{"meta":{"query_hash":"bd96c94426fe","filters":{"venue":"Research Synthesis Methods"},"cohort_total":119,"direct_labels_cover":7,"predictions_cover":119,"exported":119,"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/bd96c94426fe","api":"https://metacan.xera.ac/api/v1/cohort?venue=Research+Synthesis+Methods"},"results":[{"id":"W1484962366","doi":"10.1002/jrsm.1068","title":"An introduction to methodological issues when including non‐randomised studies in systematic reviews on the effects of interventions","year":2013,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":115,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Centre for Global Health Research; Institute of Population and Public Health","funders":"","keywords":"Psychological intervention; Systematic review; MEDLINE; Stakeholder; Medical education; Randomized controlled trial; Alternative medicine; Meta-analysis; Health care; Psychology; Medicine; Management science; Nursing; Political science; Public relations","score_opus":0.9733209713276808,"score_gpt":0.7604628857848775,"score_spread":0.21285808554280328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484962366","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20724697,0.0448398,0.6208808,0.058218945,0.0018206802,0.06489868,0.0000054604648,0.000036452835,0.002052249],"genre_scores_gemma":[0.18695597,0.0015642212,0.7873394,0.00017693946,0.00050663267,0.01853261,8.024567e-7,0.00003897345,0.004884483],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.43579584,0.5466801,0.010884028,0.0013048331,0.0048040063,0.0005312072],"domain_scores_gemma":[0.08328799,0.89568454,0.00565875,0.010318784,0.004614851,0.00043509086],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.75549674,0.00034423167,0.008007462,0.0016527218,0.00030422994,0.0005592602,0.0029248241,0.00011189815,0.003203677],"category_scores_gemma":[0.9278411,0.00012360683,0.0021150287,0.0030960133,0.00025975597,0.00031979274,0.00045846569,0.00045632277,0.0012664547],"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":[0.00031776624,0.001374428,0.0007131226,0.119868204,0.0027569022,0.0000149269445,0.025528861,0.00021101513,0.1452653,0.013811394,0.30964094,0.38049713],"study_design_scores_gemma":[0.0037216176,0.0047752196,0.010401769,0.14842601,0.0037745812,0.00005442188,0.10331221,0.03320297,0.24661082,0.3966012,0.04644484,0.002674331],"about_ca_topic_score_codex":0.000052615927,"about_ca_topic_score_gemma":0.000016279775,"teacher_disagreement_score":0.38278982,"about_ca_system_score_codex":0.00014024075,"about_ca_system_score_gemma":0.000028329618,"threshold_uncertainty_score":0.9995112},"labels":[],"label_agreement":null},{"id":"W1774942233","doi":"10.1002/jrsm.1113","title":"Clinical trial registries are of minimal use for identifying selective outcome and analysis reporting","year":2014,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":12,"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 Manitoba; George & Fay Yee Centre for Healthcare Innovation","funders":"Agency for Healthcare Research and Quality","keywords":"Outcome (game theory); Clinical trial; Medicine; Computer science; Internal medicine","score_opus":0.982106783670464,"score_gpt":0.7844786960610897,"score_spread":0.19762808760937434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1774942233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42019755,0.0002222275,0.5771626,0.00032339574,0.00014809077,0.0012145027,0.000021345879,0.0000059778954,0.000704282],"genre_scores_gemma":[0.49767634,0.000023619461,0.4996232,0.000013830987,0.00015362832,0.0001680689,0.000001554736,0.000014547092,0.0023251886],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7493601,0.20135608,0.036900457,0.0026705412,0.00886537,0.00084746524],"domain_scores_gemma":[0.12571135,0.8104067,0.04469833,0.008193919,0.010340897,0.000648781],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.80486304,0.00025998012,0.008041416,0.0016742012,0.00038820333,0.0012707952,0.0013485025,0.00021161861,0.00040716442],"category_scores_gemma":[0.954537,0.00013889138,0.0044031893,0.004370508,0.00042895792,0.00033417266,0.00035832333,0.00038610157,0.00002079445],"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":[0.0014904503,0.00014518164,0.7226487,0.00023455704,0.0032223333,0.0000035602711,0.000270263,0.000014114483,0.00040078134,0.0011614488,0.003930681,0.26647794],"study_design_scores_gemma":[0.0047151833,0.0007415977,0.8109323,0.00023979269,0.008532802,0.000011344178,0.005073032,0.068309225,0.004233915,0.021474728,0.07496393,0.00077218655],"about_ca_topic_score_codex":0.000042054115,"about_ca_topic_score_gemma":0.000043615455,"teacher_disagreement_score":0.6236487,"about_ca_system_score_codex":0.00004100867,"about_ca_system_score_gemma":0.00011395959,"threshold_uncertainty_score":0.999766},"labels":[],"label_agreement":null},{"id":"W1784175517","doi":"10.1002/jrsm.1164","title":"Methods to estimate the between‐study variance and its uncertainty in meta‐analysis","year":2015,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1615,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Medical Research Council; National Institute for Health and Care Research","keywords":"Meta-analysis; Variance (accounting); Econometrics; Computer science; Statistics; Statistical analysis; Mathematics; Economics","score_opus":0.9521150158924461,"score_gpt":0.7527147048590068,"score_spread":0.19940031103343925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1784175517","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":[0.045440685,0.012175174,0.91691387,0.011996873,0.00015599398,0.0051871045,0.000039378538,0.000022719252,0.008068215],"genre_scores_gemma":[0.31726015,0.000019936571,0.6779604,0.00008983394,0.00007303189,0.001092612,7.751697e-7,0.00002599786,0.0034772959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.4987711,0.4780998,0.00820989,0.0026548228,0.011136233,0.0011281683],"domain_scores_gemma":[0.5094136,0.46714133,0.002897857,0.012552883,0.0061749346,0.0018193533],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8450038,0.0004814694,0.008835135,0.0027196256,0.00041718673,0.0017465159,0.0044201813,0.00014188007,0.0024525698],"category_scores_gemma":[0.5537968,0.00019482385,0.002405785,0.017728556,0.00016500936,0.00029870772,0.0012093935,0.00066789926,0.00067681324],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011170121,0.0006145676,0.039598305,0.00012319832,0.16328576,0.000059496375,0.012845884,0.02119855,0.00063578517,0.00582408,0.007329979,0.7483727],"study_design_scores_gemma":[0.0006988874,0.0005737386,0.11745553,0.000054090953,0.21263441,0.00001613448,0.023946112,0.4008975,0.0026021295,0.103082225,0.1363223,0.0017169236],"about_ca_topic_score_codex":0.00049548416,"about_ca_topic_score_gemma":0.00042791554,"teacher_disagreement_score":0.74665576,"about_ca_system_score_codex":0.00012312779,"about_ca_system_score_gemma":0.00022238717,"threshold_uncertainty_score":0.99928975},"labels":[],"label_agreement":null},{"id":"W1803108444","doi":"10.1002/jrsm.1077","title":"Checklists of methodological issues for review authors to consider when including non‐randomized studies in systematic reviews","year":2013,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":140,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute of Population and Public Health; University of Ottawa","funders":"Economic and Social Research Council; National Institute for Health and Care Research; Scottish Government","keywords":"Systematic review; Operationalization; Randomized controlled trial; Confounding; MEDLINE; Meta-analysis; Psychological intervention; Checklist; Research design; Clinical study design; Psychology; Management science; Computer science; Medicine; Clinical trial; Political science; Engineering; Psychiatry; Statistics","score_opus":0.9865716552292881,"score_gpt":0.792126037302518,"score_spread":0.19444561792677018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1803108444","genre_codex":"review","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015517264,0.51135844,0.4000314,0.021291524,0.00046012804,0.061948664,0.000012747391,0.000016829461,0.0033285725],"genre_scores_gemma":[0.0019632152,0.025090845,0.94213146,0.00037880198,0.0000763864,0.022358598,7.6700695e-7,0.00003146154,0.007968463],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.26437908,0.6917942,0.0316907,0.0023494968,0.0085749505,0.0012115489],"domain_scores_gemma":[0.02675575,0.9449442,0.00940165,0.007659135,0.010571603,0.00066767907],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9009857,0.0005801839,0.03010231,0.001748142,0.00023230178,0.00040864933,0.0032102864,0.00021125424,0.0052674087],"category_scores_gemma":[0.9741291,0.00024005913,0.004266165,0.0036480946,0.0006792889,0.0003285315,0.000887362,0.0004395085,0.0013324842],"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":[0.0005920011,0.00023846804,0.00017056042,0.34343886,0.0024151013,0.0000105492045,0.009282623,0.00001715322,0.004595179,0.0054980945,0.5102397,0.12350169],"study_design_scores_gemma":[0.008666141,0.00038043383,0.00026135577,0.32615125,0.004523299,0.000059896298,0.019768054,0.015219625,0.012082303,0.43327138,0.17758024,0.0020360323],"about_ca_topic_score_codex":0.000095216936,"about_ca_topic_score_gemma":0.00001539634,"teacher_disagreement_score":0.5421001,"about_ca_system_score_codex":0.00016461036,"about_ca_system_score_gemma":0.000117643176,"threshold_uncertainty_score":0.9994451},"labels":[],"label_agreement":null},{"id":"W1873279267","doi":"10.1002/jrsm.52","title":"Structural Approach to Bias in Meta‐analyses","year":2011,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Computer science; Econometrics; Mathematics","score_opus":0.9942910586848828,"score_gpt":0.7637673632842343,"score_spread":0.23052369540064843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873279267","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085359044,0.005536405,0.4060355,0.000975333,0.00028541812,0.0033232549,0.000028628581,0.000028439063,0.49842796],"genre_scores_gemma":[0.29607856,0.000016742424,0.69854873,0.00006233675,0.000050227532,0.0004251912,6.07085e-7,0.000020765836,0.0047968477],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6558353,0.31528226,0.01067179,0.0027021423,0.014196263,0.0013122947],"domain_scores_gemma":[0.849172,0.13324419,0.002282847,0.011062958,0.0032128082,0.0010252164],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.63778496,0.0004035214,0.0061897035,0.00327328,0.00023133757,0.00084843294,0.0047815302,0.00014755187,0.026733927],"category_scores_gemma":[0.45551914,0.00016934713,0.0029007087,0.008225581,0.00018029058,0.00032397304,0.00062195084,0.0005021375,0.0027397643],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014396296,0.00059300516,0.01938468,0.00032595193,0.013572394,0.00005192055,0.0111098755,0.0007486198,0.006915443,0.03066903,0.039414264,0.87707084],"study_design_scores_gemma":[0.0006324343,0.0003987303,0.21632646,0.00020766271,0.011021029,0.00009912777,0.028664129,0.13109049,0.11014784,0.3015621,0.19664207,0.0032079213],"about_ca_topic_score_codex":0.00045762566,"about_ca_topic_score_gemma":0.00005385257,"teacher_disagreement_score":0.8738629,"about_ca_system_score_codex":0.00007785296,"about_ca_system_score_gemma":0.00012637822,"threshold_uncertainty_score":0.99803674},"labels":[],"label_agreement":null},{"id":"W1911705068","doi":"10.1002/jrsm.1106","title":"Searching for grey literature for systematic reviews: challenges and benefits","year":2013,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":803,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; University of Waterloo; University of Toronto","funders":"Workers Compensation Board of Manitoba","keywords":"Grey literature; Systematic review; Scope (computer science); Computer science; Process (computing); Data science; Management science; Information retrieval; MEDLINE; Engineering; Political science","score_opus":0.9427986778929087,"score_gpt":0.6848807056848404,"score_spread":0.25791797220806834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1911705068","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.004459862,0.61368144,0.311117,0.0119029945,0.00034853286,0.050724704,0.0001022597,0.00003259572,0.0076305894],"genre_scores_gemma":[0.009561552,0.012463657,0.9359971,0.00011234573,0.0003967708,0.027321752,0.000005876429,0.00007523696,0.014065707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.85652995,0.1276027,0.007962733,0.0018644093,0.0050433846,0.0009968068],"domain_scores_gemma":[0.4121601,0.5644368,0.0038536761,0.0075542065,0.011110426,0.0008848078],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6505072,0.00041814242,0.0063437303,0.0011378785,0.00056669716,0.0034482975,0.0022885574,0.00020833881,0.0006840758],"category_scores_gemma":[0.74172205,0.00018478988,0.0019720786,0.0012280714,0.00012564434,0.0006703832,0.00030642506,0.0003449674,0.0007095443],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009501728,0.0000404325,0.000020446694,0.04460454,0.0002644362,5.061901e-7,0.0016075214,0.0000036519398,0.00044998876,0.014477096,0.013836235,0.92468566],"study_design_scores_gemma":[0.00068441045,0.000547046,0.0018399742,0.05602794,0.0009688631,0.00007502478,0.012020423,0.0776349,0.0023166789,0.34015882,0.50623155,0.0014943697],"about_ca_topic_score_codex":0.000006923514,"about_ca_topic_score_gemma":0.000008196474,"teacher_disagreement_score":0.92319125,"about_ca_system_score_codex":0.000051482075,"about_ca_system_score_gemma":0.00006098198,"threshold_uncertainty_score":0.9975862},"labels":[],"label_agreement":null},{"id":"W1948715096","doi":"10.1002/jrsm.1144","title":"Commentary for history special issue of <i>Research Synthesis Methods</i>","year":2015,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":2,"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":"National Institute for Health and Care Research","keywords":"Computer science; Management science; Research methodology; Data science; Sociology; Economics; Demography","score_opus":0.479619870709482,"score_gpt":0.5657258296595259,"score_spread":0.08610595895004391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1948715096","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":[0.00019887729,0.001235056,0.93294704,0.014980183,0.0014313378,0.001182999,0.000021039452,0.00011078458,0.047892675],"genre_scores_gemma":[0.001089312,0.00011699735,0.99395776,0.0005380037,0.0020196391,0.0007778722,0.0000012465246,0.00003696067,0.0014622117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97427803,0.019896405,0.00065739895,0.0011441172,0.0024255938,0.001598479],"domain_scores_gemma":[0.9180058,0.07640323,0.00018066337,0.0016498744,0.0029871077,0.0007733158],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12709638,0.00027028946,0.0007697933,0.0016531774,0.0004905484,0.00017441058,0.0036082389,0.00018193724,0.00035593787],"category_scores_gemma":[0.059088748,0.0002488672,0.00028744934,0.0021798415,0.0014347018,0.00087612827,0.0018501673,0.000752644,0.00009544575],"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":[0.00006645144,0.00018698217,0.00002368869,0.000109228204,0.000048384893,0.000008783789,0.0015948535,0.0000031654376,0.016123146,0.0049314997,0.27451047,0.70239335],"study_design_scores_gemma":[0.00018172112,0.00018856725,0.000050322025,0.00012580628,0.000014933526,0.000005973533,0.0014771648,0.005290855,0.26226243,0.016739888,0.71342593,0.00023638198],"about_ca_topic_score_codex":0.00043724416,"about_ca_topic_score_gemma":0.000017225933,"teacher_disagreement_score":0.70215696,"about_ca_system_score_codex":0.0010809469,"about_ca_system_score_gemma":0.0012576701,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W1984170021","doi":"10.1002/jrsm.1062","title":"Issues relating to selective reporting when including non‐randomized studies in systematic reviews on the effects of healthcare interventions","year":2012,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Centre for Global Health Research; Institute of Population and Public Health; Ottawa Hospital","funders":"","keywords":"Psychological intervention; Randomized controlled trial; Systematic review; Documentation; Protocol (science); Suspect; MEDLINE; Health care; Psychology; Meta-analysis; Reporting bias; Medicine; Alternative medicine; Computer science; Psychiatry; Political science","score_opus":0.9651183188967614,"score_gpt":0.7655784742142648,"score_spread":0.19953984468249653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984170021","genre_codex":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21610504,0.45850468,0.18394388,0.025886636,0.0024945152,0.09447113,0.0000089030145,0.00005208608,0.01853313],"genre_scores_gemma":[0.787052,0.0010779188,0.1994367,0.00010962095,0.0001589944,0.007870462,3.0165901e-7,0.000035920606,0.0042581037],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.26903442,0.6835444,0.036442704,0.0013669909,0.0084215095,0.0011899897],"domain_scores_gemma":[0.03135087,0.9331446,0.024981745,0.0057962555,0.004325646,0.00040082494],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8891034,0.00035480148,0.012163859,0.0016530349,0.0005038368,0.0002475299,0.0016190399,0.00010474875,0.0002364372],"category_scores_gemma":[0.97967315,0.00013678013,0.0032530061,0.0040461905,0.00024872232,0.00026768257,0.00064411643,0.00065723574,0.0003369169],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012280509,0.0009399112,0.016369054,0.44108573,0.0069230553,0.00003113123,0.30235606,0.00008877073,0.008137367,0.03503939,0.043628216,0.14417326],"study_design_scores_gemma":[0.0058466224,0.0007697777,0.0035982963,0.6575893,0.0035129068,0.00005571786,0.1624149,0.009298643,0.048632193,0.10084653,0.005801431,0.0016336689],"about_ca_topic_score_codex":0.00019564878,"about_ca_topic_score_gemma":0.000052859017,"teacher_disagreement_score":0.57094693,"about_ca_system_score_codex":0.00029950417,"about_ca_system_score_gemma":0.00006395003,"threshold_uncertainty_score":0.8314971},"labels":[],"label_agreement":null},{"id":"W2015957719","doi":"10.1002/jrsm.41","title":"Reliability and validity of three quality rating instruments for systematic reviews of observational studies","year":2011,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":172,"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":"Observational study; Intraclass correlation; Reliability (semiconductor); Validity; Inter-rater reliability; Rating scale; Sign (mathematics); Statistics; Psychology; Medicine; Clinical psychology; Psychometrics; Mathematics; Physics","score_opus":0.9900024069594315,"score_gpt":0.7477755849671291,"score_spread":0.2422268219923024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015957719","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69031227,0.005514963,0.2899273,0.0002601046,0.00020341705,0.011292692,0.00007946771,0.0000066493917,0.0024031303],"genre_scores_gemma":[0.32043558,0.00023226146,0.6780772,0.000009174619,0.000022086677,0.0009794317,7.134355e-7,0.000009180136,0.00023434345],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.58907413,0.36668304,0.03072841,0.0019306123,0.01090412,0.00067969825],"domain_scores_gemma":[0.18924154,0.7585156,0.022014514,0.010588657,0.01923829,0.00040141548],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8087921,0.00024386047,0.007864277,0.00039517306,0.00021965854,0.00008880193,0.0014745918,0.00009546765,0.00074929115],"category_scores_gemma":[0.8840745,0.00011187697,0.0014424433,0.0013426879,0.0004512875,0.00028222692,0.0003930293,0.00015960349,0.000021491289],"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":[0.000185965,0.0008039449,0.3942699,0.30745676,0.0026739736,6.4213486e-7,0.008264499,0.0000086476775,0.011988516,0.05010824,0.0040459437,0.22019294],"study_design_scores_gemma":[0.0005196415,0.00046947377,0.31841803,0.013941227,0.0013954702,0.0000045734278,0.011377947,0.01290175,0.042051308,0.59541863,0.0028102067,0.0006917478],"about_ca_topic_score_codex":0.000038425496,"about_ca_topic_score_gemma":0.000022404502,"teacher_disagreement_score":0.5453104,"about_ca_system_score_codex":0.000055882876,"about_ca_system_score_gemma":0.000111448186,"threshold_uncertainty_score":0.8204213},"labels":[],"label_agreement":null},{"id":"W2017350454","doi":"10.1002/jrsm.40","title":"Inquisitio validus Index Medicus: A simple method of validating MEDLINE systematic review searches","year":2011,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Children's Hospital of Eastern Ontario","funders":"Agency for Healthcare Research and Quality","keywords":"MEDLINE; Recall; Systematic review; Computer science; Information retrieval; Medicine; Psychology","score_opus":0.9475219294562043,"score_gpt":0.7096902073900373,"score_spread":0.23783172206616698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017350454","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007246165,0.030757895,0.93636656,0.00085500354,0.00015509718,0.005419478,0.000058750204,0.00003168704,0.02563094],"genre_scores_gemma":[0.02869909,0.0019455667,0.9640691,0.00028446317,0.00014263607,0.001371055,0.000009493078,0.00008074628,0.0033978114],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.46300998,0.48434204,0.023986528,0.002516564,0.024635993,0.0015088771],"domain_scores_gemma":[0.4070384,0.5341371,0.016960813,0.02228908,0.017823048,0.0017515564],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.82300675,0.0005845067,0.011960919,0.0019739913,0.00036378947,0.00042279527,0.0062163784,0.00026282071,0.037344474],"category_scores_gemma":[0.7144439,0.000286028,0.0027556987,0.006820262,0.00047769284,0.00042688273,0.0010417497,0.00084909657,0.0013878728],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071925686,0.0010608182,0.002761544,0.5579173,0.0050281654,0.00009574865,0.0073257512,0.000021467338,0.005016879,0.01015242,0.051644865,0.3589031],"study_design_scores_gemma":[0.001570189,0.0010595195,0.002667707,0.34000832,0.014711379,0.0006544775,0.042702872,0.11012457,0.17026427,0.2855899,0.026472727,0.0041740704],"about_ca_topic_score_codex":0.00025147406,"about_ca_topic_score_gemma":0.000012359921,"teacher_disagreement_score":0.35472903,"about_ca_system_score_codex":0.00013292098,"about_ca_system_score_gemma":0.00038390164,"threshold_uncertainty_score":0.9999592},"labels":[],"label_agreement":null},{"id":"W2043360969","doi":"10.1002/jrsm.30","title":"The evolution of a new publication type: Steps and challenges of producing overviews of reviews","year":2010,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":113,"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 Manitoba; Children's Hospital Research Institute of Manitoba; Cochrane; University of Alberta","funders":"","keywords":"Systematic review; Presentation (obstetrics); Process (computing); Mandate; Identification (biology); Computer science; Engineering ethics; Management science; MEDLINE; Psychology; Medicine; Political science; Engineering","score_opus":0.9268161503390395,"score_gpt":0.6748823847148678,"score_spread":0.2519337656241717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043360969","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09160068,0.7756852,0.06307229,0.022398697,0.0007595413,0.007832166,0.000019940386,0.000011106783,0.03862041],"genre_scores_gemma":[0.28311095,0.05940237,0.64838314,0.000012466676,0.00025002324,0.00022959121,9.214424e-7,0.00003284948,0.008577714],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8318352,0.14036046,0.015572492,0.0017219508,0.009862314,0.00064756256],"domain_scores_gemma":[0.8188448,0.13902244,0.013789752,0.0148144895,0.013085708,0.00044282823],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5907845,0.0001440321,0.002469427,0.0005475733,0.00012896166,0.00013375569,0.0016563318,0.00009668593,0.00088713656],"category_scores_gemma":[0.61181235,0.000059708425,0.0005807243,0.0022280295,0.00029096415,0.00020064563,0.00025527013,0.00026743117,0.000052321408],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010018498,0.000033206616,0.0007741029,0.0004354979,0.000063570136,2.6835043e-8,0.00066872017,4.406125e-7,0.030946657,0.018379945,0.006172444,0.9425154],"study_design_scores_gemma":[0.00009440154,0.00011196808,0.039916422,0.0003952586,0.00018166074,0.0000043197056,0.0021663914,0.0016906015,0.028846782,0.03375175,0.89269084,0.00014958634],"about_ca_topic_score_codex":0.00013408349,"about_ca_topic_score_gemma":0.00011749706,"teacher_disagreement_score":0.94236577,"about_ca_system_score_codex":0.000024681987,"about_ca_system_score_gemma":0.00026937993,"threshold_uncertainty_score":0.97135234},"labels":[],"label_agreement":null},{"id":"W2062040186","doi":"10.1002/jrsm.1056","title":"Issues relating to study design and risk of bias when including non‐randomized studies in systematic reviews on the effects of interventions","year":2012,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":187,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health; University of Ottawa","funders":"National Institutes of Health; National Institute for Health and Care Research; Scottish Government","keywords":"Randomized controlled trial; Psychological intervention; Systematic review; Randomized experiment; Research design; Clinical study design; Psychology; Computer science; MEDLINE; Management science; Medicine; Applied psychology; Clinical trial; Social science; Psychiatry; Sociology; Engineering","score_opus":0.8578401848948041,"score_gpt":0.6814907782416452,"score_spread":0.1763494066531589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062040186","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.29506612,0.017651029,0.66524845,0.00010364203,0.00006339275,0.021624653,0.0000015369026,0.000056699533,0.00018444733],"genre_scores_gemma":[0.35599095,0.0027154835,0.6370519,0.0000021453704,0.000013422496,0.004144137,2.5074389e-8,0.000023382174,0.000058586156],"study_design_codex":"systematic_review","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.908967,0.08822193,0.0015874606,0.00024672714,0.00058176287,0.00039508656],"domain_scores_gemma":[0.4823799,0.515647,0.0008099584,0.0007706991,0.0003119553,0.00008048552],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19958735,0.00020610333,0.002215457,0.0005687288,0.00015730993,0.000016197824,0.00034107963,0.00006435932,0.000009840491],"category_scores_gemma":[0.7106343,0.000111657784,0.00021613244,0.0005723989,0.00031799692,0.00014027208,0.00045892064,0.0004154517,0.0000025759427],"study_design_candidate":"systematic_review","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":[0.004785346,0.0048903706,0.00652895,0.4168761,0.0056648743,0.000013183708,0.37595093,0.000028494052,0.036062445,0.06121167,0.000935411,0.0870522],"study_design_scores_gemma":[0.003631867,0.0010767782,0.0002279887,0.17337315,0.0011422439,0.0000024032126,0.02792336,0.0006734966,0.43398032,0.35762712,0.000005203264,0.00033606196],"about_ca_topic_score_codex":0.000084352134,"about_ca_topic_score_gemma":0.000008057466,"teacher_disagreement_score":0.51104695,"about_ca_system_score_codex":0.00010950849,"about_ca_system_score_gemma":0.000013031858,"threshold_uncertainty_score":0.8241933},"labels":[],"label_agreement":null},{"id":"W2068264290","doi":"10.1002/jrsm.1123","title":"A scoping review of scoping reviews: advancing the approach and enhancing the consistency","year":2014,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3082,"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 Guelph; Public Health Agency of Canada","funders":"Ontario Ministry of Agriculture, Food and Rural Affairs","keywords":"Consistency (knowledge bases); Computer science; Management science; Data science; Artificial intelligence; Engineering","score_opus":0.923851977769396,"score_gpt":0.7277039479738097,"score_spread":0.19614802979558632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068264290","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.881358e-8,0.89128095,0.08701174,0.00036275727,0.00015053486,0.013085499,0.0000071714053,0.0000063993734,0.008094846],"genre_scores_gemma":[2.5862494e-7,0.8728453,0.12292083,0.00017121351,0.0002188215,0.0030648229,0.0000024582473,0.000061287676,0.00071502157],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.3442413,0.60252833,0.03582132,0.0033598873,0.012536934,0.0015122361],"domain_scores_gemma":[0.16755807,0.7719051,0.031214796,0.023746068,0.0049097296,0.00066622894],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8674546,0.0010387482,0.032336485,0.0010539858,0.0012318883,0.0012375886,0.0076147914,0.00033329125,0.0019210866],"category_scores_gemma":[0.7785432,0.0003363213,0.0071474602,0.006299767,0.0010373698,0.00023951859,0.0017099698,0.0017074734,0.0004517362],"study_design_candidate":"systematic_review","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":[4.055199e-7,0.000009484009,5.3205434e-7,0.3897209,0.0001654179,4.8441433e-7,0.00005685872,1.8669775e-7,0.0000012501804,0.00030912814,0.0018305465,0.6079048],"study_design_scores_gemma":[0.000012652012,0.000010991995,2.3074124e-7,0.53863424,0.0013004079,0.000038747992,0.00014691554,0.00007943699,0.0000053457666,0.00023877142,0.4593396,0.00019265861],"about_ca_topic_score_codex":0.000017628292,"about_ca_topic_score_gemma":0.000016865028,"teacher_disagreement_score":0.60771215,"about_ca_system_score_codex":0.00013023637,"about_ca_system_score_gemma":0.0015124232,"threshold_uncertainty_score":0.99990886},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2072770626","doi":"10.1002/jrsm.1089","title":"Special issue on inclusion of non‐randomized studies in systematic reviews","year":2013,"lang":"en","type":"erratum","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute for Health and Care Research; Medical Research Council; University of Ottawa; U.S. Department of Health and Human Services; Agency for Healthcare Research and Quality; Scottish Government","keywords":"Systematic review; Medicine; Health services research; Library science; Agency (philosophy); Psychological intervention; Health care; Inclusion (mineral); Government (linguistics); Political science; MEDLINE; Medical education; Family medicine; Public health; Sociology; Nursing; Social science; Law","score_opus":0.9025547465330345,"score_gpt":0.7078086700810654,"score_spread":0.19474607645196906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072770626","genre_codex":"other","genre_gemma":"other","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000669489,0.16844378,0.0055661816,0.0021513316,0.03447777,0.046519272,0.000050942173,0.000014574438,0.7427092],"genre_scores_gemma":[0.00003712959,0.049862396,0.096291035,0.0001074227,0.013801527,0.008337628,0.000010708522,0.000118958196,0.8314332],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.21119867,0.7123579,0.043911066,0.0032648398,0.027977934,0.0012895953],"domain_scores_gemma":[0.077449135,0.85409313,0.03460621,0.021037117,0.012124054,0.0006903286],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8945738,0.0012358738,0.055097006,0.006612655,0.00054777646,0.00069873186,0.008393107,0.00096716377,0.028365325],"category_scores_gemma":[0.93141925,0.0005081702,0.0084572295,0.006469866,0.0013086766,0.0002711053,0.003991237,0.002497755,0.012295384],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033177293,0.00012950387,0.0000017992878,0.04990325,0.0008557799,0.000012672531,0.0027347312,0.0000041641088,0.000027587084,0.00020590879,0.88337857,0.06241424],"study_design_scores_gemma":[0.0020322395,0.00008266775,0.0000075606126,0.06186749,0.00087841647,0.000004170058,0.0024765246,0.0031645591,0.00015205066,0.009181777,0.9196676,0.00048494124],"about_ca_topic_score_codex":0.000109396824,"about_ca_topic_score_gemma":0.000053850246,"teacher_disagreement_score":0.14173526,"about_ca_system_score_codex":0.00053478405,"about_ca_system_score_gemma":0.00047988287,"threshold_uncertainty_score":0.99980354},"labels":[],"label_agreement":null},{"id":"W2078055840","doi":"10.1002/jrsm.14","title":"Evidence synthesis, economics and public policy","year":2010,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics","funders":"","keywords":"Scope (computer science); Systematic review; Economic evaluation; Economics; Empirical evidence; Variety (cybernetics); Evidence-based policy; Public economics; Management science; Computer science; Political science; MEDLINE","score_opus":0.45728461813340754,"score_gpt":0.42920831491217637,"score_spread":0.02807630322123117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078055840","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":[0.9417662,0.0031132388,0.0047657117,0.012300623,0.00033981574,0.00042314717,0.00006548245,0.000055627843,0.03717016],"genre_scores_gemma":[0.923285,0.01025922,0.06528542,0.000101256606,0.00033054184,0.00025948143,0.0000014426142,0.00004707076,0.00043057653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9974144,0.0005011472,0.0006019475,0.0007264743,0.00006236347,0.0006936805],"domain_scores_gemma":[0.9923355,0.0063756183,0.00019824502,0.0007263705,0.00003183298,0.00033241676],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.016285505,0.00018600082,0.00047214335,0.0007633451,0.0003593604,0.0002898026,0.00050397875,0.00022034561,0.0016533994],"category_scores_gemma":[0.020756323,0.0002133912,0.00010794373,0.00028499827,0.0004998879,0.0007345827,0.00031623853,0.00051618996,0.000982416],"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":[0.000012597915,0.00009099555,0.08366109,0.000041629355,0.00006860076,9.4272343e-7,0.0001298357,0.000010088619,0.0023460698,0.6216039,0.00022202321,0.2918122],"study_design_scores_gemma":[0.00033386546,0.00010700943,0.42645034,0.00008311728,0.00002393422,0.00004093764,0.0005394643,0.01233279,0.028096566,0.35467526,0.17617968,0.001137045],"about_ca_topic_score_codex":0.00076838915,"about_ca_topic_score_gemma":0.00007722152,"teacher_disagreement_score":0.34278926,"about_ca_system_score_codex":0.00026988666,"about_ca_system_score_gemma":0.00011485772,"threshold_uncertainty_score":0.99979544},"labels":[],"label_agreement":null},{"id":"W2096851309","doi":"10.1002/jrsm.1118","title":"Meta‐analysis