.009357054],"genre_scores_gemma":[0.9895754,0.0000052689265,0.009863071,0.00002702118,0.000036710022,0.000012416045,0.0000049979813,0.000005296418,0.00046984095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99548465,0.00067857205,0.0008279699,0.0010788783,0.0017083694,0.00022156615],"domain_scores_gemma":[0.99349713,0.0013556221,0.00036278542,0.0038950671,0.0007788648,0.00011050931],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02923631,0.00012868748,0.00027905646,0.00019841616,0.0001240732,0.00008665833,0.0012541636,0.00005997034,0.0025887205],"category_scores_gemma":[0.019059895,0.000096427204,0.00008954822,0.0005072486,0.00024730753,0.00036656516,0.0011075869,0.00009892801,0.00014193344],"study_design_candidate":"observational","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":[0.000045439196,0.00012448651,0.195572,0.0000062051536,0.000011017327,4.2268837e-7,0.00070732145,0.000010301699,0.000043409007,0.00018595716,0.00475834,0.7985351],"study_design_scores_gemma":[0.00038647227,0.00013091683,0.6933794,0.000016035356,0.00006608758,0.0000018433894,0.00072216446,0.013025329,0.00066701113,0.28759068,0.0038184584,0.00019559103],"about_ca_topic_score_codex":0.00053826085,"about_ca_topic_score_gemma":0.0002025817,"teacher_disagreement_score":0.7983395,"about_ca_system_score_codex":0.000040027466,"about_ca_system_score_gemma":0.00007111008,"threshold_uncertainty_score":0.9996055},"labels":[],"label_agreement":null},{"id":"W2162294668","doi":"10.1145/373626.373713","title":"The Clio project","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":343,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Set (abstract data type); Data integration; Transformation (genetics); Data science; Software engineering; Programming language; Database","score_opus":0.031767974344315664,"score_gpt":0.29049034626259007,"score_spread":0.2587223719182744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162294668","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":[0.012797477,0.000494583,0.9676254,0.0030371062,0.002014798,0.00037860297,0.00000427948,0.00033691828,0.013310831],"genre_scores_gemma":[0.20952213,0.004926079,0.73594445,0.0014835857,0.002118556,0.00045909517,0.000017429,0.00007811592,0.045450572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990768,0.00005677253,0.0001731607,0.0002655329,0.00015535812,0.00027240926],"domain_scores_gemma":[0.99825025,0.00025166228,0.00007288758,0.0013506599,0.000035552886,0.000039002603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025335918,0.000098316086,0.000096060394,0.000035034995,0.00032133175,0.000076261385,0.00096207234,0.00002914284,0.0000059288154],"category_scores_gemma":[0.00020131907,0.000059521542,0.000048633356,0.00032903053,0.00004450929,0.0005016279,0.00047343076,0.000099977085,0.000095271665],"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":[0.000011528297,0.000017060733,0.0017353448,0.0000043306604,0.000010511557,0.000016982282,0.00017438072,0.000003075662,0.00014450999,0.12671849,0.013716217,0.85744756],"study_design_scores_gemma":[0.000092519345,0.00005624884,0.00041522208,0.000009869996,0.0000011319486,0.000028360313,0.000037686244,0.000929342,0.000116995965,0.005422624,0.9927845,0.000105516534],"about_ca_topic_score_codex":0.00018199629,"about_ca_topic_score_gemma":0.00041771552,"teacher_disagreement_score":0.9790683,"about_ca_system_score_codex":0.000018978257,"about_ca_system_score_gemma":0.00005024514,"threshold_uncertainty_score":0.24714565},"labels":[],"label_agreement":null},{"id":"W2792572948","doi":"10.1145/3186549.3186559","title":"Data Quality","year":2018,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Scope (computer science); Quality (philosophy); Data quality; Empiricism; Data science; Action (physics); Data mining; Epistemology; Programming language; Engineering","score_opus":0.6848192121373361,"score_gpt":0.55904053398058,"score_spread":0.12577867815675614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792572948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4250788,0.00018925531,0.21887101,0.05202212,0.012401808,0.001081529,0.0025327324,0.00060209946,0.28722063],"genre_scores_gemma":[0.89865524,0.00005338884,0.045093898,0.0081806835,0.001891306,0.000015029494,0.00034858132,0.000027138585,0.045734715],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666893,0.00042643203,0.00067723804,0.00085369206,0.0011031732,0.00027053876],"domain_scores_gemma":[0.9894873,0.001685167,0.00024193196,0.008265403,0.00020206535,0.0001181657],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009842128,0.000111867506,0.00023540446,0.000115982395,0.00019032326,0.00032120335,0.0071133245,0.000054924927,0.0034401536],"category_scores_gemma":[0.019623693,0.000081814134,0.000049498925,0.000543984,0.00021269398,0.00094504183,0.0050032553,0.00009706799,0.008168026],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022609218,0.000039125796,0.0016710487,0.0000021133073,0.000011581835,0.0000017328605,0.00009111282,8.5897916e-8,0.000048970454,0.005743865,0.52502155,0.46734622],"study_design_scores_gemma":[0.00015041696,0.00006110441,0.008588974,0.0000038028631,0.000006493947,7.0167914e-7,0.00035230495,0.00020512336,0.000076564764,0.1165323,0.8738972,0.00012499624],"about_ca_topic_score_codex":0.00043266453,"about_ca_topic_score_gemma":0.0021389693,"teacher_disagreement_score":0.47357646,"about_ca_system_score_codex":0.000015726251,"about_ca_system_score_gemma":0.000040299135,"threshold_uncertainty_score":0.99825865},"labels":[],"label_agreement":null},{"id":"W2924482967","doi":"","title":"SIGMOD officers, committees, and awardees","year":2018,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"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; Operations research; Engineering","score_opus":0.1562836903849191,"score_gpt":0.39958671011275426,"score_spread":0.24330301972783516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924482967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9273738,0.00027150544,0.015610218,0.004985232,0.0053696726,0.0003318501,0.000035399567,0.00025101317,0.04577128],"genre_scores_gemma":[0.974619,0.000018814593,0.01071011,0.0006943772,0.00051347463,0.0000050738226,0.0000094871175,0.000014373792,0.013415329],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996916,0.00017583542,0.00052041176,0.0010170656,0.0009981222,0.00037254207],"domain_scores_gemma":[0.9953311,0.0014753669,0.00019289448,0.0025698303,0.00025949557,0.0001712966],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003692845,0.00017387349,0.00026862184,0.00030279954,0.00044488773,0.00072628,0.0020188405,0.00006444314,0.0011936805],"category_scores_gemma":[0.00490362,0.00012959527,0.00007393397,0.00081057963,0.00036282232,0.00032175877,0.0018601753,0.00012488209,0.0014540575],"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":[0.000021605272,0.000034513192,0.012695076,0.0000024411902,0.000014061905,0.0000044252683,0.00026555502,0.0000033074616,0.00008054069,0.00087816344,0.49210975,0.49389055],"study_design_scores_gemma":[0.00035027746,0.00018813912,0.022202179,0.000017476208,0.000014571173,0.000007080547,0.00063345226,0.0039315876,0.00017815715,0.021095363,0.9511402,0.00024150619],"about_ca_topic_score_codex":0.00018560275,"about_ca_topic_score_gemma":0.00023137341,"teacher_disagreement_score":0.49364904,"about_ca_system_score_codex":0.000022906093,"about_ca_system_score_gemma":0.000044570854,"threshold_uncertainty_score":0.9997194},"labels":[],"label_agreement":null},{"id":"W2999873292","doi":"10.1145/376284.375664","title":"Efficient computation of Iceberg cubes with complex measures","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Pruning; Computer science; Online analytical processing; Data cube; Computation; Scalability; Cube (algebra); Data mining; Measure (data warehouse); Tree (set theory); Theoretical computer science; Algorithm; Data warehouse; Database; Mathematics; Combinatorics","score_opus":0.042388281774761956,"score_gpt":0.2641887323800171,"score_spread":0.22180045060525516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999873292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14632902,0.000046097757,0.84922737,0.0006208377,0.00023022291,0.00018552954,0.0000027162205,0.00013362002,0.0032245656],"genre_scores_gemma":[0.88069475,0.000013631899,0.11892519,0.000106294254,0.000048182366,0.0000065444056,0.000013903996,0.000008036623,0.00018344789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886733,0.00004530096,0.0002047246,0.00031303382,0.00036123334,0.00020836957],"domain_scores_gemma":[0.99901927,0.00007539913,0.00012103627,0.00062967004,0.00010298837,0.00005163126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021413808,0.00012315507,0.00016937015,0.00012768479,0.000079031466,0.00008756069,0.0010387845,0.000023248569,0.000016574724],"category_scores_gemma":[0.00003448273,0.00009745091,0.000038744784,0.00049217755,0.000052423497,0.00021173363,0.00036214438,0.000060079892,0.0000323939],"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":[0.00004408594,0.00027185923,0.006613934,0.00003496333,0.00007640338,0.00003518337,0.00035531996,0.013352688,0.00058273115,0.0053323107,0.0043590437,0.96894145],"study_design_scores_gemma":[0.0010271006,0.00043791326,0.026779369,0.0000736062,0.00002744445,0.000019169733,0.00008448802,0.9493029,0.0003816665,0.0025133304,0.018981177,0.0003718173],"about_ca_topic_score_codex":0.00011273376,"about_ca_topic_score_gemma":0.000045934685,"teacher_disagreement_score":0.96856964,"about_ca_system_score_codex":0.000017209912,"about_ca_system_score_gemma":0.000019500594,"threshold_uncertainty_score":0.3973933},"labels":[],"label_agreement":null},{"id":"W3041888157","doi":"10.1145/376284.375685","title":"Independence