{"meta":{"query_hash":"ba0f37fc5bf0","filters":{"venue":"Sociological Methods & Research"},"cohort_total":33,"direct_labels_cover":0,"predictions_cover":33,"exported":33,"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/ba0f37fc5bf0","api":"https://metacan.xera.ac/api/v1/cohort?venue=Sociological+Methods+%26+Research"},"results":[{"id":"W1963762678","doi":"10.1177/0049124106292362","title":"Addressing Data Sparseness in Contextual Population Research","year":2007,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social Sciences","cited_by":172,"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; Variance (accounting); Cluster analysis; Cluster (spacecraft); Monte Carlo method; Statistics; Population; Econometrics; Data mining; Machine learning; Mathematics","score_opus":0.9296372523519871,"score_gpt":0.7377377898052143,"score_spread":0.19189946254677281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963762678","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":[0.7889134,0.006173645,0.026668135,0.009709407,0.00090934685,0.0021495884,0.00003808572,0.00028028592,0.16515806],"genre_scores_gemma":[0.97285604,0.000469895,0.024231818,0.000083002116,0.0009176963,0.000037064026,0.00003908351,0.00001437983,0.0013510422],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9724012,0.022392754,0.0005701516,0.00085229473,0.0020476857,0.00173593],"domain_scores_gemma":[0.9707649,0.027352963,0.000075918724,0.00061857584,0.0009194417,0.00026822195],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15156192,0.00013854746,0.00039668372,0.0005101249,0.002651283,0.00018243867,0.0012688253,0.00051265076,0.0003531359],"category_scores_gemma":[0.036628924,0.000111971436,0.00005884547,0.0020786433,0.0026844672,0.00036932592,0.00097424834,0.001881405,0.00007413095],"study_design_candidate":"observational","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":[0.00026214466,0.00031616064,0.27047047,0.000029075403,0.00003960864,0.00007506238,0.037665226,0.000004281829,0.0010498756,0.19227894,0.0038288012,0.49398035],"study_design_scores_gemma":[0.00075326476,0.00019538372,0.5626624,0.000092227434,0.000006708225,0.0000012644384,0.16264305,0.00035715642,0.00014053733,0.19766358,0.07510457,0.00037981544],"about_ca_topic_score_codex":0.01025654,"about_ca_topic_score_gemma":0.005521878,"teacher_disagreement_score":0.49360055,"about_ca_system_score_codex":0.00048965274,"about_ca_system_score_gemma":0.00029158642,"threshold_uncertainty_score":0.99864715},"labels":[],"label_agreement":null},{"id":"W2013108856","doi":"10.1177/0049124105280198","title":"Mapping Social Distance","year":2005,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social Sciences","cited_by":41,"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":"Multidimensional scaling; Ethnic group; Census; Metropolitan area; Immigration; Diversity (politics); Geography; Social distance; Sociology; Social group; Racial diversity; Census tract; Cultural diversity; Geographical distance; Economic geography; Regional science; Demography; Demographic economics; Social science; Statistics; Mathematics; Anthropology; Population","score_opus":0.496170104316695,"score_gpt":0.6084512661669489,"score_spread":0.11228116185025389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013108856","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":[0.07082711,0.005578351,0.12212713,0.09367476,0.0005747584,0.001006778,0.000017546694,0.0005672908,0.70562625],"genre_scores_gemma":[0.8924284,0.0007689943,0.088733524,0.00058817025,0.0034589295,0.00012852313,0.0000030758354,0.000014144052,0.013876253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901086,0.007365673,0.00028337623,0.00041653513,0.0008622871,0.0009635195],"domain_scores_gemma":[0.99454963,0.004638709,0.00006248639,0.00014499768,0.0004356699,0.00016849427],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015166147,0.000123683,0.00030430354,0.00010465694,0.0038251425,0.000106239124,0.0004966609,0.0003161837,0.0010706849],"category_scores_gemma":[0.004798304,0.000097570344,0.0001534272,0.0007867138,0.0022929488,0.00015200472,0.00019673724,0.0008211015,0.00024999134],"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":[0.00002883735,0.00012334241,0.0068562054,0.000010765475,0.000050939638,0.0000046070163,0.10865545,0.0000012310998,0.0005464053,0.43638873,0.017836282,0.4294972],"study_design_scores_gemma":[0.00017942397,0.00003837603,0.013797991,0.0000058582846,0.0000028945383,1.8141867e-7,0.048353318,0.000049017242,0.00004713657,0.09474343,0.84261507,0.00016728578],"about_ca_topic_score_codex":0.00019559512,"about_ca_topic_score_gemma":0.000113938666,"teacher_disagreement_score":0.8247788,"about_ca_system_score_codex":0.0003292255,"about_ca_system_score_gemma":0.00016178613,"threshold_uncertainty_score":0.99984246},"labels":[],"label_agreement":null},{"id":"W2159263306","doi":"10.1177/0049124107301944","title":"Log-Linear Randomized-Response Models Taking Self-Protective Response Behavior Into Account","year":2007,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":49,"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":"Randomized response; Respondent; Log-linear model; Response bias; Item response theory; Statistics; Outcome (game theory); Psychology; Social psychology; Econometrics; Response time; Linear model; Mathematics; Computer science; Psychometrics","score_opus":0.5305748280486128,"score_gpt":0.619559010240721,"score_spread":0.08898418219210824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159263306","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":[0.44412878,0.00013100813,0.5529666,0.00032780741,0.000072622126,0.0014527602,0.0000048144134,0.00063748925,0.000278107],"genre_scores_gemma":[0.3979232,0.000018928997,0.60100013,0.000060902104,0.00010689738,0.0007197568,0.0000024525116,0.000040384584,0.00012733144],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94390076,0.05170805,0.0011148083,0.0008693488,0.0011672155,0.0012398069],"domain_scores_gemma":[0.8583457,0.13918649,0.00031994662,0.0007348845,0.0011490223,0.0002639683],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30283156,0.00035906892,0.0010762353,0.000582255,0.0008272186,0.00009351878,0.000728001,0.00089832715,0.0001681802],"category_scores_gemma":[0.13761303,0.0002607276,0.00042268334,0.0007843976,0.0013055659,0.00018998029,0.00048161106,0.002170064,0.000054739132],"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":[0.6701828,0.001991803,0.0005465531,0.00022564616,0.0004231035,0.00027472107,0.032056935,0.000092940834,0.09996552,0.071395285,0.000568355,0.1222763],"study_design_scores_gemma":[0.008625555,0.00052526116,0.0016411825,0.000064349246,0.00005292947,0.000018024966,0.0018618583,0.0042007156,0.018165974,0.9642385,0.00019715355,0.00040848163],"about_ca_topic_score_codex":0.0002346718,"about_ca_topic_score_gemma":0.000004556497,"teacher_disagreement_score":0.89284325,"about_ca_system_score_codex":0.0005444169,"about_ca_system_score_gemma":0.00025393334,"threshold_uncertainty_score":0.9999845},"labels":[],"label_agreement":null},{"id":"W2164011803","doi":"10.1177/0049124113506406","title":"Prepaid Monetary Incentives—Predictors of Taking the Money and Completing the Survey","year":2013,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Impact; Ontario Institute for Cancer Research; University of Waterloo","funders":"National Cancer Institute","keywords":"Prepayment of loan; Cash; Payment; Incentive; Survey data collection; Sample (material); Demographic economics; Survey methodology; Survey research; Actuarial science; Business; Economics; Finance; Socioeconomics; Medicine; Statistics","score_opus":0.6779027527051609,"score_gpt":0.6117124448757337,"score_spread":0.06619030782942714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164011803","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":[0.9879187,0.001588738,0.0026910892,0.0035161674,0.00020326191,0.0007449246,0.000008490873,0.00003821447,0.0032904197],"genre_scores_gemma":[0.9726481,0.0005006793,0.026151106,0.00017382232,0.00018490675,0.00008948677,0.0000030599854,0.000008182037,0.00024069795],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6891262,0.30913165,0.0003004293,0.000318372,0.0005091809,0.0006141508],"domain_scores_gemma":[0.7240563,0.27488446,0.00016306424,0.0003216748,0.00044783537,0.00012665067],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.34705973,0.00012046363,0.00032190018,0.000066780034,0.0022046494,0.00006529105,0.00084629474,0.00031231818,0.00068307266],"category_scores_gemma":[0.17856014,0.000060007627,0.00009626731,0.00062884897,0.008620277,0.00009974147,0.00053304073,0.0012039731,0.000018857987],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000839167,0.00008700899,0.8790008,0.000013384362,0.0001448301,0.0000028380564,0.04884284,0.0000063186562,0.0047852295,0.00693011,0.0011762282,0.058171235],"study_design_scores_gemma":[0.00009360733,0.00009059369,0.95848334,0.000007917767,0.0000061302358,6.515398e-7,0.017885284,0.00011535438,0.00013927785,0.021881364,0.001223417,0.00007306772],"about_ca_topic_score_codex":0.018792396,"about_ca_topic_score_gemma":0.00037197044,"teacher_disagreement_score":0.16849957,"about_ca_system_score_codex":0.000042583422,"about_ca_system_score_gemma":0.00013426585,"threshold_uncertainty_score":0.99909437},"labels":[],"label_agreement":null},{"id":"W2224720476","doi":"10.1177/0049124115610345","title":"Obtaining