and the reversed <scp>Theorem of the Means</scp>","year":2014,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Custom Security Industries (Canada)","funders":"","keywords":"Harmonic mean; Geometric mean; Mathematics; Weighted geometric mean; Weighted arithmetic mean; Estimator; Reciprocal; Statistics; Logarithmic mean; Variance (accounting); Logarithm; Inequality of arithmetic and geometric means; Population mean; Inequality; Mathematical analysis","score_opus":0.8660683662286599,"score_gpt":0.627244256426351,"score_spread":0.23882410980230895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096851309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014690545,0.011700311,0.8344901,0.010657387,0.00022274567,0.0029778797,0.000038967333,0.000014879357,0.12520719],"genre_scores_gemma":[0.65760887,0.00039298343,0.29907575,0.0003910236,0.00014411472,0.0004966732,7.341315e-7,0.000044543634,0.041845303],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.55116427,0.42891195,0.0063277497,0.0013377665,0.0116201155,0.00063814246],"domain_scores_gemma":[0.20624858,0.7694965,0.0050693764,0.014910068,0.0038784647,0.00039702808],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7759338,0.0003187103,0.007104272,0.0010246899,0.00060484116,0.00079017493,0.0049999077,0.00013333057,0.0036501456],"category_scores_gemma":[0.62169725,0.00009392159,0.008185954,0.008293189,0.0014932175,0.00014235187,0.0007802941,0.00047901395,0.0002240486],"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":[0.00005695633,0.00020907287,0.006474621,0.00038647832,0.3734724,0.0000024461813,0.0060611293,0.00055669877,0.004294211,0.325495,0.03979464,0.24319635],"study_design_scores_gemma":[0.00049260794,0.000047195957,0.009609896,0.000040261537,0.25641218,0.00000919733,0.0053633633,0.07931301,0.025728794,0.31598836,0.30677652,0.00021862677],"about_ca_topic_score_codex":0.00011100065,"about_ca_topic_score_gemma":0.00005138699,"teacher_disagreement_score":0.64291835,"about_ca_system_score_codex":0.000022232016,"about_ca_system_score_gemma":0.00007922689,"threshold_uncertainty_score":0.99726063},"labels":[],"label_agreement":null},{"id":"W2099087018","doi":"10.1002/jrsm.42","title":"Precision of healthcare systematic review searches in a cross‐sectional sample","year":2011,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; Children's Hospital of Eastern Ontario","funders":"U.S. National Library of Medicine; Health Canada; National Institutes of Health","keywords":"Systematic review; MEDLINE; Interquartile range; Sample size determination; Health care; Sample (material); Medicine; Range (aeronautics); Information retrieval; Computer science; Statistics; Data mining; Mathematics; Physics","score_opus":0.953369109962058,"score_gpt":0.7176757588278021,"score_spread":0.23569335113425594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099087018","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":[0.073521115,0.3254367,0.5085742,0.0046366584,0.0010526957,0.036217183,0.00043982817,0.00007070923,0.050050892],"genre_scores_gemma":[0.31759802,0.0047715288,0.67160255,0.00014811558,0.00007783992,0.0021074712,0.000004818984,0.000058306097,0.0036313308],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.5662138,0.38722792,0.022828603,0.0022706424,0.020289604,0.0011694548],"domain_scores_gemma":[0.51771927,0.44758022,0.008016078,0.013960463,0.011839976,0.00088402914],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7471939,0.0003079686,0.0065816483,0.0018314397,0.00021393792,0.0003362924,0.0037129926,0.00018244749,0.011456341],"category_scores_gemma":[0.748931,0.00015265346,0.001891893,0.005143439,0.0003014078,0.00031586556,0.0005015144,0.00058259425,0.00093208026],"study_design_candidate":"systematic_review","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":[0.00015210404,0.00082843855,0.2979937,0.59407806,0.0008182451,0.00002633348,0.003157735,0.000015127774,0.00065034704,0.017845843,0.0047175777,0.07971649],"study_design_scores_gemma":[0.00056051894,0.00061338267,0.48629686,0.22778997,0.00072342576,0.000107938475,0.004066612,0.009521063,0.010929792,0.25177622,0.0062311715,0.0013830479],"about_ca_topic_score_codex":0.00070468144,"about_ca_topic_score_gemma":0.00008010812,"teacher_disagreement_score":0.3662881,"about_ca_system_score_codex":0.00017278393,"about_ca_system_score_gemma":0.00035339568,"threshold_uncertainty_score":0.9998458},"labels":[],"label_agreement":null},{"id":"W2103418324","doi":"10.1002/jrsm.53","title":"Comparison of statistical inferences from the DerSimonian–Laird and alternative random‐effects model meta‐analyses – an empirical assessment of 920 Cochrane primary outcome meta‐analyses","year":2011,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"","keywords":"Estimator; Meta-analysis; Statistics; Random effects model; Econometrics; Mathematics; Confidence interval; Medicine; Internal medicine","score_opus":0.9790827001812016,"score_gpt":0.785766586948887,"score_spread":0.19331611323231457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103418324","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":[0.04502687,0.012177295,0.9383519,0.00036002073,0.00005348774,0.0010901908,0.00018516704,0.000007171045,0.002747858],"genre_scores_gemma":[0.5398519,0.00019887483,0.45963907,0.00003908978,0.000018260871,0.00016440998,0.0000046980617,0.000014069005,0.00006959038],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.77346647,0.20340897,0.00959047,0.0016629561,0.011227643,0.00064350443],"domain_scores_gemma":[0.6498152,0.3390498,0.004116419,0.0038386022,0.002709523,0.00047047006],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2801977,0.0005748076,0.013668836,0.0008784692,0.00032378684,0.00042315052,0.003236999,0.00017326446,0.0052245376],"category_scores_gemma":[0.1510227,0.00021920234,0.0030888405,0.0017639699,0.0012379054,0.00041725597,0.00063541444,0.0006246013,0.000023187009],"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":[0.0009801857,0.0041178754,0.4355614,0.0021054838,0.36963004,0.000047430334,0.014700582,0.006743757,0.021314401,0.012514058,0.004922932,0.12736185],"study_design_scores_gemma":[0.00067158375,0.00042784505,0.111691356,0.000102326354,0.09807512,0.0000024363303,0.0042737243,0.6934372,0.030624779,0.060064472,0.00013317441,0.00049594394],"about_ca_topic_score_codex":0.001409988,"about_ca_topic_score_gemma":0.00019028859,"teacher_disagreement_score":0.6866935,"about_ca_system_score_codex":0.000049063314,"about_ca_system_score_gemma":0.0003444335,"threshold_uncertainty_score":0.9956848},"labels":[],"label_agreement":null},{"id":"W2106889389","doi":"10.1002/jrsm.46","title":"Pooling health‐related quality of life outcomes in meta‐analysis—a tutorial and review of methods for enhancing interpretability","year":2011,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":293,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; McMaster University","funders":"","keywords":"Interpretability; Pooling; Strictly standardized mean difference; Meta-analysis; Odds; Odds ratio; Construct (python library); Psychological intervention; Statistics; Medicine; Computer science; Mathematics; Artificial intelligence; Logistic regression","score_opus":0.9473026375794946,"score_gpt":0.738310881158621,"score_spread":0.20899175642087364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106889389","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008800416,0.15706329,0.82880414,0.0009333528,0.0002045368,0.0030935304,0.000054764794,0.0000070442597,0.0010389293],"genre_scores_gemma":[0.09814334,0.002349884,0.89881104,0.00007397686,0.000017357639,0.00038593504,0.0000014627253,0.000017646362,0.0001993508],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44312128,0.5137088,0.034382656,0.0022516176,0.0056047663,0.0009308822],"domain_scores_gemma":[0.31695426,0.64477134,0.0193309,0.010414266,0.007609172,0.00092008064],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86652845,0.0003648087,0.019556558,0.0018623086,0.00012310488,0.00009477402,0.0019065589,0.00017845674,0.0052007106],"category_scores_gemma":[0.764193,0.00018502027,0.007081633,0.0053508277,0.0003213858,0.00023825427,0.00043780828,0.00041484492,0.000009452427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048880785,0.0012384087,0.050648484,0.05088737,0.20854856,0.0000010764046,0.01115613,0.000032454773,0.0052929143,0.016029596,0.0005398039,0.6551364],"study_design_scores_gemma":[0.0027516603,0.0014972681,0.2094546,0.008481305,0.282389,0.000008931129,0.018964624,0.048972633,0.07612929,0.33532858,0.012232516,0.0037896275],"about_ca_topic_score_codex":0.001555747,"about_ca_topic_score_gemma":0.0002923259,"teacher_disagreement_score":0.65134674,"about_ca_system_score_codex":0.00008380038,"about_ca_system_score_gemma":0.0004453088,"threshold_uncertainty_score":0.99570864},"labels":[],"label_agreement":null},{"id":"W2126629865","doi":"10.1002/jrsm.1078","title":"Non‐randomized studies as a source of complementary, sequential or replacement evidence for randomized controlled trials in systematic reviews on the effects of interventions","year":2013,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":245,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McMaster University","funders":"","keywords":"Generalizability theory; Randomized controlled trial; Systematic review; Credibility; Context (archaeology); Evidence-based medicine; Evidence-based practice; Psychology; External validity; Health care; Psychological intervention; MEDLINE; Population; Medicine; Applied psychology; Social psychology; Alternative medicine; Nursing; Epistemology; Political science","score_opus":0.9453333605578149,"score_gpt":0.7340988391264817,"score_spread":0.21123452143133326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126629865","genre_codex":"methods","genre_gemma":"protocol","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02683709,0.09317076,0.54094416,0.0058856546,0.00073543173,0.33163136,0.000011234654,0.000008965911,0.00077535317],"genre_scores_gemma":[0.33455825,0.018133027,0.22699264,0.00028459897,0.00020465425,0.39521676,0.0000029625708,0.00008167576,0.02452541],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.09125347,0.85066575,0.04901547,0.0011203205,0.0073609045,0.0005840711],"domain_scores_gemma":[0.0027169518,0.9670022,0.02233332,0.0039143255,0.0038972958,0.00013589878],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9554551,0.00048419408,0.060256276,0.0016142393,0.00023021508,0.0004102075,0.0025463297,0.000089203306,0.0064386455],"category_scores_gemma":[0.9905246,0.00014054954,0.019973883,0.001754282,0.0008574391,0.00019359183,0.00038941883,0.0002636039,0.00020071332],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.69196254,0.0008961497,0.00003056571,0.19721459,0.031832304,0.0000027001524,0.0069889654,0.000058481408,0.006351719,0.008902861,0.037303053,0.018456046],"study_design_scores_gemma":[0.6969717,0.0009954284,0.000008255412,0.18433915,0.016253285,0.00000421969,0.013723676,0.036448855,0.015003303,0.03516182,0.0006500593,0.0004402213],"about_ca_topic_score_codex":0.0002827828,"about_ca_topic_score_gemma":0.00003637737,"teacher_disagreement_score":0.3139515,"about_ca_system_score_codex":0.00013101558,"about_ca_system_score_gemma":0.00017365457,"threshold_uncertainty_score":0.9944696},"labels":[],"label_agreement":null},{"id":"W2131468492","doi":"10.1002/jrsm.1055","title":"Evidence‐based sample size estimation based upon an updated meta‐regression analysis","year":2012,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"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; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Meta-regression; Sample size determination; Statistics; Meta-analysis; Econometrics; Regression analysis; Computer science; Set (abstract data type); Regression; Sample (material); Contrast (vision); Statistical power; Estimation; Mathematics; Medicine; Artificial intelligence","score_opus":0.6002511614464304,"score_gpt":0.6067797145749805,"score_spread":0.006528553128550052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131468492","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":[0.0025849813,0.0003180346,0.9953165,0.0006485046,0.000079767684,0.0004886725,0.00009350329,0.00016834139,0.00030168184],"genre_scores_gemma":[0.18737245,0.0000147186665,0.81208265,0.000060015725,0.00008880829,0.00029187006,0.000015050708,0.00004707424,0.000027382044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9698018,0.026004808,0.0007493504,0.0006702071,0.0016018313,0.001171998],"domain_scores_gemma":[0.76229763,0.23479056,0.00024777182,0.0013232661,0.000620763,0.0007199853],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045976393,0.000403455,0.0013018885,0.00088630186,0.0004857808,0.00022263745,0.0006689969,0.00028243588,0.012051513],"category_scores_gemma":[0.25811818,0.00027221325,0.000526335,0.0031459057,0.00025719858,0.0007293608,0.0001310802,0.0005956916,0.00003876036],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005251924,0.0015248398,0.0022213329,0.00050126744,0.0031409406,0.000011627668,0.00026531785,0.00025206007,0.031086102,0.076577276,0.00087913324,0.8830149],"study_design_scores_gemma":[0.00018276695,0.00016932911,0.004398736,0.00023416831,0.005494843,0.0000011401775,0.00009692312,0.5543201,0.16470759,0.26958135,0.00031263256,0.00050040934],"about_ca_topic_score_codex":0.00032049997,"about_ca_topic_score_gemma":0.000016921398,"teacher_disagreement_score":0.8825145,"about_ca_system_score_codex":0.00020596861,"about_ca_system_score_gemma":0.00023409403,"threshold_uncertainty_score":0.999973},"labels":[],"label_agreement":null},{"id":"W2147006306","doi":"10.1002/jrsm.18","title":"Development of a combined database for meta‐epidemiological research","year":2010,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision 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":"Ottawa Hospital","funders":"","keywords":"Meta-analysis; Systematic review; Blinding; Randomized controlled trial; Computer science; MEDLINE; Data mining; Database; Medicine; Statistics; Mathematics; Pathology; Biology","score_opus":0.9871852061995543,"score_gpt":0.7842087044533188,"score_spread":0.2029765017462355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147006306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09466042,0.0014058962,0.8754295,0.004921815,0.0004415631,0.0055596493,0.0001373718,0.000020422856,0.01742338],"genre_scores_gemma":[0.041342273,0.000023424403,0.9518229,0.00002878289,0.00009430062,0.002805319,0.0000062514105,0.000022218961,0.003854559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.52760434,0.4170967,0.021979645,0.00392318,0.026885025,0.002511128],"domain_scores_gemma":[0.12390356,0.84489524,0.003257156,0.012130138,0.014820351,0.0009935496],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9218597,0.00034964975,0.0068042264,0.0019103596,0.0007919954,0.0004840399,0.0055682096,0.00027263854,0.02436551],"category_scores_gemma":[0.8787564,0.00014814608,0.0026791075,0.003999879,0.0007763245,0.00020851787,0.0011539237,0.0012736514,0.0009788207],"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":[0.00017857275,0.00057065015,0.00085963553,0.000398034,0.0031461485,0.000005132775,0.00068208313,0.0000051244388,0.20346542,0.071080685,0.10149754,0.61811095],"study_design_scores_gemma":[0.00017628072,0.000099040335,0.0014816902,0.00004139274,0.00039432704,0.0000040384007,0.0010401135,0.0066912547,0.09220478,0.056026038,0.8415969,0.00024411923],"about_ca_topic_score_codex":0.000022070124,"about_ca_topic_score_gemma":0.000058852766,"teacher_disagreement_score":0.7400994,"about_ca_system_score_codex":0.00005081494,"about_ca_system_score_gemma":0.00063522696,"threshold_uncertainty_score":0.9998121},"labels":[],"label_agreement":null},{"id":"W2156696492","doi":"10.1002/jrsm.1146","title":"We know less than we should about methods of meta‐analysis","year":2015,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Sudbury","funders":"","keywords":"Library science; Computer science; Citation; Information retrieval; Medical library; Statistic; Operations research; Statistics; Mathematics","score_opus":0.9784588548526072,"score_gpt":0.7464486883589169,"score_spread":0.23201016649369033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156696492","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":[0.00082260824,0.1043159,0.8566325,0.007209854,0.00022945646,0.001124316,0.00005922234,0.000021780601,0.02958439],"genre_scores_gemma":[0.019828573,0.0024986584,0.94637287,0.000045513796,0.00013341152,0.0004678887,0.0000025725074,0.000054727705,0.03059581],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.51248634,0.44967574,0.013088222,0.002784685,0.020618284,0.001346757],"domain_scores_gemma":[0.6374591,0.3253931,0.006883693,0.01724392,0.011173564,0.0018466214],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8100159,0.0007086941,0.016127905,0.005278533,0.0003280864,0.0012388271,0.007299324,0.00040571688,0.019243618],"category_scores_gemma":[0.43332794,0.0003369313,0.013807189,0.018298572,0.00063466927,0.00047696158,0.0011433769,0.0008635498,0.001204231],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051778985,0.00028829274,0.0011608191,0.00027202195,0.13979436,0.000012801266,0.0022444075,0.0006245193,0.0026309139,0.0067940243,0.025821006,0.82030505],"study_design_scores_gemma":[0.00020148799,0.0001287149,0.00054056576,0.00009248523,0.14286475,0.000010966166,0.01226436,0.041691683,0.040377025,0.06720247,0.6938438,0.00078174204],"about_ca_topic_score_codex":0.00030227134,"about_ca_topic_score_gemma":0.00012331207,"teacher_disagreement_score":0.8195233,"about_ca_system_score_codex":0.0001315627,"about_ca_system_score_gemma":0.00052924105,"threshold_uncertainty_score":0.99990827},"labels":[],"label_agreement":null},{"id":"W2338480338","doi":"10.1002/jrsm.1204","title":"Disconnected by design: analytic approach in treatment networks having no common comparator","year":2016,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":53,"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; University of British Columbia","funders":"National Institutes of Health","keywords":"Computer science; Bayesian network; Risk analysis (engineering); Artificial intelligence; Medicine","score_opus":0.834068243143668,"score_gpt":0.6795690327267213,"score_spread":0.1544992104169467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338480338","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":[0.0028607831,0.0002192436,0.9925253,0.00040568959,0.00017202293,0.0014173188,0.000060647108,0.00010274605,0.002236287],"genre_scores_gemma":[0.042372115,0.00022967231,0.9555378,0.000017097054,0.0002213519,0.0008253503,0.0000014622294,0.00008771884,0.0007074263],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9428677,0.052564196,0.0014191921,0.000987526,0.00086819544,0.0012931834],"domain_scores_gemma":[0.55087423,0.44737044,0.00018834068,0.0010132722,0.00019654531,0.00035713267],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052845914,0.0004041538,0.001813638,0.00036164772,0.00020495142,0.00011686402,0.0007774948,0.0003657561,0.00082500535],"category_scores_gemma":[0.27076873,0.00024144865,0.00024673963,0.0010232386,0.00059874146,0.00011844254,0.00024989748,0.0005630326,0.0000878776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017454637,0.004148663,0.0029924836,0.00028804384,0.00077751145,0.0000742823,0.0002294546,0.00010440388,0.026121194,0.029310789,0.021100199,0.9131075],"study_design_scores_gemma":[0.0040807575,0.0013521742,0.0015162935,0.0014312061,0.00037279737,0.000014111279,0.0002824424,0.1463794,0.08137654,0.7592349,0.0025356596,0.0014237198],"about_ca_topic_score_codex":0.00009044328,"about_ca_topic_score_gemma":0.000008060801,"teacher_disagreement_score":0.9116838,"about_ca_system_score_codex":0.0007367457,"about_ca_system_score_gemma":0.00013586988,"threshold_uncertainty_score":0.98459905},"labels":[],"label_agreement":null},{"id":"W2413385969","doi":"10.1002/jrsm.1215","title":"Implications of applying methodological shortcuts to expedite systematic reviews: three case studies using systematic reviews from agri‐food public health","year":2016,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":43,"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 Guelph; Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada","keywords":"Rigour; Systematic review; Meta-analysis; Publication bias; Systematic error; Public health; Computer science; MEDLINE; Management science; Statistics; Econometrics; Psychology; Data science; Medicine; Biology; Mathematics; Economics","score_opus":0.9919902489356272,"score_gpt":0.7661392033767591,"score_spread":0.22585104555886804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2413385969","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042049894,0.14402606,0.8250104,0.0030427566,0.0002948268,0.023094099,0.00008803937,0.000023477309,0.0002153413],"genre_scores_gemma":[0.034171022,0.008084325,0.9368327,0.00025816078,0.00029874497,0.019864265,0.0000018000461,0.000070252936,0.00041869003],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.22861849,0.71264076,0.042252336,0.0037738273,0.010674288,0.0020402814],"domain_scores_gemma":[0.1327342,0.81087464,0.024417708,0.020651083,0.009163948,0.002158424],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.82718486,0.00087356346,0.0251936,0.002236255,0.00091960176,0.00084137154,0.004676858,0.00025350973,0.0013929106],"category_scores_gemma":[0.89334685,0.00032771172,0.0038793448,0.0066301594,0.0003954131,0.00058539415,0.0012894985,0.000444088,0.0012510379],"study_design_candidate":"systematic_review","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":[0.000021601089,0.00045121607,0.0009994617,0.43398455,0.0048793512,0.00006839511,0.0057151057,0.000013322045,0.016920488,0.007234041,0.017369907,0.5123426],"study_design_scores_gemma":[0.0010690645,0.0016131931,0.0011512318,0.6915168,0.00912407,0.0030789413,0.06494964,0.0063240808,0.0043694414,0.12639442,0.085384436,0.0050246664],"about_ca_topic_score_codex":0.00006369554,"about_ca_topic_score_gemma":0.00012716305,"teacher_disagreement_score":0.5073179,"about_ca_system_score_codex":0.0007255154,"about_ca_system_score_gemma":0.00035364504,"threshold_uncertainty_score":0.9999175},"labels":[],"label_agreement":null},{"id":"W2604568423","doi":"10.1002/jrsm.1287","title":"Machine learning for identifying Randomized Controlled Trials: An evaluation and practitioner's guide","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":449,"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":"U.S. National Library of Medicine; Agency for Healthcare Research and Quality; National Institutes of Health; National Cancer Institute; Medical Research Council; McMaster University","keywords":"Computer science; Machine learning; Artificial intelligence; Randomized controlled trial; Workflow; Convolutional neural network; Support vector machine; Systematic review; Sensitivity (control systems); Data mining; MEDLINE; Medicine; Database","score_opus":0.42614576340926547,"score_gpt":0.6226321823758852,"score_spread":0.19648641896661978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604568423","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":[0.00090539915,0.0022017108,0.98510647,0.0039215093,0.0003881909,0.00486666,0.0000018995609,0.00018736182,0.0024208091],"genre_scores_gemma":[0.09274568,0.0002945466,0.90208983,0.000071293085,0.0006605147,0.0035611724,0.000006904919,0.00003676202,0.00053327857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.807717,0.18767226,0.0014552803,0.0008930854,0.001576549,0.0006858312],"domain_scores_gemma":[0.60404533,0.38784233,0.0013799485,0.0014222736,0.0047808704,0.0005292166],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.54417527,0.00023098192,0.0022719135,0.00084369146,0.001321518,0.0008525858,0.00077105826,0.00016417725,0.00021216732],"category_scores_gemma":[0.6465802,0.00016653322,0.00037989736,0.0005819079,0.00031797698,0.0008118777,0.00030962608,0.00066495803,0.000014206147],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016697977,0.00006124123,0.000069347625,0.00013762123,0.000303536,0.0000017643113,0.0015083441,0.00021907943,0.0049879346,0.017874792,0.0001562171,0.9579821],"study_design_scores_gemma":[0.040827073,0.0001922546,0.00006662342,0.000105906816,0.00013152132,0.0000099324325,0.00014645974,0.92734456,0.0033508802,0.022449857,0.00520885,0.00016609058],"about_ca_topic_score_codex":0.00057931297,"about_ca_topic_score_gemma":0.000032473785,"teacher_disagreement_score":0.95781606,"about_ca_system_score_codex":0.00017317777,"about_ca_system_score_gemma":0.00045805157,"threshold_uncertainty_score":0.9999786},"labels":[],"label_agreement":null},{"id":"W2619187656","doi":"10.1002/jrsm.1243","title":"Evaluating the accuracy and economic value of a new test in the absence of a perfect reference test","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Bacterial Identification and Susceptibility Testing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; McGill University Health Centre; University of Toronto","funders":"","keywords":"Test (biology); Medicine; Confidence interval; Diagnostic test; Diagnostic accuracy; Computer science; Statistics; Internal medicine; Mathematics; Pediatrics","score_opus":0.34409201938422895,"score_gpt":0.5575045538813157,"score_spread":0.21341253449708675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619187656","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":[0.99781936,0.0001494502,0.00015175044,0.00065157126,0.000020975333,0.00025554857,0.000010179197,0.0000016495889,0.00093954057],"genre_scores_gemma":[0.9843975,0.00015555369,0.015217239,0.000009026195,0.00006124982,0.000029222841,0.0000012493977,0.000006517157,0.00012245469],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973073,0.0018082567,0.00027557128,0.00026720113,0.0001643951,0.0001772663],"domain_scores_gemma":[0.98716486,0.011355115,0.00021649768,0.0010973206,0.00012675127,0.000039459064],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016625443,0.000072441944,0.00015205139,0.000040377847,0.00025038046,0.00010723286,0.00078132714,0.00006600105,0.000025163197],"category_scores_gemma":[0.12683171,0.000045644774,0.00004006538,0.000054147054,0.000374222,0.000010012694,0.00026692852,0.00015737758,0.0000019286483],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001963153,0.000030009174,0.018494494,0.00003276566,0.000006089046,1.5143821e-7,0.00021650305,0.000004300945,0.9005696,0.00011971917,0.000034877306,0.08047186],"study_design_scores_gemma":[0.00014956204,0.00024852355,0.4613861,0.0000889465,0.000009401933,0.000006679766,0.0004655987,0.0027559067,0.53360575,0.0008105335,0.00039116267,0.00008183535],"about_ca_topic_score_codex":0.0012524643,"about_ca_topic_score_gemma":0.00016084651,"teacher_disagreement_score":0.44289163,"about_ca_system_score_codex":0.000013086578,"about_ca_system_score_gemma":0.0002607122,"threshold_uncertainty_score":0.8805233},"labels":[],"label_agreement":null},{"id":"W2623116935","doi":"10.1002/jrsm.1244","title":"Paule‐Mandel estimators for network meta‐analysis with random inconsistency effects","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Medical Research Council","keywords":"Estimator; Computer science; Meta-analysis; Random effects model; Statistics; Econometrics; Mathematics; Medicine","score_opus":0.4494998410577451,"score_gpt":0.5848635729691072,"score_spread":0.13536373191136208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623116935","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":[0.00015591913,0.0005623799,0.9927399,0.0004905143,0.00011173542,0.0013344877,0.00003944478,0.00007770979,0.004487886],"genre_scores_gemma":[0.012007573,0.00004889247,0.9853237,0.000025554396,0.00021766551,0.0019898182,0.0000015987513,0.00006869619,0.00031648058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9888695,0.0077165226,0.0005832705,0.00079758704,0.00088754087,0.0011455857],"domain_scores_gemma":[0.8237362,0.17273554,0.0003510448,0.0018837211,0.00092024344,0.0003732353],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031845655,0.00038901687,0.0024440864,0.000368989,0.0018097371,0.00054165523,0.0010861905,0.00021287725,0.00029607062],"category_scores_gemma":[0.17017461,0.00024738946,0.0009850913,0.0006337779,0.00075628544,0.00019409129,0.00028734774,0.00048177128,0.000010386018],"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":[0.0012387459,0.00036965322,0.0011284588,0.0019415653,0.13477193,0.00008173027,0.00014666806,0.00003907255,0.00022842431,0.57591534,0.0029388194,0.28119957],"study_design_scores_gemma":[0.00076177315,0.0002038085,0.0011384722,0.00010391529,0.06912198,0.000003737225,0.000033447344,0.00990197,0.005290207,0.9124053,0.00062312133,0.00041224808],"about_ca_topic_score_codex":0.000113035756,"about_ca_topic_score_gemma":0.000073790645,"teacher_disagreement_score":0.33648998,"about_ca_system_score_codex":0.000060771625,"about_ca_system_score_gemma":0.00018385191,"threshold_uncertainty_score":0.99999785},"labels":[],"label_agreement":null},{"id":"W2736946457","doi":"10.1002/jrsm.1256","title":"Network meta‐analysis of disconnected networks: How dangerous are random baseline treatment effects?","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; University of British Columbia","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Baseline (sea); Meta-analysis; Computer science; Medicine; Political science","score_opus":0.9055690218436446,"score_gpt":0.6569411513546755,"score_spread":0.24862787048896917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736946457","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":[0.003132869,0.025521843,0.96089196,0.0043767123,0.00029944335,0.002378485,0.00007899808,0.00001714806,0.0033025122],"genre_scores_gemma":[0.69733715,0.0010063307,0.28732607,0.00006700389,0.0005551212,0.0014940652,0.00001588361,0.00006505266,0.012133348],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.70130223,0.28040314,0.0064847907,0.0022354317,0.008376493,0.0011979145],"domain_scores_gemma":[0.618771,0.35316414,0.008482932,0.015871722,0.0031411822,0.00056901586],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.5441519,0.0006437598,0.017289426,0.0016443278,0.0013383472,0.0029369593,0.0051243785,0.00024048043,0.00699168],"category_scores_gemma":[0.46278784,0.00027945056,0.012123142,0.0043229572,0.0005205776,0.00039477492,0.000615641,0.00036677654,0.00017896293],"study_design_candidate":"meta_analysis","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":[0.00026385134,0.00046818366,0.010348008,0.00018537852,0.44870168,0.00007363408,0.00027573158,0.017603498,0.00029293908,0.0009244769,0.017018301,0.5038443],"study_design_scores_gemma":[0.0010132311,0.00025240128,0.017222596,0.0001224632,0.45518512,0.000004961716,0.00068691064,0.46382067,0.0023166812,0.0044919224,0.05410517,0.0007778883],"about_ca_topic_score_codex":0.00021989821,"about_ca_topic_score_gemma":0.0003981694,"teacher_disagreement_score":0.6942043,"about_ca_system_score_codex":0.00010568819,"about_ca_system_score_gemma":0.000103379265,"threshold_uncertainty_score":0.9999658},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2738931935","doi":"10.1002/jrsm.1258","title":"Reconciling disparate data to determine the <i>right</i> answer: A grounded theory of meta analysts' reasoning in meta‐analysis","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University Health Centre; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Meta-analysis; Objectivity (philosophy); Epistemology; Psychology; Grounded theory; Active listening; Confirmation bias; Process (computing); Cognitive psychology; Computer science; Data science; Social psychology; Qualitative research; Sociology; Social science","score_opus":0.9651639076525461,"score_gpt":0.6990054617714189,"score_spread":0.26615844588112725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738931935","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":[0.06269919,0.034566235,0.84014344,0.01214126,0.00036550482,0.0051647066,0.00055321853,0.00002640888,0.044340026],"genre_scores_gemma":[0.6632969,0.00025119277,0.3294215,0.0001177598,0.00008755267,0.0005121595,0.0000074296618,0.000036881247,0.006268671],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.6503727,0.31797543,0.013155924,0.0040472094,0.013024278,0.0014244994],"domain_scores_gemma":[0.62673706,0.3073268,0.00869026,0.052902456,0.003640064,0.0007033841],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.80042166,0.0005492925,0.0125192115,0.0026097354,0.0011380814,0.0029989155,0.019679138,0.00016064849,0.01199065],"category_scores_gemma":[0.5423101,0.00021386956,0.006956266,0.0068190577,0.0005695931,0.00096755393,0.0030663032,0.00064799393,0.00029196596],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025716156,0.0003516674,0.006970667,0.00024815236,0.7240057,0.00009320672,0.0020245619,0.0016953684,0.0051037287,0.014437917,0.005236435,0.23957542],"study_design_scores_gemma":[0.00029262455,0.000101281556,0.016768789,0.0001157574,0.6667506,0.000017475468,0.0034419114,0.19941352,0.012171369,0.05013745,0.04968961,0.001099598],"about_ca_topic_score_codex":0.0008523072,"about_ca_topic_score_gemma":0.003067561,"teacher_disagreement_score":0.6005977,"about_ca_system_score_codex":0.00006995125,"about_ca_system_score_gemma":0.00022126637,"threshold_uncertainty_score":0.9980361},"labels":[],"label_agreement":null},{"id":"W2744173239","doi":"10.1002/jrsm.1253","title":"Bayesian