is good","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Curse of dimensionality; Data mining; Histogram; Independence (probability theory); Exploit; Set (abstract data type); Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Image (mathematics)","score_opus":0.025710358788209507,"score_gpt":0.2582570222251933,"score_spread":0.2325466634369838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041888157","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":[0.03927759,0.00016254377,0.8789832,0.010415839,0.0023321165,0.00032401516,0.0000072588637,0.00066958455,0.067827865],"genre_scores_gemma":[0.62724566,0.0006942636,0.31278157,0.0068317824,0.00073053327,0.000051287152,0.000019547682,0.00003992358,0.051605456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987487,0.000023901017,0.00015765418,0.00044346822,0.00031971987,0.00030652428],"domain_scores_gemma":[0.9983273,0.000055938814,0.000061648105,0.0014374733,0.000037987204,0.00007962962],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021748793,0.00012336575,0.0001141766,0.000094478666,0.0000953697,0.00023716458,0.0027731638,0.000052364547,0.00022432729],"category_scores_gemma":[0.000056029974,0.0001131271,0.000050727875,0.00046785458,0.00002013618,0.0012258075,0.001236009,0.0001371754,0.0008396296],"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":[0.0000026468872,0.000050084345,0.010000815,0.000004564468,0.000017295928,0.00007731074,0.000120125216,0.0000012242851,0.00006624984,0.010032169,0.025879033,0.95374846],"study_design_scores_gemma":[0.00068221305,0.00021323768,0.012356679,0.000032198648,0.00001441915,0.000045168086,0.000044688906,0.025244653,0.00080432184,0.06978617,0.8901344,0.00064184924],"about_ca_topic_score_codex":0.00008185939,"about_ca_topic_score_gemma":0.000019825247,"teacher_disagreement_score":0.95310664,"about_ca_system_score_codex":0.000018016617,"about_ca_system_score_gemma":0.000020892872,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W3111145856","doi":"10.1145/3444831.3444841","title":"Advice from SIGMOD/PODS 2020","year":2020,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Conferences and Exhibitions Management","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Notice; Computer science; Advice (programming); Component (thermodynamics); World Wide Web; Political science; Programming language","score_opus":0.046734223800662306,"score_gpt":0.3025489882476701,"score_spread":0.2558147644470078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111145856","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3429245,0.00050916284,0.003934124,0.2130836,0.0021526364,0.00087411475,0.00007873692,0.0010370249,0.4354061],"genre_scores_gemma":[0.9885836,0.00043083527,0.003320603,0.0034412383,0.0015622826,0.000027386297,0.000028919767,0.000014637563,0.0025904435],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986671,0.00012245071,0.00020452362,0.00038023698,0.0003187809,0.0003068835],"domain_scores_gemma":[0.99908304,0.00020944602,0.00007817905,0.00032972655,0.00006376854,0.00023584887],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017744067,0.000121791025,0.00017531597,0.000026877093,0.00035819647,0.00014350109,0.0007104331,0.00008089108,0.0057104435],"category_scores_gemma":[0.0005039172,0.00012262646,0.00009753609,0.00039483444,0.00009311691,0.00021806551,0.00027498146,0.0001488028,0.00078946305],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083855775,0.00012482042,0.011597552,0.000023996872,0.00012473107,0.000050792503,0.02387894,0.000022429931,0.00032938688,0.025806352,0.35645,0.58150715],"study_design_scores_gemma":[0.00023754592,0.000080567945,0.0016144916,0.000016428357,0.000033868822,6.3858515e-8,0.0056681274,0.00084664096,0.00002660419,0.012265263,0.97898483,0.00022555042],"about_ca_topic_score_codex":0.01410978,"about_ca_topic_score_gemma":0.008421801,"teacher_disagreement_score":0.64565915,"about_ca_system_score_codex":0.00004629073,"about_ca_system_score_gemma":0.00010214818,"threshold_uncertainty_score":0.99998856},"labels":[],"label_agreement":null},{"id":"W3111316923","doi":"10.1145/376284.375749","title":"Exploiting constraint-like data characterizations in query optimization","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); York University","funders":"","keywords":"Computer science; Query optimization; Constraint (computer-aided design); Data integrity; Binary constraint; Exploit; Constraint programming; USable; Data mining; Database; Constraint satisfaction; Constraint logic programming; Mathematical optimization; Probabilistic logic; Artificial intelligence","score_opus":0.0655448349157439,"score_gpt":0.28878375790549454,"score_spread":0.22323892298975065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111316923","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":[0.017285775,0.000049184542,0.9805029,0.0006111087,0.00057384523,0.0001606806,0.000042842927,0.0001573347,0.00061634433],"genre_scores_gemma":[0.14530635,0.0003780377,0.85252875,0.0005191451,0.00022734526,0.000046279278,0.0006826666,0.00002443089,0.00028701112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987296,0.000066334105,0.00033925285,0.00048022927,0.00013468675,0.00024993878],"domain_scores_gemma":[0.9979186,0.00013543796,0.00009870174,0.001737902,0.000048511367,0.000060868533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023659265,0.00012631126,0.00016548843,0.000121113015,0.000107955515,0.000056842346,0.0009954877,0.00004708711,0.000047160516],"category_scores_gemma":[0.00029208063,0.00012662329,0.000019102225,0.00052710215,0.000043987064,0.0025389625,0.0008193166,0.00011089686,0.000022934704],"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":[0.00003510591,0.00031356348,0.04338433,0.00008151082,0.000049128033,0.00034309845,0.001479422,0.016845096,0.0053569493,0.104869165,0.002009794,0.82523286],"study_design_scores_gemma":[0.000903973,0.00007624306,0.0028390836,0.00029341146,0.000008531505,0.0001974478,0.00044747684,0.8029865,0.00022628397,0.0010337492,0.19018668,0.0008006426],"about_ca_topic_score_codex":0.00010713127,"about_ca_topic_score_gemma":0.0001304811,"teacher_disagreement_score":0.8244322,"about_ca_system_score_codex":0.000030368392,"about_ca_system_score_gemma":0.000062974184,"threshold_uncertainty_score":0.5163548},"labels":[],"label_agreement":null},{"id":"W3136198913","doi":"10.1145/3261861","title":"Session details: Database principle","year":2006,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Session (web analytics); Database; Information retrieval; Programming language; World Wide Web","score_opus":0.020976961408618672,"score_gpt":0.2764887543090294,"score_spread":0.25551179290041076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136198913","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":[0.053515255,0.00023731851,0.94259787,0.0003211999,0.0007781995,0.0001780744,0.00002967598,0.0003118285,0.002030556],"genre_scores_gemma":[0.1728058,0.00004085463,0.8229064,0.00022070204,0.00048563202,0.000054625514,0.00011309459,0.000026045343,0.003346898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985827,0.00005981509,0.00029490935,0.00049122353,0.00024378022,0.0003275451],"domain_scores_gemma":[0.9977756,0.00012529077,0.00012845622,0.0018285493,0.000060009712,0.00008209783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021884408,0.00016489203,0.00018244635,0.00007649724,0.00018363466,0.000058326892,0.00082229957,0.00004955056,0.000040985637],"category_scores_gemma":[0.00014035606,0.00013533283,0.000055295037,0.00029220834,0.000035123197,0.0013466654,0.00094375556,0.00012439842,0.00016846112],"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":[0.000039791623,0.00030653048,0.01856316,0.00014421096,0.000026885951,0.0002629081,0.00016383955,0.00019671296,0.03751428,0.6178782,0.037311483,0.28759202],"study_design_scores_gemma":[0.00041940788,0.00007032068,0.002346118,0.00009243638,0.000005337393,0.0000419024,0.000021839058,0.005609464,0.011387015,0.006023387,0.97357523,0.00040752112],"about_ca_topic_score_codex":0.00039789543,"about_ca_topic_score_gemma":0.00024965033,"teacher_disagreement_score":0.93626374,"about_ca_system_score_codex":0.000036251735,"about_ca_system_score_gemma":0.000056478195,"threshold_uncertainty_score":0.55187124},"labels":[],"label_agreement":null},{"id":"W3175620523","doi":"10.1145/3471485.3471506","title":"Scaling Dynamic Hash Tables on Real Persistent Memory","year":2021,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Hash function; Scalability; Emulation; Parallel computing; Hash table; Latency (audio); Embedded system; Operating system; Programming