{"meta":{"query_hash":"8953a914060a","filters":{"venue":"Data Intelligence"},"cohort_total":12,"direct_labels_cover":0,"predictions_cover":12,"exported":12,"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/8953a914060a","api":"https://metacan.xera.ac/api/v1/cohort?venue=Data+Intelligence"},"results":[{"id":"W2985716559","doi":"10.1162/dint_a_00039","title":"The FAIR Funding Model: Providing a Framework for Research Funders to Drive the Transition toward FAIR Data Management and Stewardship Practices","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":42,"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":"Canadian Institutes of Health Research; Stroke Association","keywords":"RDM; Stewardship (theology); Metadata; Business; Work (physics); Process management; Knowledge management; Data curation; Public relations; Computer science; Political science; Data science; Engineering; World Wide Web","score_opus":0.6366391164030468,"score_gpt":0.5222957442909713,"score_spread":0.11434337211207557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985716559","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":[0.00039357838,0.00033600567,0.9507126,0.043727905,0.00026572085,0.0034771366,0.00028498686,0.0000856823,0.00071636186],"genre_scores_gemma":[0.5451079,0.005273304,0.44648516,0.0011226445,0.0001846525,0.0005004188,0.000525199,0.000047245776,0.0007534878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99460185,0.0005481746,0.0004079823,0.0018939835,0.0015640135,0.0009840013],"domain_scores_gemma":[0.98393726,0.0065201907,0.00031401467,0.00881659,0.00021867122,0.00019325435],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.017918153,0.00022199012,0.00017316865,0.00023851081,0.0011227732,0.008857303,0.021231635,0.00006908304,0.000005284168],"category_scores_gemma":[0.0045526605,0.00014622358,0.00002717739,0.0011278937,0.00021708255,0.029803919,0.0165792,0.0007369742,0.00009459711],"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":[0.00014670605,0.000057583395,0.000049874478,0.0003140494,0.00014849906,0.000009037091,0.002330796,0.0016372175,0.00003175993,0.90573597,0.008088593,0.08144993],"study_design_scores_gemma":[0.0000776429,0.00018738199,0.000045853347,0.00016927744,0.000031923813,0.000004542175,0.015161569,0.8042773,0.00012480108,0.050370302,0.12931027,0.00023912014],"about_ca_topic_score_codex":0.00016698524,"about_ca_topic_score_gemma":0.0001573083,"teacher_disagreement_score":0.85536563,"about_ca_system_score_codex":0.00010356493,"about_ca_system_score_gemma":0.0001357348,"threshold_uncertainty_score":0.9921716},"labels":[],"label_agreement":null},{"id":"W2987816848","doi":"10.1162/dint_a_00051","title":"Considerations for the Conduction and Interpretation of FAIRness Evaluations","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institutes of Health; Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Metadata; Interpretation (philosophy); Computer science; Maturity (psychological); Software; Psychology; World Wide Web","score_opus":0.33447316204815425,"score_gpt":0.4639573840777451,"score_spread":0.12948422202959087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987816848","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":[0.0010174337,0.00014328309,0.9947752,0.002787072,0.00022838202,0.00066217367,0.00011158417,0.000016458764,0.00025842813],"genre_scores_gemma":[0.96323615,0.00030519976,0.036046103,0.00010266569,0.00001356748,0.000043689142,0.00010868552,0.0000028323173,0.00014108312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913186,0.000082196406,0.00018261738,0.00030189028,0.00021317834,0.00008828349],"domain_scores_gemma":[0.9957891,0.0024311407,0.00011418007,0.0014552647,0.00019138161,0.00001891971],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014942255,0.000048631526,0.0000630218,0.00006423175,0.00010185157,0.0006657765,0.0012974007,0.00001461