one‐step IPD network meta‐analysis of time‐to‐event data using Royston‐Parmar models","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":40,"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":"Medical Research Council; Universidad de Buenos Aires; Chang Gung Medical Foundation; University of Alberta; Sanjay Gandhi Postgraduate Institute of Medical Sciences; Universitair Medisch Centrum Groningen; Chiang Mai University; Rijksuniversiteit Groningen; Yale University","keywords":"Computer science; Bayesian probability; Consistency (knowledge bases); Proportional hazards model; Meta-analysis; Event (particle physics); Bayesian network; Data mining; Machine learning; Statistics; Artificial intelligence; Medicine; Mathematics; Internal medicine","score_opus":0.9789937325284529,"score_gpt":0.7322230783960013,"score_spread":0.24677065413245158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2744173239","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":[0.00059759454,0.0034103766,0.97816753,0.0015376752,0.00009147598,0.0012712209,0.00020368816,0.000008680513,0.014711745],"genre_scores_gemma":[0.05532733,0.000117226904,0.9359468,0.00006470803,0.0001886185,0.00013383124,0.000012169698,0.000051706957,0.0081575755],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.78128755,0.18262833,0.012407758,0.003772321,0.01831034,0.0015937202],"domain_scores_gemma":[0.8543094,0.08962889,0.0077209123,0.043174457,0.004116447,0.0010499144],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.67800254,0.0005364255,0.012947447,0.0024414726,0.0013838074,0.0025649506,0.017588565,0.0002261679,0.0406108],"category_scores_gemma":[0.24808094,0.0002977949,0.0061286716,0.005797375,0.00039192257,0.0010653483,0.004580316,0.0004820934,0.0013204198],"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":[0.000097552045,0.0004925041,0.00088765105,0.0002741671,0.39436522,0.000023563533,0.00041973867,0.25590876,0.003084031,0.0026716029,0.052738998,0.2890362],"study_design_scores_gemma":[0.000043344415,0.000019768764,0.00033411646,0.000046463072,0.082421124,0.0000015282521,0.0000981487,0.89238,0.00046185034,0.0056375414,0.018285865,0.00027024758],"about_ca_topic_score_codex":0.0005825753,"about_ca_topic_score_gemma":0.00014271149,"teacher_disagreement_score":0.6364713,"about_ca_system_score_codex":0.00010686714,"about_ca_system_score_gemma":0.00031877265,"threshold_uncertainty_score":0.9999474},"labels":[],"label_agreement":null},{"id":"W2750472691","doi":"10.1002/jrsm.1261","title":"Adapting realist synthesis methodology: The case of workplace harassment interventions","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Workplace Violence and Bullying","field":"Social Sciences","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":"University of Saskatchewan; Saskatchewan Health Authority","funders":"","keywords":"Harassment; Psychological intervention; Management science; Computer science; Conceptual framework; Macro; Knowledge management; Sociology; Psychology; Epistemology; Social psychology; Social science; Economics","score_opus":0.6355733019990915,"score_gpt":0.631846285803637,"score_spread":0.003727016195454458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750472691","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":[0.23496184,0.0065717977,0.28096995,0.11273113,0.0025036933,0.0047352756,0.00013624545,0.0004358745,0.35695422],"genre_scores_gemma":[0.6685256,0.0011051634,0.3268122,0.000024470442,0.00039086826,0.00047544972,3.16314e-7,0.000032454787,0.0026334738],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9654657,0.031779375,0.00057414133,0.00049027184,0.0007314589,0.0009590217],"domain_scores_gemma":[0.93259543,0.064722836,0.00049868296,0.0015093825,0.00045082788,0.00022286545],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.122637905,0.00017487588,0.00051775196,0.00030377225,0.007414219,0.0005198501,0.0019756581,0.00022054852,0.000688578],"category_scores_gemma":[0.13394935,0.00012745801,0.000429077,0.00049164507,0.002672376,0.00034241992,0.00063996745,0.00068386114,0.000030095744],"study_design_candidate":"design_other","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":[0.000081795246,0.00014344913,0.0017955041,0.00016499145,0.00020986256,0.00022601576,0.0047764275,0.000014592526,0.0026825087,0.046165343,0.0025869762,0.9411525],"study_design_scores_gemma":[0.0006421121,0.0003290169,0.009441427,0.012990615,0.0011420824,0.00032820628,0.56267667,0.0020011493,0.20640245,0.07642584,0.1257665,0.0018539326],"about_ca_topic_score_codex":0.02338032,"about_ca_topic_score_gemma":0.0055836714,"teacher_disagreement_score":0.9392986,"about_ca_system_score_codex":0.00021780927,"about_ca_system_score_gemma":0.00036082766,"threshold_uncertainty_score":0.993878},"labels":[],"label_agreement":null},{"id":"W2762597371","doi":"10.1002/jrsm.1272","title":"A scoping approach to systematically review published reviews: Adaptations and recommendations","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Manitoba Health; University of Manitoba","funders":"Manitoba Health Research Council; Heart and Stroke Foundation of Canada","keywords":"Systematic review; Multidisciplinary approach; Health care; Publication; MEDLINE; Engineering ethics; Medical education; Medicine; Psychology; Political science; Sociology; Social science; Engineering","score_opus":0.9562756172992223,"score_gpt":0.732530525072342,"score_spread":0.22374509222688033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762597371","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":[0.000049862752,0.05130843,0.74557483,0.043160982,0.00020108001,0.008821954,0.000020417714,0.000015071112,0.15084739],"genre_scores_gemma":[0.0016591663,0.0126232095,0.9737823,0.0005110328,0.00011219875,0.0036035546,0.0000035823548,0.00002812147,0.007676856],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.72901195,0.23999874,0.01683042,0.003037333,0.010009255,0.001112313],"domain_scores_gemma":[0.78337365,0.16554652,0.010324053,0.029767998,0.009041227,0.0019465218],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.71929663,0.0003563408,0.0061187735,0.0010032427,0.0020156987,0.0075051854,0.005244562,0.00011328469,0.005225578],"category_scores_gemma":[0.87200063,0.00017982813,0.0011757858,0.0020051126,0.00023859672,0.0010337632,0.0010645906,0.00045502544,0.0023685955],"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":[0.0000032779164,0.0001075633,0.00021640322,0.010942959,0.00020395513,0.000001385355,0.0003549346,0.0000025030827,0.00013243442,0.017989576,0.2868491,0.6831959],"study_design_scores_gemma":[0.00017419198,0.0000713302,0.0035107092,0.07739039,0.00080667174,0.000050726183,0.0016915352,0.012628443,0.000112603,0.018927647,0.8838065,0.00082924205],"about_ca_topic_score_codex":0.000028964902,"about_ca_topic_score_gemma":0.000017965442,"teacher_disagreement_score":0.68236667,"about_ca_system_score_codex":0.000080037484,"about_ca_system_score_gemma":0.00021357815,"threshold_uncertainty_score":0.99928355},"labels":[],"label_agreement":null},{"id":"W2783474459","doi":"10.1002/jrsm.1289","title":"Information retrieval for systematic reviews in food and feed topics: A narrative review","year":2018,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision 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":"University of Guelph","funders":"Iowa State University; National Pork Board","keywords":"Narrative; Computer science; Information retrieval; Data science","score_opus":0.9157350792377867,"score_gpt":0.7090918911960139,"score_spread":0.20664318804177284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783474459","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.8545997e-7,0.9527588,0.013966111,0.00037052511,0.00019368534,0.030911205,0.0000629801,0.000007259929,0.0017290675],"genre_scores_gemma":[1.4428213e-7,0.9175895,0.072015196,0.0000947631,0.00020478072,0.0077305213,0.000018493223,0.000035660327,0.0023109633],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.471439,0.47103918,0.043531157,0.0023272238,0.0103323655,0.0013310845],"domain_scores_gemma":[0.37719575,0.5492038,0.04050777,0.019579582,0.012334682,0.0011784392],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7776597,0.0009958252,0.033141404,0.0029087118,0.0003982906,0.0016800346,0.003994372,0.00058871164,0.0013596214],"category_scores_gemma":[0.8512693,0.00044241245,0.005594623,0.0066754553,0.00027033561,0.0008053106,0.0005959325,0.0009003064,0.0016348218],"study_design_candidate":"systematic_review","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":[0.0000030135384,0.000012799337,2.0155221e-7,0.48077422,0.00021699125,3.5903653e-7,0.0004004323,1.0933466e-8,7.054607e-8,0.00028774617,0.02233111,0.49597305],"study_design_scores_gemma":[0.000046082387,0.00008533736,3.8676748e-7,0.31892005,0.0007805506,0.000016640905,0.000394461,0.000085283136,0.0000012001144,0.0012809054,0.6781227,0.0002663699],"about_ca_topic_score_codex":0.000004286037,"about_ca_topic_score_gemma":0.0000112789785,"teacher_disagreement_score":0.65579164,"about_ca_system_score_codex":0.00037572402,"about_ca_system_score_gemma":0.0006201211,"threshold_uncertainty_score":0.99980277},"labels":[],"label_agreement":null},{"id":"W2800879685","doi":"10.1002/jrsm.1300","title":"A framework for identifying treatment‐covariate interactions in individual participant data network meta‐analysis","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":15,"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":"Medical Research Council; Universidad de Buenos Aires; Chang Gung Medical Foundation; University of Alberta; Sanjay Gandhi Postgraduate Institute of Medical Sciences; Universitair Medisch Centrum Groningen; Chiang Mai University; Rijksuniversiteit Groningen; Yale University","keywords":"Covariate; Meta-analysis; Computer science; Econometrics; Statistics; Machine learning; Medicine; Mathematics","score_opus":0.9532471811715045,"score_gpt":0.751006027297974,"score_spread":0.20224115387353048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800879685","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":[0.0058805603,0.014483877,0.9545559,0.007073552,0.00217355,0.0059850714,0.0012377383,0.00021957622,0.008390137],"genre_scores_gemma":[0.146658,0.00019215791,0.8441683,0.00012755746,0.0013201763,0.005357395,0.00010030031,0.00008002409,0.001996058],"study_design_codex":"meta_analysis","study_design_gemma":"not_applicable","domain_scores_codex":[0.97834545,0.016362695,0.0008964676,0.0013118582,0.000853807,0.0022297206],"domain_scores_gemma":[0.9494633,0.04667775,0.00018782131,0.0029016677,0.0002837374,0.00048572733],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03896414,0.0002939176,0.0013206227,0.0013782328,0.0007417203,0.00026041912,0.0016797591,0.00021329393,0.008959282],"category_scores_gemma":[0.010187274,0.00024269916,0.0004946243,0.0037881576,0.00042296833,0.00031966373,0.0008861547,0.000851621,0.00032432162],"study_design_candidate":"meta_analysis","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":[0.002344673,0.0031277912,0.003540931,0.00035861545,0.43869781,0.00013037496,0.016316867,0.000098196884,0.00041161856,0.092544384,0.008909232,0.4335195],"study_design_scores_gemma":[0.0031690774,0.0030996604,0.041195467,0.00045875012,0.3039972,0.000039592964,0.020498767,0.05502293,0.0083171055,0.2539779,0.3078221,0.0024014546],"about_ca_topic_score_codex":0.0028289175,"about_ca_topic_score_gemma":0.0038831462,"teacher_disagreement_score":0.43111804,"about_ca_system_score_codex":0.00024439243,"about_ca_system_score_gemma":0.00028343927,"threshold_uncertainty_score":0.99815035},"labels":[],"label_agreement":null},{"id":"W2884972765","doi":"10.1002/jrsm.1313","title":"Using systematic reviews in guideline development: The GRADE approach","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":243,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Grading (engineering); Guideline; Systematic review; Certainty; Psychological intervention; Computer science; Confounding; MEDLINE; Psychology; Medicine; Engineering; Nursing; Political science","score_opus":0.9791960199110384,"score_gpt":0.7442177456352804,"score_spread":0.23497827427575801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884972765","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","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":[0.0030952047,0.010669605,0.95466316,0.0008827338,0.00023173704,0.0061559905,0.0000021509202,0.000009875254,0.024289554],"genre_scores_gemma":[0.016825499,0.000088843466,0.97805417,0.0001413535,0.00023967796,0.00082243193,0.0000010837254,0.000029443592,0.003797495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.46801725,0.48884168,0.025636435,0.002165818,0.014022948,0.0013158493],"domain_scores_gemma":[0.7202591,0.23850991,0.0109931845,0.02147537,0.007983257,0.00077918917],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8632087,0.0004009545,0.006124179,0.0014542757,0.0007396342,0.0012525974,0.005380542,0.00014769856,0.0041935598],"category_scores_gemma":[0.5803725,0.00014576312,0.0012400511,0.0070951073,0.00040899284,0.0002504916,0.0006408031,0.0005147315,0.0031947223],"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":[0.000045234927,0.0008680836,0.003813802,0.022557134,0.0014504219,0.000024680217,0.016531084,0.00024956584,0.008574547,0.013878886,0.21715736,0.7148492],"study_design_scores_gemma":[0.00015046725,0.000031342926,0.0006250985,0.0036785966,0.00027632344,0.000061734834,0.005792775,0.24570562,0.0038162298,0.009697546,0.72958916,0.00057510735],"about_ca_topic_score_codex":0.000041638225,"about_ca_topic_score_gemma":0.00003321728,"teacher_disagreement_score":0.7142741,"about_ca_system_score_codex":0.00021462678,"about_ca_system_score_gemma":0.00029746964,"threshold_uncertainty_score":0.9998475},"labels":[],"label_agreement":null},{"id":"W2885593556","doi":"10.1002/jrsm.1314","title":"Design and implementation of a tool for conversion of search strategies between PubMed and Ovid MEDLINE","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College; College of Physicians and Surgeons of Ontario","funders":"","keywords":"MEDLINE; Computer science; Information retrieval; Online search; Syntax; Interface (matter); World Wide Web; Artificial intelligence","score_opus":0.20238052298318512,"score_gpt":0.5209453212250386,"score_spread":0.31856479824185346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885593556","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":[0.7164237,0.00042827922,0.2825265,0.00019159465,0.000012690646,0.0003676686,0.00002139595,0.0000036556592,0.000024518276],"genre_scores_gemma":[0.7202421,0.00023763553,0.2793548,0.0000036346582,0.000065641325,0.000063853986,0.0000058741703,0.000006468637,0.00002002803],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99807894,0.0010626026,0.00019510908,0.00022244683,0.0001862046,0.00025466527],"domain_scores_gemma":[0.9972993,0.0021790427,0.000051254323,0.0001504786,0.00025307035,0.00006682471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007729955,0.0000686481,0.00019742223,0.00010296158,0.00007528542,0.000015307809,0.00011505261,0.00012422273,0.000011645991],"category_scores_gemma":[0.0016824504,0.00005513737,0.000027552893,0.00010222518,0.00080552814,0.000004836017,0.00013515988,0.000057303147,1.18989554e-7],"study_design_candidate":"bench_or_experimental","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":[0.00018254266,0.000011010616,0.002207074,0.00021605572,0.00007031735,1.2933796e-7,0.0001966525,2.3799006e-7,0.49111053,0.000047922476,0.00017721644,0.50578034],"study_design_scores_gemma":[0.000306061,0.00077826355,0.01282641,0.00001854257,0.000019524012,9.693578e-7,0.0019243881,0.00012103045,0.982159,0.00034571206,0.001442693,0.000057371104],"about_ca_topic_score_codex":0.000052104195,"about_ca_topic_score_gemma":0.0000026609596,"teacher_disagreement_score":0.50572294,"about_ca_system_score_codex":0.0000068562445,"about_ca_system_score_gemma":0.00012787312,"threshold_uncertainty_score":0.2968002},"labels":[],"label_agreement":null},{"id":"W2885675882","doi":"10.1002/jrsm.1316","title":"A comparison of heterogeneity variance estimators in simulated random‐effects meta‐analyses","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1026,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Estimator; Meta-analysis; Random effects model; Variance (accounting); Econometrics; Statistics; Variance components; Computer science; Estimation; Mathematics; Economics; Medicine","score_opus":0.6474146937413818,"score_gpt":0.6854525192511277,"score_spread":0.03803782550974588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885675882","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":[0.025828188,0.0005073066,0.971609,0.000066134184,0.000089253575,0.0005744242,0.000013855614,0.000047701003,0.001264126],"genre_scores_gemma":[0.38847938,0.000009485066,0.61136204,0.000005738482,0.000035198536,0.00007265902,2.8765754e-7,0.00002331767,0.000011911037],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9779407,0.01893757,0.0009715584,0.00055433606,0.0008652472,0.00073063583],"domain_scores_gemma":[0.85708576,0.14111575,0.00023998048,0.00079488877,0.00055132713,0.00021226918],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022361413,0.00027979654,0.0019637977,0.00055377267,0.00016349618,0.000055992426,0.0005677435,0.00022277991,0.00045669006],"category_scores_gemma":[0.13551338,0.00020403301,0.00028996027,0.0015174241,0.0007661665,0.00009889595,0.00020893155,0.0005259208,0.000020482881],"study_design_candidate":"bench_or_experimental","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":[0.002154699,0.0033367942,0.008820699,0.0041350555,0.008067599,0.000095145406,0.002069505,0.0001745987,0.20835744,0.18306565,0.0007368717,0.5789859],"study_design_scores_gemma":[0.00045875905,0.00019654635,0.0012959633,0.00021700855,0.00069166283,0.000001442721,0.000050306127,0.066957325,0.6171876,0.31267804,0.00006592388,0.00019943313],"about_ca_topic_score_codex":0.00022969728,"about_ca_topic_score_gemma":0.00003856561,"teacher_disagreement_score":0.5787865,"about_ca_system_score_codex":0.00007538885,"about_ca_system_score_gemma":0.00012606953,"threshold_uncertainty_score":0.87176853},"labels":[],"label_agreement":null},{"id":"W2886527588","doi":"10.1002/jrsm.1317","title":"Discriminating between empirical studies and nonempirical works using automated text classification","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision 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":false,"ca_institutions":"McGill University; Université de Montréal; Computer Research Institute of Montréal","funders":"Medical Research Council","keywords":"Computer science; Empirical research; Natural language processing; Artificial intelligence; Statistics; Mathematics","score_opus":0.9826945330606024,"score_gpt":0.7893720715156879,"score_spread":0.1933224615449145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886527588","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":[0.5491386,0.0030178921,0.4356228,0.0055497144,0.00021212555,0.0010904763,0.000008080411,0.00007497077,0.005285339],"genre_scores_gemma":[0.5791526,0.000050120263,0.41994816,0.000032678785,0.00030002266,0.000054418146,6.2641567e-7,0.000019181041,0.0004422032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.86152214,0.12263646,0.0061623203,0.0017293269,0.0071603134,0.0007894357],"domain_scores_gemma":[0.75626814,0.2299128,0.0025983334,0.0045450903,0.0060699712,0.00060567015],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4401701,0.00032580073,0.003437842,0.0011448079,0.0010333976,0.0015706356,0.001535217,0.00021893338,0.0010514025],"category_scores_gemma":[0.47400364,0.00016093474,0.00062064175,0.0039153937,0.0011268366,0.00040990039,0.0007363214,0.00048042345,0.00064973434],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012207995,0.00004747498,0.056073386,0.00011514277,0.0004786976,0.0000038309036,0.0022147275,0.000003999419,0.0038319735,0.0003298352,0.014631664,0.92225707],"study_design_scores_gemma":[0.00018740867,0.0001648381,0.27669266,0.00076776365,0.0007091716,0.000023682132,0.021960072,0.64976406,0.004450294,0.020359268,0.024290057,0.00063069316],"about_ca_topic_score_codex":0.000013531621,"about_ca_topic_score_gemma":0.00000853711,"teacher_disagreement_score":0.9216264,"about_ca_system_score_codex":0.0001676258,"about_ca_system_score_gemma":0.00013617614,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W2888732220","doi":"10.1002/jrsm.1319","title":"Methods to calculate uncertainty in the estimated overall effect size from a random‐effects meta‐analysis","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":238,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Meta-analysis; Random effects model; Confidence interval; Statistics; Point estimation; Econometrics; Outcome (game theory); Computer science; Prediction interval; Interval (graph theory); Mathematics; Medicine","score_opus":0.8407238715168954,"score_gpt":0.6957608599089178,"score_spread":0.14496301160797764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888732220","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081764266,0.005100101,0.89604867,0.0040572532,0.00027523775,0.0055348254,0.000055305183,0.00003330248,0.007131015],"genre_scores_gemma":[0.24445195,0.00002890831,0.75138617,0.0005753125,0.00016985367,0.0018427386,0.000003744257,0.00004009022,0.0015012387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.43360215,0.5458371,0.0066496157,0.0025485905,0.010115785,0.0012467565],"domain_scores_gemma":[0.113742605,0.8687429,0.0020959885,0.011822648,0.0028461718,0.0007497158],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.78871727,0.00076434837,0.012824617,0.002584667,0.00063598366,0.0023386364,0.0065345564,0.0002948964,0.020459048],"category_scores_gemma":[0.7272811,0.00029631134,0.008801485,0.017702946,0.0004370976,0.00027096662,0.0007380999,0.0008292895,0.00259054],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001272629,0.0005026762,0.0033556612,0.0002806561,0.25244525,0.00015763949,0.0072800536,0.0060638073,0.03924012,0.0014100225,0.023019677,0.66497177],"study_design_scores_gemma":[0.001962008,0.0007775958,0.036833186,0.0001826001,0.23402844,0.00001426482,0.0010013568,0.5341312,0.048052646,0.06889893,0.07243551,0.001682243],"about_ca_topic_score_codex":0.0023308324,"about_ca_topic_score_gemma":0.00045569777,"teacher_disagreement_score":0.66328955,"about_ca_system_score_codex":0.000162511,"about_ca_system_score_gemma":0.00015143801,"threshold_uncertainty_score":0.9999489},"labels":[],"label_agreement":null},{"id":"W2899927427","doi":"10.1002/jrsm.1330","title":"The impact of the peer review of literature search strategies in support of rapid review reports","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Agency for Drugs and Technologies in Health","funders":"","keywords":"Subject (documents); Peer review; Information retrieval; Scrutiny; Inclusion (mineral); Computer science; Technical peer review; Psychology; World Wide Web; Political science","score_opus":0.7743918792844233,"score_gpt":0.7358830040339657,"score_spread":0.03850887525045765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899927427","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038855378,0.8448905,0.0012451286,0.027778223,0.00066156057,0.004764939,0.00027090075,0.000017306222,0.081516065],"genre_scores_gemma":[0.3008852,0.68021387,0.013409195,0.0001371413,0.000150242,0.00014015805,0.0000041637554,0.000044306347,0.0050157537],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.919664,0.033704843,0.0045126216,0.0013141105,0.03903083,0.0017735637],"domain_scores_gemma":[0.6658288,0.20864178,0.0030332147,0.011585344,0.10998036,0.00093044527],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.5225989,0.00020989713,0.0012123791,0.014807169,0.00029088784,0.0005684723,0.0050825765,0.00016301314,0.0019823827],"category_scores_gemma":[0.5979723,0.00008581371,0.0008382134,0.19689378,0.002228286,0.00046620815,0.0017106617,0.0009561941,0.000015568981],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007561438,0.00028132476,0.008383948,0.0048804227,0.00010276051,0.00002279088,0.00034826854,0.000003130233,0.009546359,0.0007825237,0.23717085,0.738402],"study_design_scores_gemma":[0.0004444631,0.0028010767,0.26778242,0.054895885,0.00008694873,0.00020447493,0.001811576,0.00063591363,0.25514275,0.03960421,0.37585276,0.00073752046],"about_ca_topic_score_codex":0.00036652084,"about_ca_topic_score_gemma":0.000013059389,"teacher_disagreement_score":0.73766446,"about_ca_system_score_codex":0.0001535608,"about_ca_system_score_gemma":0.002705858,"threshold_uncertainty_score":0.9989299},"labels":[],"label_agreement":null},{"id":"W2903321323","doi":"10.1002/jrsm.1333","title":"The use of mathematical modeling studies for evidence synthesis and guideline development: A glossary","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":61,"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; The Quebec Population Health Research Network","funders":"National Health and Medical Research Council; Victorian Centre for Biostatistics; TDR; World Health Organization","keywords":"Terminology; Glossary; Management science; Computer science; Guideline; Systematic review; Data science; MEDLINE; Medicine; Engineering; Pathology","score_opus":0.9114025315052573,"score_gpt":0.6791936628228623,"score_spread":0.232208868682395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903321323","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.022904387,0.007183475,0.9603471,0.0076768654,0.000057504843,0.0015477585,0.000013337757,0.000105283965,0.00016427427],"genre_scores_gemma":[0.018049328,0.002203209,0.97805107,0.00006974242,0.00014686541,0.0011188234,1.2479468e-7,0.000040703213,0.00032011973],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9911289,0.0050816233,0.0014890081,0.000628324,0.0008009139,0.0008712321],"domain_scores_gemma":[0.48611286,0.51073164,0.0002473675,0.0007910358,0.0019644196,0.00015265743],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053893365,0.0002867693,0.0010969024,0.00017521017,0.0013289325,0.00008634782,0.00061127264,0.00015047655,0.000056948582],"category_scores_gemma":[0.7502432,0.00016111795,0.00017093889,0.00043612788,0.0016820078,0.00018613701,0.0011504594,0.00026042276,0.000014080154],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010199771,0.00029593013,0.00018774395,0.0036487763,0.0018647308,0.0000046666955,0.0029237024,0.00006453782,0.004256532,0.04624926,0.020844756,0.91863936],"study_design_scores_gemma":[0.00016993494,0.00029194137,0.000078798774,0.0028168007,0.0003093596,0.000007790657,0.0021264276,0.20737602,0.04906663,0.6857678,0.05147761,0.0005108565],"about_ca_topic_score_codex":0.000026614905,"about_ca_topic_score_gemma":0.000024069692,"teacher_disagreement_score":0.91812855,"about_ca_system_score_codex":0.00019041661,"about_ca_system_score_gemma":0.00016994888,"threshold_uncertainty_score":0.9999712},"labels":[],"label_agreement":null},{"id":"W2947538236","doi":"10.1002/jrsm.1362","title":"Estimating hazard ratios from published Kaplan‐Meier survival curves: A methods validation study","year":2019,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; Public Health Ontario; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Centre for Applied Research in Cancer Control","keywords":"Intraclass correlation; Inter-rater reliability; Hazard ratio; Statistics; Reliability (semiconductor); Medicine; Standard error; Gold standard (test); Mathematics; Confidence interval; Reproducibility; Physics","score_opus":0.7748885543966163,"score_gpt":0.7029467070522295,"score_spread":0.0719418473443868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947538236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.026071317,0.00015589633,0.9575539,0.0011225785,0.0023095019,0.0043414724,0.00012934742,0.0003397504,0.007976192],"genre_scores_gemma":[0.0039468757,0.00003267494,0.9931335,0.00008260553,0.0008219396,0.00096928567,0.000010680472,0.0001786573,0.00082382065],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82870734,0.16054447,0.003183572,0.0022321856,0.0037014398,0.0016310016],"domain_scores_gemma":[0.26763305,0.72635424,0.0007851159,0.0031927086,0.0014104035,0.0006244665],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23504312,0.0005908317,0.0025959515,0.00058985554,0.0004047987,0.0006724669,0.001762715,0.00048083038,0.009094314],"category_scores_gemma":[0.82062197,0.0004926352,0.000418119,0.0017709226,0.0003356333,0.00060210755,0.00095226686,0.0019522681,0.00041123637],"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":[0.001046052,0.0042052595,0.013486969,0.002670925,0.0025562996,0.00006955235,0.0020340667,0.000074934534,0.030993896,0.023777064,0.014865037,0.9042199],"study_design_scores_gemma":[0.0014784621,0.00051047595,0.0027489504,0.001156267,0.0004753343,0.000003266934,0.0013872813,0.018356984,0.04324121,0.9289679,0.0008357418,0.00083813246],"about_ca_topic_score_codex":0.0002512846,"about_ca_topic_score_gemma":0.0000128867305,"teacher_disagreement_score":0.9051908,"about_ca_system_score_codex":0.00030464627,"about_ca_system_score_gemma":0.00041448345,"threshold_uncertainty_score":0.9997525},"labels":[],"label_agreement":null},{"id":"W2986493832","doi":"10.1002/jrsm.1385","title":"Construct validity of the Physiotherapy Evidence Database (PEDro) quality scale for randomized trials: Item response theory and factor analyses","year":2019,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Physiotherapy Foundation of Canada; National Science Foundation","keywords":"Item response theory; Construct (python library); Scale (ratio); Construct validity; Psychology; Randomized controlled trial; Clinical psychology; Quality (philosophy); Psychometrics; Physical therapy; Applied psychology; Medicine; Computer science","score_opus":0.942994865986386,"score_gpt":0.7599710097067921,"score_spread":0.18302385627959394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986493832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73163605,0.002011356,0.2629606,0.0005489071,0.00036704112,0.0021156555,0.00018178014,0.000022876142,0.00015571229],"genre_scores_gemma":[0.5596728,0.0005860564,0.4388112,0.00004623538,0.00009025429,0.00020543515,3.8959485e-7,0.00002254929,0.00056512794],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.50680315,0.48572102,0.0025300968,0.0011894222,0.0030896699,0.0006666644],"domain_scores_gemma":[0.03266813,0.9621036,0.0013989665,0.0023544165,0.001289653,0.00018521365],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7405687,0.00025668045,0.0029899129,0.00094171154,0.00040625595,0.00029114285,0.0019968448,0.00015967006,0.000805069],"category_scores_gemma":[0.9807892,0.00012375992,0.0010197462,0.0031520573,0.0015797925,0.0003849678,0.00059427967,0.0003985416,0.000006612944],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12082169,0.000066242894,0.0103404,0.00013188749,0.00017419612,3.2010766e-7,0.00038339008,0.0000060790576,0.5309297,0.0010466649,0.00022523405,0.3358742],"study_design_scores_gemma":[0.018386386,0.00023245573,0.079511024,0.0006406538,0.00015177825,0.0000057669254,0.0041218605,0.0027416057,0.7144586,0.17829923,0.0010254619,0.00042517626],"about_ca_topic_score_codex":0.00014370593,"about_ca_topic_score_gemma":0.000003159986,"teacher_disagreement_score":0.4763826,"about_ca_system_score_codex":0.000059412814,"about_ca_system_score_gemma":0.0003893722,"threshold_uncertainty_score":0.88149405},"labels":[],"label_agreement":null},{"id":"W2996058025","doi":"10.1002/jrsm.1391","title":"Adding value to core outcome set development using multimethod systematic reviews","year":2019,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Ontario Tech University","funders":"Medical Research Council","keywords":"Outcome (game theory); Value (mathematics); Set (abstract data type); Systematic review; Core (optical fiber); Computer science; Research methodology; Management science; Psychology; MEDLINE; Medicine; Mathematics; Political science; Mathematical economics; Machine learning; Environmental