language","score_opus":0.021875223175109013,"score_gpt":0.2662600561580582,"score_spread":0.2443848329829492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175620523","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":[0.07574878,0.0003380638,0.9008889,0.0030239592,0.0010531949,0.00015438843,0.0000029484167,0.0012024883,0.017587263],"genre_scores_gemma":[0.45931467,0.00042905033,0.5346201,0.0007828897,0.000096290525,0.000014240252,0.000018193063,0.000022570624,0.0047019897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986489,0.00010798479,0.00022419773,0.00050601223,0.00023617317,0.00027674675],"domain_scores_gemma":[0.9984357,0.00021707971,0.00008790912,0.0010439779,0.0001299273,0.000085444924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023239489,0.00014755833,0.00018435247,0.000095934854,0.00020161751,0.00017466069,0.0009462096,0.00008180818,0.000031468167],"category_scores_gemma":[0.0002241819,0.0001456991,0.0001375659,0.00034270587,0.000026454041,0.00016566327,0.00050195056,0.00014253684,0.00003382133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002917275,0.00039700777,0.00073420716,0.00006129863,0.00012402411,0.000203082,0.0013279377,0.05275566,0.0029121232,0.007122808,0.022733156,0.9115995],"study_design_scores_gemma":[0.0004126621,0.00022145193,0.00039537743,0.00016303238,0.00001618843,0.000050851013,0.000106163534,0.9780037,0.007481569,0.0053349235,0.0073082293,0.0005058943],"about_ca_topic_score_codex":0.00005211837,"about_ca_topic_score_gemma":0.000024755307,"teacher_disagreement_score":0.92524797,"about_ca_system_score_codex":0.00008436527,"about_ca_system_score_gemma":0.00010210542,"threshold_uncertainty_score":0.59414375},"labels":[],"label_agreement":null},{"id":"W3175911760","doi":"10.1145/3471485.3471494","title":"Efficient Directed Densest Subgraph Discovery","year":2021,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scalability; Computer science; Induced subgraph isomorphism problem; Graph; Enhanced Data Rates for GSM Evolution; Subgraph isomorphism problem; Core (optical fiber); Theoretical computer science; Graph factorization; Efficient algorithm; Algorithm; Database; Line graph; Artificial intelligence; Voltage graph","score_opus":0.01560761602411701,"score_gpt":0.23701589540386872,"score_spread":0.22140827937975172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175911760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8245572,0.00036728632,0.17097977,0.0014954965,0.0008556404,0.00004746652,0.000015914748,0.00040619305,0.001275025],"genre_scores_gemma":[0.9413182,0.00005130765,0.055583082,0.00029936034,0.000113021146,0.000008879505,0.00003397296,0.000012667913,0.0025795242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848753,0.0001086044,0.0002229092,0.00059952185,0.00026897725,0.00031245645],"domain_scores_gemma":[0.99771416,0.0002753584,0.00007725981,0.0017253029,0.000106713465,0.000101227226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017584536,0.00014666784,0.0002197973,0.00012268261,0.00014672645,0.00036408025,0.0011498114,0.00005461016,0.000038382],"category_scores_gemma":[0.0005191823,0.00013124004,0.00015890002,0.0012068291,0.000035405217,0.00022342252,0.00073046004,0.00013347327,0.00010849853],"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":[0.000039485225,0.0014523736,0.07758372,0.00008720342,0.0007166844,0.0019248301,0.001745432,0.0022845168,0.041918334,0.015661707,0.052033268,0.80455244],"study_design_scores_gemma":[0.0028833142,0.00047683966,0.11706397,0.00049304776,0.00044936393,0.00044626597,0.0006607891,0.6805172,0.07476685,0.010849198,0.10756486,0.0038282964],"about_ca_topic_score_codex":0.000119135824,"about_ca_topic_score_gemma":0.000110640176,"teacher_disagreement_score":0.80072415,"about_ca_system_score_codex":0.000025610492,"about_ca_system_score_gemma":0.00011363629,"threshold_uncertainty_score":0.53518134},"labels":[],"label_agreement":null},{"id":"W3215306199","doi":"10.1145/3516431.3516435","title":"Federated Data Science to Break Down Silos [Vision]","year":2022,"lang":"en","type":"preprint","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Data sharing; Focus (optics); Data science; Open science; Pipeline transport; Open data; Open research; World Wide Web; Engineering","score_opus":0.28799195367350366,"score_gpt":0.46530460369348814,"score_spread":0.17731265001998447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215306199","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64180046,0.00047682915,0.09282695,0.044297926,0.098379016,0.0060429936,0.006179287,0.0017274104,0.108269155],"genre_scores_gemma":[0.90838903,0.000039378687,0.05121928,0.0028931797,0.0009529786,0.00014339905,0.0016494307,0.000087800596,0.03462555],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98427624,0.00047311225,0.0015324734,0.00633881,0.0064328844,0.00094650564],"domain_scores_gemma":[0.97531074,0.002223134,0.00075738266,0.020275261,0.00082248735,0.0006109813],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.025945319,0.0005006154,0.0007438546,0.0018572995,0.0019317374,0.0069158725,0.034686103,0.00013906416,0.0053312047],"category_scores_gemma":[0.034373444,0.00039077617,0.00016843666,0.005438578,0.0004277114,0.0010411864,0.15514089,0.00097440457,0.0023119485],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033859193,0.000107608495,0.00061726855,0.0000092917635,0.000019407837,0.000039553568,0.00017542316,0.0013909971,0.00011092167,0.000106183936,0.545927,0.45146254],"study_design_scores_gemma":[0.000284803,0.00016666521,0.006413073,0.000097133794,0.000040139406,0.000012901939,0.0008439026,0.07537628,0.00007649985,0.020158142,0.89561814,0.00091231574],"about_ca_topic_score_codex":0.0013136392,"about_ca_topic_score_gemma":0.00033171655,"teacher_disagreement_score":0.4505502,"about_ca_system_score_codex":0.0003025311,"about_ca_system_score_gemma":0.0011004879,"threshold_uncertainty_score":0.9998544},"labels":[],"label_agreement":null},{"id":"W3217479643","doi":"10.1145/3503780.3503786","title":"VLDB Panel Summary","year":2021,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","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 British Columbia","funders":"","keywords":"Computer science; Very large database; SQL; Database; Point (geometry); World Wide Web; Mathematics education; Information retrieval","score_opus":0.12357829945750257,"score_gpt":0.28860616529085836,"score_spread":0.1650278658333558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217479643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6782633,0.0026472928,0.00885981,0.019058075,0.012355959,0.0005743751,0.000043349217,0.0011653699,0.27703246],"genre_scores_gemma":[0.95529026,0.0005047677,0.003836684,0.012157093,0.006810564,0.00004412513,0.00061095104,0.0001038014,0.020641733],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987527,0.000008603651,0.00025394306,0.00042114564,0.0002300591,0.0003335436],"domain_scores_gemma":[0.9986682,0.00008008221,0.00011356645,0.00087618676,0.00024703942,0.000014939569],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015640458,0.00018510733,0.00020673181,0.000111097135,0.00015595552,0.00031209094,0.00066770054,0.000100328645,0.0031417056],"category_scores_gemma":[0.00065025786,0.00017083462,0.000091951406,0.0006814601,0.000049740847,0.0011832456,0.0007927201,0.00017080363,0.0019672269],"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":[0.000056644396,0.00023612453,0.05648873,0.00031356618,0.000060326434,0.0002520658,0.000023145803,0.000010308232,0.005230614,0.010691418,0.3154403,0.61119676],"study_design_scores_gemma":[0.00017912593,0.0000041716253,0.006992421,0.00008053386,0.00004218773,0.00001125663,0.000095410775,0.0004697776,0.0013280206,0.012543746,0.9779194,0.00033394282],"about_ca_topic_score_codex":0.00042889887,"about_ca_topic_score_gemma":0.00026060478,"teacher_disagreement_score":0.6624791,"about_ca_system_score_codex":0.000015960317,"about_ca_system_score_gemma":0.00004007764,"threshold_uncertainty_score":0.9988099},"labels":[],"label_agreement":null},{"id":"W4232924440","doi":"10.1145/3262559","title":"Session details: Database principles","year":2004,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Session (web analytics); Database; Information retrieval; World Wide Web","score_opus":0.04760966187545459,"score_gpt":0.2783804266532686,"score_spread":0.23077076477781402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232924440","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":[0.060910545,0.00006321193,0.93132204,0.00061338017,0.0005006505,0.000115283525,9.4723265e-7,0.00031847347,0.0061554587],"genre_scores_gemma":[0.32842243,0.000031957996,0.67037034,0.0006471327,0.0001225962,0.000008874675,0.000007069514,0.0000113130545,0.0003782743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998763,0.000022239794,0.00040694073,0.00026644516,0.00027517413,0.00026616975],"domain_scores_gemma":[0.9984256,0.00009700554,0.0002460037,0.0010337742,0.00009471381,0.00010289635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039500793,0.00014191563,0.00015522477,0.00011352143,0.00023813834,0.0002563078,0.0013882843,0.000052033953,0.00003497277],"category_scores_gemma":[0.0004718797,0.00011867625,0.00005146087,0.00027937946,0.000027681517,0.001682533,0.0008033904,0.00013972806,0.00020449024],"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":[0.000008715523,0.0002812368,0.0010652444,0.00048327446,0.000033139248,0.000028253464,0.009802258,0.0019376199,0.0015271173,0.23498717,0.0025213924,0.7473246],"study_design_scores_gemma":[0.0030106888,0.00030572613,0.0014971928,0.0015981274,0.000030466854,0.00021879653,0.0005410848,0.4802729,0.047595717,0.3400912,0.12304035,0.0017977444],"about_ca_topic_score_codex":0.000017436336,"about_ca_topic_score_gemma":0.0000072794264,"teacher_disagreement_score":0.74552685,"about_ca_system_score_codex":0.00004993588,"about_ca_system_score_gemma":0.00013894065,"threshold_uncertainty_score":0.4839477},"labels":[],"label_agreement":null},{"id":"W4238142139","doi":"10.1145/3262194","title":"Session