041,0.000033125216],"category_scores_gemma":[0.0024741131,0.000036070654,0.000010298526,0.00017056483,0.000076356824,0.015039984,0.0007868434,0.000060138605,0.000020209847],"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":[0.0000074523496,0.000023040722,0.00015110162,0.000042871863,0.000036621917,1.5236114e-7,0.00038857336,0.0010454232,0.00063246884,0.9252445,0.0012556877,0.07117212],"study_design_scores_gemma":[0.000046345303,0.000051111747,0.00036073988,0.000014230393,0.000015720694,0.0000035723606,0.0004270641,0.9732703,0.0016797932,0.018877055,0.00520323,0.000050851406],"about_ca_topic_score_codex":0.000059707836,"about_ca_topic_score_gemma":0.000039584775,"teacher_disagreement_score":0.97222483,"about_ca_system_score_codex":0.00000840621,"about_ca_system_score_gemma":0.00005703436,"threshold_uncertainty_score":0.99873614},"labels":[],"label_agreement":null},{"id":"W2988604061","doi":"10.1162/dint_a_00029","title":"Ontology-based Access Control for FAIR Data","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Metadata; Computer science; Ontology; Access control; Data access; Metadata repository; Database; World Wide Web; Information retrieval; Computer security","score_opus":0.5944593014190421,"score_gpt":0.5293744523263445,"score_spread":0.06508484909269763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2988604061","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":[0.0017302695,0.00008323089,0.9822123,0.0019096318,0.0029431677,0.0007439051,0.008568696,0.00007782882,0.0017309373],"genre_scores_gemma":[0.9691374,0.0000053679064,0.018360507,0.0027514293,0.00018156697,0.000019447803,0.006961357,0.000016304417,0.0025666205],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955063,0.0001264602,0.0007087005,0.0022206542,0.001034978,0.00040289154],"domain_scores_gemma":[0.9816203,0.0037027302,0.0002810382,0.014029421,0.00025475476,0.00011172985],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010041349,0.00016012673,0.00030698685,0.00023741627,0.0001572851,0.0012959844,0.02443566,0.000054290016,0.001173045],"category_scores_gemma":[0.008245149,0.00011990089,0.000045957066,0.00071296137,0.00013097048,0.0017478721,0.0055401027,0.00011124904,0.0030595106],"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":[0.000086617394,0.00009426459,0.007199517,0.000018141749,0.000024883464,0.0000037501172,0.00002643152,0.0022969665,0.000020716438,0.0041192006,0.6875322,0.2985773],"study_design_scores_gemma":[0.00014777927,0.000029373969,0.000702539,0.000011295726,0.000012011133,8.585429e-7,0.00010481614,0.52102166,0.0000597101,0.0036712904,0.47412145,0.0001171986],"about_ca_topic_score_codex":0.0001399566,"about_ca_topic_score_gemma":0.00024211004,"teacher_disagreement_score":0.9674071,"about_ca_system_score_codex":0.000018123794,"about_ca_system_score_gemma":0.0001356654,"threshold_uncertainty_score":0.9997408},"labels":[],"label_agreement":null},{"id":"W2988998130","doi":"10.1162/dint_r_00024","title":"FAIR Principles: Interpretations and Implementation Considerations","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":459,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Biotechnology and Biological Sciences Research Council; European Regional Development Fund; Horizon 2020 Framework Programme; Innovative Medicines Initiative; National Institutes of Health; National Science Foundation; Ministerio de Economía y Competitividad; Common Fund; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; European Commission; Universidad Politécnica de Madrid","keywords":"Implementation; Interoperability; Computer science; Reusability; USable; Fair use; Reuse; Stakeholder; Convergence (economics); Risk analysis (engineering); Data science; Management science; Software engineering; World Wide Web; Business; Engineering; Political science; Public