health; Engineering","score_opus":0.8743403661020697,"score_gpt":0.7235574148921967,"score_spread":0.15078295120987295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996058025","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":[0.08959224,0.004583725,0.64754206,0.003745897,0.0021311573,0.062168103,0.000043480184,0.0014776023,0.18871574],"genre_scores_gemma":[0.022794817,0.00012435368,0.9708668,0.00007712402,0.00013495625,0.0015189464,9.467e-7,0.00006836639,0.004413674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9485886,0.04378557,0.0014348865,0.0009186479,0.003384701,0.0018875573],"domain_scores_gemma":[0.9484583,0.04839676,0.00026522586,0.0013019544,0.0008102736,0.0007674848],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23261164,0.00030687166,0.0013803146,0.0012691033,0.0011631706,0.000364756,0.0020488137,0.00031267022,0.0006875162],"category_scores_gemma":[0.16813591,0.00025785892,0.00025001343,0.002856929,0.0002839276,0.00028501864,0.00087670115,0.000886469,0.0017481075],"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":[0.00022786492,0.00057904725,0.014179752,0.07514148,0.00062673015,0.00015801827,0.076047294,0.00037302612,0.21605754,0.041047912,0.0072173364,0.568344],"study_design_scores_gemma":[0.0005421065,0.00024771085,0.0010700504,0.046811786,0.00017179607,0.000040478837,0.04409478,0.015386451,0.12569548,0.0033394597,0.7596039,0.0029959807],"about_ca_topic_score_codex":0.0012095417,"about_ca_topic_score_gemma":0.000053550102,"teacher_disagreement_score":0.75238657,"about_ca_system_score_codex":0.0019328134,"about_ca_system_score_gemma":0.0009151544,"threshold_uncertainty_score":0.99998736},"labels":[],"label_agreement":null},{"id":"W3001927762","doi":"10.1002/jrsm.1389","title":"Searching practices and inclusion of unpublished studies in systematic reviews of diagnostic accuracy","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Systematic review; MEDLINE; Medicine; Guideline; Meta-analysis; Cochrane collaboration; Cochrane Library; Family medicine; Internal medicine; Pathology","score_opus":0.9762685390411421,"score_gpt":0.765712340168099,"score_spread":0.2105561988730431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001927762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5303673,0.36290526,0.04853396,0.025322799,0.0003621844,0.022021778,0.00003174853,0.000022395532,0.010432545],"genre_scores_gemma":[0.8167732,0.013719969,0.16871095,0.00008054207,0.000059575592,0.00048487436,5.6725776e-7,0.000021068672,0.00014929332],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.3491783,0.60711724,0.02470879,0.002098156,0.016080748,0.00081678905],"domain_scores_gemma":[0.01607534,0.9613967,0.015167385,0.0033898198,0.0036074785,0.00036330975],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73279214,0.0002859826,0.008826553,0.0012434205,0.0003574901,0.000337154,0.0028071955,0.00009395554,0.00074700086],"category_scores_gemma":[0.99094427,0.00012927566,0.0008211068,0.0049972893,0.00039000853,0.0007812258,0.005771566,0.00049084536,0.000068159396],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012715992,0.00046711066,0.014576322,0.3014322,0.0016062483,0.000054474847,0.08766422,0.00013409091,0.03326096,0.005283825,0.0074570295,0.5479364],"study_design_scores_gemma":[0.0022918605,0.0018264741,0.016651109,0.16438258,0.004915037,0.00010200297,0.2357471,0.16265346,0.087467976,0.1895725,0.13144825,0.0029416538],"about_ca_topic_score_codex":0.000076792094,"about_ca_topic_score_gemma":0.00002120943,"teacher_disagreement_score":0.5449947,"about_ca_system_score_codex":0.000052868716,"about_ca_system_score_gemma":0.00015498618,"threshold_uncertainty_score":0.81791353},"labels":[],"label_agreement":null},{"id":"W3006673017","doi":"10.1002/jrsm.1398","title":"Comparing machine and human reviewers to evaluate the risk of bias in randomized controlled trials","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capital District Health Authority; Institute of Health Economics; University of Alberta","funders":"Canadian Institutes of Health Research; Institute of Health Economics; Alberta Innovates - Health Solutions; Physiotherapy Foundation of Canada; Government of Alberta","keywords":"Blinding; Randomized controlled trial; Computer science; Medical physics; MEDLINE; Sample size determination; Medicine; Applied psychology; Psychology; Statistics; Surgery; Mathematics","score_opus":0.9609323859410629,"score_gpt":0.7227307998086823,"score_spread":0.23820158613238063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006673017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5023127,0.10101604,0.27132413,0.041561686,0.00033164126,0.051034726,0.000059351372,0.000022953203,0.03233675],"genre_scores_gemma":[0.90182966,0.0020454985,0.093805335,0.00019907043,0.00010021931,0.001375249,6.263056e-7,0.000021837479,0.00062251894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.07757422,0.8899349,0.021750074,0.001147778,0.009117885,0.0004751256],"domain_scores_gemma":[0.020957312,0.96499586,0.007262348,0.003833479,0.002439407,0.00051158207],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.96138585,0.00031131558,0.030453082,0.00094932754,0.0002630968,0.00066408445,0.0022120012,0.00007225099,0.0040143253],"category_scores_gemma":[0.97377837,0.000098841156,0.004915943,0.0030858477,0.0003093047,0.000089949564,0.00047164128,0.00048235737,0.00018904785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.071472496,0.0002954177,0.040687066,0.001313711,0.012737396,0.000013614294,0.010342551,0.0017456308,0.013599385,0.01636753,0.029382268,0.80204296],"study_design_scores_gemma":[0.21494733,0.00038617273,0.012977618,0.002094604,0.012252291,0.000005961582,0.006069827,0.6109159,0.007147806,0.06061711,0.071502596,0.0010827675],"about_ca_topic_score_codex":0.00024206412,"about_ca_topic_score_gemma":0.000050149614,"teacher_disagreement_score":0.8009602,"about_ca_system_score_codex":0.000029754692,"about_ca_system_score_gemma":0.00008817553,"threshold_uncertainty_score":0.99689615},"labels":[],"label_agreement":null},{"id":"W3006701470","doi":"10.1002/jrsm.1399","title":"Innovations in framework synthesis as a systematic review method","year":2020,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Ontario Tech University; McMaster University Medical Centre","funders":"","keywords":"Management science; Computer science; Systematic review; Stakeholder; Data science; MEDLINE; Political science; Public relations; Economics","score_opus":0.9235373563940749,"score_gpt":0.8552043114246342,"score_spread":0.0683330449694407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006701470","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.8375476e-8,0.9234039,0.038012035,0.013100603,0.00032499683,0.018932542,0.00021047077,0.00018200441,0.005833401],"genre_scores_gemma":[6.644196e-8,0.6681702,0.28093302,0.0043752454,0.0002755316,0.045610968,0.000006594608,0.0001613152,0.00046705105],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.72518116,0.25929794,0.007791292,0.0017979823,0.0029412245,0.0029903871],"domain_scores_gemma":[0.22886987,0.759663,0.0038037845,0.00413263,0.0019421999,0.00158856],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.21428473,0.0009443407,0.010541468,0.0034617726,0.0015885128,0.00010055388,0.0033036782,0.0013911903,0.0046429373],"category_scores_gemma":[0.7660407,0.0007300405,0.0007598571,0.018513937,0.00029874232,0.0003132119,0.001296466,0.008244838,0.007903744],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002373106,0.000022106511,7.7501215e-7,0.64549214,0.00009829953,0.000020772228,0.0006475742,2.6686132e-8,3.9738714e-7,0.0048944526,0.0033986648,0.3454224],"study_design_scores_gemma":[0.000027220283,0.00001643385,5.934724e-7,0.4863464,0.00048246208,0.000010863967,0.0005003662,0.000011082301,0.0000020593284,0.0011618193,0.5111428,0.00029794336],"about_ca_topic_score_codex":0.0005297597,"about_ca_topic_score_gemma":0.000037232814,"teacher_disagreement_score":0.5517559,"about_ca_system_score_codex":0.0031832925,"about_ca_system_score_gemma":0.014426739,"threshold_uncertainty_score":0.9999052},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3008476194","doi":"10.1002/jrsm.1402","title":"The median and the mode as robust meta‐analysis estimators in the presence of small‐study effects and outliers","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":35,"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":"Medical Research Council Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Medical Research Council; University of Bristol; National Institute for Health and Care Research","keywords":"Meta-analysis; Outlier; Estimator; Statistics; Robustness (evolution); Econometrics; Publication bias; Reliability (semiconductor); Robust statistics; Computer science; Mathematics; Confidence interval; Medicine","score_opus":0.8839268872716101,"score_gpt":0.6515487591271637,"score_spread":0.23237812814444636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008476194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44725105,0.05923158,0.29960996,0.16299964,0.00020399275,0.020554846,0.000036424153,0.00002534606,0.010087169],"genre_scores_gemma":[0.9552735,0.00036471654,0.04315817,0.00015182863,0.000027721448,0.00076316023,1.9996956e-7,0.000013590835,0.0002470875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.60661674,0.37586108,0.005442837,0.0016092802,0.009754392,0.0007157042],"domain_scores_gemma":[0.2883564,0.7025124,0.0019701684,0.005679891,0.0010498248,0.00043135873],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52195716,0.00029242245,0.0044994536,0.00054158363,0.00063425105,0.001323608,0.003914703,0.00007552855,0.00027121312],"category_scores_gemma":[0.4986857,0.000082462924,0.0017077782,0.006109154,0.0011558278,0.00013252582,0.0006371169,0.00054029864,0.000032192656],"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":[0.00083890266,0.0007437906,0.07204568,0.0011915179,0.25514248,0.00012850866,0.16748974,0.017072529,0.0003998092,0.030257843,0.006634022,0.44805518],"study_design_scores_gemma":[0.0006310273,0.0002406666,0.015679976,0.00003172799,0.07206315,0.000007086352,0.067350596,0.8102425,0.0005915997,0.030283567,0.0025223386,0.0003557927],"about_ca_topic_score_codex":0.00057640544,"about_ca_topic_score_gemma":0.00047192376,"teacher_disagreement_score":0.79317,"about_ca_system_score_codex":0.000012913412,"about_ca_system_score_gemma":0.0000914292,"threshold_uncertainty_score":0.9997131},"labels":[],"label_agreement":null},{"id":"W3009456404","doi":"10.1002/jrsm.1405","title":"Multivariate network meta‐analysis of survival function parameters","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Precision Nanosystems (Canada)","funders":"","keywords":"Multivariate statistics; Multivariate analysis; Meta-analysis; Computer science; Function (biology); Statistics; Survival analysis; Econometrics; Mathematics; Medicine; Internal medicine; Biology","score_opus":0.9714935275619198,"score_gpt":0.6950105413173112,"score_spread":0.27648298624460854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009456404","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":[0.0027343638,0.0030325877,0.98169196,0.0029552553,0.00019116832,0.00080079056,0.000040453946,0.000014338942,0.008539071],"genre_scores_gemma":[0.28837368,0.0000732798,0.7091226,0.00023872768,0.00015917953,0.00023552366,0.0000057325924,0.00003425854,0.0017570182],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.67327493,0.2997704,0.010242106,0.0021504308,0.013664437,0.0008976846],"domain_scores_gemma":[0.6832762,0.30014262,0.0048539853,0.0066444823,0.004236319,0.00084639393],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.57119876,0.00036174236,0.011205383,0.0013593303,0.00026986047,0.00063034525,0.0028067576,0.00016383632,0.029384835],"category_scores_gemma":[0.36675718,0.00017699129,0.010225799,0.017694036,0.00022369751,0.00023399627,0.0004524371,0.00045170164,0.00091084593],"study_design_candidate":"meta_analysis","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":[0.00024819124,0.00019589176,0.0056073945,0.00019522777,0.7073,0.000010297937,0.0012165022,0.05827556,0.0047786743,0.010399596,0.023106448,0.18866622],"study_design_scores_gemma":[0.00016225062,0.00019483945,0.013146006,0.000015299429,0.38276538,7.19168e-7,0.0018692057,0.49009994,0.0030863164,0.013045932,0.09505379,0.0005603436],"about_ca_topic_score_codex":0.00012926593,"about_ca_topic_score_gemma":0.000024315144,"teacher_disagreement_score":0.43182436,"about_ca_system_score_codex":0.000032293134,"about_ca_system_score_gemma":0.00010226329,"threshold_uncertainty_score":0.9998671},"labels":[],"label_agreement":null},{"id":"W3015272713","doi":"10.1002/jrsm.1409","title":"Epidemiology and reporting characteristics of <scp>non‐Cochrane</scp> updates of systematic reviews: A cross‐sectional study","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":23,"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":"Interquartile range; Systematic review; Medicine; Psychological intervention; Epidemiology; MEDLINE; Family medicine; Pathology; Surgery; Political science","score_opus":0.9391071364579964,"score_gpt":0.70956632107567,"score_spread":0.2295408153823264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015272713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8858846,0.015792733,0.08925267,0.0003866905,0.00019508733,0.0066174776,0.000046713732,0.000011082967,0.001812941],"genre_scores_gemma":[0.8637645,0.0006463454,0.13398129,0.000058319718,0.00013442611,0.0005184578,0.000002105032,0.000026118178,0.00086843467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.35286063,0.53432304,0.09494281,0.003652727,0.012822,0.0013988295],"domain_scores_gemma":[0.10399921,0.80471987,0.07321344,0.007993361,0.009094462,0.0009796743],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.80902773,0.00035739105,0.014365376,0.00068581646,0.00023753631,0.00022673655,0.0019834787,0.00017355294,0.00081354345],"category_scores_gemma":[0.97222674,0.00017777436,0.0017898689,0.0023322913,0.0004381667,0.0001859923,0.00059512554,0.00047380704,0.00019817571],"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":[0.000013239454,0.00018888112,0.9474202,0.034544155,0.00075268,0.000012973958,0.0019186976,0.0000100493135,0.004278146,0.00044399526,0.0013030573,0.009113968],"study_design_scores_gemma":[0.00025195564,0.00051931635,0.9563049,0.0045692814,0.0009461637,0.00006677968,0.0070105777,0.01986412,0.0035840173,0.0042344164,0.002424701,0.00022375016],"about_ca_topic_score_codex":0.000033109587,"about_ca_topic_score_gemma":0.0000020124019,"teacher_disagreement_score":0.27039683,"about_ca_system_score_codex":0.000032687243,"about_ca_system_score_gemma":0.00013846024,"threshold_uncertainty_score":0.98198843},"labels":[],"label_agreement":null},{"id":"W3021470514","doi":"10.1002/jrsm.1511","title":"Methods for population adjustment with limited access to individual patient data: A review and simulation study","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; Institute of Conservation","keywords":"Covariate; Estimator; Standard error; Sample size determination; Measure (data warehouse); Variance (accounting); Population; Standard deviation; Confidence interval","score_opus":0.7644489907710884,"score_gpt":0.7005175490144144,"score_spread":0.06393144175667398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021470514","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":[0.0050132405,0.0026149096,0.98613596,0.00059553754,0.000027918459,0.005316366,0.00007084741,0.00014024971,0.00008499674],"genre_scores_gemma":[0.009302947,0.0004960551,0.98773247,0.00017035543,0.000039258113,0.0021163626,0.00005186282,0.00005625696,0.000034416153],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891867,0.008292384,0.00056679174,0.0008230278,0.0006777758,0.00045334283],"domain_scores_gemma":[0.95852596,0.03856514,0.00018966645,0.001514981,0.000996898,0.0002073333],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017866848,0.00022867028,0.0006958813,0.00029579987,0.00021692933,0.00017347204,0.00056246296,0.000086965374,0.000055282435],"category_scores_gemma":[0.07395944,0.0001796833,0.00003907243,0.0010477916,0.000047251444,0.0005721345,0.0012488505,0.0002750035,8.146206e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073458374,0.00046870546,0.00034639225,0.0010539461,0.00017918205,0.0000037361021,0.00031950738,0.00006806387,0.00037845655,0.00077766454,0.00048341,0.99584746],"study_design_scores_gemma":[0.003421431,0.011073912,0.0623777,0.017351616,0.008701168,0.000070888666,0.008875056,0.071381,0.20870201,0.5288903,0.07410315,0.0050517675],"about_ca_topic_score_codex":0.000031543477,"about_ca_topic_score_gemma":0.00003793998,"teacher_disagreement_score":0.99079573,"about_ca_system_score_codex":0.00013923807,"about_ca_system_score_gemma":0.00011268176,"threshold_uncertainty_score":0.933841},"labels":[],"label_agreement":null},{"id":"W3022994372","doi":"10.1002/jrsm.1416","title":"Equivalence of entropy balancing and the method of moments for matching‐adjusted indirect comparison","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":28,"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":"Medical Research Council; Medical Research Council Canada; Department of Health and Social Care; University of Bristol; National Institute for Health and Care Research; University Hospitals Bristol NHS Foundation Trust; AstraZeneca","keywords":"Covariate; Statistics; Population; Mathematics; Entropy (arrow of time); Nonparametric statistics; Standard error; Econometrics; Computer science","score_opus":0.5557337790460275,"score_gpt":0.6078522747330801,"score_spread":0.052118495687052624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022994372","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":[0.012164115,0.00028065703,0.98515284,0.00079560844,0.000017090788,0.0011029779,0.000026253732,0.00007037951,0.00039005608],"genre_scores_gemma":[0.20482934,0.00010623858,0.7947487,0.000017611786,0.000024920484,0.00022042761,5.398428e-7,0.000027547017,0.000024647978],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99246943,0.0054134447,0.00071293116,0.00033190686,0.0006526681,0.00041961827],"domain_scores_gemma":[0.91546196,0.08327115,0.0003769361,0.00041246953,0.0003633454,0.00011412344],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019007212,0.00016509411,0.0010018506,0.00015841673,0.00011603557,0.000022307811,0.00053992576,0.00010191572,0.0000389273],"category_scores_gemma":[0.056505308,0.00011218386,0.00013046956,0.0004766102,0.00044709045,0.000103659746,0.00035672408,0.00036891765,5.0724174e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010861284,0.00015299364,0.0004906186,0.0029698277,0.0003104686,0.0000012435825,0.0071293707,0.000028081287,0.5667387,0.20353179,0.0004623992,0.21709834],"study_design_scores_gemma":[0.0003036572,0.000121736965,0.00006861035,0.0002038591,0.000058154354,0.000001141139,0.0010929923,0.010980403,0.6814659,0.3054852,0.0001346859,0.000083631894],"about_ca_topic_score_codex":0.00004639043,"about_ca_topic_score_gemma":0.0000016047702,"teacher_disagreement_score":0.2170147,"about_ca_system_score_codex":0.000051166673,"about_ca_system_score_gemma":0.000066953275,"threshold_uncertainty_score":0.9514421},"labels":[],"label_agreement":null},{"id":"W3030872057","doi":"10.1002/jrsm.1425","title":"Development and validation of study filters for identifying controlled non‐randomized studies in <scp>PubMed</scp> and Ovid <scp>MEDLINE</scp>","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton Health Sciences; Impact","funders":"","keywords":"MEDLINE; Computer science; Randomized controlled trial; Medical physics; Filter (signal processing); Medicine; Information retrieval; Surgery","score_opus":0.8992365636946418,"score_gpt":0.6515213976464072,"score_spread":0.24771516604823463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030872057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.89267886,0.0052286745,0.09154469,0.0004364218,0.0001197295,0.0094519835,0.000007972299,0.000007762125,0.000523937],"genre_scores_gemma":[0.6208643,0.0005905073,0.37130627,0.000059327733,0.00009190489,0.005633731,0.000002160767,0.000033293807,0.0014185066],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8593397,0.115970306,0.013242039,0.002293329,0.008078297,0.0010763201],"domain_scores_gemma":[0.23171955,0.75648963,0.0050843228,0.0021918397,0.0037971002,0.00071756967],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.53893906,0.00038414844,0.008404632,0.0012585203,0.00033175224,0.00068199105,0.0010562773,0.00010900055,0.000040301322],"category_scores_gemma":[0.7989889,0.00020276687,0.000853867,0.0019465543,0.00044498572,0.00030772196,0.0005542744,0.00026846727,0.000019486199],"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":[0.004689531,0.0014053826,0.03786042,0.0072006476,0.01918405,0.00005999937,0.3362355,0.00039361665,0.019116655,0.00096598617,0.024400447,0.5484878],"study_design_scores_gemma":[0.1344396,0.0005317954,0.01764089,0.0010739095,0.0035190606,0.0000111841,0.60433984,0.08743389,0.110204585,0.011543809,0.028821342,0.00044010425],"about_ca_topic_score_codex":0.0000127265985,"about_ca_topic_score_gemma":0.000015640544,"teacher_disagreement_score":0.6405193,"about_ca_system_score_codex":0.000070539514,"about_ca_system_score_gemma":0.00015522084,"threshold_uncertainty_score":0.8268593},"labels":[],"label_agreement":null},{"id":"W3034095928","doi":"10.1002/jrsm.1428","title":"The Kilim plot: A tool for visualizing network meta‐analysis results for multiple outcomes","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"Public Health Research Programme; European Commission; National Institute for Health and Care Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Plot (graphics); Computer science; Meta-analysis; Forest plot; Data science; Statistics; Medicine; Mathematics; Internal medicine","score_opus":0.7463800401262789,"score_gpt":0.6693628014414853,"score_spread":0.0770172386847936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034095928","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":[0.0027774537,0.015009874,0.83359855,0.122332565,0.0010449389,0.01762511,0.0014874646,0.00048023526,0.0056438027],"genre_scores_gemma":[0.056036312,0.00049089704,0.89930713,0.0020294862,0.0017948737,0.029299239,0.00006914876,0.00026010314,0.010712836],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9803352,0.013689024,0.0011498778,0.001192538,0.001174594,0.0024587947],"domain_scores_gemma":[0.81771815,0.17976384,0.00020910404,0.0012052755,0.0005332728,0.00057035487],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056430005,0.00033750737,0.0014781161,0.0003167975,0.0018473349,0.00025500738,0.0013822104,0.0002589749,0.00027394152],"category_scores_gemma":[0.07218026,0.00022091034,0.0016993036,0.0020622695,0.0003370135,0.00011170108,0.00040993482,0.00072039646,0.000080676014],"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":[0.017792232,0.00097195216,0.0029344503,0.0015417536,0.26628667,0.000030854382,0.006148089,0.0005871455,0.00096696167,0.06423541,0.14664936,0.4918551],"study_design_scores_gemma":[0.0029179326,0.0011364709,0.0034774747,0.000024475981,0.019241719,0.0000017152031,0.0028455136,0.045884058,0.0046875845,0.0058602164,0.9132316,0.0006912333],"about_ca_topic_score_codex":0.00024652583,"about_ca_topic_score_gemma":0.00015157595,"teacher_disagreement_score":0.76658225,"about_ca_system_score_codex":0.00016788172,"about_ca_system_score_gemma":0.0002003412,"threshold_uncertainty_score":0.9994521},"labels":[],"label_agreement":null},{"id":"W3043051650","doi":"10.1002/jrsm.1435","title":"Creating effective interrupted time series graphs: Review and recommendations","year":2020,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Canadian Institutes of Health Research; Monash University; Medical Research Council; Australian Government","keywords":"Computer science; Standardization; Visualization; Data mining; Data visualization; Graph; Software; Data extraction; Graph drawing; Information retrieval; Time series; Data science; Machine learning; Theoretical computer science; MEDLINE","score_opus":0.21463601494254203,"score_gpt":0.5644807030011398,"score_spread":0.3498446880585978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043051650","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0386599e-9,0.84763044,0.14726824,0.0015509251,0.0000476415,0.001016664,0.000064016946,0.00013523508,0.0022868186],"genre_scores_gemma":[6.824384e-9,0.7557792,0.24307118,0.00011116613,0.00003686975,0.0003948928,0.000045226698,0.00003245829,0.0005289702],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98167133,0.015790965,0.0007344178,0.0008985909,0.00045711748,0.00044755565],"domain_scores_gemma":[0.98407024,0.014040993,0.0003133519,0.0009383739,0.00032465887,0.00031235305],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0112712,0.00038209558,0.0021045625,0.0006317071,0.0003969291,0.00055457826,0.0015576129,0.00017085373,0.00024415032],"category_scores_gemma":[0.021603579,0.00030281127,0.00031745556,0.0030745235,0.0001927933,0.00057424494,0.001554927,0.0007796806,0.00021501006],"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":[4.7186802e-7,0.000019425575,7.758309e-8,0.018561421,0.00017842659,0.000006048081,0.000056765322,9.998492e-9,0.0000010313793,0.0070668426,0.006205333,0.96790415],"study_design_scores_gemma":[0.000020673493,0.000050333285,2.3534113e-7,0.035293896,0.00036908544,0.000032297878,0.00001422589,0.00073687994,0.00001637691,0.0006256921,0.96257174,0.00026854614],"about_ca_topic_score_codex":0.000007849588,"about_ca_topic_score_gemma":7.220058e-7,"teacher_disagreement_score":0.9676356,"about_ca_system_score_codex":0.00012696537,"about_ca_system_score_gemma":0.00029238584,"threshold_uncertainty_score":0.9999424},"labels":[],"label_agreement":null},{"id":"W3043263805","doi":"10.1002/jrsm.1432","title":"Performance of model‐based network meta‐analysis (MBNMA) of time‐course relationships: A simulation study","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"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":"Medical Research Council; Pfizer UK; Medical Research Council Canada; Department of Health and Social Care; University of Bristol; National Institute for Health and Care Research; University Hospitals Bristol NHS Foundation Trust; Pfizer","keywords":"Pooling; Time point; Robustness (evolution); Computer science; Econometrics; Statistics; Correlation; Covariance; Random effects model; Meta-analysis; Mathematics; Artificial intelligence","score_opus":0.9625775729860939,"score_gpt":0.6951755412614352,"score_spread":0.2674020317246587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043263805","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":[0.11278426,0.0015931724,0.8793041,0.00095102354,0.000019425117,0.001872046,0.00003198227,0.000011795735,0.0034321977],"genre_scores_gemma":[0.7441535,0.000009215135,0.25514257,0.000017558077,0.000031374206,0.00010782414,0.0000019325678,0.000014559043,0.00052144984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.75438994,0.21711032,0.011748112,0.0017119071,0.014387811,0.00065190875],"domain_scores_gemma":[0.8337094,0.15257001,0.0042909123,0.004644665,0.004427894,0.0003570879],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.49085316,0.00029931008,0.0072594346,0.001101661,0.00030904516,0.00019933424,0.0022223769,0.00012932775,0.008683668],"category_scores_gemma":[0.18899281,0.0001615607,0.0044504898,0.012910172,0.00018279642,0.00029045122,0.00024942777,0.00043740767,0.00030233143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052820298,0.00021553201,0.018514648,0.0000798857,0.027730647,6.3611526e-7,0.0005262914,0.9472337,0.00016762876,0.00008472481,0.00056256284,0.0048309257],"study_design_scores_gemma":[0.000075147684,0.00011653115,0.004322288,0.000009936762,0.051653046,6.2647246e-8,0.0004526418,0.9420743,0.0004259118,0.000589067,0.00016176625,0.00011928123],"about_ca_topic_score_codex":0.00001331365,"about_ca_topic_score_gemma":0.0000075370226,"teacher_disagreement_score":0.6313693,"about_ca_system_score_codex":0.000028060378,"about_ca_system_score_gemma":0.0002438295,"threshold_uncertainty_score":0.99222255},"labels":[],"label_agreement":null},{"id":"W3081242054","doi":"10.1002/jrsm.1445","title":"A comparison of meta‐methods for synthesizing indirect effects","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Statistics; Marginal likelihood; Univariate; Point estimation; Bayesian probability; Type I and type II errors; Mathematics; Statistical power; Correlation; Mean squared error; Standard error; Sample size determination; Econometrics; Computer science; Multivariate statistics","score_opus":0.7371253621022572,"score_gpt":0.5275340000878445,"score_spread":0.20959136201441275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081242054","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":[0.03383294,0.011410837,0.94345236,0.001460513,0.00016482065,0.0011444864,0.00006622394,0.00005010626,0.00841771],"genre_scores_gemma":[0.42503244,0.0001370176,0.57412827,0.00006201703,0.000071735136,0.00046519318,0.0000028791749,0.000039966693,0.000060504466],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9961258,0.0017350739,0.000924237,0.00063537614,0.000081448954,0.000498033],"domain_scores_gemma":[0.98080784,0.018175075,0.00039902967,0.0003816483,0.000037872887,0.00019852116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018462732,0.00019711454,0.001455177,0.00031387582,0.00018247729,0.000049182792,0.00044510214,0.00016216894,0.0005803256],"category_scores_gemma":[0.016665014,0.00020660023,0.0004561119,0.00037646934,0.0001746771,0.00018215433,0.00016337463,0.00027072782,0.00014368934],"study_design_candidate":"bench_or_experimental","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":[0.00025142042,0.00058733526,0.05425704,0.0020588771,0.0043251053,0.0000012935377,0.0043336824,0.0007508371,0.06040209,0.08183717,0.0013015029,0.7898936],"study_design_scores_gemma":[0.00042774444,0.00041385344,0.011641897,0.000049427857,0.00031126352,7.5266644e-7,0.00048293464,0.06888731,0.85009104,0.033476893,0.033751957,0.0004649435],"about_ca_topic_score_codex":0.000043545686,"about_ca_topic_score_gemma":8.531273e-7,"teacher_disagreement_score":0.78968894,"about_ca_system_score_codex":0.00014509431,"about_ca_system_score_gemma":0.000026970969,"threshold_uncertainty_score":0.99161804},"labels":[],"label_agreement":null},{"id":"W3084440778","doi":"10.1002/jrsm.1443","title":"An empirical comparison of three methods for multiple cutoff diagnostic test meta‐analysis of the Patient Health Questionnaire‐9 (<scp>PHQ</scp>‐9) depression screening tool using published data vs individual level data","year":2020,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University; Centre for Advancing Health Outcomes; McGill University Health Centre","funders":"Institute of Health Services and Policy Research; Medical Research Council; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Deutsche Forschungsgemeinschaft","keywords":"Cutoff; Receiver operating characteristic; Meta-analysis; Bivariate analysis; Statistics; Confidence interval; Patient Health Questionnaire; Missing data; Medicine; Computer science; Data mining; Mathematics; Internal medicine; Psychiatry; Depressive symptoms","score_opus":0.8973377253297701,"score_gpt":0.708544593304702,"score_spread":0.1887931320250681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084440778","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023380839,0.58974934,0.39136207,0.0002664617,0.00023186266,0.0050307764,0.013274617,0.000043689317,0.000017821461],"genre_scores_gemma":[0.00018676302,0.19135809,0.8034408,0.00006324261,0.00023856359,0.0014795541,0.002996713,0.00021803856,0.000018201736],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.89521855,0.091236606,0.0046510613,0.0035289444,0.003164211,0.0022005932],"domain_scores_gemma":[0.62505734,0.35548085,0.0036627771,0.013394113,0.0011470212,0.0012579081],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.09593747,0.0009856911,0.009191738,0.0022707316,0.0010274546,0.00032782424,0.012248124,0.0010045973,0.00020441593],"category_scores_gemma":[0.35671517,0.00067814905,0.0015967467,0.0066716066,0.0008961899,0.00077025493,0.009720565,0.0033739007,0.000004615941],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005551845,0.0013188428,0.0049486374,0.012726161,0.029809976,0.000004970637,0.0006005978,0.000031822918,0.000008895655,0.000034029094,0.003215012,0.94724554],"study_design_scores_gemma":[0.00071526325,0.0015208651,0.007839146,0.009952437,0.14673343,0.00003214894,0.0013123859,0.24823141,0.0004751191,0.00024311413,0.5820501,0.0008946051],"about_ca_topic_score_codex":0.00336294,"about_ca_topic_score_gemma":0.00050722243,"teacher_disagreement_score":0.94635093,"about_ca_system_score_codex":0.0004941067,"about_ca_system_score_gemma":0.0033964,"threshold_uncertainty_score":0.999567},"labels":[],"label_agreement":null},{"id":"W3088093190","doi":"10.1002/jrsm.1458","title":"The effect direction plot revisited: Application of the 2019 Cochrane Handbook guidance on alternative synthesis methods","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":249,"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":"Medical Research Council; Medical Research Council Canada","keywords":"Plot (graphics); Metric (unit); Computer science; Forest plot; Visualization; Meta-analysis; Systematic review; Data mining; Sign (mathematics); Data science; Artificial intelligence; Statistics; MEDLINE; Medicine; Mathematics; Operations