Predictions from Models Fit to Multiply Imputed Data","year":2015,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":79,"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; Imputation (statistics); Set (abstract data type); Data set; Data mining; Missing data; Machine learning; Artificial intelligence","score_opus":0.8988619494689873,"score_gpt":0.6764142898064175,"score_spread":0.22244765966256985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2224720476","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":[0.0049684285,0.00013848284,0.98692334,0.0014565394,0.00023237201,0.0006082184,0.00050434814,0.00023284477,0.004935415],"genre_scores_gemma":[0.029379414,0.000019473295,0.96959835,0.00018790926,0.00047211116,0.0001498076,0.000035517984,0.000030878295,0.00012656515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9881436,0.0085151605,0.00056413293,0.0009952203,0.0008611418,0.00092071696],"domain_scores_gemma":[0.9612074,0.03568321,0.00007596385,0.0014591607,0.0007183636,0.00085591676],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02050031,0.00023209708,0.00058820966,0.00014898591,0.00035453244,0.00012643158,0.0016030088,0.000408734,0.00031119597],"category_scores_gemma":[0.07837649,0.00016910565,0.00007579942,0.00066862785,0.0005215381,0.00019430974,0.0021264441,0.0013835432,0.00011738268],"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":[0.00020651084,0.000334794,0.00039407948,0.00003054328,0.00014085678,0.000045904573,0.0053633023,0.000068651105,0.0010506081,0.6229985,0.0240324,0.34533387],"study_design_scores_gemma":[0.0003210211,0.0002976872,0.00048594884,0.000034701457,0.000021213013,0.000002094724,0.0018967931,0.11991829,0.000063479536,0.8747186,0.0020507588,0.00018939421],"about_ca_topic_score_codex":0.00027178944,"about_ca_topic_score_gemma":0.0000072218654,"teacher_disagreement_score":0.34514448,"about_ca_system_score_codex":0.00012571375,"about_ca_system_score_gemma":0.00025840907,"threshold_uncertainty_score":0.92938673},"labels":[],"label_agreement":null},{"id":"W2321084336","doi":"10.1177/0049124114547769","title":"What You Can—and Can’t—Do With Three-Wave Panel Data","year":2014,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Social Capital and Networks","field":"Social Sciences","cited_by":310,"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":"Econometrics; Context (archaeology); Panel data; Sign (mathematics); Computer science; Simple (philosophy); Constant (computer programming); Specification; Point (geometry); Statistics; Mathematics; Epistemology","score_opus":0.6132883582648904,"score_gpt":0.5563295464419532,"score_spread":0.05695881182293716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2321084336","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":[0.85848045,0.014479183,0.010468705,0.06355425,0.0015619928,0.0020123448,0.00006123333,0.00037587213,0.049005948],"genre_scores_gemma":[0.95671254,0.005232874,0.032883316,0.0007958942,0.0024276774,0.000098486074,0.000035494366,0.00003062696,0.0017830918],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9893209,0.00772464,0.00020124324,0.00076635927,0.000892899,0.0010940069],"domain_scores_gemma":[0.992265,0.006396141,0.000060790007,0.00056668924,0.00027535533,0.00043604148],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.02231402,0.00017014885,0.00037510865,0.000057195983,0.0016804298,0.00041686854,0.0009112635,0.0004992129,0.00029311623],"category_scores_gemma":[0.003987598,0.00011276748,0.00005352653,0.00050803495,0.004274178,0.0002738815,0.00086319377,0.0011966982,0.00001862889],"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":[0.000098503515,0.00007477128,0.0061354474,0.000017909833,0.000061239145,0.000019706642,0.03957069,9.634168e-7,0.00010170785,0.11408757,0.0019659533,0.83786553],"study_design_scores_gemma":[0.0006008926,0.0008233636,0.025173659,0.00007651342,0.00003516974,0.0000042347265,0.14494528,0.00039216224,0.00003576189,0.7288708,0.098481156,0.00056098786],"about_ca_topic_score_codex":0.0033552288,"about_ca_topic_score_gemma":0.003557648,"teacher_disagreement_score":0.83730453,"about_ca_system_score_codex":0.00012562191,"about_ca_system_score_gemma":0.00025984333,"threshold_uncertainty_score":0.99961925},"labels":[],"label_agreement":null},{"id":"W2478027989","doi":"10.1177/0049124116661575","title":"A Novel Sequential Mixed-method Technique for Contrastive Analysis of Unscripted Qualitative Data","year":2016,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroDevNet; University of British Columbia","funders":"","keywords":"Computer science; Multimethodology; Qualitative research; Qualitative property; Subject (documents); Data science; Contrastive analysis; Psychology; Linguistics; Mathematics education; Machine learning; Sociology; World Wide Web; Social science","score_opus":0.6465089207335274,"score_gpt":0.6967122529922157,"score_spread":0.05020333225868834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2478027989","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":[0.0019721375,0.00015372748,0.99175954,0.0029531189,0.00010928894,0.00087108056,0.0006754445,0.0000485827,0.0014570943],"genre_scores_gemma":[0.11243539,0.00005246648,0.8862245,0.000047054546,0.00019514973,0.00028513328,0.000084900166,0.000010982404,0.00066442334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9632133,0.033583157,0.0006545266,0.0008738209,0.00095182395,0.0007233442],"domain_scores_gemma":[0.9201405,0.07688267,0.0002694574,0.0005154745,0.0019756525,0.0002162404],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10591135,0.00017504196,0.0009059802,0.000688202,0.00069333194,0.00004309599,0.0013265826,0.00039011412,0.00052542874],"category_scores_gemma":[0.044249263,0.000109239736,0.0005027043,0.0032329005,0.002637985,0.0001893729,0.00054334215,0.00038293682,0.0000043539885],"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":[0.00030044778,0.00032715374,0.00033130276,0.000018991199,0.00279425,0.0000016538195,0.015638363,0.000017386155,0.3173119,0.42768604,0.00039594114,0.23517658],"study_design_scores_gemma":[0.0012439876,0.0004673033,0.0071199727,0.000051888306,0.001369287,6.8556994e-7,0.048765067,0.0045362907,0.011281219,0.90904945,0.015589257,0.000525572],"about_ca_topic_score_codex":0.0015442993,"about_ca_topic_score_gemma":0.00024835294,"teacher_disagreement_score":0.48136345,"about_ca_system_score_codex":0.00022043541,"about_ca_system_score_gemma":0.0004968577,"threshold_uncertainty_score":0.9719766},"labels":[],"label_agreement":null},{"id":"W2604981585","doi":"10.1177/0049124117701484","title":"The Relationship Between the Position of Name Generator Questions and Responsiveness in Multiple Name Generator Surveys","year":2017,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University; Public Health Ontario; University of Toronto","funders":"","keywords":"Satisficing; Psychology; Social psychology; Generator (circuit theory); Position (finance); Computer science; Artificial intelligence; Business; Power (physics)","score_opus":0.7044616437765651,"score_gpt":0.6221866481149423,"score_spread":0.08227499566162277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604981585","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":[0.97899604,0.0017470635,0.005436053,0.012717576,0.00021791682,0.00053278403,0.000035700137,0.000021137463,0.00029571162],"genre_scores_gemma":[0.97736233,0.00042328285,0.021389667,0.000045043562,0.00030461757,0.00013943632,0.0000057975467,0.000009598068,0.0003202427],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6219745,0.3761705,0.00039606667,0.0003859111,0.0004688529,0.0006041295],"domain_scores_gemma":[0.688298,0.31041834,0.00016581142,0.0005498359,0.00044150004,0.00012654415],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.39025435,0.00012225694,0.00031348204,0.00010694266,0.008066752,0.00016973758,0.0009285556,0.0005423613,0.000026480293],"category_scores_gemma":[0.4274241,0.00007202711,0.00009053825,0.0003157298,0.0073608966,0.00014770213,0.00033125424,0.0012401184,0.000010453964],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005804388,0.000031543426,0.94038326,0.000004644956,0.000021537511,0.000005052254,0.0033666492,0.0000021857759,0.001999846,0.030061921,0.000060019778,0.023482906],"study_design_scores_gemma":[0.0002114497,0.00009100027,0.92032504,0.000013473604,0.0000065821946,6.629836e-7,0.0021025205,0.000021156531,0.000431026,0.07513746,0.001575083,0.000084538086],"about_ca_topic_score_codex":0.0023266654,"about_ca_topic_score_gemma":0.0010491523,"teacher_disagreement_score":0.066323414,"about_ca_system_score_codex":0.00012307173,"about_ca_system_score_gemma":0.00045808926,"threshold_uncertainty_score":0.9953405},"labels":[],"label_agreement":null},{"id":"W2616014493","doi":"10.1177/0049124117747304","title":"Generalization of Classic Question Order Effects Across Cultures","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":26,"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 Saskatchewan","funders":"Economic and Social Research Council; Danmarks Frie Forskningsfond","keywords":"Contrast (vision); Norm (philosophy); Order (exchange); Generalization; Perception; Context (archaeology); Social psychology; Psychology; Positive economics; Political science; Geography; Epistemology; Economics; Law; Computer