{"meta":{"query_hash":"a02b92407db7","filters":{"venue":"Data Science Journal"},"cohort_total":31,"direct_labels_cover":4,"predictions_cover":31,"exported":31,"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/a02b92407db7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Data+Science+Journal"},"results":[{"id":"W1446508819","doi":"","title":"The Canadian Enhanced Polar Outflow Probe (e-POP) Mission: Current Status and Planned Observations and Data Distribution:Current Status and Planned Observations and Data Distribution","year":2009,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Methane Hydrates and Related Phenomena","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Current (fluid); Outflow; Distribution (mathematics); Polar; Environmental science; Meteorology; Geography; Physics; Engineering; Electrical engineering; Mathematics","score_opus":0.08234495579074003,"score_gpt":0.31894442929116634,"score_spread":0.23659947350042632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1446508819","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":[0.8589219,0.016803475,0.0036214255,0.014536383,0.0011036412,0.00095529546,0.10395591,0.000038650363,0.00006330491],"genre_scores_gemma":[0.9356751,0.025163194,0.0014170186,0.00014157138,0.00015501834,0.0000034963662,0.037404135,0.0000115116645,0.000028994486],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966586,0.00011112477,0.00046718644,0.0009808751,0.0009040389,0.0008781733],"domain_scores_gemma":[0.99680954,0.00011097279,0.0002668582,0.0014915358,0.0000842508,0.0012368291],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0029094252,0.00024013074,0.00019692571,0.000055209086,0.0040419335,0.0013157764,0.001678363,0.000069064125,0.000034629502],"category_scores_gemma":[0.0010054919,0.00016589771,0.0000094981415,0.000658163,0.0009925384,0.0039890124,0.0018839131,0.0005933863,0.0000028181128],"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":[0.0003172159,0.000603352,0.37880212,0.00009330009,0.0001041427,0.000035213263,0.0030332825,0.00033778802,0.005341636,0.003980754,0.14053254,0.46681866],"study_design_scores_gemma":[0.0005975133,0.00014403538,0.6063023,0.000108477376,0.0000679036,0.00007140024,0.00037380407,0.033415787,0.000026891066,0.0013542775,0.35721853,0.0003190837],"about_ca_topic_score_codex":0.0037467657,"about_ca_topic_score_gemma":0.022140905,"teacher_disagreement_score":0.46649957,"about_ca_system_score_codex":0.00035477552,"about_ca_system_score_gemma":0.0008029844,"threshold_uncertainty_score":0.99972093},"labels":[],"label_agreement":null},{"id":"W1978333903","doi":"10.2481/dsj.1.45","title":"A Mexican case study on a centralised database from world natural history museums","year":2002,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":33,"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":"Distribution (mathematics); Geography; Ornithology; Natural history; Species richness; Endemism; Database; Collections management; Library science; Ethnology; Ecology; Archaeology; History; Computer science; Biology; Southern Hemisphere","score_opus":0.14651411399662242,"score_gpt":0.3052122749726442,"score_spread":0.15869816097602177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978333903","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":[0.98927003,0.00011068854,0.000014216785,0.00059884286,0.0012040343,0.00016199352,0.00089383643,0.000032165288,0.0077141905],"genre_scores_gemma":[0.9983959,0.00003386961,0.00011575311,0.0008747341,0.000106209794,0.0000025914985,0.00011202165,0.0000071642094,0.00035174665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747247,0.000066361405,0.00026409578,0.0006007298,0.0010922885,0.0005040583],"domain_scores_gemma":[0.9982836,0.0000411567,0.00015263814,0.0010659213,0.000016575452,0.000440077],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00083708524,0.00015517967,0.00013547552,0.00011314227,0.0006013488,0.00021988187,0.0017608687,0.000016330154,0.13123703],"category_scores_gemma":[0.00015164824,0.0001240367,0.0000337977,0.0006518186,0.00066039193,0.002014641,0.0008182747,0.0004045866,0.0012561452],"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":[0.000048564663,0.0021968305,0.05145061,0.0000017073321,0.00002262252,0.010283608,0.0041848393,0.000009404587,0.012921118,0.000098697186,0.91292816,0.0058538513],"study_design_scores_gemma":[0.004073201,0.00044990043,0.26776862,0.00005259111,0.000121367535,0.006229777,0.05635346,0.012290613,0.000551304,0.000026450014,0.6508609,0.0012217963],"about_ca_topic_score_codex":0.00174713,"about_ca_topic_score_gemma":0.003861384,"teacher_disagreement_score":0.26206723,"about_ca_system_score_codex":0.0019807199,"about_ca_system_score_gemma":0.000029797096,"threshold_uncertainty_score":0.9995215},"labels":[],"label_agreement":null},{"id":"W1985018337","doi":"10.2481/dsj.4.21","title":"Rescuing