details: Database principles","year":2006,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Session (web analytics); Database; World Wide Web; Information retrieval","score_opus":0.03559642318195582,"score_gpt":0.2633261416628337,"score_spread":0.22772971848087786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238142139","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":[0.056620978,0.00008390432,0.9240166,0.00034094488,0.00047141899,0.00011193447,0.0000012962922,0.00034217755,0.018010762],"genre_scores_gemma":[0.3743936,0.00001662816,0.62294143,0.0004036873,0.00025697815,0.00001084888,0.000017382543,0.000013868125,0.0019455386],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987204,0.00003200222,0.00045024446,0.00026044107,0.00027132803,0.00026556925],"domain_scores_gemma":[0.9984506,0.00014879637,0.00027392065,0.000966778,0.00009702409,0.000062907864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040058108,0.00014043177,0.00015391532,0.00011503652,0.0002307405,0.0002870181,0.0012391086,0.000050834955,0.00004975754],"category_scores_gemma":[0.00025469976,0.00011791948,0.00005064539,0.0002664552,0.000025701063,0.001453968,0.00070432754,0.00011853776,0.00015270237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008428219,0.00030960646,0.005858141,0.00051362213,0.00002255275,0.000023602086,0.0023983533,0.0007998082,0.0021527107,0.22902688,0.03107507,0.7278112],"study_design_scores_gemma":[0.00059388194,0.000062510146,0.0017763448,0.0003058533,0.000010520121,0.0000500541,0.00008416845,0.78300804,0.01107846,0.07350182,0.12890297,0.00062535476],"about_ca_topic_score_codex":0.000038633818,"about_ca_topic_score_gemma":0.000012869215,"teacher_disagreement_score":0.78220826,"about_ca_system_score_codex":0.00002912469,"about_ca_system_score_gemma":0.00007161054,"threshold_uncertainty_score":0.48086166},"labels":[],"label_agreement":null},{"id":"W4238783465","doi":"10.1145/376284.375729","title":"Data-driven understanding and refinement of schema mappings","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Schema (genetic algorithms); Schema evolution; Database schema; Theoretical computer science; Programming language; Information retrieval; Data mining; Database design","score_opus":0.13553835996809832,"score_gpt":0.3042947998079359,"score_spread":0.16875643983983757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238783465","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":[0.032848068,0.00018930342,0.96433055,0.0008869363,0.00022136427,0.00011321314,0.00003120258,0.00006582073,0.0013135126],"genre_scores_gemma":[0.39848205,0.00044067664,0.6004036,0.00013330943,0.00009341684,0.00000864492,0.000040074967,0.00001247303,0.00038573256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904215,0.000022474964,0.00023232758,0.0003690086,0.00015817967,0.0001758594],"domain_scores_gemma":[0.9982579,0.00009599787,0.00013004082,0.0014297933,0.000028824814,0.000057481462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020052909,0.000099072444,0.0001748473,0.000066860885,0.000083209066,0.000024645817,0.0006983144,0.000030272808,0.000016590746],"category_scores_gemma":[0.000110923735,0.00008653111,0.000017346629,0.00020119526,0.000053687094,0.0007258606,0.0013559526,0.00006424701,0.000005142637],"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":[0.00005227929,0.00011404672,0.014026093,0.00024780582,0.00012846538,0.00009265543,0.001322504,0.000038177455,0.012723685,0.81639606,0.013180571,0.14167768],"study_design_scores_gemma":[0.0011116449,0.000286231,0.001166102,0.00038190864,0.000020892638,0.00011917256,0.0012056715,0.023498463,0.0013475589,0.017345458,0.9529275,0.0005894521],"about_ca_topic_score_codex":0.00009183414,"about_ca_topic_score_gemma":0.00008565571,"teacher_disagreement_score":0.93974686,"about_ca_system_score_codex":0.000033228782,"about_ca_system_score_gemma":0.000025168962,"threshold_uncertainty_score":0.3528636},"labels":[],"label_agreement":null},{"id":"W4241938281","doi":"10.1145/376284.375672","title":"Data bubbles","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Computer science; Data mining; CURE data clustering algorithm; Data stream clustering; Canopy clustering algorithm; Hierarchical clustering; Correlation clustering; Set (abstract data type); Data set; Data compression; Key (lock); Constrained clustering; Determining the number of clusters in a data set; Fuzzy clustering; Algorithm; Artificial intelligence","score_opus":0.123803096386827,"score_gpt":0.366511782884858,"score_spread":0.24270868649803096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241938281","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":[0.015085021,0.00015959123,0.9793649,0.0024989839,0.00052847486,0.00012862992,0.000008645049,0.0003343661,0.001891403],"genre_scores_gemma":[0.07812442,0.00045341285,0.9138129,0.00035889167,0.0004240146,0.000024056437,0.000025812751,0.00003255143,0.006743989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983473,0.00005282237,0.00017574486,0.0006360096,0.00035203993,0.00043607948],"domain_scores_gemma":[0.9951127,0.00025814588,0.000046995086,0.0043864106,0.00006503283,0.00013070786],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003168061,0.00012148369,0.00013533368,0.00009631546,0.0001231608,0.00014925378,0.0068877744,0.00005068796,0.000053846634],"category_scores_gemma":[0.00053305074,0.000111964524,0.000025659067,0.00050688634,0.000045019035,0.0010793585,0.0053141345,0.00019924244,0.0002467739],"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":[0.000007884198,0.00003175601,0.00073152286,0.000005157086,0.000009954611,0.00008758646,0.000056276578,0.00007121411,0.00040487407,0.0004059025,0.003807564,0.9943803],"study_design_scores_gemma":[0.00052808353,0.00017625747,0.003346164,0.000033208365,0.000003970431,0.00019441632,0.000027846763,0.43123528,0.00052226207,0.024606079,0.53887224,0.00045415363],"about_ca_topic_score_codex":0.00010035999,"about_ca_topic_score_gemma":0.00006600292,"teacher_disagreement_score":0.99392617,"about_ca_system_score_codex":0.000041703326,"about_ca_system_score_gemma":0.000060517916,"threshold_uncertainty_score":0.99848545},"labels":[],"label_agreement":null},{"id":"W4245210711","doi":"10.1145/376284.375666","title":"Iceberg-cube computation with PC clusters","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Computer science; Computation; Cube (algebra); Cuboid; Parallel computing; Algorithm; Data cube; Data mining; Mathematics","score_opus":0.020947862199152976,"score_gpt":0.246467051847856,"score_spread":0.22551918964870302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245210711","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":[0.033772737,0.000022543763,0.95373136,0.002843852,0.00059167045,0.00020096403,0.0000014257735,0.00028749465,0.008547944],"genre_scores_gemma":[0.47282907,0.00011158727,0.51725453,0.002190662,0.00038639896,0.00003913827,0.000075760865,0.000037616912,0.0070752176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988676,0.00003681889,0.00015780146,0.0004066963,0.0002555898,0.00027551697],"domain_scores_gemma":[0.9989706,0.00008267341,0.00008535161,0.0007390859,0.00004721163,0.000075051226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016443193,0.00013943041,0.00012809748,0.00011544859,0.000114820505,0.00025654197,0.0012268721,0.000032114895,0.000026365493],"category_scores_gemma":[0.00002370938,0.00011460221,0.000034357377,0.0005057715,0.000030775293,0.0011550363,0.00050437107,0.00009264735,0.00017908686],"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":[0.00002103898,0.000065014705,0.0030394008,0.0000110079645,0.000037690614,0.0000837494,0.00017784692,0.00038507918,0.000021383861,0.0018481325,0.015463976,0.97884566],"study_design_scores_gemma":[0.0028081778,0.00094332075,0.012947051,0.00010116142,0.000054349675,0.00010116076,0.00018675312,0.69024825,0.00019471943,0.01520523,0.27602318,0.00118666],"about_ca_topic_score_codex":0.000088330344,"about_ca_topic_score_gemma":0.00007430787,"teacher_disagreement_score":0.97765905,"about_ca_system_score_codex":0.000028185535,"about_ca_system_score_gemma":0.0000190466,"threshold_uncertainty_score":0.46733424},"labels":[],"label_agreement":null},{"id":"W4246773344","doi":"10.1145/3262443","title":"Session details: Database principles","year":2002,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Session (web analytics); Database; Information retrieval; World Wide