science; Philosophy","score_opus":0.2567032230430472,"score_gpt":0.6683574336594847,"score_spread":0.41165421061643753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616014493","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":[0.8986949,0.00065485254,0.04328748,0.0040665492,0.0014561688,0.0006128932,0.000004011331,0.00013736151,0.051085796],"genre_scores_gemma":[0.94725883,0.00035712114,0.047549207,0.00040494927,0.0021490797,0.00008160317,0.0000060958487,0.000011232113,0.0021818916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9852867,0.013071651,0.00022841216,0.00032851216,0.00045458128,0.0006301574],"domain_scores_gemma":[0.99660254,0.0019456242,0.00007866219,0.00015723545,0.0010971796,0.0001187402],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.011864956,0.00009241389,0.00024286275,0.000054433054,0.0010523783,0.000040362407,0.00039178107,0.0005607883,0.00043684963],"category_scores_gemma":[0.009328505,0.000066636865,0.00008964222,0.0008194772,0.00488616,0.00008971724,0.00012917214,0.0004368521,0.000078935525],"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":[0.00014594189,0.00027270583,0.011677848,0.000035041372,0.000058777274,0.0000033076972,0.07324263,6.2966006e-7,0.10613496,0.5740595,0.009731855,0.22463681],"study_design_scores_gemma":[0.0006847407,0.0019849564,0.11751028,0.000058596088,0.000014432359,0.0000010295986,0.020564485,0.00006922128,0.013307392,0.6982426,0.14721619,0.00034610985],"about_ca_topic_score_codex":0.0011725591,"about_ca_topic_score_gemma":0.00021330795,"teacher_disagreement_score":0.2242907,"about_ca_system_score_codex":0.000119288896,"about_ca_system_score_gemma":0.00008455942,"threshold_uncertainty_score":0.99901634},"labels":[],"label_agreement":null},{"id":"W2761888982","doi":"10.1177/0049124117729709","title":"Power Law Distributions and the Size Distribution of Strikes","year":2017,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Labor Movements and Unions","field":"Social Sciences","cited_by":8,"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":"Log-normal distribution; Econometrics; Distribution (mathematics); Power law; Statistics; Power (physics); Perspective (graphical); Pareto distribution; Duration (music); Law; Economics; Mathematics; Political science; Physics","score_opus":0.17155189800997964,"score_gpt":0.5483748844190327,"score_spread":0.3768229864090531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2761888982","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":[0.80392736,0.000974579,0.0076289102,0.059396278,0.00034881066,0.001073294,0.00043428544,0.000054712455,0.12616177],"genre_scores_gemma":[0.9965387,0.00033954272,0.002278716,0.00007534583,0.000095174946,0.000037061855,0.0000059058416,0.0000026190962,0.0006269275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939556,0.0048639295,0.00017174544,0.00019362844,0.00040786806,0.0004072249],"domain_scores_gemma":[0.9926074,0.00646951,0.00009352659,0.00035692152,0.00036219982,0.0001104485],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.016360067,0.00006436038,0.00019300326,0.0000068911636,0.0051966533,0.00017823534,0.00058485055,0.00016942817,0.00031303213],"category_scores_gemma":[0.018152481,0.00003470415,0.000084157145,0.00011425907,0.012119811,0.000108995,0.00035703313,0.0004389115,0.0000014837384],"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":[0.00002725402,0.000040621686,0.0013442903,0.0000011876837,0.000015368856,5.289907e-7,0.0010597565,3.0149e-8,0.00025006878,0.99227875,0.00029697022,0.004685145],"study_design_scores_gemma":[0.00047350305,0.00006843267,0.30929548,0.000007029201,0.000008372969,1.0993519e-7,0.004510638,0.0000028118998,0.0002334874,0.57969534,0.10564342,0.00006140162],"about_ca_topic_score_codex":0.0046750945,"about_ca_topic_score_gemma":0.00020412946,"teacher_disagreement_score":0.41258344,"about_ca_system_score_codex":0.00006123839,"about_ca_system_score_gemma":0.00008508649,"threshold_uncertainty_score":0.99609846},"labels":[],"label_agreement":null},{"id":"W2792032639","doi":"10.1177/0049124117747302","title":"Optimizing Count Responses in Surveys: A Machine-learning Approach","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":21,"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 British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Science Research Institute, Duke University; University of British Columbia; University of Victoria","keywords":"Censoring (clinical trials); Count data; Poisson distribution; Computer science; Bayesian probability; Multinomial distribution; Machine learning; Statistics; Artificial intelligence; Mathematics","score_opus":0.6338353326777821,"score_gpt":0.602291176727981,"score_spread":0.03154415594980109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792032639","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":[0.19575998,0.0003434719,0.79350626,0.00023082449,0.0000624135,0.0004630191,0.000006438911,0.00048409708,0.00914351],"genre_scores_gemma":[0.29747367,0.000060406735,0.7017583,0.000028371454,0.00010914597,0.00013041636,0.000007948908,0.000024339937,0.00040737068],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.955602,0.042007882,0.0004989511,0.0005541374,0.0005520859,0.0007849384],"domain_scores_gemma":[0.9716456,0.027256982,0.00009520695,0.00038746858,0.00049443875,0.00012028948],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12610207,0.00019043575,0.00046569746,0.00037454374,0.0005024675,0.000088796594,0.00048569744,0.00041304764,0.00020646631],"category_scores_gemma":[0.05589541,0.00014306883,0.00009891347,0.0008085016,0.00096951704,0.00008159902,0.00033174438,0.0017724081,0.000040223058],"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":[0.0023551988,0.003171595,0.1410369,0.00089714397,0.00031042125,0.00011024253,0.05720783,0.00020737234,0.031108595,0.20610315,0.004343772,0.5531478],"study_design_scores_gemma":[0.00076911156,0.0013090593,0.018691719,0.00014791159,0.000011174621,0.000020388588,0.003937999,0.043733716,0.0060923067,0.92147225,0.003159029,0.00065532705],"about_ca_topic_score_codex":0.00028107114,"about_ca_topic_score_gemma":0.000011587739,"teacher_disagreement_score":0.7153691,"about_ca_system_score_codex":0.00019163101,"about_ca_system_score_gemma":0.00009760294,"threshold_uncertainty_score":0.9520572},"labels":[],"label_agreement":null},{"id":"W2801448578","doi":"10.1177/0049124118769089","title":"Figure It Out!","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Management and Organizational Studies","field":"Business, Management and Accounting","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 Toronto","funders":"","keywords":"Creativity; Value (mathematics); Epistemology; Sociology; Visualization; Domain (mathematical analysis); Computer science; Visual reasoning; Cognitive science; Psychology; Artificial intelligence; Social psychology; Mathematics","score_opus":0.33708040067142014,"score_gpt":0.5101817443061937,"score_spread":0.17310134363477353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801448578","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014389439,0.0004919302,0.027031379,0.02841988,0.0008163593,0.0005503927,0.000001248734,0.0003008342,0.92799854],"genre_scores_gemma":[0.8370198,0.00016641479,0.08955909,0.014904811,0.018532544,0.00013575752,0.000041477284,0.00006261902,0.03957746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980738,0.00027215332,0.00020844415,0.00039520813,0.00048811318,0.0005622674],"domain_scores_gemma":[0.99835396,0.00063940027,0.000057943493,0.00021207568,0.0007183462,0.000018284358],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0056798407,0.00013814172,0.00020918995,0.00017909145,0.0009839782,0.00020289695,0.000494035,0.0001427453,0.010466279],"category_scores_gemma":[0.0032464364,0.000097279466,0.000074655865,0.00075493386,0.00081800064,0.00024945388,0.0009951572,0.00038158652,0.0067849886],"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":[0.00005140354,0.000116446856,0.023065975,0.00008947282,0.00007994008,0.000010172657,0.00037315744,6.2997026e-7,0.0010527432,0.49469012,0.44184482,0.03862511],"study_design_scores_gemma":[0.00015021767,0.000035789035,0.018859817,0.00000927876,0.000010577258,8.597146e-8,0.00096770097,0.00014707,0.00007692689,0.26158792,0.7180133,0.00014136606],"about_ca_topic_score_codex":0.000049956558,"about_ca_topic_score_gemma":0.000016574442,"teacher_disagreement_score":0.88842106,"about_ca_system_score_codex":0.00003759898,"about_ca_system_score_gemma":0.000012223584,"threshold_uncertainty_score":0.99398834},"labels":[],"label_agreement":null},{"id":"W2802314382","doi":"10.1177/0049124118769087","title":"Regression-based Adjustment for Time-varying Confounders","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":35,"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":"Marginal structural model; Econometrics; Estimator; Inverse probability; Regression; Average treatment effect; Statistics; Propensity score matching; Matching (statistics); Regression analysis; Computer science; Conditional expectation; Observational study; Outcome (game theory); Confounding; Estimation; Mathematics; Economics; Bayesian