management","score_opus":0.4509388357373815,"score_gpt":0.5858464710871348,"score_spread":0.1349076353497533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088093190","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":[0.008642462,0.032400757,0.8238878,0.110646665,0.001025052,0.006396451,0.00052503316,0.00018804205,0.016287725],"genre_scores_gemma":[0.30737978,0.0123259025,0.65041083,0.00878112,0.0046843477,0.011661224,0.000025996898,0.00062500587,0.004105767],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.96411693,0.030521078,0.0031222955,0.0010165152,0.000521369,0.0007018409],"domain_scores_gemma":[0.87756336,0.117916666,0.002264894,0.0016583579,0.00031571748,0.00028101998],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16048898,0.00029650357,0.0014422307,0.00030571767,0.0009259196,0.00014594161,0.0013448285,0.00020869084,0.00013661687],"category_scores_gemma":[0.19557038,0.00022479992,0.00037560397,0.0010028211,0.0004352261,0.00022985222,0.0002457504,0.00065449637,0.00064256473],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014717231,0.00042300197,0.014647763,0.004702932,0.0018998736,0.0000020810598,0.0052377065,0.0027239537,0.018579854,0.22521546,0.08500356,0.6400921],"study_design_scores_gemma":[0.00096052955,0.00082227617,0.022322243,0.0022129328,0.00011583506,0.0000062940708,0.00075897935,0.14516711,0.42541787,0.024179498,0.37695473,0.001081698],"about_ca_topic_score_codex":0.0008064705,"about_ca_topic_score_gemma":0.000015881864,"teacher_disagreement_score":0.63901037,"about_ca_system_score_codex":0.00067011244,"about_ca_system_score_gemma":0.00013560678,"threshold_uncertainty_score":0.91670746},"labels":[],"label_agreement":null},{"id":"W3175297421","doi":"10.1002/jrsm.1530","title":"Bibliometric study of ‘overviews of systematic reviews’ of health interventions: Evaluation of prevalence, citation and journal impact factor","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; McMaster University; Nova Scotia Health Authority; Cochrane; Impact; University of British Columbia","funders":"","keywords":"Citation; Impact factor; Bibliometrics; Systematic review; MEDLINE; Psychological intervention; Publication; Meta-analysis; Sample size determination; Medicine; Scopus; Family medicine; Library science; Computer science; Statistics; Mathematics; Political science; Pathology; Nursing","score_opus":0.9829367848151381,"score_gpt":0.7881862511010701,"score_spread":0.19475053371406803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175297421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70530784,0.22608398,0.06246164,0.00006589263,0.000099239674,0.005692545,0.000041962543,0.0000010530744,0.00024581823],"genre_scores_gemma":[0.939799,0.011138245,0.048709832,0.0000016287524,0.000012488421,0.0001752436,8.125481e-7,0.000010407231,0.0001523332],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.12948193,0.80285996,0.03948665,0.0010815491,0.026600508,0.0004894189],"domain_scores_gemma":[0.7421339,0.16949421,0.04358755,0.005850533,0.03856491,0.00036889006],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.8167696,0.00021197923,0.008242541,0.030376608,0.00010926747,0.00019690332,0.0012328963,0.00007008547,0.0054374887],"category_scores_gemma":[0.71221226,0.00010352252,0.00245457,0.06891619,0.00012224873,0.00035820133,0.00021776507,0.00022315867,0.000011302021],"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":[0.000016003398,0.0013233717,0.029557005,0.13740325,0.0012906569,5.157393e-7,0.003328406,0.000067341934,0.0030675032,0.00007590708,0.00066734897,0.82320267],"study_design_scores_gemma":[0.0012418287,0.0027226855,0.85159606,0.0695587,0.0044846,0.00004931495,0.03605671,0.017335067,0.0076403734,0.008779683,0.00016794335,0.00036701703],"about_ca_topic_score_codex":0.000050721792,"about_ca_topic_score_gemma":0.000013114761,"teacher_disagreement_score":0.8228357,"about_ca_system_score_codex":0.000120961515,"about_ca_system_score_gemma":0.0006056586,"threshold_uncertainty_score":0.99547166},"labels":[],"label_agreement":null},{"id":"W3177444756","doi":"10.1002/jrsm.1508","title":"Including <scp>non‐English</scp> language articles in systematic reviews: A reflection on processes for identifying low‐cost sources of translation support","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":53,"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":"Medical Research Council; Medical Research Council Canada","keywords":"Systematic review; Computer science; English language; Reflection (computer programming); Process (computing); Social media; Psychology; MEDLINE; Political science; World Wide Web; Mathematics education","score_opus":0.9211131536084689,"score_gpt":0.6872420127582198,"score_spread":0.23387114085024907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177444756","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":[0.37542894,0.02541586,0.57582206,0.00046376724,0.00041623352,0.012270489,0.00004319509,0.00003447706,0.010104982],"genre_scores_gemma":[0.8084993,0.0009000794,0.18414654,0.00004564717,0.0001950737,0.0032745101,0.000008064577,0.000055236807,0.00287559],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.89920837,0.0834851,0.009864047,0.0013863377,0.005342976,0.000713204],"domain_scores_gemma":[0.6790939,0.3055851,0.004999263,0.0038374283,0.006185341,0.00029897632],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4478641,0.00029667869,0.004411368,0.0016203141,0.00027647224,0.0008832807,0.001149221,0.00015081064,0.0003709069],"category_scores_gemma":[0.7567448,0.00017012388,0.0011664478,0.006246998,0.00008594299,0.00048320155,0.00012562283,0.00030413637,0.00012850254],"study_design_candidate":"bench_or_experimental","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":[0.0000626107,0.0009179571,0.0076811514,0.23526844,0.00080190605,0.00004364073,0.07923243,0.0005451592,0.13708016,0.00081217324,0.004839963,0.5327144],"study_design_scores_gemma":[0.00062936125,0.00019525293,0.0018244492,0.032691777,0.00079314475,0.000023016866,0.087851495,0.018161913,0.83353215,0.009590907,0.014330834,0.00037568194],"about_ca_topic_score_codex":0.000015583733,"about_ca_topic_score_gemma":0.00012120529,"teacher_disagreement_score":0.696452,"about_ca_system_score_codex":0.000118020216,"about_ca_system_score_gemma":0.000277941,"threshold_uncertainty_score":0.85174966},"labels":[],"label_agreement":null},{"id":"W3186411542","doi":"10.1002/jrsm.1515","title":"Measurement error in <scp>meta‐analysis</scp> (<scp>MEMA</scp>)—A Bayesian framework for continuous outcome data subject to non‐differential measurement error","year":2021,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Covariate; Bayesian probability; Observational error; Outcome (game theory); Computer science; Statistics; Regression analysis; Meta-analysis; Meta-regression; Point estimation; Regression; Linear regression; Errors-in-variables models; Econometrics; Mathematics; Machine learning; Artificial intelligence; Medicine","score_opus":0.9485732251554616,"score_gpt":0.6820488264211971,"score_spread":0.2665243987342645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186411542","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000046444807,0.5178592,0.47222704,0.00025828063,0.00054766005,0.0077532707,0.0005546907,0.000023071387,0.00077212113],"genre_scores_gemma":[0.00029275473,0.36439583,0.613424,0.00015267686,0.0009849495,0.013402807,0.00022438976,0.0004846445,0.0066379486],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.54031575,0.34507695,0.040645134,0.013549702,0.054950047,0.0054623936],"domain_scores_gemma":[0.2258903,0.63929695,0.025733834,0.07439613,0.02926304,0.0054197735],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.74181974,0.0031868191,0.061078474,0.010819655,0.000953619,0.0057684723,0.023264013,0.0018795787,0.003495646],"category_scores_gemma":[0.84656864,0.001801305,0.03086549,0.023820661,0.00035429167,0.0005483301,0.0049736868,0.0035596984,0.0015874149],"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":[0.000010321014,0.0009973417,0.00016603562,0.016636144,0.18756409,0.00009038431,0.0006248024,0.000064714746,0.000036992504,0.000561837,0.050952245,0.7422951],"study_design_scores_gemma":[0.00017781062,0.000104176106,0.000075649026,0.0041451096,0.17114978,0.000011496639,0.0016924742,0.0015797646,0.00006993804,0.0010037835,0.8195383,0.0004517406],"about_ca_topic_score_codex":0.00018643019,"about_ca_topic_score_gemma":0.0010830375,"teacher_disagreement_score":0.76858604,"about_ca_system_score_codex":0.0015576886,"about_ca_system_score_gemma":0.0031006658,"threshold_uncertainty_score":0.9994162},"labels":[],"label_agreement":null},{"id":"W3197721016","doi":"10.1002/jrsm.1565","title":"Parametric G‐computation for compatible indirect treatment comparisons with limited individual patient data","year":2022,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computation; Computer science; Parametric statistics; Econometrics; Statistics; Algorithm; Mathematics","score_opus":0.8280228066436652,"score_gpt":0.6339570443067984,"score_spread":0.1940657623368668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197721016","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":[0.047688764,0.00021580723,0.946629,0.00031299726,0.000056385215,0.0030646168,0.0008853438,0.0004322956,0.0007147834],"genre_scores_gemma":[0.23304045,0.000021588306,0.76370656,0.000013882011,0.000024249008,0.002892051,0.00019957956,0.000059156853,0.000042457723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913964,0.0053967726,0.00050459063,0.00073541177,0.001249973,0.00071683805],"domain_scores_gemma":[0.9394452,0.058547653,0.00028266272,0.0012400714,0.00031482012,0.00016957628],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008945559,0.0002675319,0.0006684144,0.0010665886,0.0009452446,0.00011423979,0.00094912486,0.0000715708,0.00012710779],"category_scores_gemma":[0.011248709,0.00021665804,0.000076546305,0.001993048,0.00017038338,0.00021442708,0.00089384714,0.00047937146,0.0000031527998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005404515,0.0024616544,0.0010012563,0.00015607134,0.00065893383,0.000017721095,0.0013618439,0.0011823064,0.00076394225,0.006683903,0.01628407,0.96888787],"study_design_scores_gemma":[0.0026997766,0.016703198,0.0019274857,0.00031551236,0.0009838433,0.00009385453,0.012904877,0.27303338,0.2850648,0.30090302,0.10324477,0.0021254884],"about_ca_topic_score_codex":0.00010708099,"about_ca_topic_score_gemma":0.000029192122,"teacher_disagreement_score":0.96676236,"about_ca_system_score_codex":0.00066203024,"about_ca_system_score_gemma":0.00029788815,"threshold_uncertainty_score":0.99707997},"labels":[],"label_agreement":null},{"id":"W3210017165","doi":"10.1002/jrsm.1535","title":"Introduction to PRISMA 2020 and implications for research synthesis methodologists","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":256,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Systematic review; Statement (logic); Computer science; Key (lock); MEDLINE; Research methodology; Data science; Management science; Epistemology; Medicine; Political science","score_opus":0.9629191545952714,"score_gpt":0.7585722339411163,"score_spread":0.20434692065415516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210017165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066505377,0.0026333954,0.8049579,0.17760749,0.00028266132,0.0025675185,0.00007828387,0.000019870247,0.005202318],"genre_scores_gemma":[0.009192144,0.0003989231,0.97003055,0.00010925819,0.001103885,0.0035153953,0.000004358129,0.00004377317,0.0156017095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6141402,0.3629912,0.0077437363,0.0044930647,0.008902233,0.0017295684],"domain_scores_gemma":[0.18985899,0.7723045,0.0015947823,0.013117075,0.021735363,0.0013892838],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7612048,0.00033515674,0.003493674,0.0017288248,0.0012874226,0.0022011967,0.0026207278,0.00026099425,0.0063792737],"category_scores_gemma":[0.91520816,0.00020015772,0.0011240743,0.008558288,0.0004335091,0.00028431127,0.0011164907,0.00068447535,0.0011631602],"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":[0.00003207567,0.00007822228,0.00054208934,0.000111178946,0.00020682132,0.000002659835,0.00024047264,0.000016496382,0.03969796,0.012048755,0.27239874,0.6746245],"study_design_scores_gemma":[0.000061130966,0.000069392845,0.0112085,0.000052975432,0.00014156185,0.000043010732,0.0021378482,0.0011636954,0.06777566,0.08954083,0.8275459,0.0002594857],"about_ca_topic_score_codex":0.000029485127,"about_ca_topic_score_gemma":0.00003390164,"teacher_disagreement_score":0.67436504,"about_ca_system_score_codex":0.00020813254,"about_ca_system_score_gemma":0.00046875008,"threshold_uncertainty_score":0.99961454},"labels":[],"label_agreement":null},{"id":"W3210125699","doi":"10.1002/jrsm.1606","title":"Adjusting for misclassification of an exposure in an individual participant data meta‐analysis","year":2022,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Mosquito-borne diseases and control","field":"Medicine","cited_by":4,"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":"Canadian Institutes of Health Research","keywords":"Gold standard (test); Statistics; Covariate; Random effects model; Estimator; Bayesian probability; Standard error; Standard deviation; Computer science; Bayes' theorem; Meta-analysis; Econometrics; Mathematics; Medicine","score_opus":0.9098197562552974,"score_gpt":0.673500867850549,"score_spread":0.23631888840474846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210125699","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029511284,0.99341106,0.0015969807,0.000091939386,0.00003187641,0.0026225958,0.0021279645,0.000027839349,0.000060258073],"genre_scores_gemma":[0.00036280774,0.9107963,0.07829361,0.000014967608,0.00022238572,0.006731963,0.0033789228,0.00011014767,0.00008894319],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9769508,0.0178701,0.0014938983,0.0014412275,0.0014194353,0.0008245015],"domain_scores_gemma":[0.9740073,0.02029292,0.000636812,0.004212274,0.00031361988,0.00053707033],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043325458,0.00039929134,0.0052439086,0.0017798007,0.00019608068,0.00008781589,0.0018005471,0.000291045,0.0014369313],"category_scores_gemma":[0.017306393,0.0003024072,0.0016848019,0.002592696,0.00013906973,0.00022189692,0.0005674628,0.00082564965,0.0000016464679],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118571275,0.0006791784,0.00000989874,0.011393213,0.06333526,0.000016047248,0.000105379615,0.000007488506,0.000024843172,0.000085811356,0.000031598138,0.9241927],"study_design_scores_gemma":[0.0002601008,0.00040486312,0.00012832007,0.00059938483,0.6551417,0.00000387333,0.001017067,0.007475447,0.000024552563,0.000041871688,0.33461884,0.00028397606],"about_ca_topic_score_codex":0.00019930558,"about_ca_topic_score_gemma":0.00010409184,"teacher_disagreement_score":0.9239087,"about_ca_system_score_codex":0.0000918793,"about_ca_system_score_gemma":0.0013318409,"threshold_uncertainty_score":0.9999428},"labels":[],"label_agreement":null},{"id":"W3211380584","doi":"10.1002/jrsm.1534","title":"Subsequent full publication of qualitative studies presented at United Kingdom Royal College of Nursing Research Conference 2015 and 2016: A follow‐up study","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane","funders":"","keywords":"Medicine; Publication bias; Qualitative research; MEDLINE; Cohort study; Research design; Family medicine; Confidence interval; Internal medicine; Social science; Political science; Sociology","score_opus":0.9706364010025503,"score_gpt":0.7647866689740885,"score_spread":0.2058497320284618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211380584","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":[0.95713764,0.009105024,0.014620656,0.008024684,0.00022494479,0.004152205,0.00029799592,0.000011252733,0.0064255865],"genre_scores_gemma":[0.92393047,0.0002493993,0.05198942,0.0000063822017,0.00003702621,0.00045539308,0.000009716486,0.00002605641,0.023296166],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.5405042,0.43377125,0.007879096,0.0018361778,0.015167636,0.0008415851],"domain_scores_gemma":[0.44791183,0.44542295,0.005391823,0.008699258,0.09179711,0.000777029],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.60573345,0.00030424458,0.0041639283,0.0027366793,0.0005449053,0.00035765377,0.001787298,0.00014314779,0.0020821735],"category_scores_gemma":[0.6328241,0.00017519105,0.0006368881,0.0091406545,0.0014369311,0.00025506283,0.001106478,0.00051439716,0.000083322855],"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":[0.0016416789,0.0052716634,0.011069992,0.0018092107,0.00893204,0.00008370757,0.2175043,0.00005269769,0.08697056,0.060803454,0.49840084,0.10745986],"study_design_scores_gemma":[0.0015066022,0.00103875,0.0075250287,0.0019834782,0.00073172833,0.000020280271,0.84087527,0.014729408,0.05352694,0.053867035,0.023634205,0.0005613027],"about_ca_topic_score_codex":0.00023018786,"about_ca_topic_score_gemma":0.00017556554,"teacher_disagreement_score":0.62337095,"about_ca_system_score_codex":0.00032865204,"about_ca_system_score_gemma":0.0007155025,"threshold_uncertainty_score":0.9988301},"labels":[],"label_agreement":null},{"id":"W4200065546","doi":"10.1002/jrsm.1542","title":"A new taxonomy was developed for overlap across 'overviews of systematic reviews': A meta‐research study of research waste","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision 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":"Ottawa Hospital; University of Ottawa; McMaster University; Nova Scotia Health Authority; Cochrane; Impact; University of British Columbia","funders":"","keywords":"Systematic review; Scope (computer science); Meta-analysis; Psychological intervention; MEDLINE; Computer science; Psychology; Taxonomy (biology); Research design; Data science; Management science; Information retrieval; Medicine; Sociology; Pathology; Political science; Social science; Engineering","score_opus":0.9858741720690846,"score_gpt":0.7632002114989404,"score_spread":0.2226739605701442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200065546","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09292877,0.23728527,0.5158628,0.0031079818,0.0010503528,0.12866122,0.000351185,0.00004145727,0.020710919],"genre_scores_gemma":[0.08091691,0.0027885197,0.8322027,0.000032267413,0.00037227423,0.028165674,0.0000059838067,0.000148912,0.055366796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.16076228,0.7523518,0.033979397,0.0046302336,0.044946186,0.0033300456],"domain_scores_gemma":[0.13029279,0.7705564,0.010131935,0.024817506,0.06257806,0.0016233431],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9038802,0.0007222967,0.019852033,0.0031170202,0.0010803789,0.0016291705,0.008775742,0.0003461097,0.006813658],"category_scores_gemma":[0.8418532,0.00036461948,0.0058931718,0.021688737,0.0006330529,0.0005275515,0.0030752767,0.0015220359,0.00087323046],"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":[0.0005843008,0.0056798635,0.0027920378,0.23334035,0.027868023,0.000118084,0.026343958,0.00012513665,0.025730435,0.011588664,0.2285007,0.43732846],"study_design_scores_gemma":[0.002213161,0.002019692,0.0008322943,0.019772412,0.00610275,0.000057487112,0.3081209,0.0055837226,0.09624826,0.025269506,0.5322679,0.0015118899],"about_ca_topic_score_codex":0.0004721768,"about_ca_topic_score_gemma":0.0005049935,"teacher_disagreement_score":0.43581656,"about_ca_system_score_codex":0.0003158084,"about_ca_system_score_gemma":0.0023204398,"threshold_uncertainty_score":0.9999047},"labels":[],"label_agreement":null},{"id":"W4200258716","doi":"10.1002/jrsm.1543","title":"Reevaluation of statistically significant meta‐analyses in advanced cancer patients using the <scp>Hartung–Knapp</scp> method and prediction intervals—A methodological study","year":2021,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane","funders":"","keywords":"Meta-analysis; Random effects model; Confidence interval; Hazard ratio; Medicine; Fixed effects model; Statistics; Sample size determination; Randomized controlled trial; Internal medicine; Mathematics","score_opus":0.9859069302083531,"score_gpt":0.7982354511094404,"score_spread":0.18767147909891269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200258716","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021865763,0.6264358,0.36872247,0.000026303544,0.0001413533,0.004089758,0.00022009497,0.0000049141113,0.00014060311],"genre_scores_gemma":[0.00011546105,0.51374614,0.48371458,0.000008907411,0.000056427558,0.0020061005,0.000014746519,0.00004920047,0.0002884547],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.2786574,0.68656737,0.017727764,0.0032645687,0.01288821,0.00089471403],"domain_scores_gemma":[0.27151614,0.7026977,0.011309733,0.006159148,0.00785539,0.0004618849],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6933302,0.00097159226,0.02210005,0.002370077,0.00036663492,0.00092475355,0.003054399,0.00045905146,0.0022273625],"category_scores_gemma":[0.73991936,0.00039724636,0.004372184,0.00747978,0.00040532148,0.0003030409,0.0012433643,0.0014524824,0.000021656659],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061386413,0.0004076539,0.00029557376,0.0023556529,0.008254646,0.000007883851,0.0005274751,0.0002440945,0.00008982429,0.00013227653,0.00033458738,0.9873442],"study_design_scores_gemma":[0.0010899273,0.0015111126,0.00643354,0.017781112,0.2113571,0.000036495978,0.022725482,0.07615028,0.00064609013,0.012027257,0.6490877,0.0011538962],"about_ca_topic_score_codex":0.00019329201,"about_ca_topic_score_gemma":0.000047742207,"teacher_disagreement_score":0.9861903,"about_ca_system_score_codex":0.00033279136,"about_ca_system_score_gemma":0.0008858987,"threshold_uncertainty_score":0.99984795},"labels":[],"label_agreement":null},{"id":"W4200415437","doi":"10.1002/jrsm.1539","title":"A non‐parametric approach for jointly combining evidence on progression free and overall survival time in network meta‐analysis","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"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":"Medical Research Council Canada; Medical Research Council; University of Bristol; National Institute for Health and Care Research","keywords":"Meta-analysis; Computer science; Parametric statistics; Survival analysis; Network analysis; Statistics; Medicine; Internal medicine; Mathematics","score_opus":0.927587277312563,"score_gpt":0.6722385246920699,"score_spread":0.25534875262049306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200415437","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":[0.020162918,0.04186477,0.9138724,0.0035193309,0.00017316466,0.0047885906,0.000044955177,0.000024421419,0.015549415],"genre_scores_gemma":[0.08623883,0.00029947015,0.90732604,0.00007617596,0.00009921027,0.0011622374,0.000006496109,0.000034434095,0.004757108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8341116,0.14524952,0.0063816495,0.002833549,0.01028105,0.0011426464],"domain_scores_gemma":[0.6197684,0.36670303,0.0023108039,0.0076528466,0.003025496,0.00053943705],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5996791,0.00043449507,0.008552641,0.0026047446,0.00042114488,0.0018022098,0.0024774503,0.00022275696,0.0030348757],"category_scores_gemma":[0.484894,0.00022747082,0.0041149054,0.015426364,0.00017592788,0.00033783802,0.00090731605,0.0006024404,0.00012482688],"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":[0.0010460825,0.0030504141,0.049631674,0.002532604,0.248537,0.00019704408,0.0019248977,0.037000388,0.0067318287,0.015458516,0.077079475,0.5568101],"study_design_scores_gemma":[0.0004951004,0.0002894949,0.011959148,0.00030719856,0.04019512,0.000009678784,0.0006620347,0.9071983,0.0027039275,0.030966666,0.004470449,0.00074286],"about_ca_topic_score_codex":0.000036762678,"about_ca_topic_score_gemma":0.000020451444,"teacher_disagreement_score":0.87019795,"about_ca_system_score_codex":0.00009224111,"about_ca_system_score_gemma":0.00022414261,"threshold_uncertainty_score":0.999234},"labels":[],"label_agreement":null},{"id":"W4210542220","doi":"10.1002/jrsm.1547","title":"Meta‐analysis of prevalence: <scp><i>I</i><sup>2</sup></scp> statistic and how to deal with heterogeneity","year":2022,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":524,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Meta-analysis; Statistics; Statistic; Point estimation; Econometrics; Study heterogeneity; Sample size determination; Confidence interval; Systematic review; Pooled variance; Publication bias; Summary statistics; Subgroup analysis; Demography; Medicine; Mathematics; MEDLINE; Internal medicine; Biology","score_opus":0.8023315025989195,"score_gpt":0.6016847519460555,"score_spread":0.20064675065286397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210542220","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":[0.41308254,0.011817537,0.5665437,0.0018259101,0.00003407725,0.0029358903,0.0011275527,0.00001965209,0.002613172],"genre_scores_gemma":[0.33390185,0.0001398012,0.65482676,0.00011215609,0.000028043863,0.0013847778,0.00000575277,0.000038703016,0.009562159],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.7508338,0.22300465,0.0047366433,0.0025525822,0.017833477,0.0010388383],"domain_scores_gemma":[0.7217814,0.26465333,0.0028384507,0.0065383585,0.0032218713,0.0009666217],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47585452,0.00043136702,0.0074824938,0.0032827517,0.00072298193,0.0009285659,0.0031557116,0.00007685479,0.0065785903],"category_scores_gemma":[0.12230743,0.00022147328,0.0027591975,0.011821651,0.00033823473,0.00022810248,0.001261187,0.00050781947,0.00008736854],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015551888,0.0008424343,0.061638687,0.0018124263,0.6031743,0.00011815604,0.00977348,0.055118494,0.0037770416,0.004288578,0.04859291,0.21070795],"study_design_scores_gemma":[0.000465195,0.001352346,0.03228266,0.000058536738,0.3855777,0.00007317916,0.022095008,0.23545502,0.009804004,0.0056176158,0.30645382,0.00076486944],"about_ca_topic_score_codex":0.000065813765,"about_ca_topic_score_gemma":0.00003979616,"teacher_disagreement_score":0.3535471,"about_ca_system_score_codex":0.00009435392,"about_ca_system_score_gemma":0.00022362574,"threshold_uncertainty_score":0.9943295},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"meta_analysis","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4221118345","doi":"10.1002/jrsm.1557","title":"Graphical Representation of Overlap for <scp>OVErviews</scp>: <scp>GROOVE</scp> tool","year":2022,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":257,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Universitat Autònoma de Barcelona; Instituto de Salud Carlos III; Fondo Nacional de Desarrollo Científico y Tecnológico; Agencia Nacional de Investigación y Desarrollo; Ministerio de Economía y Competitividad","keywords":"Computer science; Representation (politics); Matrix (chemical analysis); Data mining; Groove (engineering); Information retrieval; Matrix representation","score_opus":0.8564511360551862,"score_gpt":0.6584873612399715,"score_spread":0.19796377481521465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221118345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.26340288,0.0076064277,0.6655095,0.0014595503,0.0011669884,0.008203508,0.000542524,0.000051476527,0.052057154],"genre_scores_gemma":[0.2227294,0.0007397193,0.700323,0.00039896884,0.0006419328,0.007561858,0.00005115587,0.00018528782,0.06736869],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.70015144,0.2503756,0.01549563,0.0037633996,0.028299456,0.0019145015],"domain_scores_gemma":[0.30058357,0.67549556,0.0068625864,0.010928185,0.0054495838,0.0006805441],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52069604,0.00044661225,0.0050329156,0.0021751146,0.00095673266,0.0008084142,0.0046746447,0.0001968038,0.0034650366],"category_scores_gemma":[0.732603,0.00027633941,0.004343123,0.008245128,0.00033016992,0.00042426522,0.0013068956,0.00079741766,0.00031355672],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030307665,0.00069050235,0.0129391495,0.00063297123,0.0013002943,0.00001715587,0.0022952915,0.0005167964,0.02492379,0.043987326,0.56211245,0.35055396],"study_design_scores_gemma":[0.0003134067,0.00024619367,0.008521835,0.00005467782,0.0003319354,0.000019087713,0.011127956,0.01822026,0.018776305,0.09997199,0.8423187,0.00009765067],"about_ca_topic_score_codex":0.000060747112,"about_ca_topic_score_gemma":0.0000085503525,"teacher_disagreement_score":0.42511994,"about_ca_system_score_codex":0.00015889507,"about_ca_system_score_gemma":0.0003114165,"threshold_uncertainty_score":0.9999689},"labels":[],"label_agreement":null},{"id":"W4280489194","doi":"10.1002/jrsm.1569","title":"Causal assessment in evidence synthesis: A methodological review of reviews","year":2022,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"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":"Medical Research Council; Medical Research Council Canada; Chief Scientist Office; Wellcome Trust","keywords":"Viewpoints; Systematic review; Causal inference; Causality (physics); Transparency (behavior); Population; Computer science; MEDLINE; Data science; Management science; Medicine; Pathology; Political science; Environmental health; Engineering","score_opus":0.9459944482734105,"score_gpt":0.7674090534540664,"score_spread":0.1785853948193441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280489194","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.591808e-8,0.9348742,0.055482447,0.00016228705,0.00009738453,0.0064448398,0.000050418497,0.00017169527,0.0027166794],"genre_scores_gemma":[2.927868e-8,0.51603496,0.4679727,0.000022356988,0.000050327697,0.01571788,0.0000035551598,0.00010615459,0.00009200752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.73707956,0.24934563,0.006254393,0.0022134094,0.0032483125,0.0018586784],"domain_scores_gemma":[0.32853666,0.66284597,0.0031182987,0.0045564002,0.00051843596,0.0004242282],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28095433,0.0011383046,0.012613268,0.0018337197,0.00021701696,0.00005408562,0.0035640376,0.00075710873,0.0072549134],"category_scores_gemma":[0.67089033,0.00082993886,0.0019467302,0.004452846,0.00062295556,0.0003168854,0.002372064,0.0055103037,0.000031177064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006941916,0.00018379194,4.4285818e-7,0.30734745,0.00009012221,0.00004423151,0.000018169076,2.5747307e-8,0.000010384843,0.0065182573,0.001732865,0.6840473],"study_design_scores_gemma":[0.000018190633,0.00010009328,4.5468664e-7,0.37044466,0.00069663255,0.00003364447,0.000025089545,0.0000038580097,0.00013433036,0.02587573,0.6022171,0.00045024866],"about_ca_topic_score_codex":0.000061555475,"about_ca_topic_score_gemma":0.000006562062,"teacher_disagreement_score":0.6835971,"about_ca_system_score_codex":0.0023051784,"about_ca_system_score_gemma":0.0021061,"threshold_uncertainty_score":0.99941516},"labels":[],"label_agreement":null},{"id":"W4290018571","doi":"10.1002/jrsm.1595","title":"Using systems perspectives in evidence synthesis: A methodological mapping review","year":2022,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":15,"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":"Fonds de Recherche du Québec - Santé","keywords":"Computer science; Perspective (graphical); Management science; Data science; Rank (graph theory); Complex system; Systems thinking; Artificial intelligence; Engineering","score_opus":0.9957484707324901,"score_gpt":0.8810398296369721,"score_spread":0.11470864109551793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290018571","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018119425,0.9775292,0.006984416,0.0017301455,0.0005946558,0.010593647,0.000111753565,0.00013622823,0.0023180856],"genre_scores_gemma":[6.2505063e-7,0.82943636,0.14194034,0.00042116563,0.0004459159,0.027315406,0.0000017232713,0.0001326154,0.00030584665],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5802242,0.40828806,0.0041420897,0.0018394641,0.002637896,0.0028682875],"domain_scores_gemma":[0.21491782,0.77773255,0.002683961,0.002765537,0.0008784395,0.0010216752],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42459106,0.00083335105,0.0069584055,0.0035864266,0.0028535614,0.00009385918,0.0031202924,0.00080006954,0.008926379],"category_scores_gemma":[0.64883447,0.00065888325,0.00077459833,0.009440515,0.00057440595,0.00035103224,0.0023554496,0.007514388,0.00039336673],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000009405698,0.00003942189,0.000009234804,0.25537625,0.000079403,0.000044940614,0.0022790777,0.0000022135396,0.0000049362257,0.00061099866,0.0017087279,0.7398354],"study_design_scores_gemma":[0.000046331435,0.000023966562,0.0000065498143,0.25127187,0.00020858449,0.000032596647,0.011893815,0.00011270102,6.1471246e-7,0.00006923787,0.73592484,0.0004088896],"about_ca_topic_score_codex":0.00198602,"about_ca_topic_score_gemma":0.000021671056,"teacher_disagreement_score":0.7394265,"about_ca_system_score_codex":0.009145436,"about_ca_system_score_gemma":0.011962062,"threshold_uncertainty_score":0.9995862},"labels":[],"label_agreement":null},{"id":"W4307343125","doi":"10.1002/jrsm.1608","title":"Network meta‐interpolation: Effect modification adjustment in network meta‐analysis using subgroup analyses","year":2022,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"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":"Statistics; Meta-analysis; Standard