and recovering lost or endangered data","year":2005,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Digital and Cyber Forensics","field":"Computer Science","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":"Dominion Astrophysical Observatory; Herzberg Institute of Astrophysics","funders":"","keywords":"Scope (computer science); Computer science; Transparency (behavior); Open data; Metadata; Usability; Reuse; Data science; Implementation; World Wide Web; Data curation; Open science; Engineering; Software engineering; Computer security","score_opus":0.1006452456693089,"score_gpt":0.31146841387309215,"score_spread":0.21082316820378327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985018337","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":[0.28378868,0.002513954,0.611541,0.023977853,0.006986304,0.00050153263,0.0017780752,0.0004200705,0.06849254],"genre_scores_gemma":[0.53565705,0.0007955978,0.45974284,0.0015461018,0.0012478557,5.037006e-7,0.00007665662,0.000016584681,0.0009168095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998228,0.000012222564,0.00022090338,0.00057696743,0.0005829153,0.00037899907],"domain_scores_gemma":[0.9976349,0.000041894582,0.000102634775,0.0019003329,0.000064317304,0.00025590835],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0018402562,0.000093394025,0.000100022415,0.00011967748,0.00041266673,0.002539361,0.007528788,0.00001803821,0.000021969709],"category_scores_gemma":[0.0002795089,0.00006570332,0.0000088856295,0.000621687,0.00028868258,0.021112455,0.00657994,0.00019383602,0.000048205868],"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":[0.0000058436744,0.000024818079,0.00030333758,0.000002959497,0.0000045266947,0.00005407867,0.00022922785,0.000012825512,0.0006239468,0.0030429652,0.013356662,0.9823388],"study_design_scores_gemma":[0.0005524473,0.00012972047,0.0050946856,0.00014715335,0.000012081465,0.0054572276,0.00019056312,0.30629873,0.0013170354,0.002794568,0.67750126,0.0005045437],"about_ca_topic_score_codex":0.0000074681316,"about_ca_topic_score_gemma":0.00006239803,"teacher_disagreement_score":0.9818343,"about_ca_system_score_codex":0.00004215307,"about_ca_system_score_gemma":0.0003369909,"threshold_uncertainty_score":0.9984961},"labels":[],"label_agreement":null},{"id":"W2021867077","doi":"10.2481/dsj.8.27","title":"CISTI'S Activities in Support of Scientific Data Management in Canada 2008-2010","year":2009,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Scope (computer science); Computer science; Transparency (behavior); Usability; Metadata; Implementation; Open data; Reuse; Data management; Data science; World Wide Web; Publishing; Data publishing; Political science; Database; Engineering; Software engineering; Computer security","score_opus":0.16621443021793386,"score_gpt":0.38273437009272043,"score_spread":0.21651993987478657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021867077","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":[0.5688199,0.0012432646,0.23440202,0.092666045,0.018771559,0.0039904313,0.0068425797,0.00017015851,0.07309406],"genre_scores_gemma":[0.93538517,0.0011320125,0.061775666,0.0005806049,0.00006222464,0.0000025491038,0.00033669613,0.0000070964347,0.0007179871],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9946444,0.00011580968,0.00057523354,0.001141552,0.0027025673,0.0008204466],"domain_scores_gemma":[0.9935417,0.000103092316,0.000337765,0.0057039205,0.00008607248,0.00022745477],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.013960787,0.00013437786,0.00020019723,0.0013475806,0.0003092705,0.004411082,0.03220082,0.00001611021,0.000040622614],"category_scores_gemma":[0.00065682677,0.00012221556,0.000010374134,0.0037057253,0.00039598014,0.10238769,0.009457158,0.0004597836,0.0000061302067],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064951346,0.0008541809,0.024602706,0.000088132474,0.00004096268,0.0043327487,0.00039726656,0.0006636226,0.002638246,0.037608307,0.5165929,0.41211596],"study_design_scores_gemma":[0.0015817946,0.00019692002,0.4637489,0.00016971893,0.000019373863,0.00035986106,0.001597063,0.12398552,0.0007930856,0.002060679,0.40470725,0.0007798312],"about_ca_topic_score_codex":0.08816091,"about_ca_topic_score_gemma":0.45075867,"teacher_disagreement_score":0.4391462,"about_ca_system_score_codex":0.00046859073,"about_ca_system_score_gemma":0.0045576915,"threshold_uncertainty_score":0.99855417},"labels":[],"label_agreement":null},{"id":"W2031989156","doi":"10.2481/dsj.2.25","title":"Data