relations; Software; Law; Economics","score_opus":0.21350192087230005,"score_gpt":0.4376810240360997,"score_spread":0.22417910316379966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2988998130","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":[0.003090768,0.000079462334,0.98982865,0.0025837768,0.00016313975,0.00047975365,0.00016155063,0.000082117745,0.0035307957],"genre_scores_gemma":[0.8926328,0.00056866603,0.105216146,0.0005619911,0.000019019963,0.000030340752,0.0005144855,0.000006780319,0.00044980427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860185,0.000091630696,0.00024886036,0.00059089554,0.00027385468,0.00019289063],"domain_scores_gemma":[0.9972207,0.0004851563,0.00009904593,0.0020539754,0.00007327079,0.00006787247],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007842351,0.00008590251,0.00007872999,0.00012838349,0.000115220006,0.0020644881,0.0019493181,0.000017599325,0.00022917149],"category_scores_gemma":[0.0004908955,0.00008303223,0.000009426699,0.0002384644,0.00004974555,0.030370997,0.0029551708,0.00011368812,0.00036095397],"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":[0.0000012159177,0.000019425685,0.0022990727,0.00002128371,0.00002152211,0.000004526263,0.00039042687,0.000056094294,0.000113901646,0.9754397,0.0012234729,0.02040932],"study_design_scores_gemma":[0.00029498345,0.00028838418,0.014244454,0.000080832906,0.000033946668,0.00006811807,0.00421137,0.5950091,0.0035040197,0.02948134,0.3520832,0.00070023973],"about_ca_topic_score_codex":0.00013001397,"about_ca_topic_score_gemma":0.0002163334,"teacher_disagreement_score":0.9459584,"about_ca_system_score_codex":0.000020223357,"about_ca_system_score_gemma":0.00007753687,"threshold_uncertainty_score":0.99897146},"labels":[],"label_agreement":null},{"id":"W3017715546","doi":"10.1162/dint_a_00058","title":"The Semantic Data Dictionary – An Approach for Describing and Annotating Data","year":2020,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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":"CARE Canada; Privacy Analytics (Canada)","funders":"National Institute of Environmental Health Sciences","keywords":"Computer science; Natural language processing; Data dictionary; Information retrieval; Artificial intelligence; World Wide Web; Metadata","score_opus":0.3725294609797752,"score_gpt":0.37406425153345557,"score_spread":0.0015347905536803874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017715546","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":[0.0058208914,0.0043100575,0.98394203,0.0013063115,0.00011284833,0.00021443516,0.004183926,0.000035958274,0.00007356018],"genre_scores_gemma":[0.65665245,0.0023028147,0.2389399,0.0013574234,0.0009804609,0.000019980554,0.09966188,0.000036315978,0.00004877497],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998675,0.000047474197,0.00018150637,0.00080767274,0.000098048804,0.0001903007],"domain_scores_gemma":[0.9974102,0.00010491946,0.000056730805,0.0023091994,0.000028120661,0.00009083242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006288765,0.00010036101,0.000089900495,0.0000069898406,0.00025596892,0.000088801695,0.0029433132,0.00007203253,0.0000014904438],"category_scores_gemma":[0.001786921,0.00007213671,0.000007798151,0.00006580591,0.00023961035,0.000028468263,0.0035650835,0.00009581059,0.0000015844013],"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":[0.00011688119,0.000056742036,0.0010786,0.00008757353,0.00008999468,0.000003050153,0.00019230202,0.000028389817,0.009267421,0.00016071499,0.043468248,0.94545007],"study_design_scores_gemma":[0.00009489647,0.00022536171,0.00014932088,0.000017167442,0.000041845065,0.00002564718,0.0022873913,0.7125035,0.001492657,0.000072740906,0.2828795,0.0002099846],"about_ca_topic_score_codex":0.000024568479,"about_ca_topic_score_gemma":0.000017745584,"teacher_disagreement_score":0.9452401,"about_ca_system_score_codex":0.0000015211549,"about_ca_system_score_gemma":0.000043506658,"threshold_uncertainty_score":0.5469457},"labels":[],"label_agreement":null},{"id":"W3128327914","doi":"10.1162/dint_a_00086","title":"Implementation