probability","score_opus":0.6894510924192692,"score_gpt":0.6691776798557132,"score_spread":0.02027341256355597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802314382","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":[0.0045693624,0.00016351555,0.9798696,0.0013019772,0.000120046934,0.0014715707,0.0000105119425,0.000532043,0.011961352],"genre_scores_gemma":[0.031138452,0.000021047843,0.9663354,0.00036224254,0.00041331432,0.0007049002,0.000009226991,0.000038133116,0.0009772744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947033,0.0029645322,0.000390741,0.00055025064,0.0004974925,0.0008936751],"domain_scores_gemma":[0.9737692,0.02452296,0.00011739842,0.0005431314,0.0008627854,0.00018450714],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011814191,0.00022109419,0.00046134493,0.00014593122,0.00056135457,0.00003757104,0.0005285004,0.00043286395,0.0011196815],"category_scores_gemma":[0.017558932,0.00014713235,0.00017021562,0.0002951738,0.0018173736,0.00007463795,0.00023751312,0.0007416842,0.000097134085],"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":[0.0005713783,0.0004225386,0.00007951002,0.00021529866,0.000091709866,0.000008418156,0.0009364871,0.0000017881388,0.16948475,0.56532615,0.02650374,0.23635821],"study_design_scores_gemma":[0.00035614692,0.001115901,0.00002712683,0.00008066962,0.000011006682,0.0000010587625,0.00038557602,0.0021944756,0.055565476,0.93608606,0.003984477,0.00019202329],"about_ca_topic_score_codex":0.000005698633,"about_ca_topic_score_gemma":5.8692063e-7,"teacher_disagreement_score":0.37075987,"about_ca_system_score_codex":0.000305177,"about_ca_system_score_gemma":0.00016900866,"threshold_uncertainty_score":0.9997934},"labels":[],"label_agreement":null},{"id":"W2812371591","doi":"10.1177/0049124118782554","title":"Perceived Corruption, Trust, and Interviewer Behavior in 26 European Countries","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Corruption and Economic Development","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Interview; European Social Survey; Deviance (statistics); Language change; Psychology; Social psychology; Survey research; Variation (astronomy); Criminology; Political science; Applied psychology; Statistics; Law","score_opus":0.32786452904723834,"score_gpt":0.5547942230466409,"score_spread":0.2269296939994026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2812371591","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":[0.9317585,0.00018879608,0.00057929126,0.0026864232,0.00036232136,0.0003787627,0.0000019416614,0.000080024656,0.06396391],"genre_scores_gemma":[0.97698665,0.0011849927,0.016195256,0.00048838777,0.0004146308,0.000075931566,0.0000017294345,0.000013453514,0.004638945],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99184626,0.0067217643,0.00028582328,0.0003681619,0.0002406004,0.00053738995],"domain_scores_gemma":[0.998491,0.00088376756,0.00003901168,0.0001367404,0.00027081592,0.00017869612],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021357613,0.00009374983,0.0002046472,0.00014047301,0.0007302239,0.00011905324,0.0003027518,0.00014959334,0.004201103],"category_scores_gemma":[0.0019016853,0.000077325625,0.00004487544,0.00022554405,0.0027515567,0.00010318457,0.0002679275,0.0004463684,0.00069180183],"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":[0.000090802576,0.00013977714,0.1763524,0.0000129701675,0.00001188047,0.00002058082,0.08352716,7.6515896e-8,0.0008607612,0.023269922,0.0009448089,0.7147689],"study_design_scores_gemma":[0.00021250651,0.00013489305,0.7489058,0.000014452202,0.0000025081074,0.000001173951,0.019772235,0.000016024173,0.0000071297272,0.0027580254,0.22805399,0.000121281104],"about_ca_topic_score_codex":0.00034356312,"about_ca_topic_score_gemma":0.0003548815,"teacher_disagreement_score":0.7146476,"about_ca_system_score_codex":0.00027951263,"about_ca_system_score_gemma":0.0001302163,"threshold_uncertainty_score":0.9999624},"labels":[],"label_agreement":null},{"id":"W2887293044","doi":"10.1177/0049124118789717","title":"A Note on a Reformulation of the KHB Method","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":106,"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":"Logit; Probit; Statistics; Mathematics; Probit model; Logistic regression; Econometrics; Residual; Confounding; Variance (accounting); Constant (computer programming); Conditional probability; Conditional logistic regression; Computer science; Economics; Algorithm","score_opus":0.40826412402656087,"score_gpt":0.5321633408856649,"score_spread":0.12389921685910399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887293044","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":[0.20738266,0.0006051449,0.6651391,0.0070701833,0.00060067535,0.00070806924,0.00023407553,0.000053707845,0.11820639],"genre_scores_gemma":[0.81180984,0.000053539545,0.18674795,0.00029829092,0.00031818965,0.000028262919,0.000007669121,0.000009565025,0.00072670507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99733174,0.0014006875,0.00044050833,0.00038469466,0.00011114292,0.0003312538],"domain_scores_gemma":[0.997301,0.0017566025,0.00017839715,0.0005514798,0.00015351515,0.00005904236],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01265113,0.00009061189,0.000356738,0.00017133278,0.00029849508,0.00002203395,0.0005363959,0.00021992125,0.0010656166],"category_scores_gemma":[0.004032522,0.000055336463,0.00021104173,0.00078689936,0.0005223538,0.000052023417,0.00025143276,0.0004841624,0.00037729114],"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":[0.00016177392,0.00017435377,0.01716466,0.000024541008,0.00011052036,9.761611e-7,0.0019314038,0.000027973314,0.0041612745,0.79403675,0.00071447983,0.18149129],"study_design_scores_gemma":[0.0002441233,0.00051915355,0.10907685,0.00001295048,0.0000075475873,7.2129694e-7,0.00014336531,0.0075805476,0.0046131457,0.8458377,0.03182149,0.00014241316],"about_ca_topic_score_codex":0.000584391,"about_ca_topic_score_gemma":0.000013763239,"teacher_disagreement_score":0.60442716,"about_ca_system_score_codex":0.00008692563,"about_ca_system_score_gemma":0.000020929974,"threshold_uncertainty_score":0.99984753},"labels":[],"label_agreement":null},{"id":"W2888408547","doi":"10.1177/0049124118782550","title":"Analyzing Heaped Counts Versus Longitudinal Presence/Absence Data in Joint Zero-inflated Discrete Regression Models","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Count data; Statistics; Outcome (game theory); Event (particle physics); Regression analysis; Event data; Econometrics; Mathematics; Rounding; Psychology; Computer science; Covariate","score_opus":0.6965302466042542,"score_gpt":0.6410708432010603,"score_spread":0.055459403403193885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888408547","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":[0.6023011,0.0024477732,0.19657429,0.007690695,0.0022565203,0.0014238318,0.00010594375,0.00026984696,0.18692996],"genre_scores_gemma":[0.979512,0.00037101115,0.018394308,0.000013838138,0.00036336668,0.000021701202,0.00001997429,0.000008187769,0.0012956522],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99399334,0.0039505786,0.00030035,0.00054486387,0.00056275696,0.00064810604],"domain_scores_gemma":[0.99754614,0.0014068541,0.00006392527,0.00053750305,0.00029023548,0.0001553255],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013057266,0.000104422455,0.00022980956,0.00013809647,0.0007396097,0.000109617016,0.00089661643,0.00022739923,0.0029507142],"category_scores_gemma":[0.003990226,0.000075585995,0.000082614555,0.0006082889,0.0016999595,0.00030805808,0.0007820885,0.0007125792,0.00020721625],"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":[0.0020238827,0.0012323816,0.10286548,0.00018120224,0.000412793,0.00022239985,0.03976082,0.000078985715,0.021044012,0.2167147,0.11462692,0.50083643],"study_design_scores_gemma":[0.0034304622,0.0022235417,0.11105936,0.0015001965,0.00008120243,0.000004456895,0.028232582,0.101634875,0.0014170102,0.66761243,0.081047796,0.0017560883],"about_ca_topic_score_codex":0.0025428592,"about_ca_topic_score_gemma":0.00035881778,"teacher_disagreement_score":0.49908033,"about_ca_system_score_codex":0.0001648366,"about_ca_system_score_gemma":0.00013171531,"threshold_uncertainty_score":0.99796075},"labels":[],"label_agreement":null},{"id":"W2983060199","doi":"10.1177/0049124119882460","title":"The Double Bind of Qualitative Comparative Analysis","year":2019,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Qualitative comparative analysis; Computer science; Theoretical computer science; Simple (philosophy); Set (abstract data type); Algorithm; Face (sociological concept); Data mining; Machine learning; Epistemology","score_opus":0.817819447521365,"score_gpt":0.7678292769503934,"score_spread":0.04999017057097166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983060199","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":[0.67637205,0.0021222504,0.013630902,0.0050372356,0.00010990434,0.0015892916,0.000019035166,0.000047284128,0.30107206],"genre_scores_gemma":[0.9708741,0.00025667113,0.014309443,0.0000287615,0.000084063635,0.00014943651,0.000009016269,0.000006794085,0.014281761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9029754,0.09248542,0.0006479234,0.00061451487,0.0021874127,0.0010893623],"domain_scores_gemma":[0.9233207,0.07258976,0.0002446271,0.000585356,0.0030042918,0.00025523934],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.10911055,0.00018577732,0.0009920532,0.0005561821,0.0019391294,0.00015959988,0.0015174133,0.0002565034,0.003713286],"category_scores_gemma":[0.005873456,0.00011065844,0.00059988233,0.0069294013,0.008999777,0.00017874998,0.0004267094,0.0013577584,0.00078681874],"study_design_candidate":"qualitative","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":[0.0003107965,0.0001339551,0.0034845248,0.000009200758,0.0014937572,7.9503565e-7,0.31384626,0.00003425766,0.0036852513,0.6738952,0.0010933257,0.0020126791],"study_design_scores_gemma":[0.00047183913,0.00041406485,0.008871319,0.00000852902,0.000084702406,4.1634042e-8,0.7779014,0.00043869807,0.0020346055,0.17034665,0.03921575,0.0002124106],"about_ca_topic_score_codex":0.002303633,"about_ca_topic_score_gemma":0.0006803283,"teacher_disagreement_score":0.50354856,"about_ca_system_score_codex":0.00031816927,"about_ca_system_score_gemma":0.0004900111,"threshold_uncertainty_score":0.9999912},"labels":[],"label_agreement":null},{"id":"W3015404063","doi":"10.1177/0049124120914943","title":"Clustered