Web","score_opus":0.07280586807241568,"score_gpt":0.2691107056749638,"score_spread":0.19630483760254813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246773344","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":[0.029688943,0.0001773622,0.94522125,0.00067766773,0.0006210273,0.00013288808,0.0000012227049,0.0004022537,0.02307739],"genre_scores_gemma":[0.3579013,0.00011619826,0.6374607,0.0009712111,0.00020447349,0.000013574716,0.000006118219,0.000017425451,0.0033089735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987347,0.00003541925,0.00041412318,0.00026678722,0.00027774577,0.00027122395],"domain_scores_gemma":[0.99829817,0.00016207396,0.0002504699,0.0010996108,0.00008717366,0.0001024794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034125248,0.00014175591,0.00015782665,0.00011607442,0.00024076008,0.00027076824,0.0014094915,0.000051638457,0.0002571],"category_scores_gemma":[0.0005151634,0.000118913515,0.00005143325,0.00028296805,0.000025725734,0.001648465,0.0007665522,0.0001403432,0.000440024],"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":[0.0000018643683,0.00014015533,0.00090515305,0.00021849829,0.000015663314,0.000010900647,0.0049322858,0.000098913195,0.00033690894,0.02629091,0.017334297,0.9497144],"study_design_scores_gemma":[0.0002685069,0.000039810937,0.00013992222,0.00015708068,0.0000048344455,0.000030374207,0.00006202392,0.914968,0.0019463603,0.0069206324,0.075174965,0.00028748394],"about_ca_topic_score_codex":0.0000055828973,"about_ca_topic_score_gemma":0.0000026251892,"teacher_disagreement_score":0.94942695,"about_ca_system_score_codex":0.000026172045,"about_ca_system_score_gemma":0.000024106394,"threshold_uncertainty_score":0.56557655},"labels":[],"label_agreement":null},{"id":"W4247707248","doi":"10.1145/3262132","title":"Session details: Database principles","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Session (web analytics); Database; Database design; Information retrieval; World Wide Web","score_opus":0.051649521499406346,"score_gpt":0.2777147422639968,"score_spread":0.22606522076459043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247707248","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":[0.031266846,0.00009127001,0.9422684,0.00017572353,0.0006217946,0.000117528645,7.352621e-7,0.00025136644,0.025206357],"genre_scores_gemma":[0.26624888,0.000037308546,0.7316942,0.0005935116,0.00007120077,0.000010708669,0.0000048942234,0.0000131301595,0.0013261243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987313,0.00006195024,0.0004087953,0.00026665878,0.000258215,0.00027309416],"domain_scores_gemma":[0.99829966,0.00017664721,0.00024789185,0.001074056,0.00009901384,0.00010272315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006215575,0.00014196681,0.0001577258,0.000107297055,0.00023759599,0.00024822514,0.0010874794,0.000051475574,0.000094522526],"category_scores_gemma":[0.0010761918,0.00011894691,0.000049371592,0.00028824195,0.000023865983,0.0014146179,0.00041618862,0.00013415486,0.00017400978],"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":[0.0000051273987,0.0002274315,0.0033300854,0.00044656682,0.000033134984,0.000017199427,0.005832279,0.00024706722,0.0010784704,0.42416942,0.0096856775,0.5549275],"study_design_scores_gemma":[0.0010304801,0.00012567763,0.0004923634,0.0004890781,0.000017604085,0.0001291909,0.00036330253,0.46697226,0.027340643,0.09184592,0.41014808,0.0010453892],"about_ca_topic_score_codex":0.0000045562847,"about_ca_topic_score_gemma":0.000002882406,"teacher_disagreement_score":0.5538821,"about_ca_system_score_codex":0.000027657316,"about_ca_system_score_gemma":0.00010939936,"threshold_uncertainty_score":0.48505142},"labels":[],"label_agreement":null},{"id":"W4248260714","doi":"10.1145/376284.375693","title":"SPARTAN","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Spartan; Lossy compression; Data mining; Table (database); Data compression; Data structure; Theoretical computer science; Algorithm; Artificial intelligence; Programming language","score_opus":0.04318286130473845,"score_gpt":0.272622653250019,"score_spread":0.22943979194528055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248260714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089803636,0.000067806264,0.8905946,0.0021041145,0.00060929364,0.00005947297,3.0304514e-7,0.00028783915,0.016472917],"genre_scores_gemma":[0.9162623,0.00008735772,0.08013705,0.0008385464,0.00017015486,0.0000086866885,8.6152664e-7,0.000008049597,0.0024869721],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990415,0.000045172375,0.0001648735,0.0003110294,0.00014476437,0.00029265237],"domain_scores_gemma":[0.9987539,0.00010123008,0.000047036385,0.00094303733,0.000055703957,0.00009911215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017627238,0.00010292152,0.00011601013,0.00005163406,0.00010660762,0.000069882546,0.0012766385,0.0000674635,0.00008203275],"category_scores_gemma":[0.000104315404,0.00009286328,0.00004548988,0.00026961399,0.000021383103,0.00028763743,0.00029729755,0.00016355856,0.00047128988],"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":[0.000008854988,0.000051456613,0.011139235,0.0000053158897,0.0000149062225,0.00006034387,0.00036888808,0.00004624093,0.0010354085,0.049302664,0.010774806,0.92719185],"study_design_scores_gemma":[0.0009293414,0.00047148624,0.00945825,0.00010113352,0.000017641054,0.00015146592,0.000072670344,0.22795448,0.0015877925,0.48475623,0.2732982,0.001201307],"about_ca_topic_score_codex":0.000069280286,"about_ca_topic_score_gemma":0.000028057786,"teacher_disagreement_score":0.9259906,"about_ca_system_score_codex":0.00001967736,"about_ca_system_score_gemma":0.00004361837,"threshold_uncertainty_score":0.6057635},"labels":[],"label_agreement":null},{"id":"W4250963083","doi":"10.1145/376284.375677","title":"Filtering algorithms and implementation for very fast publish/subscribe systems","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Publication; Scalability; Implementation; Event (particle physics); Workload; Polling; Database; Distributed computing; Computer network; Programming language; Operating system","score_opus":0.03398909794582906,"score_gpt":0.2917580653035587,"score_spread":0.25776896735772964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250963083","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":[0.14715038,0.00020929448,0.8455192,0.0036352854,0.0018118388,0.00072674366,0.0000139290305,0.0007234408,0.00020990024],"genre_scores_gemma":[0.6148847,0.00012934206,0.38278422,0.00039371557,0.00045942422,0.0005747664,0.000028572586,0.000036552596,0.0007087306],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850315,0.000025704712,0.0002809683,0.00051828177,0.00020427584,0.00046764573],"domain_scores_gemma":[0.99867314,0.00017810595,0.000100310164,0.00084680243,0.000106416024,0.00009524114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034006312,0.00017109718,0.00020383758,0.00021101808,0.00015199058,0.00059488014,0.0013169236,0.00008761044,0.0000049199216],"category_scores_gemma":[0.00015570452,0.00016876291,0.000042573283,0.00047737488,0.000024954794,0.0010051659,0.0008751415,0.000101936035,0.000010780823],"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":[0.000008619817,0.000014454121,0.0026602186,0.000022325026,0.000023589299,0.000010775175,0.00023288719,0.00006863544,0.0009675348,0.0016742351,0.025790429,0.9685263],"study_design_scores_gemma":[0.0032842825,0.0019996027,0.016628029,0.00024859712,0.00005724057,0.00039349138,0.0024786545,0.2675327,0.0061405813,0.024881402,0.67423815,0.002117239],"about_ca_topic_score_codex":0.00018454882,"about_ca_topic_score_gemma":0.00010333724,"teacher_disagreement_score":0.9664091,"about_ca_system_score_codex":0.00007508441,"about_ca_system_score_gemma":0.000027712638,"threshold_uncertainty_score":0.68819517},"labels":[],"label_agreement":null},{"id":"W4288696362","doi":"10.1145/3552490.3552499","title":"Reminiscences on Influential Papers","year":2022,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Column (typography); Computer science; Value (mathematics); Citation; Key (lock); Reading (process); Library science; World Wide Web; Operations research; History; Telecommunications; Law; Computer security; Political science; Mathematics","score_opus":0.22026839757357825,"score_gpt":0.3827781944790289,"score_spread":0.16250979690545064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288696362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93411416,0.00006708889,0.0001836838,0.021537522,0.0012334053,0.0003321043,0.00017886402,0.0003241413,0.042029005],"genre_scores_gemma":[0.99430376,0.000026733993,0.0017140809,0.0010570543,0.00006572925,0.00013623937,0.000012899053,0.000007853504,0.002675664],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979301,0.00007752057,0.00034074622,0.000518248,0.00091741205,0.00021593609],"domain_scores_gemma":[0.9971546,0.0008424714,0.00016659834,0.0017461838,0.000039192477,0.00005096927],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080584746,0.00009833144,0.00014673338,0.00016152946,0.0005940971,0.00010990865,0.0030362746,0.000048641443,0.0035551793],"category_scores_gemma":[0.0021846136,0.00007420227,0.00008354829,0.0008881112,0.00010461822,0.00009871886,0.0014343912,0.000284494,0.00043932415],"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":[0.00002489847,0.000058705155,0.003114775,3.8697618e-7,0.000005856742,0.0000038777384,0.00005621438,0.000044796157,0.0011059722,0.008006719,0.13876474,0.84881306],"study_design_scores_gemma":[0.00011696088,0.00018170718,0.0030383682,0.0000015366029,0.0000035699322,0.0000043979744,0.0013495557,0.00007547249,0.00047510254,0.045237415,0.9493995,0.00011646649],"about_ca_topic_score_codex":0.00004856706,"about_ca_topic_score_gemma":0.000028472874,"teacher_disagreement_score":0.8486966,"about_ca_system_score_codex":0.000032451884,"about_ca_system_score_gemma":0.000039305585,"threshold_uncertainty_score":0.9973557},"labels":[],"label_agreement":null},{"id":"W4309505072","doi":"10.1145/3572751.3572765","title":"Characterizing