integration and knowledge discovery in biomedical databases. Reliable information from unreliable sources","year":2003,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Artificial Intelligence in Healthcare","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":"Dalhousie University","funders":"","keywords":"Scope (computer science); Computer science; Data science; Usability; Metadata; Transparency (behavior); Open data; Reuse; Implementation; World Wide Web; Data discovery; Data publishing; Publishing; Software engineering; Political science; Engineering","score_opus":0.2754938637313639,"score_gpt":0.5016500590355036,"score_spread":0.22615619530413972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031989156","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":[0.9100146,0.0022244747,0.05944523,0.003495337,0.0089503415,0.0011870136,0.0092792725,0.00008636026,0.005317365],"genre_scores_gemma":[0.9623731,0.0026818735,0.025507964,0.0012534095,0.00081353897,0.000018659479,0.0071746367,0.000022028396,0.0001548111],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968604,0.00031127527,0.00105772,0.00048686838,0.0006409665,0.00064277434],"domain_scores_gemma":[0.9967422,0.0006503429,0.00040019155,0.0016014435,0.00025838768,0.00034745716],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009279463,0.00013635067,0.00021028315,0.0004363615,0.0017730084,0.0002811909,0.001959139,0.000104914376,0.0002932659],"category_scores_gemma":[0.008379996,0.00010610655,0.000008638024,0.0011206454,0.0005607523,0.021426389,0.0015262251,0.0012047318,0.0002505665],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016556654,0.00041556166,0.6449422,0.00024404268,0.000018610514,0.000030162963,0.020742796,0.000063206964,0.0020389098,0.01804375,0.2351105,0.078184634],"study_design_scores_gemma":[0.00054743,0.00008433536,0.014764967,0.0015319699,0.000023560342,0.000041099276,0.060975403,0.14454563,0.00034512125,0.00424817,0.772508,0.00038429635],"about_ca_topic_score_codex":0.006725489,"about_ca_topic_score_gemma":0.007182514,"teacher_disagreement_score":0.63017726,"about_ca_system_score_codex":0.00025687963,"about_ca_system_score_gemma":0.0034468004,"threshold_uncertainty_score":0.9999728},"labels":[],"label_agreement":null},{"id":"W2032869846","doi":"10.2481/dsj.6.od26","title":"Canadian National Consultation on Access to Scientific Research Data","year":2007,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada; Université de Montréal","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Strong","keywords":"Scope (computer science); Computer science; Transparency (behavior); Usability; Metadata; Data science; Open data; Reuse; Implementation; World Wide Web; Engineering; Computer security; Software engineering","score_opus":0.6443846780180462,"score_gpt":0.5804227013872811,"score_spread":0.06396197663076508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032869846","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":[0.029792689,0.000084591265,0.6988483,0.15510972,0.007028805,0.0018552337,0.0027052346,0.00013424136,0.10444116],"genre_scores_gemma":[0.83622724,0.00022771607,0.15353754,0.004962541,0.0011011503,0.000009323553,0.0015442369,0.00002517569,0.0023650967],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9893884,0.00019736016,0.00036651388,0.0015666916,0.0071610776,0.0013199247],"domain_scores_gemma":[0.9892991,0.0010097036,0.0001581076,0.005559531,0.0024169125,0.0015566275],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.115344875,0.000104260376,0.000085552536,0.0044248453,0.0037213292,0.055719722,0.061073102,0.000028820014,0.000042437],"category_scores_gemma":[0.0286426,0.00009212034,0.000008597463,0.009378552,0.00068092125,0.17915164,0.01571452