Iconography: A Resurrected Method for Representing Multidimensional Data","year":2020,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Data Visualization and Analytics","field":"Computer Science","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":"Université Laval","funders":"","keywords":"Iconography; Computer science; Presentation (obstetrics); Data science; Data mining; Information retrieval; History; Archaeology","score_opus":0.6367181529069946,"score_gpt":0.6249219023411513,"score_spread":0.011796250565843325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015404063","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":[0.00023137352,0.00020126255,0.98632205,0.011848016,0.00012911388,0.00049066066,0.00008477137,0.00024323497,0.00044952147],"genre_scores_gemma":[0.0022750753,0.00004265511,0.99525154,0.0017964379,0.00025846553,0.000043749515,0.00022774166,0.000013711651,0.00009061486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98989314,0.0069725006,0.0004831241,0.0013642574,0.0005862136,0.0007007418],"domain_scores_gemma":[0.9876876,0.009837075,0.00012162229,0.0013655981,0.00061563135,0.00037250615],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018057846,0.00016495664,0.00038640457,0.00015315197,0.00052510476,0.00021764888,0.0030075568,0.00021204921,0.000060538518],"category_scores_gemma":[0.020270584,0.00012855881,0.00014762889,0.001437656,0.00027843053,0.00038629002,0.0043074153,0.0006933763,0.000029478266],"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":[0.00024631494,0.00038904708,0.0012358732,0.00017156408,0.00029742677,0.000036026802,0.0032213018,0.0001298546,0.040636647,0.35364455,0.07466406,0.5253273],"study_design_scores_gemma":[0.0005248138,0.00017493904,0.00035275795,0.00001108688,0.000008307138,0.0000022375707,0.00034024692,0.90927166,0.0010210808,0.02217655,0.06593434,0.00018197796],"about_ca_topic_score_codex":0.000023030243,"about_ca_topic_score_gemma":8.182879e-7,"teacher_disagreement_score":0.9091418,"about_ca_system_score_codex":0.000024320052,"about_ca_system_score_gemma":0.00014550849,"threshold_uncertainty_score":0.9879821},"labels":[],"label_agreement":null},{"id":"W3019463389","doi":"10.1177/0049124120914928","title":"Joint Modeling of Multivariate Survival Data With an Application to Retirement","year":2020,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":7,"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; University of Victoria","funders":"","keywords":"Univariate; Multivariate statistics; Proportional hazards model; Covariate; Event (particle physics); Econometrics; Survival analysis; Variety (cybernetics); Multivariate analysis; Event data; Computer science; Statistics; Actuarial science; Psychology; Mathematics; Economics","score_opus":0.5795516871879395,"score_gpt":0.581134355203404,"score_spread":0.0015826680154644723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019463389","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":[0.18028057,0.000106286745,0.7970667,0.009606573,0.00009357703,0.0021831216,0.000036358568,0.00015172451,0.010475075],"genre_scores_gemma":[0.72606874,0.00008010024,0.27328703,0.0001864027,0.0002237057,0.00010290755,0.000022939605,0.000012021862,0.000016194672],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98843205,0.008207172,0.0004181201,0.00089341326,0.0013828491,0.0006664013],"domain_scores_gemma":[0.997551,0.00060069247,0.0000961207,0.00082151487,0.0005376913,0.00039297677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027042333,0.00014004385,0.00037660424,0.000099755016,0.0005922476,0.00006537624,0.0014490015,0.00016474676,0.000067167806],"category_scores_gemma":[0.0022966443,0.00010593753,0.000062536805,0.0010072134,0.0007894181,0.00017901453,0.00086704746,0.0005603202,0.000019461158],"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":[0.0013229955,0.0012024747,0.034213945,0.000286663,0.0003816758,0.000022221393,0.063952856,0.008891698,0.01983483,0.5621394,0.00046572724,0.30728552],"study_design_scores_gemma":[0.0020807893,0.0044769696,0.08986247,0.00011825208,0.00014176639,2.8540285e-7,0.11489561,0.5850684,0.0008669573,0.16703154,0.033888437,0.0015685454],"about_ca_topic_score_codex":0.0040083737,"about_ca_topic_score_gemma":0.00028882455,"teacher_disagreement_score":0.5761767,"about_ca_system_score_codex":0.00009473405,"about_ca_system_score_gemma":0.0001322211,"threshold_uncertainty_score":0.9372387},"labels":[],"label_agreement":null},{"id":"W3128078314","doi":"10.1177/0049124120986197","title":"Mobilizing the Masses: Measuring Resource Mobilization on Twitter","year":2021,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Social Media and Politics","field":"Social Sciences","cited_by":23,"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":"Measure (data warehouse); Social media; Social movement; Resource mobilization; Resource (disambiguation); Computer science; Frame (networking); Simple (philosophy); Point (geometry); Parsing; Movement (music); Lexicon; Variation (astronomy); Data science; Artificial intelligence; Political science; World Wide Web; Data mining; Mathematics; Epistemology; Politics","score_opus":0.5893974947116389,"score_gpt":0.6022507172952619,"score_spread":0.01285322258362298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128078314","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":[0.7129616,0.0014950226,0.0035236662,0.03562195,0.0008214168,0.0009166043,0.000003786917,0.0002283177,0.24442764],"genre_scores_gemma":[0.97299385,0.0005882807,0.016531108,0.002628029,0.002794693,0.00024382197,0.0000064746105,0.000024620087,0.0041891322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9748581,0.02256453,0.00023239944,0.00040119688,0.0010586584,0.00088512496],"domain_scores_gemma":[0.9815963,0.017313987,0.000046623638,0.0003485104,0.00048399766,0.00021058808],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.014766907,0.000114524635,0.00021732818,0.000060557628,0.0021796012,0.00016629536,0.0005056837,0.00037713273,0.0004521982],"category_scores_gemma":[0.025643988,0.0000763829,0.0001442517,0.0008286788,0.0017635723,0.000056662517,0.00020491643,0.0012153974,0.00009218196],"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":[0.000056673427,0.00036343065,0.027003648,0.00004974925,0.000097453536,0.000076156444,0.19266278,0.000047798378,0.014894969,0.60756063,0.008946981,0.14823973],"study_design_scores_gemma":[0.00016996307,0.000096440875,0.0027009821,0.00003225138,0.00001275393,0.0000010899935,0.2981441,0.000038060232,0.004895115,0.18988952,0.50383544,0.00018426152],"about_ca_topic_score_codex":0.00033392967,"about_ca_topic_score_gemma":0.0000376287,"teacher_disagreement_score":0.49488848,"about_ca_system_score_codex":0.00030579336,"about_ca_system_score_gemma":0.00040896743,"threshold_uncertainty_score":0.9991194},"labels":[],"label_agreement":null},{"id":"W3129011248","doi":"10.1177/0049124120986192","title":"A New Methodological Approach to Study Household Structure From Census and Survey Data","year":2021,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Quebec Statistical Institute; Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Census; Indigenous; Representation (politics); Survey data collection; Current Population Survey; Population; Survey methodology; Yield (engineering); Econometrics; Geography; Computer science; Regional science; Data science; Sociology; Statistics; Demography; Mathematics; Political science","score_opus":0.890380508101297,"score_gpt":0.6410469044849224,"score_spread":0.24933360361637458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129011248","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":[0.79886997,0.008656938,0.16744906,0.005949946,0.00071327126,0.0024477537,0.0016622372,0.00036015688,0.013890668],"genre_scores_gemma":[0.37507504,0.00038910625,0.6225163,0.00030356122,0.00067432,0.000031769196,0.00014431946,0.00001672007,0.00084890315],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9357049,0.06048596,0.00039095734,0.0014443314,0.0011022115,0.00087162707],"domain_scores_gemma":[0.96769744,0.03019846,0.0000670401,0.0009150414,0.0005130693,0.0006089697],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034585077,0.00023041708,0.000743956,0.00009018412,0.0016064236,0.00027461626,0.0012479526,0.00047326487,0.0003878521],"category_scores_gemma":[0.054720353,0.00016275971,0.00006686906,0.0010851714,0.00079908123,0.00012467672,0.0024169036,0.0012426419,0.000008391694],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046755918,0.001332297,0.43460906,0.000018530198,0.00083104457,0.00011347822,0.121246465,0.000010838556,0.0019046268,0.02021255,0.030753514,0.38850003],"study_design_scores_gemma":[0.00070006936,0.0002865646,0.8073251,0.0000057617713,0.000045583558,0.0000017443227,0.07940107,0.00004553475,0.00007943878,0.08854928,0.023174433,0.00038538055],"about_ca_topic_score_codex":0.011945785,"about_ca_topic_score_gemma":0.0015209384,"teacher_disagreement_score":0.45506722,"about_ca_system_score_codex":0.00009197401,"about_ca_system_score_gemma":0.0003624587,"threshold_uncertainty_score":0.99969333},"labels":[],"label_agreement":null},{"id":"W3134225231","doi":"10.1177/0049124121995548","title":"Marginal