I/O in Machine Learning with MLPerf Storage","year":2022,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Focus (optics); Inference; Software; Machine learning; Computer data storage; Training set; Training (meteorology); Data access; Database; Artificial intelligence; Computer engineering; Operating system","score_opus":0.017438022209979483,"score_gpt":0.23393867511933225,"score_spread":0.21650065290935278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309505072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7306154,0.0003285848,0.26400766,0.0024360039,0.00044861776,0.00030324011,0.000014591221,0.0014146034,0.00043135398],"genre_scores_gemma":[0.89224565,0.000031161788,0.10703437,0.00022930442,0.000020257301,0.00010304464,0.000019135961,0.000022110187,0.0002949711],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985131,0.00010651261,0.00019496222,0.0005379151,0.00028060187,0.00036689918],"domain_scores_gemma":[0.99847585,0.00014920799,0.00014165643,0.0011778341,0.000017303722,0.000038175873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030349803,0.00016614515,0.00020883132,0.00027403398,0.00027691392,0.000060865896,0.0022606004,0.00003545777,0.00006351681],"category_scores_gemma":[0.0002332974,0.00015567825,0.000026552652,0.0008548382,0.00004315693,0.0007629736,0.0029241608,0.0008144728,0.000016924247],"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":[0.00011837346,0.0002057347,0.048766684,0.000028324395,0.000030589166,0.0012870504,0.002273113,0.0064571984,0.019591514,0.005648853,0.0002984343,0.9152941],"study_design_scores_gemma":[0.004925001,0.0052123833,0.025834262,0.0001641588,0.000025114428,0.0009254786,0.002896303,0.31936437,0.010594159,0.021403003,0.6050707,0.0035850515],"about_ca_topic_score_codex":0.000115312774,"about_ca_topic_score_gemma":0.00006550504,"teacher_disagreement_score":0.9117091,"about_ca_system_score_codex":0.00018558095,"about_ca_system_score_gemma":0.000042431268,"threshold_uncertainty_score":0.63483745},"labels":[],"label_agreement":null},{"id":"W4317952578","doi":"10.1145/3582302.3582312","title":"Mid-Career Researcher, huh?","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Health and Medical Research Impacts","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Wonder; Mistake; Negotiation; Promotion (chess); Ask price; Computer science; Work (physics); Law; Psychology; Social psychology; Political science; Business; Engineering","score_opus":0.4168772941303401,"score_gpt":0.4880706105098954,"score_spread":0.07119331637955534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317952578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7957112,0.00039017914,0.000079661404,0.17873316,0.00069363473,0.0009838124,0.000018483775,0.0005056455,0.022884184],"genre_scores_gemma":[0.8754089,0.004178739,0.0021405811,0.019450478,0.0021968063,0.00021168911,0.00021101788,0.0001289945,0.09607278],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996464,0.0001313315,0.00026750413,0.00032787764,0.0011710334,0.0016382462],"domain_scores_gemma":[0.991532,0.0010693892,0.000031852494,0.00094583596,0.00022361569,0.0061972598],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024306078,0.00012911441,0.0002899447,0.00032913493,0.000113897964,0.000022167917,0.0003427493,0.00018111076,0.0014619486],"category_scores_gemma":[0.12285467,0.00009823513,0.00009629435,0.0010715008,0.00013268029,0.00008011392,0.0002535752,0.0007521609,0.0036604514],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024942882,0.000059328515,0.0069209365,0.0002129403,0.000027500926,0.0004365318,0.0001369606,1.6953446e-7,0.0035047936,0.000025656846,0.60419476,0.38423097],"study_design_scores_gemma":[0.0019670625,0.0010816974,0.034815848,0.00023240707,0.000015939448,0.00003016344,0.00017895958,0.00027309183,0.0020452281,0.0015858002,0.95762956,0.00014426991],"about_ca_topic_score_codex":0.00039736045,"about_ca_topic_score_gemma":0.000052628096,"teacher_disagreement_score":0.3840867,"about_ca_system_score_codex":0.00017797317,"about_ca_system_score_gemma":0.0027874555,"threshold_uncertainty_score":0.99945086},"labels":[],"label_agreement":null},{"id":"W4317952630","doi":"10.1145/3582302.3582314","title":"Report on the First International Workshop on Data Systems Education (DataEd '22)","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Computer science; Bridging (networking); Panel discussion; Data management; Conjunction (astronomy); Data science; Engineering management; Library science; World Wide Web; Database; Engineering","score_opus":0.08682560969649208,"score_gpt":0.3362625693619047,"score_spread":0.2494369596654126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317952630","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28537634,0.00035932014,0.2522799,0.338578,0.08990632,0.002372483,0.00004429053,0.006748558,0.024334788],"genre_scores_gemma":[0.98226625,0.00003336006,0.0067821266,0.0007978864,0.0011403312,0.00009320008,0.00035719943,0.000027219656,0.008502444],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984751,0.00011034165,0.00023209093,0.00057746685,0.0003968419,0.00020817619],"domain_scores_gemma":[0.99574745,0.0008782774,0.0001730225,0.003117774,0.00003704991,0.000046431094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012481195,0.0001164575,0.000098133794,0.00013911686,0.00029521552,0.00048040246,0.0037909348,0.00005355126,0.000010584336],"category_scores_gemma":[0.0025532462,0.00008368027,0.000034740315,0.00042612577,0.00001973414,0.00029371594,0.0009936398,0.00037170772,0.00033472446],"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":[0.000008908111,0.00008856654,0.0030408679,0.000008750318,0.000033372064,0.000038530456,0.00038815432,0.00056400406,0.0000056121576,0.0072431075,0.15404563,0.8345345],"study_design_scores_gemma":[0.00007011954,0.00003702239,0.0036942083,0.00019117206,0.0000039851784,0.00003379702,0.00015663027,0.029607035,0.000006045203,0.00018669957,0.96588033,0.00013297622],"about_ca_topic_score_codex":0.00021486232,"about_ca_topic_score_gemma":0.000015597509,"teacher_disagreement_score":0.83440155,"about_ca_system_score_codex":0.000043157546,"about_ca_system_score_gemma":0.00008908168,"threshold_uncertainty_score":0.7044563},"labels":[],"label_agreement":null},{"id":"W4379797318","doi":"10.1145/3604437.3604439","title":"TECHNICAL PERSPECTIVE: Ad Hoc Transactions: What They Are and Why We Should Care","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Perspective (graphical); Set (abstract data type); Data science; Programming language; Artificial intelligence","score_opus":0.04067911802497789,"score_gpt":0.3036587340324514,"score_spread":0.26297961600747355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379797318","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":[0.0058750813,0.018611271,0.95239764,0.019290892,0.0015901685,0.00056227617,0.00007014558,0.0013284729,0.00027403003],"genre_scores_gemma":[0.5779957,0.07224912,0.344367,0.0016719812,0.00058185385,0.00065885886,0.000047444344,0.00015005888,0.0022779691],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986588,0.000060255254,0.00018774865,0.00057757716,0.00022597455,0.00028965462],"domain_scores_gemma":[0.9985161,0.00020051828,0.00007248714,0.0009902306,0.00011785017,0.00010281943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013054314,0.00017966064,0.00022908283,0.00013738738,0.00024837354,0.0001508541,0.0005136675,0.0001010553,0.000015249398],"category_scores_gemma":[0.00010177005,0.00015155956,0.00007768928,0.00043542383,0.00006838171,0.0016704547,0.00022282249,0.0002357761,0.00004207374],"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":[0.000038386996,0.000044343004,0.0002221641,0.00013666828,0.000035798003,0.00011313102,0.009596566,0.00006732357,0.0013739006,0.016387476,0.0038317465,0.9681525],"study_design_scores_gemma":[0.0011755527,0.0005865731,0.0021499624,0.0010477133,0.00004394035,0.00020706218,0.09692659,0.0026366063,0.0014377809,0.028373104,0.8641087,0.0013064223],"about_ca_topic_score_codex":0.000086985376,"about_ca_topic_score_gemma":0.0012034775,"teacher_disagreement_score":0.96684605,"about_ca_system_score_codex":0.000079091966,"about_ca_system_score_gemma":0.00003901029,"threshold_uncertainty_score":0.618042},"labels":[],"label_agreement":null},{"id":"W4379800102","doi":"10.1145/3604437.3604444","title":"Efficiently Making Cross-Engine Transactions Consistent","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Limiting; Isolation (microbiology); Correctness; Database; Operating system; Programming language","score_opus":0.032594072378710856,"score_gpt":0.3036519960292631,"score_spread":0.27105792365055226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379800102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07454263,0.00010592908,0.9185564,0.0011542398,0.0027112495,0.00022126612,0.000034557703,0.0009160537,0.0017576689],"genre_scores_gemma":[0.9903199,0.000015083158,0.0067937872,0.00014834756,0.00008537357,0.000043483855,0.000008715587,0.000014323993,0.0025709753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984889,0.000041288542,0.00032076647,0.00044870985,0.00027814816,0.00042217743],"domain_scores_gemma":[0.9985861,0.00016472352,0.00008272111,0.0009784476,0.00009833936,0.00008965893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003200895,0.00015305572,0.00020237004,0.00013134064,0.00026495254,0.00028401232,0.0010680543,0.000077903765,0.000043677683],"category_scores_gemma":[0.00008024217,0.00014399822,0.00013705262,0.0010712545,0.000045183362,0.00029381557,0.00010906082,0.00016326574,0.00051531126],"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":[0.000029777573,0.00025117208,0.0036019231,0.0001508291,0.0001441437,0.00028406738,0.00147777,0.025257623,0.0023778535,0.009261461,0.017648187,0.9395152],"study_design_scores_gemma":[0.00157991,0.00022231461,0.020166129,0.0002609461,0.000024682091,0.00012315575,0.00015556974,0.65037745,0.0013542258,0.002407763,0.32233986,0.000988024],"about_ca_topic_score_codex":0.000027746088,"about_ca_topic_score_gemma":0.000016721422,"teacher_disagreement_score":0.93852717,"about_ca_system_score_codex":0.00004571556,"about_ca_system_score_gemma":0.000048853308,"threshold_uncertainty_score":0.6623456},"labels":[],"label_agreement":null},{"id":"W4379932427","doi":"10.1145/3604437.3604458","title":"Accurate Summary-based Cardinality Estimation Through the Lens of Cardinality Estimation Graphs","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"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":"Estimator; Cardinality (data modeling); Computer science; Graph; Joins; Proxy (statistics); Context (archaeology); Theoretical computer science; Mathematical optimization; Mathematics; Statistics; Data mining; Machine learning","score_opus":0.0549768818470338,"score_gpt":0.31388724108751587,"score_spread":0.25891035924048206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379932427","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":[0.0446665,0.00008481925,0.95160913,0.0017160227,0.00072984875,0.0003896639,0.00009830563,0.00031582266,0.00038990972],"genre_scores_gemma":[0.83528787,0.0000441725,0.16417938,0.00012682247,0.000051282736,0.00008498365,0.00013469798,0.000015210059,0.00007558859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980202,0.00028744905,0.00049599045,0.0004535309,0.00043249028,0.00031036953],"domain_scores_gemma":[0.9969392,0.0006347487,0.0003456441,0.0018492275,0.00018795233,0.000043268377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009275511,0.00020138833,0.00034512577,0.0000850803,0.00029458018,0.000056150173,0.00079605484,0.00007211185,0.000005430308],"category_scores_gemma":[0.00066842535,0.00014742825,0.00018317977,0.0011189672,0.00013805885,0.0013813578,0.00036422574,0.00015604967,0.000035333273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016323233,0.00016124413,0.008898905,0.00093882426,0.00028710134,0.000042833122,0.0037014775,0.23412788,0.0024352898,0.44549656,0.020069188,0.28367746],"study_design_scores_gemma":[0.00081633974,0.00023629055,0.024497133,0.00029307572,0.00007687288,0.0000117584905,0.00030854956,0.8316631,0.005788471,0.104289986,0.031331908,0.0006865464],"about_ca_topic_score_codex":0.0013305154,"about_ca_topic_score_gemma":0.00009272749,"teacher_disagreement_score":0.79062134,"about_ca_system_score_codex":0.000049468243,"about_ca_system_score_gemma":0.00011189689,"threshold_uncertainty_score":0.601195},"labels":[],"label_agreement":null},{"id":"W4388233567","doi":"10.1145/3631504.3631514","title":"Kùzu: A Database Management System For \"Beyond Relational\" Workloads","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","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","funders":"","keywords":"Computer science; Relational database; Relational database management system; Set (abstract data type); Database; Relational model; World Wide Web; Programming language","score_opus":0.02996732447430424,"score_gpt":0.25584146233573296,"score_spread":0.22587413786142874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388233567","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":[0.008588446,0.00008449394,0.9823405,0.0012042788,0.0023529506,0.0006084575,0.00003349328,0.00086723565,0.0039201127],"genre_scores_gemma":[0.26975808,0.000080257734,0.7141235,0.00052099844,0.00051415584,0.0007351487,0.00018162346,0.000055519187,0.014030741],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99866974,0.000060329756,0.0002336254,0.00047500184,0.0002282864,0.00033303973],"domain_scores_gemma":[0.99824816,0.0003979411,0.000080247264,0.0011404294,0.00004741875,0.00008577703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071035686,0.00013779296,0.00014483358,0.00022705781,0.00023340384,0.00008578198,0.0011924239,0.000049153165,0.000011271174],"category_scores_gemma":[0.00006159464,0.00012840709,0.00010511004,0.0009176602,0.000024177767,0.00039980107,0.0006336193,0.00008874113,0.00035707175],"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":[0.00002268639,0.00003297928,0.00022953525,0.00014330466,0.00007044496,0.00006577102,0.00017186938,0.00012823209,0.000095022326,0.7446325,0.012965658,0.24144201],"study_design_scores_gemma":[0.0027413066,0.0003029315,0.0026349328,0.0005546169,0.00009109327,0.000046977042,0.00067615724,0.24166922,0.0011541898,0.5559715,0.19300288,0.0011541978],"about_ca_topic_score_codex":0.0000034229415,"about_ca_topic_score_gemma":0.0000019084237,"teacher_disagreement_score":0.26821706,"about_ca_system_score_codex":0.00003440114,"about_ca_system_score_gemma":0.000017414035,"threshold_uncertainty_score":0.5236289},"labels":[],"label_agreement":null},{"id":"W4391055211","doi":"10.1145/3641832.3641842","title":"Future Database Engine Development: You Will Only Need One Programming Language","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; SPARK (programming language); Database; Java; Programming language; Productivity; Operating system","score_opus":0.021180013553948315,"score_gpt":0.2615194378698532,"score_spread":0.24033942431590488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391055211","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":[0.21565905,0.00074116717,0.7665132,0.005044687,0.0015301536,0.0006813864,0.000056850786,0.009617753,0.00015571003],"genre_scores_gemma":[0.03962586,0.00013050849,0.9585849,0.00016096204,0.00025256645,0.00008067561,0.0003060551,0.000038811548,0.0008196422],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980576,0.000027921487,0.0002844687,0.00067395426,0.00034499232,0.000611079],"domain_scores_gemma":[0.997389,0.00013272127,0.00011766725,0.0022089847,0.00005317558,0.000098406636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002874254,0.00024701963,0.00024130073,0.00034026257,0.0001819508,0.00011622516,0.002787605,0.00012278394,0.000018231925],"category_scores_gemma":[0.0005698354,0.0002365464,0.000043750148,0.001721666,0.000054419743,0.0013508042,0.0026581446,0.00034626474,0.00029827893],"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":[0.0000053823983,0.00004051284,0.00027162812,0.000029055833,0.00002302106,0.00014103192,0.00075637037,0.000008172776,0.0025358265,0.0019502185,0.0017516476,0.99248713],"study_design_scores_gemma":[0.0012281878,0.00023864012,0.0022828253,0.0002019724,0.000023794639,0.00006580218,0.0026949926,0.0044172565,0.03103282,0.004003331,0.95227253,0.0015378429],"about_ca_topic_score_codex":0.000024328248,"about_ca_topic_score_gemma":0.00007424275,"teacher_disagreement_score":0.9909493,"about_ca_system_score_codex":0.00008308006,"about_ca_system_score_gemma":0.00010863181,"threshold_uncertainty_score":0.9646082},"labels":[],"label_agreement":null},{"id":"W4396883491","doi":"10.1145/3665252.3665266","title":"Technical Perspective: Synthetic Data Needs a Reproducibility Benchmark","year":2024,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"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; Benchmark (surveying); Perspective (graphical); Reproducibility; Data mining; Data science; Database; Artificial