,0.0007426076,0.00050583377],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032287928,0.00014612896,0.001204467,0.000008186363,0.000016022594,0.00030746037,0.0003529262,0.00020030474,0.0019372905,0.19682556,0.683045,0.11592431],"study_design_scores_gemma":[0.00023001972,0.00008314685,0.022770705,0.000041812706,0.0000020211332,0.00010480718,0.0002524629,0.033785727,0.00042381114,0.0018176999,0.94028664,0.00020113734],"about_ca_topic_score_codex":0.0065042856,"about_ca_topic_score_gemma":0.065616906,"teacher_disagreement_score":0.8064345,"about_ca_system_score_codex":0.00090587826,"about_ca_system_score_gemma":0.008137026,"threshold_uncertainty_score":0.9975757},"labels":[],"label_agreement":null},{"id":"W2036014579","doi":"10.2481/dsj.5.178","title":"Geography Markup Language","year":2006,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Galdos Systems (Canada)","funders":"","keywords":"Markup language; XML; Geospatial analysis; Geomatics; Computer science; Document type definition; World Wide Web; Interoperability; Information retrieval; Geography; Document Structure Description; Remote sensing","score_opus":0.024363899319102905,"score_gpt":0.3337672918235531,"score_spread":0.30940339250445015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036014579","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":[0.3803984,0.0009756615,0.001130918,0.0037778215,0.0029099337,0.0002845026,0.00013824341,0.00015557626,0.61022896],"genre_scores_gemma":[0.9967363,0.000115822586,0.001794394,0.00015804105,0.00072861783,0.0000015950608,0.000015920057,0.0000029834443,0.0004463477],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774075,0.00004683043,0.00028880662,0.00017592142,0.0012667138,0.00048096955],"domain_scores_gemma":[0.99895114,0.000039223753,0.00020061838,0.00041025932,0.00026587147,0.00013289842],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0063074846,0.00006965171,0.00009503196,0.00043948108,0.0030372262,0.00077540823,0.0018784408,0.000029369246,0.00017482786],"category_scores_gemma":[0.00025504647,0.000057282276,0.00003989557,0.0015401072,0.00135599,0.0037513564,0.00029786365,0.0001560703,0.00009503751],"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":[0.000011012427,0.00011994317,0.64874643,0.00001545308,0.00003834819,0.00006451304,0.02984191,0.000027248287,0.0006315579,0.10483549,0.18876041,0.026907686],"study_design_scores_gemma":[0.00027747767,0.000017887858,0.30534467,0.000029424145,0.000013483159,0.000083909465,0.04944879,0.000095656906,0.000027144,0.002118951,0.6422946,0.00024803748],"about_ca_topic_score_codex":0.003408645,"about_ca_topic_score_gemma":0.0013368345,"teacher_disagreement_score":0.6163379,"about_ca_system_score_codex":0.00004793714,"about_ca_system_score_gemma":0.00027718046,"threshold_uncertainty_score":0.9982607},"labels":[],"label_agreement":null},{"id":"W2059472642","doi":"10.2481/dsj.5.143","title":"A hashing technique using separate binary tree","year":2006,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Scope (computer science); Usability; Data science; Metadata; Transparency (behavior); Data publishing; Implementation; World Wide Web; Publishing; Software engineering; Computer security; Political science","score_opus":0.05802956779394889,"score_gpt":0.3299944953690478,"score_spread":0.2719649275750989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059472642","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":[0.026214123,0.00012544314,0.9719428,0.00020978972,0.0005360648,0.00008537449,0.000026644599,0.00007140768,0.00078834785],"genre_scores_gemma":[0.19722098,0.000015738864,0.8021817,0.000099001634,0.00040825646,0.0000016521068,0.000021959273,0.000007523606,0.00004315561],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978426,0.000045086737,0.00030275513,0.0005530382,0.0007848041,0.00047171777],"domain_scores_gemma":[0.99804604,0.000027199932,0.0002136016,0.0014413592,0.00010667498,0.00016513119],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002588516,0.00012597062,0.00012648721,0.00032223813,0.001201362,0.0012995879,0.0065340432,0.0000371168,0.0000120277755],"category_scores_gemma":[0.00004912259,0.00009739359,0.000027223357,0.0012216761,0.00022853567,0.012268809,0.0030689905,0.0003168499,0.000015349415],"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":[0.000014029309,0.0003265747,0.0020891477,0.