and Conditional Confounding Using Logits","year":2021,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"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":"Medical Research Council; Chief Scientist Office","keywords":"Confounding; Statistics; Weighting; Econometrics; Marginal structural model; Conditional probability; Odds; Conditional probability distribution; Logistic regression; Marginal model; Inverse probability weighting; Conditional logistic regression; Mathematics; Odds ratio; Regression analysis; Medicine; Propensity score matching","score_opus":0.8690128158201307,"score_gpt":0.7315306657257828,"score_spread":0.13748215009434783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134225231","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":[0.20627204,0.0004887863,0.78647,0.00055852596,0.00005303602,0.00023699708,0.000012052937,0.00017405864,0.005734492],"genre_scores_gemma":[0.1845722,0.00009555203,0.81478536,0.000098816294,0.000118162454,0.000036372414,0.000007736904,0.0000138577925,0.00027193932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948002,0.0035674565,0.00026615692,0.00041605675,0.000400684,0.0005494551],"domain_scores_gemma":[0.98743176,0.011598381,0.00005992096,0.00022680013,0.0005403337,0.00014280928],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070893536,0.00013793563,0.00033994686,0.000087023385,0.00038790566,0.00006904678,0.00016916257,0.00028471297,0.00080981303],"category_scores_gemma":[0.013113068,0.000111409834,0.00006428956,0.00028051916,0.0011454541,0.000111733105,0.0004275862,0.0010176664,0.000009722043],"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":[0.000014428733,0.00005191367,0.0006259979,0.000045750505,0.000022683664,0.00008487861,0.00015362038,8.8925066e-7,0.09753379,0.893609,0.000193197,0.007663876],"study_design_scores_gemma":[0.00013281239,0.000091503636,0.0007499135,0.00003283257,0.000007778885,0.0000781013,0.0009300018,0.0002863266,0.01638613,0.9802098,0.00096097396,0.0001337968],"about_ca_topic_score_codex":0.000005017172,"about_ca_topic_score_gemma":6.888489e-7,"teacher_disagreement_score":0.086600855,"about_ca_system_score_codex":0.00016305565,"about_ca_system_score_gemma":0.00014874061,"threshold_uncertainty_score":0.9951999},"labels":[],"label_agreement":null},{"id":"W4200319388","doi":"10.1177/00491241211067514","title":"And the Rest is History: Measuring the Scope and Recall of Wikipedia’s Coverage of Three Women’s Movement Subgroups","year":2021,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Wikis in Education and Collaboration","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":"University of British Columbia","funders":"","keywords":"Scope (computer science); Recall; Typology; Phrase; Operationalization; Movement (music); Comparative historical research; Categorical variable; Historical method; Computer science; Sociology; Epistemology; History; Social science; Cognitive psychology; Psychology; Natural language processing; Aesthetics","score_opus":0.255754211112796,"score_gpt":0.4841200688200403,"score_spread":0.22836585770724427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200319388","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":[0.92203856,0.014000615,0.0009078642,0.02963176,0.00030125974,0.0005729905,0.000004854327,0.0000123789405,0.032529727],"genre_scores_gemma":[0.9822295,0.009874401,0.005171175,0.00080275175,0.00021462947,0.0001554965,8.535842e-7,0.000006026582,0.0015452189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9908415,0.007806871,0.00023692736,0.00022722849,0.0006126388,0.00027480413],"domain_scores_gemma":[0.9942461,0.00466725,0.00009813537,0.00023527846,0.00067228987,0.000080938335],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.024770692,0.000064554406,0.00021552805,0.00003492921,0.00048544494,0.00004364928,0.00025540372,0.00012823654,0.0003931072],"category_scores_gemma":[0.0077271713,0.000036237314,0.000038867056,0.00034554882,0.0034090083,0.000062894185,0.00019643184,0.00037897823,0.0000011252037],"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":[0.00027243857,0.00018157817,0.010117725,0.00007287449,0.00007739195,0.0000017898634,0.21666011,0.0000018977905,0.0068706973,0.63325715,0.0030702327,0.12941608],"study_design_scores_gemma":[0.0010362077,0.00023322822,0.077940024,0.000045866513,0.000020725765,5.128904e-7,0.13584946,0.0000509246,0.002000122,0.65700275,0.12565337,0.00016680975],"about_ca_topic_score_codex":0.00078113266,"about_ca_topic_score_gemma":0.00037475405,"teacher_disagreement_score":0.12924927,"about_ca_system_score_codex":0.00031476672,"about_ca_system_score_gemma":0.00062504545,"threshold_uncertainty_score":0.99930316},"labels":[],"label_agreement":null},{"id":"W4210644525","doi":"10.1177/00491241211036165","title":"Moving Beyond Linear Regression: Implementing and Interpreting Quantile Regression Models With Fixed Effects","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":104,"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":"Quantile regression; Econometrics; Regression; Quantile; Linear regression; Fixed effects model; Regression analysis; Replication (statistics); Range (aeronautics); Wage; Statistics; Computer science; Mathematics; Economics; Panel data","score_opus":0.3809058897593379,"score_gpt":0.5984629512409576,"score_spread":0.21755706148161968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210644525","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":[0.44257948,0.0007950206,0.55120003,0.0005008477,0.00006233161,0.0011318657,0.000009315304,0.0004938741,0.0032272507],"genre_scores_gemma":[0.3745821,0.00004412289,0.62462187,0.000068726775,0.00005229179,0.0004340069,0.0000052893743,0.000035929777,0.00015567546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98928136,0.0077209286,0.00045810983,0.0007311508,0.0008288889,0.000979536],"domain_scores_gemma":[0.98264873,0.016221412,0.00023528162,0.0004894121,0.00023529456,0.00016988225],"candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014928043,0.0002802134,0.0005758141,0.00020006474,0.0015673981,0.000067668574,0.0005023113,0.00019269796,0.00022468278],"category_scores_gemma":[0.0059415344,0.00017670244,0.00008890225,0.00047411222,0.00052750256,0.0002066949,0.002793104,0.0023765753,0.000001383583],"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":[0.0008989158,0.00042153246,0.0040050256,0.0008593732,0.00014641444,0.0003021974,0.011298617,0.00008812167,0.22497724,0.44001225,0.0022310887,0.31475922],"study_design_scores_gemma":[0.00037162413,0.0012220896,0.000057930567,0.00032895122,0.000016446731,0.000029595261,0.006893532,0.012703054,0.017447684,0.96008366,0.00054190116,0.00030350257],"about_ca_topic_score_codex":0.000021524465,"about_ca_topic_score_gemma":0.0000013343637,"teacher_disagreement_score":0.52007145,"about_ca_system_score_codex":0.00021073276,"about_ca_system_score_gemma":0.000070884795,"threshold_uncertainty_score":0.99992496},"labels":[],"label_agreement":null},{"id":"W4210865241","doi":"10.1177/00491241221077238","title":"Comparing Single- and Multiple-Question Designs of Measuring Family Income in China Family Panel Studies","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Econometrics; Percentile; Economics; Contrast (vision); Quarter (Canadian coin); Demographic economics; Statistics; Mathematics; Geography; Computer science","score_opus":0.9006386086819724,"score_gpt":0.6303685016720665,"score_spread":0.27027010700990595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210865241","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":[0.9205536,0.0019802698,0.075818844,0.00010322638,0.00003650231,0.00061526155,0.0000043699074,0.00016479264,0.00072312367],"genre_scores_gemma":[0.6434115,0.00019278008,0.35617825,0.000013663696,0.000015123928,0.00015849873,0.0000011116231,0.000015285079,0.000013776609],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98836356,0.0093468465,0.0006076172,0.00046369672,0.00064235635,0.0005759034],"domain_scores_gemma":[0.98550427,0.013714969,0.00015939123,0.00030520058,0.00023583298,0.000080351376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021118358,0.00019476158,0.00076007383,0.00032128574,0.00038442106,0.000017238357,0.00038986,0.00014832028,0.000009289399],"category_scores_gemma":[0.014730973,0.0001622769,0.000069980466,0.0005489275,0.00088758604,0.00010607666,0.0013713815,0.0015892797,6.226452e-7],"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":[0.0002946616,0.00060831156,0.067915775,0.0004537399,0.00009721679,0.000044752975,0.0079374015,0.0002661641,0.7837699,0.1047085,0.00003089711,0.033872686],"study_design_scores_gemma":[0.00037142375,0.00074472826,0.07381517,0.00012297365,0.000008917817,0.00000459496,0.010566258,0.0010600998,0.007968342,0.90511626,0.000022241251,0.00019902039],"about_ca_topic_score_codex":0.000100128585,"about_ca_topic_score_gemma":0.0000060802204,"teacher_disagreement_score":0.8004077,"about_ca_system_score_codex":0.00052331114,"about_ca_system_score_gemma":0.000044801793,"threshold_uncertainty_score":0.99356836},"labels":[],"label_agreement":null},{"id":"W4290613457","doi":"10.1177/00491241221113877","title":"The