error; Mean squared error; Mathematics; Sample size determination; Subgroup analysis; Confidence interval; Data mining; Econometrics; Computer science; Medicine","score_opus":0.8152217341987545,"score_gpt":0.6479104043905357,"score_spread":0.16731132980821883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307343125","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":[0.0022674955,0.010789439,0.98414356,0.00021841004,0.00008014324,0.0014343025,0.000020503976,0.00026475175,0.00078142475],"genre_scores_gemma":[0.18639773,0.00012067775,0.8096294,0.000036738595,0.00016125233,0.0034418893,0.000010760055,0.00006967527,0.00013186126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9605968,0.034712084,0.0010539404,0.00091452134,0.0015496111,0.0011730476],"domain_scores_gemma":[0.9407361,0.057036493,0.00041936376,0.0013872118,0.00025246385,0.00016835799],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.046532635,0.00042694493,0.0024817577,0.0013100915,0.0006882597,0.00009776812,0.00083409983,0.0001436332,0.00277467],"category_scores_gemma":[0.007840147,0.00035360962,0.001431493,0.006988328,0.00016102074,0.00029301003,0.00072979886,0.0010573209,0.0000041912713],"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":[0.00051754253,0.0007172277,0.0008421571,0.00037272696,0.31714863,0.000055011446,0.00067491434,0.57704985,0.016882936,0.062399868,0.0017972004,0.021541936],"study_design_scores_gemma":[0.00013945068,0.0002467117,0.00027412825,0.00002563199,0.1883855,0.000007774099,0.00030746748,0.32875538,0.01430863,0.46652615,0.0004107156,0.00061246956],"about_ca_topic_score_codex":0.00043008025,"about_ca_topic_score_gemma":0.00009271006,"teacher_disagreement_score":0.4041263,"about_ca_system_score_codex":0.0007831217,"about_ca_system_score_gemma":0.00010712225,"threshold_uncertainty_score":0.9998916},"labels":[],"label_agreement":null},{"id":"W4312065242","doi":"10.1002/jrsm.1617","title":"Graphical tools for visualizing the results of network meta‐analysis of multicomponent interventions","year":2022,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; University of Toronto; St. Michael's Hospital","funders":"European Commission","keywords":"Computer science; Asynchronous communication; Psychological intervention; Context (archaeology); Inference; Component (thermodynamics); Intervention (counseling); Meta-analysis; Machine learning; Artificial intelligence; Medicine; Nursing; Computer network","score_opus":0.9761087512398074,"score_gpt":0.7425387459641508,"score_spread":0.23357000527565663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312065242","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.008044548,0.011966305,0.9692089,0.0046190373,0.00023123877,0.0032172264,0.00074362213,0.000008177351,0.0019609348],"genre_scores_gemma":[0.6577825,0.000079176105,0.33850712,0.000038101884,0.00005569948,0.0020599074,0.000016966334,0.00002120474,0.0014393264],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.59362763,0.37017238,0.018757401,0.0017438905,0.014801308,0.00089737255],"domain_scores_gemma":[0.39751753,0.58480364,0.0068424707,0.007083421,0.0035368348,0.0002160766],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7234403,0.00021884606,0.0066949376,0.0019777094,0.00077500864,0.00037165626,0.00386443,0.000059560476,0.007019991],"category_scores_gemma":[0.35384288,0.00009624165,0.018153928,0.011379258,0.0003148767,0.0001338769,0.0010258275,0.0003911086,0.000011536023],"study_design_candidate":"meta_analysis","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":[0.00063115737,0.0015087405,0.00071918784,0.0006708611,0.58713835,0.000004078036,0.0024936863,0.0630738,0.0067669256,0.08461433,0.03953172,0.21284717],"study_design_scores_gemma":[0.00050534547,0.000447875,0.0061490517,0.00008464356,0.32392895,0.000004119526,0.0115692755,0.38918757,0.0048450176,0.041263565,0.2215243,0.00049025874],"about_ca_topic_score_codex":0.00009176645,"about_ca_topic_score_gemma":0.000044540262,"teacher_disagreement_score":0.64973795,"about_ca_system_score_codex":0.00004345193,"about_ca_system_score_gemma":0.00007965181,"threshold_uncertainty_score":0.9938877},"labels":[],"label_agreement":null},{"id":"W4313648545","doi":"10.1002/jrsm.1613","title":"How should we handle predatory journals in evidence synthesis? A descriptive survey‐based cross‐sectional study of evidence synthesis experts","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Health Research","keywords":"Inclusion (mineral); Psychology; Quality (philosophy); Medical education; Survey research; Medicine; Applied psychology; Social psychology","score_opus":0.9810529051559126,"score_gpt":0.7283173833840576,"score_spread":0.252735521771855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313648545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9512891,0.010803306,0.029637296,0.0029479018,0.00054767245,0.0042944998,0.00013262327,0.000053091375,0.00029448033],"genre_scores_gemma":[0.97458255,0.0011249194,0.017510753,0.00001982757,0.00012932044,0.0027794905,6.768584e-7,0.00007118923,0.003781254],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.44383878,0.5018369,0.0149538275,0.004499841,0.03271677,0.0021539144],"domain_scores_gemma":[0.20640694,0.7696234,0.0052392413,0.008542751,0.009341377,0.0008462994],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7537488,0.00077422557,0.006443548,0.0061284527,0.00080401753,0.0045325076,0.0068199052,0.00044858293,0.0061353166],"category_scores_gemma":[0.90925515,0.0004169237,0.0021207533,0.014000246,0.0007116982,0.002125143,0.0010336412,0.0010438652,0.0005184897],"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":[0.00053968193,0.0010413113,0.8693914,0.0005568887,0.0007876102,0.00010266371,0.0026655113,0.0010241402,0.011769259,0.000021443982,0.010698498,0.101401635],"study_design_scores_gemma":[0.00025999363,0.0002742917,0.92032456,0.0033575506,0.00025938687,0.000012124847,0.01414424,0.020769026,0.037026588,0.00096749107,0.0019497925,0.0006549209],"about_ca_topic_score_codex":0.0008230994,"about_ca_topic_score_gemma":0.0006817871,"teacher_disagreement_score":0.26778653,"about_ca_system_score_codex":0.0005431074,"about_ca_system_score_gemma":0.0011519771,"threshold_uncertainty_score":0.9998283},"labels":[],"label_agreement":null},{"id":"W4315754436","doi":"10.1002/jrsm.1620","title":"<scp>SeroTracker‐RoB</scp> : A decision rule‐based algorithm for reproducible risk of bias assessment of seroprevalence studies","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Viral Infections and Outbreaks Research","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo; University of Toronto; McGill University Health Centre; University of Calgary","funders":"Robert Koch Institut; Canadian Medical Association; Public Health Agency of Canada; World Health Organization","keywords":"Reliability (semiconductor); Algorithm; Computer science; Checklist; Intraclass correlation; Critical appraisal; Set (abstract data type); Data mining; Mathematics; Statistics; Medicine; Psychology; Psychometrics","score_opus":0.44257546081880744,"score_gpt":0.6125206899488027,"score_spread":0.16994522912999527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315754436","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58216625,0.003547143,0.40746224,0.0007651228,0.00029290456,0.0038612643,0.00034732098,0.00020489871,0.0013528654],"genre_scores_gemma":[0.05984368,0.008623168,0.9281649,0.0000100392435,0.00016410764,0.0010914928,0.0000109549055,0.00007263745,0.002019022],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99121946,0.004221908,0.00088621286,0.0009094566,0.0018751279,0.00088785804],"domain_scores_gemma":[0.93671423,0.05816839,0.0002773164,0.0014176763,0.0031492035,0.0002731643],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051207256,0.00023891588,0.0011103859,0.0016845919,0.00037112628,0.00003444289,0.0003639541,0.00018741173,0.00006107468],"category_scores_gemma":[0.09683677,0.00017964806,0.0004705667,0.0033300978,0.00057075254,0.00012826892,0.00036790906,0.00066500297,0.000023594825],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008911422,0.0005198756,0.00967654,0.0018987607,0.0005709273,0.00001632818,0.00017375579,0.0002550753,0.077564016,0.000061029947,0.003946634,0.90522796],"study_design_scores_gemma":[0.0010548057,0.0014484846,0.064041436,0.0016211438,0.00025627358,0.000009170507,0.001877661,0.19228582,0.7312989,0.0021627613,0.003839819,0.000103689716],"about_ca_topic_score_codex":0.00022420209,"about_ca_topic_score_gemma":0.000008764948,"teacher_disagreement_score":0.90512425,"about_ca_system_score_codex":0.00022133837,"about_ca_system_score_gemma":0.0007248497,"threshold_uncertainty_score":0.9769818},"labels":[],"label_agreement":null},{"id":"W4321372764","doi":"10.1002/jrsm.1629","title":"Why do researchers co‐author evidence syntheses with librarians? A mixed‐methods study","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Council of University Libraries; University of Toronto","funders":"","keywords":"Psychology; Medical education; Public relations; Sociology; Political science; Medicine","score_opus":0.9682560317549335,"score_gpt":0.7497295080168404,"score_spread":0.21852652373809311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321372764","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0995299,0.010212053,0.76499057,0.03920231,0.0011753518,0.016584093,0.00012570826,0.00048354792,0.06769648],"genre_scores_gemma":[0.14175674,0.00040619753,0.8194314,0.00018886202,0.00034784846,0.0033588826,0.0000022596912,0.000196633,0.03431116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.28376564,0.66499966,0.010600468,0.005122811,0.032622997,0.002888428],"domain_scores_gemma":[0.12245448,0.84910965,0.003063064,0.01736879,0.0061583063,0.0018456973],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8532224,0.000833203,0.0065175756,0.005525176,0.00142996,0.00745099,0.010129879,0.00033424643,0.02352117],"category_scores_gemma":[0.8755521,0.0004056975,0.0019372512,0.024261786,0.0010754296,0.0015872519,0.0018534748,0.0016571789,0.0086923735],"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":[0.00017872706,0.00033178565,0.007548596,0.00019954823,0.0009864315,0.00017465618,0.0027001528,0.00007023203,0.0018919641,0.00092072895,0.25659308,0.7284041],"study_design_scores_gemma":[0.0002852834,0.001304711,0.025848402,0.0021185055,0.0006585715,0.00005396449,0.09393532,0.015659515,0.011988633,0.016087158,0.8306812,0.001378726],"about_ca_topic_score_codex":0.00020467633,"about_ca_topic_score_gemma":0.000056056335,"teacher_disagreement_score":0.7270254,"about_ca_system_score_codex":0.00021259615,"about_ca_system_score_gemma":0.0008274698,"threshold_uncertainty_score":0.99987006},"labels":[],"label_agreement":null},{"id":"W4378190436","doi":"10.1002/jrsm.1636","title":"A real‐world evaluation of the implementation of <scp>NLP</scp> technology in abstract screening of a systematic review","year":2023,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":27,"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 Toronto; McGill University; The Quebec Population Health Research Network; University of Calgary; McGill University Health Centre","funders":"Canadian Medical Association; Robert Koch Institut; Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology; Public Health Agency; Rhodes Scholarships; Public Health Agency of Canada; World Health Organization","keywords":"Computer science; Context (archaeology); Systematic review; Recall; Inclusion (mineral); Machine learning; Artificial intelligence; Precision and recall; Natural language processing; MEDLINE; Psychology","score_opus":0.9514931780577904,"score_gpt":0.7593710306945818,"score_spread":0.19212214736320865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378190436","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051919793,0.9846416,0.00073873973,0.00009802077,0.00007072409,0.012858621,0.000081346625,0.0000059131585,0.0014531164],"genre_scores_gemma":[0.00012199044,0.9768335,0.019031726,0.000002681187,0.000019392974,0.0032483868,0.000006365093,0.000051024686,0.00068491034],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.33932814,0.54961693,0.06618163,0.002935802,0.040589526,0.0013479536],"domain_scores_gemma":[0.6196575,0.30965245,0.0459981,0.013706509,0.010810352,0.0001750841],"candidate_categories":["metaresearch","metaepi_broad","bibliometrics","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.79247606,0.0005418818,0.021925464,0.0066946046,0.00010609604,0.000118067896,0.005887507,0.00033796692,0.0011153389],"category_scores_gemma":[0.64735925,0.00023968122,0.0049753897,0.024286112,0.00032444665,0.00014306535,0.00080020213,0.00079780363,0.0001324078],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.7182838e-7,0.00003513919,0.000045424043,0.5491176,0.0006149151,5.89168e-7,0.00007635008,0.0000031584232,0.000014306709,0.00046772888,0.00060855626,0.44901595],"study_design_scores_gemma":[0.00010064556,0.000041255764,0.00029894622,0.9622547,0.01152956,0.0000069929642,0.0028897796,0.00050366,0.00035007249,0.005102103,0.016778799,0.000143458],"about_ca_topic_score_codex":0.00026560386,"about_ca_topic_score_gemma":0.0002496475,"teacher_disagreement_score":0.44887248,"about_ca_system_score_codex":0.00027665633,"about_ca_system_score_gemma":0.0013990047,"threshold_uncertainty_score":0.99979776},"labels":[],"label_agreement":null},{"id":"W4379768508","doi":"10.1002/jrsm.1645","title":"Methodological considerations for novel approaches to covariate‐adjusted indirect treatment comparisons","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Econometrics; Weighting; Robustness (evolution); Outcome (game theory); Computer science; Context (archaeology); Extrapolation; Statistics; Mathematics; Medicine","score_opus":0.9848045933522044,"score_gpt":0.6880955858430207,"score_spread":0.2967090075091837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379768508","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":[0.0023612294,0.000026600661,0.9877505,0.0037523136,0.00006691334,0.002740915,0.000146783,0.0010776977,0.0020770943],"genre_scores_gemma":[0.021316824,0.000031042473,0.970554,0.00003832592,0.000096842006,0.0071275895,0.0000113579135,0.00007283546,0.0007511724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9907481,0.0063374606,0.00060534396,0.0007477892,0.0005371334,0.001024175],"domain_scores_gemma":[0.76840544,0.23015517,0.00010460762,0.00075209746,0.0002917578,0.00029092073],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024735572,0.00031593148,0.0010185457,0.0008480359,0.0005912342,0.00012707456,0.0003574457,0.00027474985,0.00016900884],"category_scores_gemma":[0.17852296,0.00024666748,0.00022534796,0.0014087934,0.00023778611,0.00010977255,0.00027140972,0.00035693866,0.000057045694],"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":[0.00020991874,0.0009018177,0.00007947864,0.00020266953,0.00046534286,0.000014177688,0.0016559712,0.00026795914,0.09320831,0.7808395,0.019336488,0.10281839],"study_design_scores_gemma":[0.00024616506,0.00040093003,0.00031215817,0.00006406443,0.000077997785,0.000008986025,0.00086612074,0.007368461,0.39713648,0.58566993,0.0075434237,0.00030529004],"about_ca_topic_score_codex":0.00005087157,"about_ca_topic_score_gemma":0.000051402112,"teacher_disagreement_score":0.30392817,"about_ca_system_score_codex":0.00041202907,"about_ca_system_score_gemma":0.00024133455,"threshold_uncertainty_score":0.99999857},"labels":[],"label_agreement":null},{"id":"W4386617069","doi":"10.1002/jrsm.1664","title":"What are the best methods for rapid reviews of the research evidence? A systematic review of reviews and primary studies","year":2023,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Pan American Health Organization","keywords":"Data extraction; Systematic review; Credibility; Protocol (science); Computer science; Data science; Publication bias; Information retrieval; MEDLINE; Management science; Meta-analysis; Medicine; Alternative medicine; Engineering","score_opus":0.9855286116620706,"score_gpt":0.7959365036411353,"score_spread":0.1895921080209353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386617069","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.953266e-8,0.93956697,0.0029707504,0.0020819835,0.00068042026,0.054391615,0.000055098928,0.000006995871,0.00024609335],"genre_scores_gemma":[1.7080618e-8,0.8635753,0.10099192,0.00012175928,0.00019503162,0.027530177,0.000002690396,0.00011768207,0.0074654655],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.08494691,0.84580564,0.04762109,0.0036429141,0.016355025,0.0016284039],"domain_scores_gemma":[0.021577409,0.8932293,0.040899225,0.026764628,0.01705161,0.00047781775],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.95479786,0.0014925385,0.06536757,0.0026571958,0.001258067,0.0014517675,0.01657104,0.00058385724,0.00059131806],"category_scores_gemma":[0.95990825,0.00046669628,0.017623091,0.020030323,0.0026502092,0.00069015607,0.0048376457,0.0024085222,0.0006555366],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002540107,0.000028162161,4.9950336e-7,0.51427996,0.0010097334,5.8497096e-7,0.00019375766,1.84235e-8,0.0000028628676,0.00013193808,0.02098247,0.4633675],"study_design_scores_gemma":[0.000018575696,0.00004805522,4.6274468e-7,0.5049701,0.0062151537,0.000013752558,0.0015277354,0.000012057057,0.000008974987,0.0014535551,0.4855326,0.00019899188],"about_ca_topic_score_codex":0.000012954357,"about_ca_topic_score_gemma":0.000010300432,"teacher_disagreement_score":0.46455017,"about_ca_system_score_codex":0.00045324521,"about_ca_system_score_gemma":0.0012835339,"threshold_uncertainty_score":0.99989295},"labels":[],"label_agreement":null},{"id":"W4386705315","doi":"10.1002/jrsm.1670","title":"How to plan and manage an individual participant data meta‐analysis. An illustrative toolkit","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University; Université de Montréal; McGill University Health Centre","funders":"Institute of Genetics; Horizon 2020 Framework Programme","keywords":"Computer science; Harmonization; Plan (archaeology); Multinational corporation; Aggregate data; Data collection; Knowledge management; Work (physics); Data extraction; Meta-analysis; Process management; MEDLINE; Medicine; Business","score_opus":0.992173161325795,"score_gpt":0.7511059871365069,"score_spread":0.24106717418928814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386705315","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":[0.20445326,0.011058248,0.70358086,0.054930374,0.0004729366,0.010381583,0.0050730375,0.00028971917,0.009759957],"genre_scores_gemma":[0.42801085,0.00014406923,0.556002,0.00024504322,0.00022951965,0.00080723903,0.00021899996,0.000059879778,0.014282387],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.79330635,0.18588644,0.0044865264,0.0034856738,0.011600742,0.0012342493],"domain_scores_gemma":[0.86650395,0.10841837,0.0016823941,0.019647928,0.0017793527,0.0019680127],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6419351,0.0004466984,0.0065258755,0.0034881695,0.00061072776,0.006529439,0.007783369,0.0001582826,0.004131803],"category_scores_gemma":[0.23360355,0.00022239877,0.0014484636,0.012718519,0.0002914874,0.00156376,0.0023524468,0.0004414837,0.000997525],"study_design_candidate":"meta_analysis","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":[0.000088990644,0.00044797955,0.0022248556,0.00021995515,0.36478934,0.00023227405,0.013400477,0.0011243143,0.001966755,0.011359602,0.06032248,0.543823],"study_design_scores_gemma":[0.0002110195,0.0005388624,0.044045974,0.000030073083,0.3333858,0.00001588302,0.06408022,0.22670451,0.0015647436,0.023091031,0.3048846,0.0014472734],"about_ca_topic_score_codex":0.00010425973,"about_ca_topic_score_gemma":0.0006289337,"teacher_disagreement_score":0.5423757,"about_ca_system_score_codex":0.00001689532,"about_ca_system_score_gemma":0.00011009229,"threshold_uncertainty_score":0.9997803},"labels":[],"label_agreement":null},{"id":"W4386911034","doi":"10.1002/jrsm.1669","title":"Evaluation of statistical methods used to meta‐analyse results from interrupted time series studies: A simulation study","year":2023,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision 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":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Monash University; Medical Research Council; Australian Government","keywords":"Statistics; Autocorrelation; Meta-analysis; Random effects model; Context (archaeology); Econometrics; Interrupted Time Series Analysis; Restricted maximum likelihood; Ordinary least squares; Series (stratigraphy); Time series; Mathematics; Variance (accounting); Computer science; Maximum likelihood; Medicine","score_opus":0.9895385164088845,"score_gpt":0.8199393673767278,"score_spread":0.16959914903215667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386911034","genre_codex":"review","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002269264,0.78728664,0.20091505,0.00013148859,0.00027615647,0.009675543,0.0012188583,0.000031213553,0.00044237004],"genre_scores_gemma":[0.00004826524,0.2974312,0.6949514,0.0000075420894,0.00020887962,0.0041884487,0.00008464436,0.0001585169,0.00292107],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.08831113,0.8363052,0.032444313,0.0048514404,0.037044663,0.0010432323],"domain_scores_gemma":[0.07951949,0.8666249,0.013128775,0.014379083,0.025580237,0.00076753803],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.917397,0.0012829268,0.03611669,0.005990727,0.0003914232,0.0012172576,0.0053154672,0.0004986093,0.010942595],"category_scores_gemma":[0.9399383,0.0006212661,0.006926229,0.015222461,0.0003508941,0.00038523672,0.0018912609,0.0010333606,0.0052369027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006444406,0.00022029728,9.237652e-7,0.0014339596,0.05585716,0.000007963249,0.002271139,0.0009932928,0.000008191795,0.000021097721,0.0032543,0.93586725],"study_design_scores_gemma":[0.00047573674,0.0005277792,0.000053636173,0.006552453,0.27240223,0.000002498485,0.011747454,0.08511228,0.00005983052,0.014836258,0.60707176,0.0011581061],"about_ca_topic_score_codex":0.00020486608,"about_ca_topic_score_gemma":0.00013944457,"teacher_disagreement_score":0.93470913,"about_ca_system_score_codex":0.00074649265,"about_ca_system_score_gemma":0.0014148781,"threshold_uncertainty_score":0.99999225},"labels":[],"label_agreement":null},{"id":"W4389309117","doi":"10.1002/jrsm.1684","title":"Predatory journals and their practices present a conundrum for systematic reviewers and evidence synthesisers of health research: A qualitative descriptive study","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Queen's University","funders":"National Health and Medical Research Council; Medical Research Council; Canadian Institutes of Health Research","keywords":"Publishing; Inclusion (mineral); Evidence-based practice; Best evidence; Critical appraisal; Qualitative research; Psychology; Public relations; Political science; Social science; Medical education; Sociology; Alternative medicine; Social psychology; Medicine; Law","score_opus":0.9866112398185908,"score_gpt":0.8221297151216669,"score_spread":0.1644815246969239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389309117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6495919,0.2631735,0.027990356,0.027188322,0.00044255517,0.030678159,0.0002994985,0.00011770543,0.00051797484],"genre_scores_gemma":[0.9485409,0.022482244,0.0246097,0.000020392046,0.00008151276,0.0029725053,5.24436e-7,0.000058327154,0.0012338946],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5612597,0.386266,0.006337558,0.0041600983,0.037466552,0.0045101303],"domain_scores_gemma":[0.08855725,0.8844719,0.0027512193,0.0022559352,0.02058237,0.0013813229],"candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.8245599,0.00032661806,0.0021477467,0.05746787,0.001624346,0.0031530885,0.0030391389,0.00017402701,0.000060766757],"category_scores_gemma":[0.9212538,0.00019842054,0.00025102877,0.10780317,0.0018171862,0.0015905375,0.0023888892,0.0010578762,0.000029491914],"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":[0.0010878394,0.0016511744,0.008074489,0.04768666,0.0014109814,0.000035092882,0.2202984,0.000016955273,0.011944195,0.0014264155,0.027212977,0.6791548],"study_design_scores_gemma":[0.00044505278,0.0024252643,0.010726812,0.013907735,0.000043375883,0.000013624283,0.9374943,0.007904987,0.0037832248,0.02092237,0.001988144,0.00034514125],"about_ca_topic_score_codex":0.0006337473,"about_ca_topic_score_gemma":0.0000350275,"teacher_disagreement_score":0.71719587,"about_ca_system_score_codex":0.00043830532,"about_ca_system_score_gemma":0.0016363261,"threshold_uncertainty_score":0.9996754},"labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"evaluation","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","scholarly_communication","research_integrity"],"domain":"evaluation","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4389569015","doi":"10.1002/jrsm.1686","title":"<scp>metamedian</scp>: An R package for meta‐analyzing studies reporting medians","year":2023,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":55,"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 Health Centre; McGill University","funders":"National Science Foundation","keywords":"Meta-analysis; Computer science; Sample size determination; Median; Software; Sample (material); Outcome (game theory); Statistics; Data science; Medicine; Mathematics","score_opus":0.9897344879680611,"score_gpt":0.7931787116963884,"score_spread":0.19655577627167264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389569015","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000030885678,0.9278075,0.063740745,0.00022422071,0.00080850563,0.0055002407,0.00025220882,0.000073020354,0.0015904609],"genre_scores_gemma":[3.9671698e-7,0.71153414,0.25893095,0.000015161315,0.0008632597,0.010331027,0.00003339659,0.00024074125,0.018050933],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3886073,0.49652806,0.073929705,0.00885993,0.028065145,0.00400988],"domain_scores_gemma":[0.02764321,0.88902223,0.051328063,0.019510023,0.010796224,0.001700253],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.9003953,0.0018650235,0.05576103,0.007191729,0.0014347713,0.0037424625,0.009950289,0.000961508,0.0016754132],"category_scores_gemma":[0.97161514,0.0008502941,0.027905932,0.014203185,0.00069583085,0.00067686697,0.0016569097,0.00201484,0.0038007621],"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":[7.563701e-7,0.0000525189,0.00000525688,0.019548073,0.033594858,0.000075185075,0.00056530687,0.000001922285,0.0000057908264,0.00045213682,0.04074061,0.9049576],"study_design_scores_gemma":[0.000037186954,0.0000491608,0.0000020017949,0.0038761138,0.039660487,0.0000340469,0.0040215105,0.00027862177,0.000054379987,0.011094647,0.94055444,0.00033742998],"about_ca_topic_score_codex":0.000029832992,"about_ca_topic_score_gemma":0.000088850706,"teacher_disagreement_score":0.9046202,"about_ca_system_score_codex":0.0003792137,"about_ca_system_score_gemma":0.0013970173,"threshold_uncertainty_score":0.99986523},"labels":[],"label_agreement":null},{"id":"W4389801794","doi":"10.1002/jrsm.1696","title":"A study of search strategy availability statements and sharing practices for systematic reviews: Ask and you might receive","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Manitoba","funders":"","keywords":"Systematic review; Ask price; Transparency (behavior); Quality (philosophy); Computer science; Data collection; Data science; Information retrieval; Psychology; MEDLINE; Business; Political science; Sociology","score_opus":0.9639013715567339,"score_gpt":0.7566105992377656,"score_spread":0.2072907723189683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389801794","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":[0.9510416,0.008294593,0.009186154,0.0006650359,0.00010477263,0.027660869,0.000061890525,0.000022536658,0.0029625748],"genre_scores_gemma":[0.8135766,0.004592175,0.14465718,0.000023965955,0.00012920093,0.010100478,0.0000064787637,0.000099324425,0.026814597],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.63751495,0.32795975,0.017548356,0.00362831,0.012105278,0.0012433617],"domain_scores_gemma":[0.6038704,0.37277004,0.009683595,0.0076808115,0.005372375,0.0006227515],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7796497,0.0003315974,0.005666789,0.001279605,0.00045290278,0.0013533416,0.0018334276,0.000102947255,0.0006856202],"category_scores_gemma":[0.63764155,0.00016207472,0.0005478942,0.0035414887,0.00020740376,0.0006383328,0.0008049837,0.00032298538,0.00023092276],"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":[0.00036751182,0.0022097176,0.0828446,0.22765303,0.0054419828,0.000043786415,0.03695687,0.00009468893,0.007986816,0.001433687,0.015388896,0.6195784],"study_design_scores_gemma":[0.0030624461,0.004552975,0.06795304,0.023910666,0.004905092,0.00005558584,0.6228989,0.17293575,0.0050197137,0.047526177,0.044921387,0.002258305],"about_ca_topic_score_codex":0.000144957,"about_ca_topic_score_gemma":0.00006851846,"teacher_disagreement_score":0.6173201,"about_ca_system_score_codex":0.000061635,"about_ca_system_score_gemma":0.00011205067,"threshold_uncertainty_score":0.9996833},"labels":[],"label_agreement":null},{"id":"W4390234748","doi":"10.1002/jrsm.1688","title":"Consensus on the definition and assessment of external validity of randomized controlled trials: A <scp>Delphi</scp> study","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Institute of Infection and Immunity; University of Alberta","funders":"","keywords":"External validity; Delphi method; Internal validity; Systematic review; Delphi; Predictive validity; Criterion validity; Randomized controlled trial; Psychological intervention; Psychology; Management science; Applied psychology; Computer science; Construct validity; Medicine; MEDLINE; Social psychology; Psychometrics; Nursing; Clinical psychology; Artificial intelligence","score_opus":0.7225730919611445,"score_gpt":0.6545780482241669,"score_spread":0.06799504373697762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390234748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9157476,0.00036288632,0.008039392,0.0064502293,0.0002102199,0.016172936,0.00005710154,0.00018011736,0.052779526],"genre_scores_gemma":[0.9574451,0.0015472097,0.037314165,0.000008912056,0.000109836896,0.0031913046,5.630319e-7,0.000025160709,0.0003577629],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6499667,0.34033975,0.0024018963,0.00062714395,0.005644881,0.0010196016],"domain_scores_gemma":[0.34016517,0.6571873,0.00069682574,0.0005890068,0.001181569,0.00018015942],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5963983,0.00018808787,0.0032023033,0.001071328,0.000648444,0.0001595355,0.0007801998,0.0001790368,0.00013359197],"category_scores_gemma":[0.6637228,0.000110373156,0.0006685631,0.0016041145,0.0024759911,0.000055214336,0.00032055724,0.0007329299,0.000006943883],"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":[0.06430057,0.0052583343,0.0061649983,0.0006591148,0.0050472883,0.00017703841,0.035684086,0.00005232343,0.1329315,0.58248323,0.015697116,0.15154442],"study_design_scores_gemma":[0.17817402,0.00226554,0.011951154,0.0015854384,0.0014066586,0.0000049815103,0.22750461,0.012543299,0.116980456,0.44500569,0.0021511323,0.00042702453],"about_ca_topic_score_codex":0.0016826636,"about_ca_topic_score_gemma":0.000062558094,"teacher_disagreement_score":0.31684753,"about_ca_system_score_codex":0.00013440842,"about_ca_system_score_gemma":0.0008083713,"threshold_uncertainty_score":0.91228926},"labels":[],"label_agreement":null},{"id":"W4390519786","doi":"10.1002/jrsm.1694","title":"Advancing the methodology of mapping reviews: A scoping review","year":2024,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Diverse Aspects of Tourism Research","field":"Social Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Public Health Ontario; Queen's University; University of Toronto; St. Michael's Hospital; Bruyère; University of Ottawa","funders":"National Health and Medical Research Council; La Trobe University","keywords":"PsycINFO; CINAHL; MEDLINE; Citation; Protocol (science); Computer science; Test (biology); Systematic review; Data science; Cochrane Library; Medical education; Psychology; Medicine; Library science; Alternative medicine; Political science","score_opus":0.7551232860667084,"score_gpt":0.7100772784172794,"score_spread":0.04504600764942901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390519786","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.493368e-9,0.95451576,0.0021134343,0.0028735448,0.00051593786,0.007940588,0.000015564698,0.00008969638,0.031935446],"genre_scores_gemma":[9.850967e-9,0.84284145,0.15201738,0.000056996065,0.0007393912,0.0020451501,0.0000021705737,0.0001034497,0.0021940114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.81944454,0.17196189,0.0023330527,0.0012704112,0.0028588478,0.0021312519],"domain_scores_gemma":[0.84752506,0.14743964,0.0010828472,0.0024572439,0.00094640534,0.000548811],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.34768683,0.000604824,0.0061228154,0.001671213,0.0011799695,0.0002878024,0.00455797,0.0005954585,0.0016859948],"category_scores_gemma":[0.27638686,0.00036889125,0.0021500809,0.0063407742,0.0023177525,0.0002668636,0.0020560496,0.0032647685,0.00091229513],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011977419,0.000016895436,3.1325214e-8,0.27787367,0.00017881839,0.00004224663,0.00034556107,2.7903578e-8,0.0000016202092,0.0022355951,0.015681252,0.7036231],"study_design_scores_gemma":[0.000008697224,0.000011940868,1.3501335e-8,0.44135126,0.0005623696,0.000005460649,0.0005728994,8.357529e-7,0.000005798998,0.0009843863,0.55631626,0.00018004356],"about_ca_topic_score_codex":0.0011907179,"about_ca_topic_score_gemma":0.00014972215,"teacher_disagreement_score":0.70344305,"about_ca_system_score_codex":0.0007841738,"about_ca_system_score_gemma":0.0057531823,"threshold_uncertainty_score":0.9998833},"labels":[],"label_agreement":null},{"id":"W4390706575","doi":"10.1002/jrsm.1698","title":"Using