000012475818,0.0000092214505,0.00088669773,0.00024618962,0.003949196,0.8668347,0.010814416,0.038745258,0.07607212],"study_design_scores_gemma":[0.00018254948,0.00004637907,0.0024471649,0.000081314676,0.0000045815827,0.0027517572,0.000023674827,0.97550553,0.005683639,0.0032903808,0.009747108,0.00023591158],"about_ca_topic_score_codex":0.00012230611,"about_ca_topic_score_gemma":0.0000056785852,"teacher_disagreement_score":0.97155637,"about_ca_system_score_codex":0.00009391203,"about_ca_system_score_gemma":0.00053580245,"threshold_uncertainty_score":0.99973714},"labels":[],"label_agreement":null},{"id":"W2083696640","doi":"10.2481/dsj.009-026","title":"Data Management Activities of Canada's National Science Library - 2010 Update and Prospective","year":2010,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","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":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Mandate; Political science; Transformational leadership; Parliament; Research council; Library science; Engineering management; Public relations; Management; Business; Engineering; Computer science; Government (linguistics)","score_opus":0.0732256112792575,"score_gpt":0.34985363900726973,"score_spread":0.2766280277280122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083696640","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":[0.33824614,0.0010844127,0.30753028,0.1239088,0.020777483,0.0040435954,0.01645581,0.00046944333,0.18748403],"genre_scores_gemma":[0.6512221,0.0014989959,0.3455606,0.00058045716,0.0002538911,0.000005621283,0.00013774261,0.0000132403975,0.0007272992],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943461,0.000041848045,0.00029615266,0.001084342,0.0036438883,0.00058770366],"domain_scores_gemma":[0.99557483,0.00012416914,0.00034151642,0.0033563701,0.00023971724,0.00036340186],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.009693839,0.00012446755,0.00012531868,0.0006788873,0.0011843523,0.007575611,0.028790426,0.00001659627,0.000039129616],"category_scores_gemma":[0.0011946983,0.0001035004,0.0000071782183,0.0021036614,0.0020749695,0.22412351,0.028456824,0.0005545259,0.0000023628727],"study_design_candidate":"theoretical_or_conceptual","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":[0.000022822673,0.00016018588,0.0060981736,0.000044323915,0.000053304615,0.00012992597,0.00009035276,0.000013998748,0.007926772,0.8784237,0.07163564,0.035400823],"study_design_scores_gemma":[0.0012098325,0.00015811795,0.3781372,0.00010960492,0.00004029651,0.0010759955,0.0011337055,0.1477136,0.012454207,0.021472823,0.4355026,0.0009920506],"about_ca_topic_score_codex":0.0016537135,"about_ca_topic_score_gemma":0.008087299,"teacher_disagreement_score":0.8569509,"about_ca_system_score_codex":0.00007663316,"about_ca_system_score_gemma":0.0063503236,"threshold_uncertainty_score":0.9992828},"labels":[],"label_agreement":null},{"id":"W2123356220","doi":"10.2481/dsj.5.174","title":"The Crystallographic Information File (CIF)","year":2006,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","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":"McMaster University; Brockhouse Institute for Materials Research","funders":"","keywords":"Computer science; Scope (computer science); Transparency (behavior); Usability; Open data; Metadata; World Wide Web; Data science; Reuse; Data publishing; Data curation; Implementation; Software; Publishing; Political science; Software engineering; Computer security","score_opus":0.014380177954742022,"score_gpt":0.22447322685658352,"score_spread":0.2100930489018415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123356220","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":[0.01389526,0.00041315742,0.6820613,0.047301892,0.0033234141,0.0003236115,0.0003480311,0.00033035473,0.25200298],"genre_scores_gemma":[0.96355337,0.00008047044,0.034440134,0.0006032989,0.0003846908,0.0000045429306,0.00015873974,0.0000012641351,0.0007734713],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988,0.000016923397,0.00021723498,0.00015575689,0.00049154577,0.0003185547],"domain_scores_gemma":[0.99863356,0.000070302434,0.00016695181,0.0008569684,0.00020062488,0.000071564886],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00208839,0.000058894468,0.000044265624,0.00007852489,0.0015866472,0.0017648833,0.005072091,0.000020289295,0.000081454324