Design and Optimality of Survey Counts: A Unified Framework Via the Fisher Information Maximizer","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":3,"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 British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Hong Kong Polytechnic University","keywords":"Fisher information; Range (aeronautics); Mathematics; Statistics; Generalized linear model; Computer science; Econometrics; Optimal design; Mathematical optimization","score_opus":0.6171696352915063,"score_gpt":0.5685923866874328,"score_spread":0.04857724860407342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290613457","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":[0.0052647796,0.00014321091,0.9920392,0.0008009196,0.000061339124,0.00041931352,0.000013588661,0.00005664245,0.0012010101],"genre_scores_gemma":[0.10367368,0.000100175064,0.8957006,0.000112676484,0.0000189005,0.00023647318,0.000008276874,0.000007682564,0.00014158296],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9831102,0.015926229,0.00026674007,0.00010183862,0.00039091444,0.00020409036],"domain_scores_gemma":[0.9493376,0.049991872,0.000091597496,0.0002873913,0.00026426464,0.000027299278],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.067398556,0.00006217152,0.00014334076,0.000033043514,0.00078219624,0.00004634321,0.00032662586,0.000105924315,0.00026070984],"category_scores_gemma":[0.019930165,0.00003191103,0.000036829962,0.00027556837,0.00050383684,0.000043123364,0.0002632465,0.00078289607,0.00000515025],"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":[0.0010294187,0.000255829,0.005992867,0.00014446085,0.00020369647,0.0000015187296,0.007119836,0.00022882727,0.0002001848,0.44083023,0.07579109,0.46820202],"study_design_scores_gemma":[0.00005499393,0.000104846884,0.007884416,0.0000041169037,0.0000035875873,0.000001393333,0.0005302235,0.002535113,0.00009247405,0.9843289,0.0044095484,0.000050348823],"about_ca_topic_score_codex":0.000093506715,"about_ca_topic_score_gemma":4.0657048e-7,"teacher_disagreement_score":0.5434987,"about_ca_system_score_codex":0.00004422359,"about_ca_system_score_gemma":0.00004637995,"threshold_uncertainty_score":0.98832536},"labels":[],"label_agreement":null},{"id":"W4310576792","doi":"10.1177/00491241221123088","title":"From Ends to Means: The Promise of Computational Text Analysis for Theoretically Driven Sociological Research","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":34,"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; Skepticism; Field (mathematics); Relevance (law); Management science; Set (abstract data type); Computational model; Epistemology; Selection (genetic algorithm); Computational sociology; Data science; Process (computing); Sociology; Artificial intelligence; Political science","score_opus":0.4486729254285306,"score_gpt":0.6277772920025255,"score_spread":0.17910436657399492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310576792","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":[0.24353512,0.00050645275,0.6876985,0.05424897,0.00019226187,0.0025633783,0.00028693542,0.00009804356,0.010870337],"genre_scores_gemma":[0.6546878,0.000019985118,0.34298882,0.00024397342,0.00043918326,0.0009805417,0.00007061293,0.0000113843425,0.00055765855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93320286,0.06137319,0.0006671379,0.0008738088,0.0028483437,0.0010346464],"domain_scores_gemma":[0.9047949,0.092488244,0.00013177365,0.0003849402,0.0018969461,0.00030321363],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.09616744,0.00017668767,0.000715454,0.0006165434,0.0047960556,0.00011424364,0.0019943607,0.00025163623,0.0046421383],"category_scores_gemma":[0.021668732,0.00011528106,0.0007760964,0.005022982,0.0049467115,0.00005269825,0.0013299539,0.0017230038,0.00002307089],"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":[0.00048121825,0.0004857278,0.0039580334,0.000008001253,0.0010180585,0.0000048150846,0.036669087,0.02182173,0.00097493426,0.86008596,0.0020076756,0.07248474],"study_design_scores_gemma":[0.000247517,0.00051799876,0.013072118,0.0000030617998,0.000111588844,2.1064379e-7,0.031731132,0.012150576,0.00003163528,0.9228437,0.01913661,0.00015384232],"about_ca_topic_score_codex":0.00092055264,"about_ca_topic_score_gemma":0.000051574796,"teacher_disagreement_score":0.41115272,"about_ca_system_score_codex":0.00043134406,"about_ca_system_score_gemma":0.0006834728,"threshold_uncertainty_score":0.99776125},"labels":[],"label_agreement":null},{"id":"W4380046704","doi":"10.1177/00491241231176845","title":"Lagged Dependent Variable Predictors, Classical Measurement Error, and Path Dependency: The Conditions Under Which Various Estimators are Appropriate","year":2023,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"School Choice and Performance","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Estimator; Instrumental variable; Ordinary least squares; Statistics; Mathematics; Invariant estimator; Econometrics; Efficient estimator; Standard error; Least-squares function approximation; Consistency (knowledge bases); Minimum-variance unbiased estimator","score_opus":0.28849293208312177,"score_gpt":0.5023517921103442,"score_spread":0.21385886002722243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380046704","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":[0.8685257,0.0024432798,0.029605668,0.06491447,0.0018976644,0.0034458865,0.00012505865,0.0012687511,0.027773537],"genre_scores_gemma":[0.9871559,0.00084205484,0.009377298,0.00030289317,0.0007925215,0.0004732891,0.000015468257,0.000023602925,0.0010169694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98635805,0.00937372,0.0003461216,0.00062722847,0.0021098217,0.0011850387],"domain_scores_gemma":[0.9938831,0.0044538295,0.00010150876,0.00039525473,0.00077389594,0.00039245802],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036366075,0.00019821753,0.000336986,0.00013320007,0.0035010397,0.0002580138,0.00074590766,0.0005418889,0.00043616],"category_scores_gemma":[0.009254226,0.00012493454,0.00008323254,0.0015371349,0.0014249388,0.00018935035,0.0004178656,0.0018819269,0.00016837956],"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":[0.00042570007,0.0011737855,0.30009615,0.00031388408,0.00095854123,0.0001334291,0.0500781,0.0013538917,0.009925533,0.5533727,0.052322574,0.029845698],"study_design_scores_gemma":[0.0008144919,0.00031522292,0.27271825,0.00009598324,0.00007682365,0.0000055566757,0.035398047,0.0028705623,0.00010762041,0.66530615,0.021804633,0.00048662996],"about_ca_topic_score_codex":0.00083995564,"about_ca_topic_score_gemma":0.0009292798,"teacher_disagreement_score":0.118630216,"about_ca_system_score_codex":0.0003438601,"about_ca_system_score_gemma":0.0008214232,"threshold_uncertainty_score":0.99909127},"labels":[],"label_agreement":null},{"id":"W4386245620","doi":"10.1177/00491241231192383","title":"Comparing Methods for Estimating Demographics in Racially Polarized Voting Analyses","year":2023,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Electoral Systems and Political Participation","field":"Social Sciences","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Geocoding; Voting; Turnout; Bayesian probability; Demographics; Population; Race (biology); Econometrics; Inference; Causal inference; Statistics; Geography; Demography; Computer science; Political science; Mathematics; Sociology; Cartography; Artificial intelligence; Politics","score_opus":0.7717421973928245,"score_gpt":0.7209083247582806,"score_spread":0.050833872634543864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386245620","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":[0.28241488,0.0002543822,0.708948,0.0036233577,0.00037711163,0.0011574178,0.000003536074,0.00029525708,0.0029260323],"genre_scores_gemma":[0.5269778,0.00000678894,0.4723633,0.000034856035,0.00034131037,0.00016763143,0.0000062158324,0.000009460204,0.00009265879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9751964,0.021895418,0.0005745539,0.00043071556,0.00046568827,0.0014372062],"domain_scores_gemma":[0.97057176,0.028547375,0.00009869501,0.00014311075,0.00038401567,0.00025505543],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07244547,0.00013078483,0.0005204515,0.00039015018,0.001456097,0.00015076136,0.00039125062,0.0003900592,0.000039679948],"category_scores_gemma":[0.048581388,0.00010802369,0.00019750601,0.0026151915,0.0008080862,0.00012186772,0.00015851384,0.00082833046,0.000019408937],"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":[0.000108099455,0.00012868567,0.2358229,0.00016231126,0.00008440842,0.000007141209,0.011491291,0.0004839672,0.06454584,0.56273204,0.00016922358,0.1242641],"study_design_scores_gemma":[0.0007248724,0.0002698199,0.07727837,0.00011489984,0.00003134547,3.562054e-7,0.0066445605,0.29892653,0.0005560837,0.6120435,0.0029719598,0.00043769553],"about_ca_topic_score_codex":0.006496795,"about_ca_topic_score_gemma":0.0010634545,"teacher_disagreement_score":0.29844257,"about_ca_system_score_codex":0.00020523446,"about_ca_system_score_gemma":0.00020752242,"threshold_uncertainty_score":0.9998439},"labels":[],"label_agreement":null},{"id":"W4401031998","doi":"10.1177/00491241241266634","title":"Promises