qualitative comparative analysis as a mixed methods synthesis in systematic mixed studies reviews: Guidance and a worked example","year":2024,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation; McGill University","funders":"Institute of Health Services and Policy Research","keywords":"Qualitative comparative analysis; Management science; Computer science; Outcome (game theory); Causation; Context (archaeology); Multimethodology; Bridge (graph theory); Systematic review; Data science; Qualitative research; Risk analysis (engineering); Machine learning; Psychology; Engineering; MEDLINE; Medicine; Epistemology; Sociology; Mathematics; Social science; Mathematics education","score_opus":0.8342374288615383,"score_gpt":0.7526588746716723,"score_spread":0.08157855418986604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390706575","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":[0.06584511,0.3931644,0.5167396,0.0027031547,0.00036748417,0.0067081894,0.000053204873,0.00028260192,0.014136253],"genre_scores_gemma":[0.31047752,0.009819887,0.672709,0.000027281716,0.00014138252,0.0043662624,0.0000028096383,0.0000604823,0.0023953714],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.66570973,0.3274282,0.0018255749,0.0015062152,0.0021154592,0.001414834],"domain_scores_gemma":[0.5491127,0.445767,0.0005715832,0.0013361456,0.0024966032,0.00071597635],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.3072275,0.00062195986,0.0046531577,0.0050382363,0.0014704105,0.00093001226,0.0011883267,0.00026909454,0.0005870574],"category_scores_gemma":[0.23869804,0.0004960504,0.0008195079,0.0201999,0.0036424533,0.0008433919,0.0006242205,0.0011545613,0.00019707995],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019229657,0.00032378477,0.00019300185,0.016401678,0.014791795,0.00008210991,0.83580303,0.00015213156,0.011082737,0.08194814,0.0015732596,0.037456024],"study_design_scores_gemma":[0.0001627015,0.000102300066,0.0003679149,0.017090542,0.0024691555,0.0000029614625,0.8797978,0.03303227,0.013914972,0.043544732,0.008524117,0.0009905214],"about_ca_topic_score_codex":0.008522725,"about_ca_topic_score_gemma":0.0055750837,"teacher_disagreement_score":0.38334453,"about_ca_system_score_codex":0.0018211073,"about_ca_system_score_gemma":0.0008681601,"threshold_uncertainty_score":0.99982953},"labels":[],"label_agreement":null},{"id":"W4392959368","doi":"10.1002/jrsm.1717","title":"Combining randomized and non‐randomized data to predict heterogeneous effects of competing treatments","year":2024,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Amgen (Canada)","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; European Commission; Biogen; Celgene; Sanofi; National Science Foundation","keywords":"Randomized controlled trial; Medicine; Internal medicine","score_opus":0.19089427978971288,"score_gpt":0.5087678801306569,"score_spread":0.31787360034094403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392959368","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":[0.81462336,0.055274397,0.08138737,0.0059677535,0.0009102622,0.0321533,0.0002690591,0.0006200917,0.008794389],"genre_scores_gemma":[0.79750836,0.006140856,0.19418545,0.000026004232,0.000150053,0.0015787623,0.000018619352,0.000079258534,0.0003126329],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9814749,0.014212779,0.0008619121,0.0010182149,0.0015398465,0.0008923555],"domain_scores_gemma":[0.8145484,0.1828208,0.00009741728,0.0014841438,0.00041050732,0.0006387482],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044950854,0.0003355637,0.0029758476,0.0010095475,0.0002515566,0.00013385879,0.00052119355,0.00012791633,0.00006643106],"category_scores_gemma":[0.14093968,0.00022330692,0.0003402877,0.0006792165,0.0014970313,0.00013263169,0.0016067645,0.00057050353,0.000023198312],"study_design_candidate":"randomized_trial","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":[0.34179872,0.0005595918,0.00034760457,0.0076555624,0.008660505,0.0003375077,0.0041064285,0.000015834483,0.25504407,0.00013095616,0.0007758458,0.38056737],"study_design_scores_gemma":[0.5311647,0.00072150404,0.0008382907,0.010063572,0.0017506861,0.000057418354,0.000534118,0.15111119,0.3020639,0.00028450592,0.0010056287,0.00040450133],"about_ca_topic_score_codex":0.00033493064,"about_ca_topic_score_gemma":0.0000052820806,"teacher_disagreement_score":0.38016286,"about_ca_system_score_codex":0.00014245704,"about_ca_system_score_gemma":0.00022263089,"threshold_uncertainty_score":0.98342407},"labels":[],"label_agreement":null},{"id":"W4399722064","doi":"10.1002/jrsm.1731","title":"Automation tools to support undertaking scoping reviews","year":2024,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Public Health Ontario; University of Toronto; St. Michael's Hospital; Queen's University","funders":"National Health and Medical Research Council; La Trobe University","keywords":"Automation; Interoperability; Computer science; Systematic review; Software engineering; Software; Software development; Best practice; Engineering management; Data science; Process management; Systems engineering; Engineering; World Wide Web; MEDLINE","score_opus":0.9755536338275869,"score_gpt":0.7709541161889004,"score_spread":0.20459951763868645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399722064","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":[0.0013314239,0.007145432,0.9239428,0.0040573734,0.00057108054,0.00278261,0.000008776445,0.00005005193,0.06011045],"genre_scores_gemma":[0.031525984,0.0005619577,0.9389257,0.00034462853,0.0004562926,0.0012378248,0.0000037752063,0.000060557108,0.02688331],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7807766,0.18880148,0.013191701,0.0026951658,0.013365818,0.0011692103],"domain_scores_gemma":[0.65090895,0.33074677,0.0023686744,0.011696043,0.0031284236,0.0011511758],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7276119,0.00032033632,0.0037534158,0.0021950903,0.0003879368,0.0067002606,0.0026928964,0.000133169,0.03477805],"category_scores_gemma":[0.5935033,0.00016009224,0.0018088557,0.006768458,0.00007874315,0.00073763105,0.0004613593,0.0004418353,0.03561473],"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":[0.00000195422,0.000012109011,0.000063829655,0.0005124146,0.00007613577,0.000009836334,0.00040558184,0.00002181772,0.0027821725,0.0044176048,0.07619767,0.91549885],"study_design_scores_gemma":[0.000022622784,0.000056389847,0.0004893735,0.0033282656,0.000111246314,0.000016769152,0.0005162605,0.019705292,0.00440951,0.012081761,0.95898193,0.0002805626],"about_ca_topic_score_codex":0.00001384245,"about_ca_topic_score_gemma":0.00001741517,"teacher_disagreement_score":0.9152183,"about_ca_system_score_codex":0.00020702087,"about_ca_system_score_gemma":0.00037370832,"threshold_uncertainty_score":0.9943309},"labels":[],"label_agreement":null},{"id":"W4400983681","doi":"10.1002/jrsm.1736","title":"Considerations for conducting systematic reviews: A follow‐up study to evaluate the performance of various automated methods for reference de‐duplication","year":2024,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Dalhousie University; Queen's University","funders":"","keywords":"Computer science; Evaluation methods; Research methodology; Reliability engineering; Engineering; Medicine","score_opus":0.9579403401628281,"score_gpt":0.7454122149889704,"score_spread":0.21252812517385777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400983681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03120945,0.005886632,0.9337484,0.0016190077,0.00034944314,0.026709888,0.000031487823,0.000056701258,0.00038898783],"genre_scores_gemma":[0.23846945,0.000081386745,0.74206185,0.000047254816,0.000055682536,0.017369198,0.0000014903205,0.000031922482,0.001881744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.63825804,0.33689916,0.015742382,0.0023451322,0.0056851488,0.0010701513],"domain_scores_gemma":[0.31809366,0.6638458,0.0025184504,0.0067582233,0.0084644975,0.00031937743],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8064832,0.00034728515,0.0045530885,0.0009969515,0.0008388587,0.0015684338,0.0020153425,0.00010029845,0.00059085264],"category_scores_gemma":[0.7719032,0.00015046312,0.0013497397,0.0034169827,0.000117413074,0.00027229512,0.0001962648,0.00030564782,0.00023693539],"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":[0.00015241253,0.0006570884,0.00027318945,0.07756174,0.0048198546,0.000002493126,0.040262517,0.0011219529,0.13939874,0.025187794,0.06321147,0.6473507],"study_design_scores_gemma":[0.0001986981,0.00043982302,0.00016104714,0.003890978,0.0019685822,0.00002258609,0.0071999575,0.9395254,0.01838154,0.014599679,0.013304669,0.00030700833],"about_ca_topic_score_codex":0.000032120715,"about_ca_topic_score_gemma":0.000021572818,"teacher_disagreement_score":0.9384035,"about_ca_system_score_codex":0.00018291915,"about_ca_system_score_gemma":0.00056100864,"threshold_uncertainty_score":0.999468},"labels":[],"label_agreement":null},{"id":"W4401175765","doi":"10.1002/jrsm.1744","title":"Two decades of network meta‐analysis: Roadmap to their applications and challenges","year":2024,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; Ottawa Hospital; Impact; McMaster University; Ottawa Public Health; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Computer science; Management science; Data science; Guideline; Reliability (semiconductor); Risk analysis (engineering); Knowledge management; Engineering; Political science; Medicine","score_opus":0.9577047552678494,"score_gpt":0.7108394919747318,"score_spread":0.24686526329311753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401175765","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":[0.000320703,0.37606996,0.5998866,0.007964788,0.00004969351,0.0013249611,0.0000338742,0.00001831088,0.014331108],"genre_scores_gemma":[0.18174651,0.0072961855,0.8036103,0.000070526265,0.00029992845,0.0026829103,0.0000016373754,0.00004130931,0.0042506945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8878958,0.09747698,0.0058500296,0.0020565777,0.0060268897,0.000693666],"domain_scores_gemma":[0.8298677,0.16231035,0.0007635729,0.005004547,0.0015839009,0.0004699172],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5076229,0.00030286235,0.0057560387,0.0022962831,0.00024451406,0.0010255979,0.002223651,0.0001020786,0.004713458],"category_scores_gemma":[0.050768398,0.0001358895,0.0037300244,0.009978314,0.000199429,0.00017491075,0.00051522534,0.0002993436,0.0005587174],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067978035,0.0000500028,0.00012949927,0.00034410332,0.09293783,0.000002471099,0.00093294546,0.00070983055,0.00047631524,0.07260173,0.0041388245,0.8276697],"study_design_scores_gemma":[0.00003024793,0.000045441702,0.00088560616,0.00006458148,0.054678105,0.0000058873147,0.003071286,0.019074967,0.0025144957,0.116920516,0.8023952,0.00031362896],"about_ca_topic_score_codex":0.000030635332,"about_ca_topic_score_gemma":0.00007649454,"teacher_disagreement_score":0.82735604,"about_ca_system_score_codex":0.000026376543,"about_ca_system_score_gemma":0.000099521276,"threshold_uncertainty_score":0.9961964},"labels":[],"label_agreement":null},{"id":"W4401551114","doi":"10.1002/jrsm.1742","title":"Scoping review search practices in the social sciences: A scoping review","year":2024,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":19,"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; Ontario Council of University Libraries; University of Toronto","funders":"","keywords":"Citation; Citation index; Systematic review; Social Sciences Citation Index; Science Citation Index; MEDLINE; Data science; Library science; Computer science; Medical education; Political science; Medicine","score_opus":0.9889760406366395,"score_gpt":0.8389961357747868,"score_spread":0.14997990486185264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401551114","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.197959e-8,0.9532787,0.00091536937,0.0059532234,0.00025039137,0.020314805,0.000022389044,0.000016543545,0.019248484],"genre_scores_gemma":[7.646019e-8,0.96587086,0.024867058,0.0007696243,0.00049019366,0.0066582863,0.000006068244,0.000084013394,0.0012538503],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.27197918,0.66011983,0.027996251,0.0053302725,0.03235682,0.002217637],"domain_scores_gemma":[0.1681871,0.78093743,0.027347723,0.017850367,0.0050520077,0.00062536774],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.9228172,0.0012950549,0.027915511,0.003672055,0.0016143838,0.0065415287,0.017964201,0.0005044507,0.010727881],"category_scores_gemma":[0.7518052,0.0004984256,0.009392559,0.033212107,0.0010949952,0.0007716537,0.0021923645,0.003879508,0.010705075],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6761847e-7,0.00002608729,4.2669794e-7,0.46805927,0.00012745023,0.000025814123,0.000086096574,6.8290284e-8,7.070802e-8,0.0003222903,0.023838852,0.50751317],"study_design_scores_gemma":[0.000010331855,0.000016984523,1.6182751e-7,0.5865782,0.0019904696,0.000060798775,0.00020589196,0.000027931083,2.6368707e-7,0.00030053387,0.41052622,0.00028221498],"about_ca_topic_score_codex":0.0000542073,"about_ca_topic_score_gemma":0.00006704655,"teacher_disagreement_score":0.507231,"about_ca_system_score_codex":0.00036694654,"about_ca_system_score_gemma":0.0072100437,"threshold_uncertainty_score":0.9999801},"labels":[],"label_agreement":null},{"id":"W4402285950","doi":"10.1002/jrsm.1751","title":"Narrative reanalysis: A methodological framework for a new brand of reviews","year":2024,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":12,"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 Saskatchewan; University of Alberta","funders":"","keywords":"Narrative; Systematic review; Scope (computer science); Identification (biology); Phenomenon; Computer science; Process (computing); Data extraction; Narrative inquiry; Selection (genetic algorithm); Data science; Management science; Epistemology; Political science; Artificial intelligence; Linguistics; MEDLINE","score_opus":0.9822347056140353,"score_gpt":0.7876605260465089,"score_spread":0.19457417956752632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402285950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045702877,0.05014,0.9394055,0.004134605,0.00021155727,0.0018859123,0.000016916698,0.00001287241,0.003735597],"genre_scores_gemma":[0.004065248,0.0011443598,0.97894037,0.00006472531,0.00034043635,0.00063412404,0.0000015838128,0.000027806595,0.014781361],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.57698417,0.39307445,0.015533313,0.003005586,0.01038035,0.0010221413],"domain_scores_gemma":[0.09272961,0.8897961,0.0037137328,0.009122469,0.003797643,0.00084047],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7929913,0.0004043769,0.008327521,0.0017572391,0.00027991226,0.0012604699,0.0031507914,0.00032118955,0.023212638],"category_scores_gemma":[0.86986053,0.00017402795,0.005972528,0.007824452,0.00030437173,0.00025782193,0.00031750376,0.0007084582,0.00088744506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048642574,0.000043578748,0.000041736654,0.00046705708,0.0009317657,0.0000043202067,0.0043441504,0.000011100402,0.002348279,0.04643956,0.11808666,0.82723314],"study_design_scores_gemma":[0.000041207182,0.00008394093,0.000068008325,0.00061403745,0.0005147317,0.0000046885734,0.0021338307,0.0059676543,0.004156499,0.43209946,0.55415195,0.00016398245],"about_ca_topic_score_codex":0.00003288374,"about_ca_topic_score_gemma":0.000009913611,"teacher_disagreement_score":0.82706916,"about_ca_system_score_codex":0.00007601291,"about_ca_system_score_gemma":0.00039234303,"threshold_uncertainty_score":0.9998905},"labels":[],"label_agreement":null},{"id":"W4408173758","doi":"10.1017/rsm.2024.6","title":"A practical guide to evaluating sensitivity of literature search strings for systematic reviews using relative recall","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Australian Research Council","keywords":"Recall; Systematic review; Sensitivity (control systems); Computer science; Research methodology; Information retrieval; Management science; Psychology; MEDLINE; Sociology; Political science; Cognitive psychology; Engineering","score_opus":0.9529631762949683,"score_gpt":0.7824454287408193,"score_spread":0.17051774755414895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408173758","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038571367,0.0021817742,0.97810143,0.0019949584,0.00011622808,0.010196601,0.000028799901,0.0000068861746,0.0035162074],"genre_scores_gemma":[0.0074531506,0.000060858074,0.9818941,0.00008433569,0.00007132949,0.0008914482,0.0000012728564,0.000023749053,0.009519768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.2837029,0.67878914,0.019813629,0.0028286094,0.013544785,0.001320924],"domain_scores_gemma":[0.19744347,0.7713102,0.0048750066,0.0076436144,0.018179256,0.0005484218],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.88239557,0.00041432897,0.007851126,0.002241256,0.00048351465,0.0011566379,0.0014867138,0.00026121995,0.00043028797],"category_scores_gemma":[0.9484475,0.00021080459,0.002454067,0.008500503,0.00016627145,0.00047755352,0.00071846106,0.00074223394,0.00019076704],"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":[0.0005615361,0.0007176453,0.0014531153,0.1511838,0.004097297,0.00005589698,0.007617408,0.0011851606,0.21798827,0.08473226,0.11008532,0.4203223],"study_design_scores_gemma":[0.0003805317,0.00032249908,0.00029849922,0.08045484,0.001842771,0.00005855913,0.0049245264,0.80936366,0.037671797,0.022086779,0.041883796,0.00071174646],"about_ca_topic_score_codex":0.000039211845,"about_ca_topic_score_gemma":0.000012048135,"teacher_disagreement_score":0.8081785,"about_ca_system_score_codex":0.0003419573,"about_ca_system_score_gemma":0.00070435484,"threshold_uncertainty_score":0.99988025},"labels":[],"label_agreement":null},{"id":"W4408236585","doi":"10.1017/rsm.2024.18","title":"Translating systematic searches in the APA PsycInfo database from Ovid to EBSCOhost: A tutorial based on a filter translation","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"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 Victoria","funders":"","keywords":"PsycINFO; Computer science; MEDLINE; Translation (biology); Psychology","score_opus":0.2116884651036383,"score_gpt":0.5070427482358725,"score_spread":0.29535428313223416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408236585","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":[0.14715125,0.004000421,0.802391,0.029772656,0.0008138548,0.004703408,0.0003457097,0.00009960855,0.010722103],"genre_scores_gemma":[0.73880273,0.000032360975,0.25905138,0.00066527043,0.00033236935,0.00089787116,0.000055898043,0.00002421138,0.00013789786],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9910272,0.007005822,0.00038697588,0.00051386084,0.00060180173,0.00046436128],"domain_scores_gemma":[0.98981035,0.009213038,0.00003674609,0.0007733304,0.00007506528,0.00009144614],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01338222,0.00017037783,0.00033895427,0.00032090634,0.00016962911,0.00009379189,0.0006354862,0.0002212303,0.00002976275],"category_scores_gemma":[0.013976333,0.00011349424,0.00011963118,0.0006566549,0.00016124558,0.0000048623433,0.0000642381,0.00040178403,0.000010466566],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014815195,0.00036275134,0.00043235347,0.003350157,0.00016503746,0.000021436832,0.0020443099,0.00017831233,0.57703847,0.00020100309,0.0018736079,0.41285104],"study_design_scores_gemma":[0.0034400441,0.0016173268,0.0044867196,0.017052807,0.00023554493,0.00000499899,0.007537293,0.04357897,0.8644032,0.0018885724,0.05461507,0.001139444],"about_ca_topic_score_codex":0.00023390367,"about_ca_topic_score_gemma":0.00012784044,"teacher_disagreement_score":0.5916515,"about_ca_system_score_codex":0.00004125363,"about_ca_system_score_gemma":0.00022873069,"threshold_uncertainty_score":0.9943294},"labels":[],"label_agreement":null},{"id":"W4408297730","doi":"10.1017/rsm.2025.2","title":"Effect modification and non-collapsibility together may lead to conflicting treatment decisions: A review of marginal and conditional estimands and recommendations for decision-making","year":2025,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Medical Research Council","keywords":"Lead (geology); Marginal structural model; Computer science; Risk analysis (engineering); Actuarial science; Econometrics; Economics; Business; Causal inference","score_opus":0.536206654897272,"score_gpt":0.6934173618985573,"score_spread":0.15721070700128525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408297730","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010821497,0.5622438,0.43270034,0.0001874383,0.000017616427,0.0044267005,0.00023898749,0.00003002588,0.00014424106],"genre_scores_gemma":[0.0000106302205,0.5163332,0.48014757,0.000010727064,0.000014299383,0.0033950468,0.000014071777,0.000024608644,0.00004978765],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9932663,0.0040050778,0.0011013161,0.00083914073,0.00040367918,0.00038450558],"domain_scores_gemma":[0.70565,0.29273152,0.0003599257,0.00063742575,0.00048608493,0.00013504756],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.021902742,0.00042361874,0.0023251215,0.0007189739,0.00032464607,0.000076983844,0.000246472,0.0002685082,0.00004668765],"category_scores_gemma":[0.17748784,0.00031448712,0.0002233739,0.0006087561,0.00023755117,0.00011700229,0.00030192902,0.00031581247,8.859418e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051824645,0.00005708857,0.0000027719884,0.05562502,0.00010965258,7.5645704e-7,0.00003927765,6.169403e-8,0.00001153737,0.0028130403,0.00039169687,0.9408973],"study_design_scores_gemma":[0.00025377108,0.0010250211,0.000009483471,0.6058107,0.0014705474,0.00003757233,0.000062836356,0.0004089213,0.00061221,0.14391653,0.24585417,0.0005382342],"about_ca_topic_score_codex":0.000009124606,"about_ca_topic_score_gemma":0.0000040123005,"teacher_disagreement_score":0.94035906,"about_ca_system_score_codex":0.00036112778,"about_ca_system_score_gemma":0.0003335322,"threshold_uncertainty_score":0.99993074},"labels":[],"label_agreement":null},{"id":"W4408636096","doi":"10.1017/rsm.2024.3","title":"Visualization toolkits for enriching meta-analyses through evidence maps, bibliometrics, and alternative impact metrics","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Australian Research Council; National Natural Science Foundation of China","keywords":"Bibliometrics; Visualization; Computer science; Meta-analysis; Data science; Information retrieval; Data mining; Medicine","score_opus":0.982746142638343,"score_gpt":0.805248268991111,"score_spread":0.17749787364723202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408636096","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.001713831,0.048691392,0.9437038,0.0013378415,0.0001898894,0.0016460272,0.000069546004,0.0000126415825,0.0026350443],"genre_scores_gemma":[0.12253013,0.0048987484,0.86258554,0.0002664572,0.00014614195,0.0008595919,0.0000070266415,0.000043935863,0.0086624315],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8034738,0.16681205,0.01066261,0.0031474973,0.014674415,0.0012296609],"domain_scores_gemma":[0.1908421,0.78373504,0.0048310026,0.0062780106,0.01381948,0.0004943533],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.5816067,0.0005222296,0.0063630454,0.026919322,0.0007534629,0.00436651,0.003158907,0.0002025652,0.002600378],"category_scores_gemma":[0.8696154,0.0002434018,0.0038821585,0.08964452,0.00023364996,0.0015205265,0.0007456948,0.00039299444,0.00011309801],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011004592,0.00026643637,0.006843273,0.00076185085,0.027601728,0.000007911289,0.00092468574,0.00068270747,0.005437054,0.050499726,0.148387,0.75847757],"study_design_scores_gemma":[0.00045908566,0.00038359806,0.008023359,0.00042704315,0.022276776,0.0000124529915,0.002605938,0.17205834,0.058541358,0.44629043,0.28779453,0.001127085],"about_ca_topic_score_codex":0.0003299767,"about_ca_topic_score_gemma":0.000013354721,"teacher_disagreement_score":0.7573505,"about_ca_system_score_codex":0.00023062559,"about_ca_system_score_gemma":0.00032468373,"threshold_uncertainty_score":0.9983114},"labels":[{"model":"gemma","categories":["metaresearch","bibliometrics"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4409040122","doi":"10.1017/rsm.2024.11","title":"Selecting a specialized education database for literature reviews and evidence synthesis projects","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Research methodology; Database; Data science; Information retrieval; Medicine; Environmental health","score_opus":0.22041869199387587,"score_gpt":0.5656706600618855,"score_spread":0.3452519680680096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409040122","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":[0.0008366511,0.046613947,0.93077236,0.017985327,0.0003479963,0.001638008,0.000006551369,0.00015068833,0.0016484404],"genre_scores_gemma":[0.0043030116,0.0053460076,0.9865858,0.00014718849,0.0003026488,0.0007616239,0.0000014790561,0.000014400512,0.0025378447],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99222076,0.005768129,0.00037810556,0.00077262375,0.00035340994,0.0005069838],"domain_scores_gemma":[0.9689533,0.02916161,0.00013542667,0.0009680881,0.0006353324,0.00014621927],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024622345,0.00017970217,0.000443097,0.0007286587,0.00053130195,0.0007571244,0.000902088,0.000108300694,0.0000066779567],"category_scores_gemma":[0.14095594,0.00014749684,0.00011324658,0.0025080643,0.00008453917,0.0005753997,0.0004067172,0.00049031177,0.000005957517],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002216368,0.00007975196,0.00015964154,0.0012709169,0.000025887404,0.0000014199829,0.00037121808,0.0000011700648,0.007625056,0.013698414,0.0048723,0.97187203],"study_design_scores_gemma":[0.00036264505,0.00019397312,0.00095913786,0.03969528,0.0002622679,0.00004047119,0.00073041517,0.18566447,0.16089745,0.04012628,0.57000124,0.0010663467],"about_ca_topic_score_codex":0.000045119326,"about_ca_topic_score_gemma":0.000007050309,"teacher_disagreement_score":0.9708057,"about_ca_system_score_codex":0.00011015242,"about_ca_system_score_gemma":0.00095440255,"threshold_uncertainty_score":0.86628014},"labels":[],"label_agreement":null},{"id":"W4409040302","doi":"10.1017/rsm.2024.9","title":"Key concepts and reporting recommendations for mapping reviews: A scoping review of 68 guidance and methodological studies","year":2025,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Rural development and sustainability","field":"Agricultural and Biological Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Campbell Scientific (Canada); Bruyère; University of Ottawa","funders":"","keywords":"Key (lock); Computer science; Management science; Data science; Engineering","score_opus":0.8011495550496224,"score_gpt":0.6703051375203792,"score_spread":0.13084441752924314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409040302","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032964494,0.99200386,0.0003594905,0.0025432461,0.00007088668,0.004762467,0.00002621497,0.000024172656,0.00020638066],"genre_scores_gemma":[1.3201061e-7,0.8082125,0.18931761,0.00005694709,0.00006178462,0.0020400856,0.000016739297,0.000001982909,0.00029216916],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97755325,0.017744398,0.0030559136,0.00085032167,0.00027921947,0.00051690894],"domain_scores_gemma":[0.883175,0.11316036,0.0023354408,0.0002393668,0.0009435135,0.00014629813],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.099723324,0.00035170693,0.0043322477,0.00009365447,0.0005300004,0.00005998045,0.0003666874,0.00020097304,0.00006925599],"category_scores_gemma":[0.33942124,0.00013050874,0.00048798227,0.0011060964,0.00041002297,0.00010390685,0.0006728115,0.00036786214,6.675046e-7],"study_design_candidate":"systematic_review","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":[0.0000018735772,0.0000086640775,0.000013150503,0.29756954,0.000046040237,8.3106454e-7,0.000028974391,7.566736e-10,0.00001583897,0.00007318254,0.0013396448,0.7009022],"study_design_scores_gemma":[0.000012679039,0.000024303381,0.000025289344,0.45535812,0.00010480928,0.000004850781,0.0002545372,6.141968e-7,0.000019742833,0.0008251573,0.5432196,0.0001502509],"about_ca_topic_score_codex":0.000016742644,"about_ca_topic_score_gemma":0.00000589623,"teacher_disagreement_score":0.700752,"about_ca_system_score_codex":0.000113589,"about_ca_system_score_gemma":0.00018499797,"threshold_uncertainty_score":0.9270243},"labels":[],"label_agreement":null},{"id":"W4409040342","doi":"10.1017/rsm.2024.8","title":"Prioritizing qualitative meta-synthesis findings in a mixed methods systematic review study: A description of the method","year":2025,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Health Policy Implementation Science","field":"Health Professions","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":"York University; University of Alberta","funders":"","keywords":"Computer science; Systematic review; Qualitative research; Meta-analysis; Management science; Multimethodology; Research methodology; MEDLINE; Mathematics education; Psychology; Medicine; Sociology; Chemistry; Social science; Engineering; Environmental health","score_opus":0.9420958320568493,"score_gpt":0.8419525791387364,"score_spread":0.10014325291811288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409040342","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000021456806,0.92447585,0.037383825,0.0016105064,0.00051952363,0.034683086,0.00026746487,0.0000679583,0.000989647],"genre_scores_gemma":[0.0000012610536,0.58907676,0.33275145,0.00033154484,0.00004095583,0.07682189,0.0000015510642,0.00007953658,0.0008950466],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.3553404,0.62961525,0.008549719,0.0015714722,0.002805049,0.0021181493],"domain_scores_gemma":[0.22224939,0.7663621,0.004561223,0.004104308,0.0021974978,0.00052551477],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58219254,0.0010492508,0.015127407,0.0037216425,0.0016770907,0.00008086616,0.003828947,0.00081797247,0.0005535441],"category_scores_gemma":[0.6853789,0.00062819215,0.0021814704,0.013797632,0.00045459293,0.00037707563,0.0020907975,0.0045725866,0.000077212506],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006738018,0.00010045605,0.0000023040752,0.79647696,0.0012018994,0.000002547795,0.013019502,5.0912288e-8,0.000011667273,0.00043529941,0.0007484063,0.18799415],"study_design_scores_gemma":[0.00017094474,0.000061387545,0.000021677979,0.85006064,0.01666686,0.0000052623927,0.033839744,0.000016228592,0.000050110128,0.0008954624,0.09768564,0.0005260135],"about_ca_topic_score_codex":0.0017397989,"about_ca_topic_score_gemma":0.00034533985,"teacher_disagreement_score":0.3353991,"about_ca_system_score_codex":0.0029894786,"about_ca_system_score_gemma":0.0095263,"threshold_uncertainty_score":0.9996226},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4409111062","doi":"10.1017/rsm.2025.11","title":"metaConvert: an automatic suite for estimation of 11 different effect size measures and flexible conversion across them","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Mental Health Research Topics","field":"Psychology","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":"Ottawa Hospital; University of Ottawa","funders":"Agence Nationale de la Recherche; National Institute for Health and Care Research","keywords":"Suite; Estimation; Computer science; Research methodology; Econometrics; Statistics; Mathematics; Geography; Systems