],"category_scores_gemma":[0.00040037118,0.000036078152,0.000019244815,0.0008630502,0.00033032216,0.006450942,0.00094281253,0.00018930192,0.00003110138],"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":[0.000003729475,0.000037805094,0.0015247599,0.0000068005497,0.0000058117544,0.000019481007,0.00020334774,0.0009088664,0.0027114083,0.057374448,0.8562754,0.08092816],"study_design_scores_gemma":[0.00007136831,0.000012928156,0.011280234,0.000007501288,0.0000010979337,0.00037366658,0.00006927886,0.045820788,0.00017629567,0.014294271,0.92781353,0.000079041354],"about_ca_topic_score_codex":0.000018401313,"about_ca_topic_score_gemma":0.0000073471415,"teacher_disagreement_score":0.94965816,"about_ca_system_score_codex":0.000016252945,"about_ca_system_score_gemma":0.00021091284,"threshold_uncertainty_score":0.9997131},"labels":[],"label_agreement":null},{"id":"W2125590838","doi":"10.2481/dsj.4.106","title":"The long-term preservation of accurate and authentic digital data: the INTERPARES project","year":2005,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scope (computer science); Computer science; Usability; Transparency (behavior); Implementation; Metadata; Digital preservation; Open data; Data science; Reuse; World Wide Web; Data publishing; Electronic publishing; Publishing; Open science; Data curation; Political science; Software engineering; Engineering; The Internet; Computer security","score_opus":0.13836117726891836,"score_gpt":0.3153712717204733,"score_spread":0.17701009445155494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125590838","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":[0.8409565,0.00040705234,0.0006918022,0.0145267565,0.0011017966,0.00060384907,0.0040299194,0.000031469393,0.13765086],"genre_scores_gemma":[0.99843925,0.00011281234,0.000024065574,0.00006143337,0.00030575582,0.0000011965578,0.0001831411,0.0000022387435,0.00087011524],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991996,0.000010873825,0.00017686412,0.0001483735,0.00033197948,0.00013226985],"domain_scores_gemma":[0.9992553,0.00008725054,0.00012503604,0.00045633514,0.000047693735,0.000028405153],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006010377,0.000052176623,0.000044703647,0.00004623296,0.00083912484,0.0030748206,0.0020396858,0.000001990089,0.000016144868],"category_scores_gemma":[0.00009573165,0.00002337088,0.000010941422,0.000047085414,0.001239047,0.011153212,0.0011790277,0.0000805684,0.0000055833852],"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":[0.00005490146,0.00021293148,0.0016342974,0.000031983243,0.000092679365,0.0000064386986,0.009719093,0.000012634784,0.000021192658,0.47797778,0.032154057,0.478082],"study_design_scores_gemma":[0.00035881158,0.0001840977,0.13821018,0.0001682535,0.00005863684,0.0001176531,0.0035167397,0.017321374,0.000018211003,0.020223964,0.8195981,0.00022399375],"about_ca_topic_score_codex":0.000007380647,"about_ca_topic_score_gemma":0.00009935794,"teacher_disagreement_score":0.78744406,"about_ca_system_score_codex":0.0000072632874,"about_ca_system_score_gemma":0.00006701525,"threshold_uncertainty_score":0.9979601},"labels":[],"label_agreement":null},{"id":"W2132929844","doi":"10.2481/dsj.008-011","title":"Structured Query Translation in Peer to Peer Database Sharing Systems","year":2009,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Scope (computer science); Usability; Transparency (behavior); Data sharing; World Wide Web; Metadata; Implementation; Open data; Reuse; Data science; Database; Software engineering","score_opus":0.07014835883326626,"score_gpt":0.3407390784558296,"score_spread":0.27059071962256337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132929844","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":[0.01965325,0.00023267292,0.9741516,0.0034363559,0.0015026998,0.00023646411,0.00032679306,0.000056926925,0.00040321855],"genre_scores_gemma":[0.6321974,0.000029993864,0.36629948,0.00053830957,0.00050724606,0.000004003308,0.00021194144,0.000010266438,0.00020136878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99637455,0.000042879914,0.00050766696,0.0007776316,0.001750441,0.00054682663],"domain_scores_gemma":[0.9973039,0.00003497904,0.00016253923,0.0017962016,0.00036201198,0.00034034753],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0048160036,0.0001603143,0.0002074944,0.00051693484,0.00043007