of an Open Science Instruction Program for Undergraduates","year":2021,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Transparency (behavior); Curriculum; Context (archaeology); Best practice; Political science; Undergraduate research; Subject (documents); Medical education; Public relations; Engineering ethics; Pedagogy; Engineering; Library science; Sociology; Computer science; Medicine; Geography","score_opus":0.4297001939532424,"score_gpt":0.566531096562857,"score_spread":0.13683090260961467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128327914","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":[0.37378177,0.000052692594,0.6177576,0.0013240533,0.0026425386,0.0016720003,0.0014860402,0.000087447654,0.0011958638],"genre_scores_gemma":[0.82593817,0.000009141147,0.17261797,0.00007262376,0.000044217268,0.000029478551,0.0010944544,0.000005420278,0.00018851018],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682707,0.00007595629,0.00060045643,0.0012162398,0.0010554952,0.00022479593],"domain_scores_gemma":[0.99533576,0.0003121794,0.0002644254,0.003165444,0.0008366208,0.000085597574],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00800633,0.00007853307,0.00014346335,0.00020315766,0.0003043875,0.0017961283,0.0077621276,0.000015515741,0.00018225613],"category_scores_gemma":[0.002926831,0.00006535561,0.000019517964,0.002180117,0.00029232536,0.0027092467,0.004877346,0.000039132963,0.000030234747],"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":[0.0000065860477,0.00008754764,0.0004699044,0.0000049429204,0.0000041591243,7.377477e-7,0.00010852293,0.00008088726,0.00055247423,0.013361197,0.0033565143,0.98196656],"study_design_scores_gemma":[0.00053411815,0.0006954909,0.0144879185,0.000052615782,0.00004564849,0.000028518854,0.038136065,0.2675488,0.23810455,0.21968567,0.22019392,0.00048667428],"about_ca_topic_score_codex":0.0003642582,"about_ca_topic_score_gemma":0.0008492616,"teacher_disagreement_score":0.9814798,"about_ca_system_score_codex":0.000026693133,"about_ca_system_score_gemma":0.00037516328,"threshold_uncertainty_score":0.9992401},"labels":[],"label_agreement":null},{"id":"W4312713146","doi":"10.1162/dint_x_00187","title":"About The Author","year":2022,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.15165752942592567,"score_gpt":0.42420798732970744,"score_spread":0.27255045790378174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312713146","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":[0.07775372,0.011810307,0.06315175,0.27827868,0.012965643,0.0025656314,0.0030208176,0.0014743026,0.54897916],"genre_scores_gemma":[0.9687074,0.00043874574,0.0036910265,0.002312992,0.0011289265,0.00004778073,0.0005663466,0.000018787217,0.02308803],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885833,0.0002820373,0.00010523581,0.00019126493,0.00036837626,0.00019475911],"domain_scores_gemma":[0.9991383,0.00019061066,0.00004510198,0.00055311644,0.000020976391,0.00005191869],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015737157,0.00004118665,0.000045447712,0.000021012695,0.001533936,0.000070433416,0.0018889332,0.000014467848,0.0032359348],"category_scores_gemma":[0.00060135213,0.00003140588,0.000017023709,0.00033887263,0.00014244037,0.00017327005,0.0007434152,0.00029241774,0.00020959826],"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":[0.000007914538,0.000045043173,0.0009678985,0.0000024493354,0.000010107297,0.000009833828,0.010034175,0.00021210105,0.0000101289925,0.1549231,0.07502278,0.7587545],"study_design_scores_gemma":[0.000005525534,0.000013901251,0.000026276091,0.0000015492495,0.0000034382012,0.000001081489,0.032274075,0.0008010985,0.000010774496,0.0012996519,0.9655135,0.00004910568],"about_ca_topic_score_codex":0.00074265094,"about_ca_topic_score_gemma":0.00039808685,"teacher_disagreement_score":0.89095366,"about_ca_system_score_codex":0.000029350245,"about_ca_system_score_gemma":0.00032269125,"threshold_uncertainty_score":0.99976593},"labels":[],"label_agreement":null},{"id":"W4380629788","doi":"10.1162/dint_a_00209","title":"MillenniumDB: An Open-Source Graph Database System","year":2023,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":5,"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":"Agencia Nacional de Investigación y Desarrollo; Pontificia Universidad Católica de Chile; Universidad de Chile; University of Waterloo; University of Toronto; University of Galway; National University of Ireland; Universidad Técnica Federico Santa María","keywords":"Computer science; Graph database; Query language; Query optimization; Graph; Search engine indexing; Information retrieval; Theoretical computer science; Joins; Database; Programming language","score_opus":0.103571274253965,"score_gpt":0.32994977076281207,"score_spread":0.22637849650884706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380629788","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":[0.0023258745,0.00015154455,0.99370176,0.00016517208,0.00082739064,0.00029537847,0.0006439297,0.0010335351,0.0008554342],"genre_scores_gemma":[0.8434447,0.0006604272,0.14642061,0.0012485444,0.00047475728,0.00013951582,0.0060680583,0.000110115114,0.0014332948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974902,0.00021183345,0.0003376935,0.0011406615,0.00034525292,0.00047435507],"domain_scores_gemma":[0.99405813,0.0001832105,0.00009789443,0.0053562685,0.0000672674,0.00023720384],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018745757,0.00020598536,0.00020932937,0.00023751639,0.0003381568,0.0006767775,0.015548903,0.00005682358,0.000029095774],"category_scores_gemma":[0.000093473325,0.00018790714,0.000029571125,0.0019270355,0.00010985974,0.0034880564,0.0074321222,0.00020003316,0.0016500602],"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":[0.000019253413,0.00017144288,0.00010017327,0.00011108276,0.000044486802,0.00030816413,0.0010627699,0.0005354655,0.0009888925,0.7422851,0.01861267,0.23576051],"study_design_scores_gemma":[0.00017160825,0.0002415073,0.00018279193,0.00025094204,0.000020451116,0.00016122393,0.0024117213,0.8856417,0.007564248,0.013787294,0.088663764,0.00090274285],"about_ca_topic_score_codex":0.00019416765,"about_ca_topic_score_gemma":0.000025403519,"teacher_disagreement_score":0.88510627,"about_ca_system_score_codex":0.000015331658,"about_ca_system_score_gemma":0.00005207317,"threshold_uncertainty_score":0.99912727},"labels":[],"label_agreement":null},{"id":"W4390025222","doi":"10.1162/dint_a_00240","title":"BIKAS: Bio-Inspired Knowledge Acquisition and Simulacrum—A Knowledge Database to Support Multifunctional Design Concept Generation","year":2023,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Design Education and Practice","field":"Engineering","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Simulacrum; Computer science; Knowledge acquisition; Knowledge management; Artificial intelligence","score_opus":0.20127910444684868,"score_gpt":0.3756119567879984,"score_spread":0.17433285234114973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390025222","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":[0.004702853,0.00068789435,0.9886681,0.00023873712,0.002476477,0.00054946885,0.0011180794,0.00066191825,0.00089648913],"genre_scores_gemma":[0.9663575,0.0006595974,0.016222898,0.00037145277,0.0010265505,0.00011105272,0.013698835,0.00007553224,0.0014765632],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986792,0.00011352517,0.00031227717,0.00047679665,0.00014662072,0.0002715675],"domain_scores_gemma":[0.9984293,0.0004761004,0.000036170044,0.00073700084,0.0001247289,0.00019668975],