and Limits of Using Targeted Social Media Advertising to Sample Global Migrant Populations: Nigerians at Home and Abroad","year":2024,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Migration, Ethnicity, and Economy","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Saint Mary's University; McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Nigerians; Sample (material); Advertising; Social media; Media use; Sociology; Demographic economics; Political science; Business; Psychology; Economics; Social psychology","score_opus":0.33410954546525834,"score_gpt":0.5486357934169476,"score_spread":0.21452624795168923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401031998","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":[0.9888405,0.0040359274,0.004341344,0.0016367892,0.00019019138,0.00041190805,0.000070151684,0.000056839788,0.0004163251],"genre_scores_gemma":[0.9051904,0.00036928413,0.093901664,0.000049536346,0.00038313176,0.00002835462,0.000011815511,0.000008436187,0.000057399902],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956508,0.0027728712,0.00030670743,0.0004122449,0.0003507208,0.0005066438],"domain_scores_gemma":[0.996373,0.0031071466,0.000040552328,0.00008517741,0.00017792647,0.00021618533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061745723,0.00011194704,0.00030576356,0.00010608474,0.0012335586,0.00011789368,0.00015722543,0.00027200306,0.00019653437],"category_scores_gemma":[0.005291349,0.00009320424,0.00007431278,0.0005828708,0.0011376877,0.00015755702,0.00016625535,0.00024543176,0.0000041078397],"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":[0.0003425726,0.00015502142,0.16752814,0.00034476328,0.00014499313,0.000015106646,0.53090674,0.000021537066,0.024342662,0.07982401,0.0016444345,0.19473004],"study_design_scores_gemma":[0.00040553877,0.00025273612,0.46245706,0.00012986432,0.000050510997,0.0000043147065,0.04356731,0.0009523671,0.00030044158,0.47892088,0.012458812,0.0005001582],"about_ca_topic_score_codex":0.0046223006,"about_ca_topic_score_gemma":0.0050813304,"teacher_disagreement_score":0.4873394,"about_ca_system_score_codex":0.0002796771,"about_ca_system_score_gemma":0.00016247471,"threshold_uncertainty_score":0.948766},"labels":[],"label_agreement":null},{"id":"W4407112381","doi":"10.1177/00491241251314039","title":"When to Use Counterfactuals in Causal Historiography: Methods for Semantics and Inference","year":2025,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Qualitative Comparative Analysis Research","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":"McGill University","funders":"","keywords":"Counterfactual conditional; Causal inference; Historiography; Semantics (computer science); Inference; Econometrics; Computer science; Causal model; Epistemology; Linguistics; Counterfactual thinking; Statistics; Artificial intelligence; Mathematics; Programming language; Political science; Philosophy; Law","score_opus":0.6295248969421484,"score_gpt":0.7249763478686025,"score_spread":0.09545145092645413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407112381","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":[0.08103139,0.0013680181,0.89980406,0.011819211,0.00013996003,0.001697439,0.000015965652,0.00004810933,0.0040758783],"genre_scores_gemma":[0.21698985,0.0004848226,0.7769505,0.00042808597,0.00007141733,0.000571265,0.0000042141337,0.000011358221,0.0044885487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.958075,0.038967047,0.00048789012,0.000760233,0.00061967043,0.0010901486],"domain_scores_gemma":[0.9176032,0.08021435,0.00005899798,0.0003237429,0.0014916691,0.00030801818],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06335555,0.00018698999,0.0006804787,0.0010890039,0.00093419466,0.0002803239,0.0007275663,0.000343192,0.00026709025],"category_scores_gemma":[0.07829102,0.00015429533,0.00015185578,0.0022512658,0.0026107144,0.00022171933,0.0005130433,0.0009947923,0.000016226411],"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":[0.00036794433,0.00026391444,0.046394806,0.00009772055,0.00023005491,0.000004895868,0.1099609,0.000008895654,0.015508902,0.6573323,0.009808004,0.16002163],"study_design_scores_gemma":[0.00037127675,0.00037907116,0.026215281,0.000059510003,0.000017917693,6.206226e-8,0.023812344,0.00058183016,0.000801243,0.5998853,0.3476112,0.00026500353],"about_ca_topic_score_codex":0.003700632,"about_ca_topic_score_gemma":0.0011405533,"teacher_disagreement_score":0.33780318,"about_ca_system_score_codex":0.0005603642,"about_ca_system_score_gemma":0.00051399955,"threshold_uncertainty_score":0.9644726},"labels":[],"label_agreement":null},{"id":"W4410554739","doi":"10.1177/00491241251339188","title":"Updating “The Future of Coding”: Qualitative Coding with Generative Large Language Models","year":2025,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":27,"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":"Russell Sage Foundation","keywords":"Coding (social sciences); Generative grammar; Computer science; Natural language processing; Linguistics; Qualitative research; Artificial intelligence; Sociology; Social science","score_opus":0.2818745422435381,"score_gpt":0.6225325648240265,"score_spread":0.34065802258048844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410554739","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":[0.05357642,0.0019109263,0.8853077,0.010808975,0.0001221268,0.00046538768,0.000016593263,0.00005142595,0.047740404],"genre_scores_gemma":[0.63701487,0.00013432409,0.36074945,0.00023464927,0.00029820375,0.00005661263,0.000009084752,0.000005569766,0.0014972425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.97054213,0.027589908,0.00030970204,0.00034850353,0.0007048061,0.0005049744],"domain_scores_gemma":[0.9836655,0.015173978,0.00012178872,0.00018006517,0.00078072434,0.00007790979],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.04042321,0.00011785691,0.00036497874,0.0001701724,0.0016773588,0.00006897556,0.00050263567,0.0001769391,0.00023708672],"category_scores_gemma":[0.0025707996,0.00006646978,0.00014739571,0.0016508996,0.0014513263,0.00010562768,0.00022811184,0.0007973563,0.0000032217595],"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":[0.000033577373,0.00004334928,0.00011096832,0.000010720842,0.00009170164,0.000001980707,0.13278322,0.00008180809,0.00079556444,0.823782,0.00023190066,0.042033177],"study_design_scores_gemma":[0.00018866747,0.00006571945,0.00033076122,0.000024576735,0.000020965688,1.4066363e-7,0.51354843,0.003798995,0.000438294,0.4792315,0.002260648,0.00009127773],"about_ca_topic_score_codex":0.00038711147,"about_ca_topic_score_gemma":0.00022339533,"teacher_disagreement_score":0.58343846,"about_ca_system_score_codex":0.00012489442,"about_ca_system_score_gemma":0.0002825468,"threshold_uncertainty_score":0.99962234},"labels":[],"label_agreement":null},{"id":"W4414803296","doi":"10.1177/00491241251358895","title":"Beyond the Diagonal Reference Model: Critiques and New Directions in the Analysis of Mobility Effects","year":2025,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Intergenerational and Educational Inequality Studies","field":"Social 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":"Identification (biology); Diagonal; Bounding overwatch; Sign (mathematics); Social mobility; Mobility model","score_opus":0.46987687223096936,"score_gpt":0.6426193233113723,"score_spread":0.17274245108040293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414803296","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":[0.8140847,0.005466132,0.010235343,0.12187222,0.00017093758,0.0006559012,0.000021482594,0.000023063905,0.047470223],"genre_scores_gemma":[0.9891347,0.00083020295,0.008100121,0.0006642014,0.000086246895,0.00017874526,0.0000043818604,0.0000010290215,0.0010003411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99042434,0.008633803,0.00019394155,0.0001976129,0.00033587104,0.00021443945],"domain_scores_gemma":[0.97927606,0.020189418,0.000024487075,0.00012929531,0.00034664987,0.00003407433],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016288072,0.000054861073,0.00018756943,0.000124704,0.00089416734,0.000040024668,0.0002953788,0.0000966958,0.00004260337],"category_scores_gemma":[0.009213297,0.00002781965,0.00008208363,0.0012520802,0.0014250727,0.00004386588,0.00011069718,0.0004052489,5.811153e-7],"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":[0.00001327767,0.00010546198,0.008092085,0.000009869636,0.00013040687,1.1743049e-7,0.020209773,0.00005821624,0.00016406528,0.95931405,0.0016847011,0.010217976],"study_design_scores_gemma":[0.000026617441,0.000022631073,0.21613146,0.000004771239,0.000046717043,1.971323e-8,0.011132272,0.0006318418,0.000056490677,0.77031213,0.0016029757,0.00003203941],"about_ca_topic_score_codex":0.006070736,"about_ca_topic_score_gemma":0.0029938268,"teacher_disagreement_score":0.20803939,"about_ca_system_score_codex":0.00007134306,"about_ca_system_score_gemma":0.0002769571,"threshold_uncertainty_score":0.9991325},"labels":[],"label_agreement":null}]}