engineering; Demography; Engineering; Sociology","score_opus":0.2722541542213411,"score_gpt":0.6149071688955015,"score_spread":0.34265301467416037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409111062","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":[0.93764484,0.00072029396,0.05586671,0.00080519676,0.0003435121,0.0029218963,0.000057596433,0.000101931095,0.0015380041],"genre_scores_gemma":[0.9251764,0.00008789434,0.0702511,0.000045360906,0.00004315272,0.0013568347,0.0000071907994,0.00003940463,0.0029926721],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9854285,0.011731839,0.0005305608,0.0005855743,0.0007687532,0.00095474947],"domain_scores_gemma":[0.95099145,0.047563966,0.000113538925,0.0007701668,0.00027445014,0.00028643233],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026246937,0.00022337274,0.0007055262,0.0003031282,0.00044340227,0.00008262975,0.00048455704,0.00023021719,0.00056285574],"category_scores_gemma":[0.014622001,0.0001724351,0.00013167154,0.000513816,0.00043948807,0.00015686719,0.00025702032,0.00036391718,0.000018289335],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007092269,0.0003150931,0.0074138986,0.00393391,0.00016811126,0.0000027589101,0.0011878904,0.000003621412,0.014714985,0.0048941374,0.0005908417,0.9660655],"study_design_scores_gemma":[0.0023446872,0.0012320457,0.0856691,0.0006596605,0.00013166762,0.0000071195677,0.0017037212,0.04629273,0.84905636,0.009586639,0.00300645,0.0003098168],"about_ca_topic_score_codex":0.00037690706,"about_ca_topic_score_gemma":0.000023420234,"teacher_disagreement_score":0.9657557,"about_ca_system_score_codex":0.0002183891,"about_ca_system_score_gemma":0.00012242555,"threshold_uncertainty_score":0.9936783},"labels":[],"label_agreement":null},{"id":"W4409815285","doi":"10.1017/rsm.2025.18","title":"An investigation of the impact of using contrast- and arm-synthesis models for network meta-analysis","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Diverse Approaches in Healthcare and Education Studies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"Health Research Council of New Zealand; Monash University","keywords":"Contrast (vision); Meta-analysis; Computer science; Artificial intelligence; Medicine; Internal medicine","score_opus":0.7330309420615649,"score_gpt":0.6219425931112957,"score_spread":0.1110883489502692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409815285","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":[0.85784286,0.0068824887,0.12897043,0.002763425,0.00008673812,0.0022425496,0.00011389616,0.00002302374,0.0010746131],"genre_scores_gemma":[0.8104235,0.00013856428,0.1890894,0.00002920789,0.00003540856,0.00021992614,0.000001271989,0.000009229541,0.000053474356],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995393,0.0031535157,0.00047467477,0.00029841752,0.00036347803,0.00031696336],"domain_scores_gemma":[0.983989,0.014072629,0.00019712755,0.0006625957,0.0009480808,0.00013054024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012625596,0.00013037818,0.001202166,0.00045894692,0.00024295371,0.00001847733,0.00018161103,0.00010105871,0.00004847707],"category_scores_gemma":[0.004803552,0.00007730307,0.0008105817,0.0017094826,0.00049505895,0.000097859855,0.00008950104,0.00015554078,6.976964e-8],"study_design_candidate":"meta_analysis","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":[0.0016137211,0.001059708,0.29017568,0.003453616,0.47331253,9.688147e-7,0.0071591786,0.051346555,0.028578307,0.019278156,0.0018093921,0.122212216],"study_design_scores_gemma":[0.00044988428,0.00037100827,0.11828213,0.0002837117,0.24317162,0.0000031924162,0.008394449,0.41300207,0.14917997,0.06649136,0.00005109856,0.0003194976],"about_ca_topic_score_codex":0.0016168635,"about_ca_topic_score_gemma":0.0000110003,"teacher_disagreement_score":0.36165553,"about_ca_system_score_codex":0.000104703984,"about_ca_system_score_gemma":0.00055895984,"threshold_uncertainty_score":0.5750647},"labels":[],"label_agreement":null},{"id":"W4409818715","doi":"10.1017/rsm.2025.20","title":"Same, same, but different: A method to harmonise and deduplicate study records from WHO ICTRP and ClinicalTrials.gov prior to screening","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Medical Coding and Health Information","field":"Health Professions","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 Victoria","funders":"","keywords":"Computer science; Medicine; Statistics; Mathematics","score_opus":0.6562454175277866,"score_gpt":0.683828765393392,"score_spread":0.027583347865605345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409818715","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5359193,0.00038957217,0.42616287,0.030247746,0.00037192032,0.005127255,0.00008207643,0.00014327244,0.0015559812],"genre_scores_gemma":[0.05497677,0.000854138,0.9298227,0.0058327974,0.00063217577,0.0033568703,0.000006015858,0.000062087754,0.004456478],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.966646,0.02817448,0.0018826518,0.0009803949,0.0009670879,0.0013493566],"domain_scores_gemma":[0.89937216,0.09737686,0.00026034407,0.00091614015,0.0004965247,0.0015779827],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065204255,0.00031600276,0.0013461071,0.00094474375,0.002287761,0.00012932146,0.0005006873,0.0004420383,0.00033281217],"category_scores_gemma":[0.085231274,0.00024936174,0.00008401966,0.00106945,0.00012163057,0.00014475778,0.0013099052,0.0020870604,0.000081541664],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013187437,0.00010271866,0.030508306,0.0005298037,0.00010786441,0.00000276111,0.0058981404,0.0000012675251,0.0010153765,0.00040039912,0.006111812,0.9540028],"study_design_scores_gemma":[0.004021019,0.0014485412,0.78557485,0.005692611,0.00030297358,0.000001254147,0.030399192,0.007852458,0.004181937,0.00731536,0.15238716,0.0008226307],"about_ca_topic_score_codex":0.006229592,"about_ca_topic_score_gemma":0.00040827415,"teacher_disagreement_score":0.9531802,"about_ca_system_score_codex":0.00023720087,"about_ca_system_score_gemma":0.00053733075,"threshold_uncertainty_score":0.9999959},"labels":[],"label_agreement":null},{"id":"W4411329051","doi":"10.1017/rsm.2025.25","title":"Methodology for mapping reviews, evidence maps, and gap maps","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bruyère; University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.9841751325838622,"score_gpt":0.8580608507643787,"score_spread":0.1261142818194836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411329051","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":[0.001108649,0.0074597807,0.8567607,0.11702925,0.000847899,0.007212765,0.00008647459,0.00011391974,0.009380584],"genre_scores_gemma":[0.0005178228,0.00649293,0.9707007,0.008366811,0.00025839842,0.006431466,0.0000019953852,0.000025893802,0.0072040283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9091291,0.08627363,0.0014877362,0.0008098642,0.0005228106,0.0017768608],"domain_scores_gemma":[0.6192711,0.37818322,0.00034436965,0.0009028671,0.0008530123,0.00044543258],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24312124,0.00019797357,0.0008503188,0.0010521354,0.0022242845,0.000042626274,0.00070974376,0.00026446028,0.00045061202],"category_scores_gemma":[0.42432672,0.00016704413,0.000098569464,0.0018085683,0.00043308365,0.00027618036,0.00061629066,0.0009798139,0.00014442444],"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":[0.00009979059,0.000016430657,0.0031972118,0.006298527,0.000035124078,0.000001331885,0.0044377814,2.5492793e-7,0.020141572,0.03682416,0.22016375,0.70878404],"study_design_scores_gemma":[0.00023777473,0.000046001533,0.002911296,0.0019860924,0.000018451523,0.0000012887921,0.0034154896,0.00011672576,0.0029548907,0.039212953,0.94895846,0.00014055647],"about_ca_topic_score_codex":0.00044060792,"about_ca_topic_score_gemma":0.00007423417,"teacher_disagreement_score":0.72879475,"about_ca_system_score_codex":0.00045330243,"about_ca_system_score_gemma":0.0017030494,"threshold_uncertainty_score":0.9990747},"labels":[],"label_agreement":null},{"id":"W4412173418","doi":"10.1017/rsm.2025.10021","title":"Regression augmented weighting adjustment for indirect comparisons in health decision modelling","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weighting; Computer science; Regression analysis; Econometrics; Statistics; Regression; Machine learning; Mathematics; Medicine","score_opus":0.6488356191652721,"score_gpt":0.6639908171596867,"score_spread":0.01515519799441456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412173418","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":[0.0030607465,0.0011936296,0.9917498,0.0007803959,0.00008686779,0.0016183542,0.000008743772,0.00021390969,0.0012875528],"genre_scores_gemma":[0.01869961,0.0006443611,0.9791272,0.0000341971,0.000033048917,0.0010748217,0.0000028608956,0.000039925893,0.00034396886],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99296534,0.0039780857,0.000940424,0.00059054204,0.00061601325,0.0009096197],"domain_scores_gemma":[0.93301773,0.06566726,0.00021752152,0.0006647255,0.00029050972,0.00014226834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02569179,0.00023019801,0.00078989926,0.001185554,0.0003763894,0.00004917974,0.00046741674,0.00017912353,0.000034158766],"category_scores_gemma":[0.025278693,0.00018798995,0.00011976324,0.0011242209,0.00009704023,0.0001416294,0.00029956998,0.00064542115,0.0000022411348],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002827421,0.000394168,0.00014525527,0.0008237957,0.000049296123,0.00000232522,0.00032854968,0.00068316015,0.004548033,0.08255699,0.006626704,0.90355897],"study_design_scores_gemma":[0.0002747535,0.000095785224,0.00005933554,0.0046778857,0.000010952646,6.9934754e-7,0.00049506524,0.20328973,0.15822382,0.62682295,0.0058766264,0.00017239373],"about_ca_topic_score_codex":0.00010353154,"about_ca_topic_score_gemma":0.00004372301,"teacher_disagreement_score":0.9033866,"about_ca_system_score_codex":0.000982528,"about_ca_system_score_gemma":0.00032284865,"threshold_uncertainty_score":0.9829318},"labels":[],"label_agreement":null},{"id":"W4412173579","doi":"10.1017/rsm.2025.10018","title":"Knowledge user involvement is still uncommon in published rapid reviews—a meta-research cross-sectional study","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Mental Health and Patient Involvement","field":"Health Professions","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":"Cochrane","funders":"","keywords":"Meta-analysis; Cross-sectional study; Computer science; Medicine; Pathology","score_opus":0.8388442732339678,"score_gpt":0.7061133124162564,"score_spread":0.1327309608177114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412173579","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":[0.75608623,0.046413347,0.001522813,0.0053137746,0.005701616,0.04507766,0.00026394404,0.0002848984,0.13933574],"genre_scores_gemma":[0.743047,0.008339087,0.038246967,0.004007471,0.0013795882,0.093499266,0.00021471032,0.00027126278,0.11099467],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.88034207,0.10844444,0.0033968976,0.0017249231,0.0029293967,0.0031622518],"domain_scores_gemma":[0.95112747,0.043557882,0.00030837426,0.0019979132,0.002262247,0.0007460993],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.24622197,0.0004726767,0.0015910735,0.0032758433,0.0026871061,0.00019860361,0.0015726356,0.00050159113,0.011211456],"category_scores_gemma":[0.0143904565,0.00035622722,0.00038589162,0.005280315,0.00039582778,0.0004712477,0.0019920685,0.0046632444,0.0011667236],"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":[0.0005777108,0.0041755997,0.88083535,0.0058742035,0.00064871815,0.000008657239,0.007430429,0.0000026959565,0.00024438262,0.0019401666,0.054016158,0.04424593],"study_design_scores_gemma":[0.0019870284,0.0007747577,0.28726584,0.0016255936,0.00012978466,2.1386535e-7,0.009116497,0.00029472855,0.0023039319,0.0045054466,0.69157463,0.00042155365],"about_ca_topic_score_codex":0.0057629948,"about_ca_topic_score_gemma":0.0030643528,"teacher_disagreement_score":0.63755846,"about_ca_system_score_codex":0.0030312908,"about_ca_system_score_gemma":0.0023060543,"threshold_uncertainty_score":0.99988896},"labels":[],"label_agreement":null},{"id":"W4413135087","doi":"10.1017/rsm.2025.10028","title":"Assessing risk of bias of cohort studies with large language models","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","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":"McMaster University","funders":"","keywords":"Cohort; Consistency (knowledge bases); Kappa; Confidence interval; Population; Cohort study; Medicine; Gold standard (test); Statistics; Demography; Psychology; Internal medicine; Environmental health; Computer science; Mathematics; Artificial intelligence","score_opus":0.6953569907842155,"score_gpt":0.6929927833746521,"score_spread":0.0023642074095634458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413135087","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":[0.9262246,0.0045474675,0.06261148,0.0007900948,0.000077902056,0.0004916782,0.0000070537876,0.000019799736,0.005229955],"genre_scores_gemma":[0.88310367,0.0015953025,0.114793986,0.000017298313,0.000044125583,0.00007414991,0.0000013176293,0.000011073529,0.0003590761],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99581265,0.0026818365,0.0004646299,0.0002302171,0.0004947395,0.00031592284],"domain_scores_gemma":[0.98258924,0.015439998,0.00014809858,0.00047917617,0.0012663489,0.00007715659],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018143,0.000087891945,0.00050894235,0.00047336976,0.00014050397,0.000013968599,0.00011196675,0.00008444303,0.000040684317],"category_scores_gemma":[0.024184322,0.00006042782,0.00007172048,0.0008968541,0.00028334535,0.00012060093,0.00006376002,0.0003224973,0.00000200694],"study_design_candidate":"bench_or_experimental","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":[0.00039792058,0.0005493408,0.18362916,0.0025794038,0.0015153354,0.000009448709,0.00874448,0.00014050941,0.018055702,0.003074845,0.00046876687,0.7808351],"study_design_scores_gemma":[0.000045350214,0.00016285799,0.013455408,0.0017192714,0.00032299777,0.000002037582,0.0679313,0.0053511695,0.9049255,0.0058476203,0.00016446115,0.000072019],"about_ca_topic_score_codex":0.0014179655,"about_ca_topic_score_gemma":0.000053886462,"teacher_disagreement_score":0.8868698,"about_ca_system_score_codex":0.00011022122,"about_ca_system_score_gemma":0.00061798684,"threshold_uncertainty_score":0.9840354},"labels":[],"label_agreement":null},{"id":"W4414132264","doi":"10.1017/rsm.2025.10031","title":"StudyTypeTeller—Large language models to automatically classify research study types for systematic reviews","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Universität Zürich; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Generative grammar; Transformer; Systematic review; Language model; Scientific literature; Encoder","score_opus":0.4744790487850936,"score_gpt":0.5983134327456537,"score_spread":0.12383438396056012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414132264","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":[0.0016391064,0.00168452,0.9781677,0.001845038,0.00016688273,0.011008892,0.0000034582504,0.00019599465,0.0052884086],"genre_scores_gemma":[0.11966454,0.000050900406,0.8674881,0.00011891447,0.00009359236,0.008151558,3.5942574e-7,0.000035066354,0.0043969806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96751285,0.026666153,0.0011854949,0.00127153,0.0018521876,0.0015117687],"domain_scores_gemma":[0.9570294,0.038427595,0.00009332129,0.0030310196,0.0011001194,0.00031856608],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12847896,0.00026767052,0.0011638756,0.0014902934,0.0007509533,0.00059467816,0.003614338,0.00014977934,0.000027872478],"category_scores_gemma":[0.050952,0.00020234191,0.00019979184,0.002938013,0.0000757496,0.00032794618,0.0020776808,0.0007182938,0.00017803068],"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":[0.00012188368,0.002832184,0.00007371175,0.043035973,0.00072458456,0.00006283352,0.033814143,0.00085998286,0.006832332,0.525389,0.012436674,0.3738167],"study_design_scores_gemma":[0.00040204366,0.00040752758,0.00007221654,0.0065354547,0.00005300429,0.0000021683416,0.0073735113,0.94985986,0.0031621412,0.02844194,0.0033161116,0.0003740476],"about_ca_topic_score_codex":0.00007092837,"about_ca_topic_score_gemma":0.00004687865,"teacher_disagreement_score":0.9489998,"about_ca_system_score_codex":0.00036529332,"about_ca_system_score_gemma":0.00044507472,"threshold_uncertainty_score":0.9570422},"labels":[],"label_agreement":null},{"id":"W4414926616","doi":"10.1017/rsm.2025.10041","title":"Making sense of conducting a critical interpretive synthesis: A scoping review","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Management and Organizational Studies","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Data extraction; Process (computing); Systematic review; Consolidation (business); Quality (philosophy); Best practice","score_opus":0.2885263093294941,"score_gpt":0.5377724213233885,"score_spread":0.24924611199389446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414926616","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":[0.0018708295,0.1019052,0.22426306,0.029729582,0.0011280563,0.0042330003,0.000012052144,0.0005143556,0.6363439],"genre_scores_gemma":[0.86034894,0.0052774604,0.12913394,0.0029892742,0.0007445157,0.0008237955,0.0000015093672,0.00009129827,0.0005892973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"systematic_review","domain_scores_codex":[0.9970878,0.00082376105,0.0005833855,0.0004415403,0.0005766962,0.00048683304],"domain_scores_gemma":[0.9692502,0.028884362,0.00020161128,0.00045049103,0.0011962461,0.000017094919],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011676489,0.00019128443,0.0006339822,0.00075939734,0.00046336182,0.00018085154,0.0003728016,0.00006368456,0.0012433539],"category_scores_gemma":[0.2157243,0.00017054693,0.00013730432,0.002031794,0.00034075452,0.00047323926,0.0010604162,0.00025534566,0.000055815508],"study_design_candidate":"systematic_review","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":[0.00018510818,0.00039109497,0.0032462347,0.19336009,0.00089463644,0.00008202675,0.00026517303,0.000011690456,0.0072080917,0.57996386,0.022129036,0.19226293],"study_design_scores_gemma":[0.00014462468,0.000019696588,0.0010615899,0.92929906,0.0010515165,0.0000050099584,0.0047260937,0.0028158117,0.024528032,0.02430657,0.011145099,0.0008968848],"about_ca_topic_score_codex":0.00007207659,"about_ca_topic_score_gemma":0.000013601423,"teacher_disagreement_score":0.85847807,"about_ca_system_score_codex":0.00007160661,"about_ca_system_score_gemma":0.00007989342,"threshold_uncertainty_score":0.9996697},"labels":[],"label_agreement":null},{"id":"W4415020931","doi":"10.1017/rsm.2025.10034","title":"Using large language models to directly screen electronic databases as an alternative to traditional search strategies such as the Cochrane highly sensitive search for filtering randomized controlled trials in systematic reviews","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; Hotel Dieu Hospital","funders":"","keywords":"Systematic review; Randomized controlled trial; MEDLINE; Keyword search; Cochrane collaboration; Electronic database; Filter (signal processing); Meta-analysis","score_opus":0.8796393867588007,"score_gpt":0.6853275020424803,"score_spread":0.19431188471632044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415020931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05166774,0.00634182,0.9002811,0.001846646,0.00011353544,0.035916977,0.00030073046,0.000014267023,0.00351719],"genre_scores_gemma":[0.7065411,0.0010791562,0.27041227,0.00059879746,0.0003669809,0.016921867,0.000047141846,0.000079692145,0.003952974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.33213425,0.6387397,0.015905479,0.0022101735,0.009270117,0.0017402862],"domain_scores_gemma":[0.1647188,0.82208824,0.002836174,0.0050224904,0.0047307657,0.00060350494],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8866688,0.00063308066,0.023147812,0.0033170474,0.0007141744,0.0025881096,0.0029589725,0.0001252539,0.0009043589],"category_scores_gemma":[0.68721163,0.00027361073,0.0040678214,0.004361481,0.00020683896,0.0007458497,0.00046915765,0.00068945525,0.00020774279],"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":[0.07920998,0.0009489641,0.000009048385,0.014294735,0.01089765,0.000093547555,0.028597346,0.02973774,0.08975711,0.7136908,0.002063225,0.030699855],"study_design_scores_gemma":[0.031638395,0.0003399039,0.0000149343,0.016513113,0.0023828587,0.000027979524,0.04782804,0.8070372,0.049676448,0.0429328,0.00078627,0.00082206086],"about_ca_topic_score_codex":0.0016446366,"about_ca_topic_score_gemma":0.00044229784,"teacher_disagreement_score":0.77729946,"about_ca_system_score_codex":0.00045718323,"about_ca_system_score_gemma":0.0013936382,"threshold_uncertainty_score":0.9999716},"labels":[],"label_agreement":null},{"id":"W4415167908","doi":"10.1017/rsm.2025.10040","title":"Data analysis and presentation methods in umbrella reviews/overviews of reviews in health care: A cross-sectional study","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Queen's University","funders":"","keywords":"Data extraction; Terminology; Systematic review; Presentation (obstetrics); Consistency (knowledge bases); Inclusion (mineral); MEDLINE; Descriptive statistics; Data collection; Research design","score_opus":0.944420581537522,"score_gpt":0.786600604477756,"score_spread":0.15781997705976591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415167908","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0158891,0.35556507,0.6108318,0.0010708262,0.00027869243,0.011396488,0.00012751855,0.00000739091,0.004833095],"genre_scores_gemma":[0.015018129,0.022677094,0.95814204,0.00011142701,0.000046362253,0.0010008746,0.000027816448,0.000019959076,0.0029562705],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.19171162,0.7591058,0.034900673,0.004796835,0.008377478,0.0011076106],"domain_scores_gemma":[0.75547963,0.20675199,0.011341302,0.022698412,0.0031803215,0.0005483269],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.83059394,0.00040092185,0.009288326,0.005925069,0.00023609473,0.000797902,0.0042386325,0.00015946756,0.0018264534],"category_scores_gemma":[0.46677807,0.0002289908,0.0013318224,0.022527004,0.00023664098,0.00046863526,0.0015277137,0.0006692173,0.00007290723],"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":[0.000023467961,0.00022024201,0.4667333,0.0010134949,0.0003507941,0.0000014189133,0.0009327504,0.00004304982,0.00013350263,0.00020388352,0.0024152189,0.5279289],"study_design_scores_gemma":[0.00028348857,0.0000651479,0.7732277,0.0004207336,0.00036947156,0.0000010565251,0.0017710611,0.00950266,0.00013187106,0.0020167474,0.2120087,0.0002013561],"about_ca_topic_score_codex":0.0019867243,"about_ca_topic_score_gemma":0.0035976674,"teacher_disagreement_score":0.563768,"about_ca_system_score_codex":0.00028110415,"about_ca_system_score_gemma":0.00042032584,"threshold_uncertainty_score":0.999086},"labels":[],"label_agreement":null},{"id":"W4415211633","doi":"10.1017/rsm.2025.10038","title":"Incorporating the possibility of cure into network meta-analyses: A case study from resected Stage III/IV melanoma","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","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":"MD Precision (Canada)","funders":"Bristol-Myers Squibb Foundation","keywords":"Metric (unit); Stage (stratigraphy); Multivariate analysis; Baseline (sea); Multivariate statistics; Survival analysis; Randomized controlled trial; Nomogram; Bayesian network; Clinical trial","score_opus":0.2411920970865163,"score_gpt":0.5541646686975652,"score_spread":0.3129725716110489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415211633","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":[0.9050394,0.004861627,0.08647854,0.00027899706,0.000021426104,0.00129754,0.000020231842,0.000040611274,0.0019615856],"genre_scores_gemma":[0.8674832,0.00007024173,0.13103698,0.000036326528,0.00009702352,0.00038805278,0.000017280723,0.000025756935,0.0008451528],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9783531,0.018703558,0.00090499996,0.00096024026,0.0006100961,0.00046800298],"domain_scores_gemma":[0.99076235,0.0052059544,0.00031659118,0.0026936103,0.00091756886,0.000103909006],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02602756,0.0002886279,0.0009921194,0.0002751461,0.0004943474,0.00012052055,0.0010207793,0.00022610156,0.00017139266],"category_scores_gemma":[0.011281233,0.00018560365,0.0006119006,0.0017781891,0.00047893284,0.000012052141,0.0012670957,0.0005584823,0.0000012704437],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033484344,0.00061764114,0.0068599987,0.00007430019,0.014942119,0.00028786875,0.00051339314,0.0001386962,0.9449691,0.00006097078,0.003034431,0.028166607],"study_design_scores_gemma":[0.00021808193,0.00025414184,0.00058304775,0.000023327482,0.0029867939,0.000007882206,0.006128204,0.0014977389,0.98378026,0.0026211757,0.0016867709,0.0002125507],"about_ca_topic_score_codex":0.018325653,"about_ca_topic_score_gemma":0.004831614,"teacher_disagreement_score":0.044558443,"about_ca_system_score_codex":0.00006661092,"about_ca_system_score_gemma":0.00033486212,"threshold_uncertainty_score":0.9970472},"labels":[],"label_agreement":null},{"id":"W4415242003","doi":"10.1017/rsm.2025.10039","title":"Estimands and their implications for evidence synthesis for oncology: A simulation study of treatment switching in meta-analysis","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of British Columbia","funders":"","keywords":"Pooling; Estimator; Censoring (clinical trials); Average treatment effect; Treatment effect; Randomized controlled trial; Random effects model; Clinical trial","score_opus":0.9585664962779277,"score_gpt":0.7594752801360958,"score_spread":0.1990912161418319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415242003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.062537655,0.003385545,0.92412233,0.0038082239,0.000022869186,0.0057422933,0.00006158673,0.000005543144,0.00031392832],"genre_scores_gemma":[0.78535366,0.000055816807,0.2065848,0.000013895144,0.00001088252,0.007499357,8.314438e-7,0.000009811327,0.00047094596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.91904044,0.06995813,0.007331286,0.0018277213,0.0013270772,0.000515356],"domain_scores_gemma":[0.27079996,0.71833557,0.002304967,0.0054673185,0.0029331492,0.0001590507],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3762189,0.00031971402,0.0074167913,0.0033437384,0.00040702848,0.0004069198,0.0016744602,0.0001305095,0.00028131148],"category_scores_gemma":[0.482777,0.0001473906,0.0035383974,0.005587201,0.000088285306,0.00022624609,0.0002552284,0.00012557357,0.0000035409892],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021430173,0.0012508993,0.016330618,0.00022388923,0.09020017,2.9813458e-7,0.003164336,0.018781269,0.0026071558,0.001679506,0.00027742886,0.86527014],"study_design_scores_gemma":[0.00039378868,0.0008634718,0.02047495,0.0000556599,0.13988203,5.477185e-7,0.008511797,0.7707188,0.0023463448,0.05104703,0.0054305475,0.00027500812],"about_ca_topic_score_codex":0.00020389046,"about_ca_topic_score_gemma":0.0006027196,"teacher_disagreement_score":0.8649951,"about_ca_system_score_codex":0.00028461986,"about_ca_system_score_gemma":0.00029713608,"threshold_uncertainty_score":0.64231396},"labels":[],"label_agreement":null},{"id":"W4415779881","doi":"10.1017/rsm.2025.10029","title":"How to conduct an individual participant data meta-analysis in response to an emerging pathogen: Lessons learned from Zika and COVID-19","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia; Jewish General Hospital","funders":"H2020 Health; Institute of Genetics","keywords":"Pooling; Spurious relationship; Missing data; Data collection; Key (lock); Zika virus","score_opus":0.9891121810702769,"score_gpt":0.7652660671837509,"score_spread":0.22384611388652598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415779881","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":[0.21502143,0.008479883,0.5388343,0.23113477,0.00011670906,0.003252369,0.002821891,0.000036969446,0.00030167014],"genre_scores_gemma":[0.44717687,0.000076860284,0.54504883,0.0017428601,0.000059980637,0.00087308994,0.00007751974,0.00003954246,0.004904427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5449413,0.43193218,0.006810533,0.0053542396,0.009586383,0.0013753533],"domain_scores_gemma":[0.625073,0.3329379,0.0022724916,0.032922197,0.0024510599,0.004343331],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.72485006,0.00054081966,0.00882597,0.0065745055,0.00063701376,0.0049269632,0.0080913585,0.00021560445,0.005652621],"category_scores_gemma":[0.70871896,0.00030397068,0.0016489208,0.015482904,0.00022833717,0.00097244105,0.002984157,0.000584698,0.00015464786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012909976,0.0008216056,0.0053996635,0.00015082343,0.1562748,0.0002184249,0.020662852,0.0038320883,0.08588188,0.0029563971,0.025754623,0.6967558],"study_design_scores_gemma":[0.0005008198,0.00032532535,0.026160916,0.00004966528,0.20127654,0.000004596032,0.067664735,0.06499272,0.003960058,0.026673237,0.607023,0.0013683783],"about_ca_topic_score_codex":0.0011362764,"about_ca_topic_score_gemma":0.0036756443,"teacher_disagreement_score":0.6953875,"about_ca_system_score_codex":0.00010612164,"about_ca_system_score_gemma":0.00089654286,"threshold_uncertainty_score":0.99994123},"labels":[],"label_agreement":null},{"id":"W4416300709","doi":"10.1017/rsm.2025.10056","title":"Impact of matrix-construction assumptions on quantitative overlap assessment in overviews: A meta-research study","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; MD Precision (Canada); St. Michael's Hospital","funders":"Universitat Autònoma de Barcelona","keywords":"Pairwise comparison; Metric (unit); Guideline; Selection (genetic algorithm); Evaluation methods; Matrix (chemical analysis); Sample size determination","score_opus":0.9545881302189179,"score_gpt":0.801307371359501,"score_spread":0.15328075885941683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416300709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","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":[0.84449065,0.003722596,0.095983,0.0015582332,0.00031233756,0.007704651,0.00011086845,0.000014926375,0.04610274],"genre_scores_gemma":[0.74800473,0.00016240859,0.24706304,0.000007711708,0.000024765584,0.0013610852,0.0000014841381,0.000020319965,0.0033544765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.4272873,0.5339258,0.01299905,0.002695001,0.021786312,0.0013065467],"domain_scores_gemma":[0.5640324,0.41302106,0.0032577226,0.0098192105,0.009468284,0.00040137567],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7209196,0.00041607354,0.0063331085,0.008097918,0.00044864655,0.0009305388,0.0029057418,0.00017304593,0.011261972],"category_scores_gemma":[0.37246186,0.00020078383,0.0037305504,0.014543312,0.0004411569,0.0003779705,0.00061396667,0.0014053304,0.00053913414],"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":[0.0003597545,0.006517672,0.35869962,0.00048450427,0.021002585,0.00003377133,0.0029524416,0.0026666676,0.0067986,0.21626484,0.017685398,0.36653414],"study_design_scores_gemma":[0.0006538141,0.0014670033,0.84506106,0.00039023318,0.0017512109,0.000003901518,0.036703527,0.022865634,0.001065907,0.08386542,0.005752643,0.0004196192],"about_ca_topic_score_codex":0.000935139,"about_ca_topic_score_gemma":0.00020019742,"teacher_disagreement_score":0.48636147,"about_ca_system_score_codex":0.00073065667,"about_ca_system_score_gemma":0.0010619682,"threshold_uncertainty_score":0.98964185},"labels":[],"label_agreement":null},{"id":"W7101419411","doi":"10.1017/rsm.2025.10032","title":"Exploring the methodological quality and risk of bias in 200 systematic reviews: A comparative study of ROBIS and AMSTAR-2 tools","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University; Public Health Agency of Canada; Nova Scotia Health Authority; St. Michael's Hospital; University of Ottawa; Queen's University; McMaster University; University of Toronto; University of British Columbia","funders":"","keywords":"Rigour; Quality (philosophy); Systematic review; Sample (material); Systematic error; Critical appraisal; Meta-analysis; Publication bias","score_opus":0.9957225701194713,"score_gpt":0.7796026000981889,"score_spread":0.21611997002128236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7101419411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94831395,0.012931665,0.032032,0.00020256745,0.00004675852,0.0053942767,0.000010415202,0.0000023649848,0.0010660234],"genre_scores_gemma":[0.8447992,0.0043374356,0.14870112,0.000011222235,0.000011348391,0.0017443236,1.6789143e-7,0.0000068520685,0.00038831358],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.20790268,0.77238834,0.013724025,0.0011697467,0.004419682,0.00039553086],"domain_scores_gemma":[0.15143265,0.83607346,0.0056793415,0.004780695,0.0018788956,0.00015493577],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8446142,0.00027721983,0.009755316,0.0010564964,0.00021575218,0.0003614849,0.0015749456,0.00006827503,0.00020747297],"category_scores_gemma":[0.79580903,0.00010366801,0.0006964266,0.0042420966,0.00041268772,0.0002615943,0.00064099487,0.0004748945,0.000012933362],"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":[0.00037527553,0.0018309647,0.2974161,0.050514303,0.0049555446,0.000008900789,0.05583151,0.00027557835,0.003092816,0.010849186,0.0016268287,0.573223],"study_design_scores_gemma":[0.0007317233,0.0005174943,0.6839071,0.011294249,0.002100907,0.0000055291016,0.2618609,0.009144755,0.004127986,0.023837699,0.001984195,0.0004874683],"about_ca_topic_score_codex":0.00043191554,"about_ca_topic_score_gemma":0.00019581124,"teacher_disagreement_score":0.57273555,"about_ca_system_score_codex":0.000041382016,"about_ca_system_score_gemma":0.000063956664,"threshold_uncertainty_score":0.6668539},"labels":[],"label_agreement":null}]}