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079182774,0.00019224684,0.00013891437,0.00024570606,0.00014840896,0.00013526721,0.00039376027,0.00007711719,0.00067023904],"category_scores_gemma":[0.00034945685,0.00020944644,0.00001722395,0.00076237065,0.00004825576,0.00095951895,0.00020371308,0.0001407047,0.005074508],"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":[0.000045965568,0.0001657273,0.00008901494,0.00010521928,0.00007011827,0.000012369104,0.0034518817,0.03906659,0.034092315,0.0010329608,0.676435,0.24543284],"study_design_scores_gemma":[0.00010806896,0.000076996126,0.00026816485,0.000029614923,0.000029916697,0.00001202073,0.00035674343,0.73406994,0.022032414,0.00003667229,0.24266653,0.0003129389],"about_ca_topic_score_codex":0.000014652933,"about_ca_topic_score_gemma":0.000028938775,"teacher_disagreement_score":0.9724452,"about_ca_system_score_codex":0.00006204692,"about_ca_system_score_gemma":0.00009950766,"threshold_uncertainty_score":0.9957002},"labels":[],"label_agreement":null},{"id":"W4394770144","doi":"10.1162/dint_a_00251","title":"LLaMA-LoRA Neural Prompt Engineering: A Deep Tuning Framework for Automatically Generating Chinese Text Logical Reasoning Thinking Chains","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Language model; Artificial intelligence; Natural language processing; Comprehension; Benchmark (surveying); Inference; Logical reasoning; Question answering; Programming language","score_opus":0.05625293307651095,"score_gpt":0.3232568566701648,"score_spread":0.2670039235936538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394770144","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":[0.007559526,0.00094790244,0.9880491,0.0008340873,0.0010956984,0.00037533286,0.00002087379,0.0010718767,0.00004562119],"genre_scores_gemma":[0.36811766,0.0000103069615,0.6310749,0.00021679969,0.0004560454,0.000040286188,0.00004478011,0.000024916915,0.000014287148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971735,0.000049413913,0.0005659973,0.0011516209,0.00043981188,0.0006196663],"domain_scores_gemma":[0.99707747,0.0009889175,0.00008214969,0.0016183696,0.00007446998,0.00015863359],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011060471,0.00031766793,0.0002914296,0.00014313609,0.00025975742,0.00139777,0.0033772571,0.00015475458,0.00002633889],"category_scores_gemma":[0.0025020773,0.00026598747,0.00008478696,0.0006251409,0.00003783749,0.0011619304,0.0017426092,0.0006127355,0.000033859822],"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":[0.000004448858,0.000031395426,0.00010036343,0.0002606503,0.00004426127,0.00010544482,0.0039399257,0.10159823,0.0006395959,0.672863,0.000064691936,0.220348],"study_design_scores_gemma":[0.000023442886,0.0000465099,0.000037527003,0.00044670174,0.000010001953,0.0000722141,0.000049892733,0.98398834,0.000109716326,0.014490521,0.0004102202,0.0003149078],"about_ca_topic_score_codex":0.000016096907,"about_ca_topic_score_gemma":0.0000059484655,"teacher_disagreement_score":0.8823901,"about_ca_system_score_codex":0.00006460859,"about_ca_system_score_gemma":0.00008712547,"threshold_uncertainty_score":0.99997926},"labels":[],"label_agreement":null},{"id":"W4400522920","doi":"10.1162/dint_a_00255","title":"FAIR Enough: Develop and Assess a FAIR-Compliant Dataset for Large Language Model Training?","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Toronto Metropolitan University; Vector Institute","funders":"Government of Canada; Canadian Institute for Advanced Research","keywords":"Stewardship (theology); Computer science; Context (archaeology); Interoperability; Frame (networking); Process (computing); Work (physics); Engineering ethics; Knowledge management; Process management; Accreditation; Checklist; Data science; Risk analysis (engineering); Political science; Business; Engineering; Psychology; World Wide Web; Medical