intelligence; Statistics; Mathematics","score_opus":0.22098713037544487,"score_gpt":0.44072847411390287,"score_spread":0.219741343738458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396883491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2805924,0.00853009,0.28118828,0.095573835,0.04660543,0.0030597565,0.0010450124,0.004376065,0.27902913],"genre_scores_gemma":[0.97244173,0.00002305956,0.017628858,0.00015535935,0.00047943482,0.000013490979,0.00004664752,0.000020234475,0.009191191],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.992431,0.00031093162,0.00076999445,0.004559235,0.001523517,0.0004053491],"domain_scores_gemma":[0.9643829,0.004099552,0.00012807363,0.03087793,0.00032327094,0.00018826313],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.026199736,0.00020101795,0.0003126135,0.0006347472,0.00023342088,0.001572976,0.0070719635,0.000079905316,0.0017711887],"category_scores_gemma":[0.06861946,0.00014317696,0.00014364469,0.0033492087,0.00024683966,0.00078247156,0.0073192245,0.00033613015,0.0015945602],"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":[0.000015413843,0.00007628812,0.00065813074,0.000008819616,0.0000161159,0.000026694635,0.00022646954,0.0000076131078,0.00013981503,0.0031205243,0.46927685,0.52642727],"study_design_scores_gemma":[0.0001194759,0.00009639403,0.0033306303,0.0000909988,0.000058574118,0.000047679718,0.0021274886,0.06341286,0.00006242527,0.19081347,0.7394693,0.0003707499],"about_ca_topic_score_codex":0.0002851028,"about_ca_topic_score_gemma":0.00011352885,"teacher_disagreement_score":0.69184935,"about_ca_system_score_codex":0.00013444989,"about_ca_system_score_gemma":0.00014812312,"threshold_uncertainty_score":0.9994635},"labels":[],"label_agreement":null},{"id":"W4406379941","doi":"10.1145/3712311.3712323","title":"A Roadmap to Graph Analytics","year":2025,"lang":"en","type":"article","venue":"ACM SIGMOD Record","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","funders":"","keywords":"Computer science; Analytics; Data science; Graph; Data analysis; Product (mathematics); Task (project management); Data mining; Theoretical computer science; Engineering; Systems engineering","score_opus":0.013973507860048258,"score_gpt":0.2632285770793657,"score_spread":0.24925506921931745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406379941","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":[0.037514005,0.0000815477,0.94807845,0.0044629984,0.0014295215,0.00016825633,0.0000018436943,0.00023600746,0.008027376],"genre_scores_gemma":[0.78321505,0.000024389052,0.2045303,0.004921357,0.000107894055,0.00003803755,0.0000018044547,0.000011951424,0.0071492125],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99896216,0.000057372148,0.00018505781,0.00038566094,0.00013153184,0.00027820325],"domain_scores_gemma":[0.9984187,0.0001642341,0.00003548166,0.0012114446,0.00006256126,0.00010761182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027082028,0.00012628632,0.00016167581,0.0003322798,0.00012528863,0.000113952476,0.0018229553,0.000054173317,0.00001962983],"category_scores_gemma":[0.00019187182,0.00011510429,0.000108337925,0.0015533852,0.000027113207,0.00018932307,0.0005960827,0.00012385126,0.00010856379],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014152337,0.00006241657,0.0024493793,0.000013570123,0.00006642558,0.000024457613,0.0003517678,0.00010051806,0.0005883497,0.37725058,0.0122859515,0.6067924],"study_design_scores_gemma":[0.00032136487,0.00016096477,0.0024879123,0.000054508637,0.000017753104,0.0000046974883,0.00004338375,0.00845452,0.0034499643,0.93805903,0.046623006,0.0003228948],"about_ca_topic_score_codex":0.000021092557,"about_ca_topic_score_gemma":0.000017346341,"teacher_disagreement_score":0.7457011,"about_ca_system_score_codex":0.000017202432,"about_ca_system_score_gemma":0.000046234236,"threshold_uncertainty_score":0.4693817},"labels":[],"label_agreement":null},{"id":"W4406379983","doi":"10.1145/3712311.3712321","title":"Multi-Analyst Differential Privacy with Fine-Grained Provenance for Databases","year":2025,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Differential privacy; Privilege (computing); Computer science; Internet privacy; Safeguarding; Information privacy; Personally identifiable information; Computer security; Data mining","score_opus":0.0500052720731431,"score_gpt":0.3125504361115713,"score_spread":0.2625451640384282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406379983","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":[0.017813746,0.000112684975,0.95952016,0.0201692,0.00051599223,0.00077900593,0.00010628402,0.00087792973,0.00010498292],"genre_scores_gemma":[0.1399018,0.000025842306,0.8585773,0.00017853428,0.000047774614,0.00028721936,0.000063087966,0.00001864928,0.00089977053],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978302,0.000049418246,0.0003571521,0.0010089872,0.00023426826,0.0005199436],"domain_scores_gemma":[0.98484397,0.0006148543,0.00019635574,0.014147942,0.00014006752,0.000056836565],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00021414882,0.00028636114,0.00037421988,0.00024693995,0.00021109113,0.0001724831,0.029911455,0.00009275835,0.000014636506],"category_scores_gemma":[0.027041983,0.00022287942,0.000100859725,0.0008233015,0.00012407877,0.0007143552,0.05412843,0.00024012476,0.000007835182],"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":[0.00024391215,0.00064077263,0.0136730345,0.00034215013,0.0004781349,0.00003685054,0.000073892494,0.000011405366,0.00941284,0.012054462,0.6339018,0.32913074],"study_design_scores_gemma":[0.0065019974,0.0007131668,0.009766649,0.00072024646,0.00022677275,0.000017328784,0.000038672915,0.6275309,0.049994487,0.17579219,0.1271,0.0015976101],"about_ca_topic_score_codex":0.00010267073,"about_ca_topic_score_gemma":0.00020322754,"teacher_disagreement_score":0.6275195,"about_ca_system_score_codex":0.00007131634,"about_ca_system_score_gemma":0.00015924794,"threshold_uncertainty_score":0.98115367},"labels":[],"label_agreement":null},{"id":"W4409918354","doi":"10.1145/3733620.3733635","title":"Reservoir Sampling over Joins","year":2025,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Joins; Sampling (signal processing); Computer science; Programming language; Computer vision","score_opus":0.03661353942592897,"score_gpt":0.3200537669503436,"score_spread":0.2834402275244146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409918354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6866974,0.00041655725,0.29854998,0.00016230294,0.0013887419,0.00011607242,0.0000038177163,0.0007367752,0.011928326],"genre_scores_gemma":[0.83766735,0.00018643454,0.15728949,0.000097455944,0.0002749843,0.00003600971,0.000012057549,0.00006368435,0.004372542],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991252,0.00003187025,0.00025568312,0.00019016823,0.00012141037,0.00027566293],"domain_scores_gemma":[0.99877864,0.0004049093,0.000015433872,0.0007012151,0.000034675064,0.000065125074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024784906,0.00016112733,0.00020183378,0.00020379516,0.00006540088,0.00005168027,0.0003651873,0.00012189319,0.00013507275],"category_scores_gemma":[0.00049772667,0.00016390882,0.00008640554,0.00042021784,0.000013298481,0.00012371861,0.0000970798,0.00025240317,0.000030219331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009482298,0.000008654041,0.003471225,0.00010627333,0.000057952057,0.0000024658054,0.000052157073,0.96507156,0.0034458176,0.0007162333,0.007571094,0.01948711],"study_design_scores_gemma":[0.00065643777,0.000020751328,0.010598936,0.00012215115,0.000020425654,0.0000011606039,0.000018340696,0.6472319,0.0028135055,0.007920867,0.3302418,0.00035376707],"about_ca_topic_score_codex":0.000024443669,"about_ca_topic_score_gemma":0.000012429067,"teacher_disagreement_score":0.3226707,"about_ca_system_score_codex":0.000070587725,"about_ca_system_score_gemma":0.00001725595,"threshold_uncertainty_score":0.6684007},"labels":[],"label_agreement":null},{"id":"W4412402624","doi":"10.1145/3749116.3749124","title":"Reminiscences on Influential Papers","year":2025,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Library science; Computer science","score_opus":0.12901287901589728,"score_gpt":0.439895915516474,"score_spread":0.3108830365005767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412402624","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24283487,0.00007482253,0.0017896678,0.021829331,0.0053904704,0.00043259253,0.00003403587,0.00016217402,0.72745204],"genre_scores_gemma":[0.9280356,0.000066828565,0.0018082674,0.0084297815,0.0001349199,0.000024955418,0.000010085684,0.0000068394456,0.06148271],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997725,0.00019011926,0.00049452035,0.000548426,0.00081099215,0.00023093565],"domain_scores_gemma":[0.9966261,0.0015995047,0.00012921817,0.0015149162,0.00006819359,0.000062084844],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002015107,0.00012231969,0.0002102655,0.00027065998,0.0001767163,0.00028702285,0.001995449,0.00006506922,0.0012025423],"category_scores_gemma":[0.0066224723,0.000088091896,0.00010538728,0.0007021045,0.00009986593,0.00022478116,0.00068176404,0.00012896112,0.0010909939],"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":[0.00006393772,0.00005433889,0.0021864928,0.0000045466027,0.000022590431,0.000005180948,0.00010500213,0.0000113057295,0.00012555221,0.027618982,0.22292525,0.74687684],"study_design_scores_gemma":[0.00023060868,0.000085151914,0.007787824,0.000029612995,0.000011737365,2.2254265e-7,0.00067291316,0.00003857572,0.00041346956,0.071809165,0.91880786,0.00011284459],"about_ca_topic_score_codex":0.00009086941,"about_ca_topic_score_gemma":0.0001698397,"teacher_disagreement_score":0.746764,"about_ca_system_score_codex":0.000023305314,"about_ca_system_score_gemma":0.000050672686,"threshold_uncertainty_score":0.9997105},"labels":[],"label_agreement":null}]}