education; Medicine","score_opus":0.39620062148958934,"score_gpt":0.46542847373583285,"score_spread":0.0692278522462435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400522920","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":[0.00013058214,0.00085048657,0.9582657,0.00201164,0.00018102548,0.0004458553,0.03762138,0.00016868074,0.00032465695],"genre_scores_gemma":[0.15715496,0.0018809257,0.7866951,0.001313735,0.00017561585,0.00019885034,0.0514195,0.000055799326,0.001105479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972439,0.000079754405,0.00031797012,0.0013065676,0.00046006797,0.0005917808],"domain_scores_gemma":[0.9961771,0.0007432081,0.00006632492,0.0027937284,0.000065572465,0.00015407467],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0026981898,0.00020528291,0.00018787853,0.00015627421,0.00018013797,0.0041485736,0.0064097685,0.000049338003,0.000019931993],"category_scores_gemma":[0.0012247408,0.00018221664,0.000019786903,0.0006260299,0.00006392137,0.02551872,0.0055686366,0.00026309505,0.000108036045],"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":[0.000014692888,0.00008869802,0.000010899658,0.0004503621,0.00010625523,0.00022612225,0.0024278483,0.00009579117,0.00024285672,0.7147921,0.11457271,0.16697168],"study_design_scores_gemma":[0.000037713042,0.000027750393,0.000009180864,0.00004941401,0.000010734018,0.00001699268,0.000521019,0.60874945,0.000216032,0.0013862546,0.3888081,0.00016734787],"about_ca_topic_score_codex":0.0000757524,"about_ca_topic_score_gemma":0.00012897486,"teacher_disagreement_score":0.71340585,"about_ca_system_score_codex":0.000031862553,"about_ca_system_score_gemma":0.00025292847,"threshold_uncertainty_score":0.99896604},"labels":[],"label_agreement":null},{"id":"W4400831116","doi":"10.3724/2096-7004.di.2024.0002","title":"Risk Factors Categorizations of Ischemic Heart Disease in South-Western Bangladesh","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","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 Saskatchewan","funders":"","keywords":"Disease; Voting; Population; Actuarial science; Medicine; Geography; Environmental health; Demography; Business; Political science; Pathology; Sociology","score_opus":0.21853472166579566,"score_gpt":0.4789780423696013,"score_spread":0.2604433207038056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400831116","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":[0.9501914,0.0029070128,0.031135425,0.0015261626,0.0026329798,0.0016088509,0.009215719,0.0003408202,0.00044162886],"genre_scores_gemma":[0.9972646,0.00025870051,0.00024249461,0.00023040046,0.00022098511,0.00007487992,0.001310215,0.00004810042,0.00034958596],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967209,0.00041760257,0.0011866981,0.00074204407,0.0003395486,0.00059321045],"domain_scores_gemma":[0.99629325,0.0015227587,0.00018838905,0.0015517037,0.00016771565,0.00027616954],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008533082,0.00022960587,0.00032372834,0.0002957312,0.00027077744,0.00002712318,0.0010355355,0.00019595226,0.00078662374],"category_scores_gemma":[0.0018372192,0.00020720887,0.000057070523,0.00094641186,0.00018071147,0.000534165,0.00057690183,0.0010831015,0.0014031136],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027722435,0.00005084317,0.9782073,0.0006021496,0.0000133271815,0.000014029464,0.0132785225,0.00033861032,0.000121270146,0.0016243202,0.0047491984,0.00097272015],"study_design_scores_gemma":[0.00020101905,0.0003273332,0.23519643,0.0076156724,0.00040915085,0.0000042507318,0.072267264,0.29866716,0.009782171,0.0198892,0.35294986,0.0026904787],"about_ca_topic_score_codex":0.008654701,"about_ca_topic_score_gemma":0.0030027982,"teacher_disagreement_score":0.7430109,"about_ca_system_score_codex":0.00014744593,"about_ca_system_score_gemma":0.00073008845,"threshold_uncertainty_score":0.9993744},"labels":[],"label_agreement":null}]}