167,0.0009863587,0.0037082548,0.000034127657,0.000008998238],"category_scores_gemma":[0.00054976717,0.00013189903,0.000021472064,0.0015594901,0.00007680603,0.013894306,0.0006362256,0.000345153,0.00002007154],"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":[0.00012525314,0.00031272034,0.006884302,0.00009912108,0.000025031988,0.001129402,0.012310961,0.032238357,0.16908766,0.40447477,0.040565472,0.33274695],"study_design_scores_gemma":[0.0016110948,0.00028527074,0.032207437,0.0007929841,0.000013893695,0.002956096,0.0018939949,0.560372,0.0020851188,0.0021219037,0.3942818,0.0013784249],"about_ca_topic_score_codex":0.00010476561,"about_ca_topic_score_gemma":0.00010669309,"teacher_disagreement_score":0.6125442,"about_ca_system_score_codex":0.00012259494,"about_ca_system_score_gemma":0.00030607576,"threshold_uncertainty_score":0.99989784},"labels":[],"label_agreement":null},{"id":"W2133007173","doi":"10.2481/dsj.4.127","title":"Multi-sensor data fusion for land vehicle attitude estimation using a fuzzy expert system","year":2005,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Inertial Sensor and Navigation","field":"Engineering","cited_by":31,"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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gyroscope; Accelerometer; Kalman filter; Sensor fusion; Compass; Computer science; Inertial measurement unit; Fuzzy logic; Dead reckoning; Vibrating structure gyroscope; Artificial intelligence; Position (finance); Field (mathematics); Inertial navigation system; Global Positioning System; Computer vision; Control theory (sociology); Real-time computing; Inertial frame of reference; Engineering; Mathematics; Geography; Telecommunications; Aerospace engineering","score_opus":0.10433213707563253,"score_gpt":0.35159105032011034,"score_spread":0.2472589132444778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133007173","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":[0.6659661,0.00030004408,0.33174282,0.00013749025,0.00097031565,0.00023783393,0.0004588946,0.00012484839,0.000061652274],"genre_scores_gemma":[0.77687836,0.000030049732,0.22218235,0.00002302032,0.00063137576,9.723291e-7,0.00023771195,0.000012149345,0.000004005419],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891824,0.000012129664,0.00024936156,0.00023313185,0.00032545926,0.00026165432],"domain_scores_gemma":[0.9991177,0.000023052338,0.000063979925,0.0006032234,0.00008379332,0.00010829003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000987898,0.00008854179,0.00009877604,0.000100552454,0.0004528069,0.000266168,0.00094984786,0.000036824644,0.000005856706],"category_scores_gemma":[0.00011811647,0.00007548454,0.000013900809,0.00022876007,0.000050125804,0.002983,0.00018484818,0.000116374555,0.000015337482],"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":[0.000024742203,0.00004337715,0.00055338524,0.000061810926,0.00001287733,0.000007193788,0.00036328484,0.22136578,0.7274735,0.000024580364,0.002252854,0.047816627],"study_design_scores_gemma":[0.00038435825,0.000009696599,0.00073368364,0.00008315879,0.000011806542,0.000115362905,0.00008194189,0.9918023,0.004314865,0.0000014380068,0.0023568827,0.00010455351],"about_ca_topic_score_codex":0.000038490587,"about_ca_topic_score_gemma":0.000029179133,"teacher_disagreement_score":0.77043647,"about_ca_system_score_codex":0.00017658381,"about_ca_system_score_gemma":0.000051395313,"threshold_uncertainty_score":0.34826705},"labels":[],"label_agreement":null},{"id":"W2141093030","doi":"10.2481/dsj.3.202","title":"Appraising digital records for long-term preservation","year":2004,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scope (computer science); Computer science; Digital preservation; Usability; Transparency (behavior); Metadata; Implementation; Open data; World Wide Web; Data science; Reuse; Data curation; Data publishing; Electronic publishing; Publishing; Political science; Software engineering; The Internet; Computer security; Engineering","score_opus":0.13525818568589779,"score_gpt":0.30130213518249066,"score_spread":0.16604394949659287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141093030","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":[0.4352731,0.0000343514,0.058492534,0.0056525823,0.0032049855,0.00050215086,0.0022883478,0.0000878168,0.49446413],"genre_scores_gemma":[0.9964588,0.000008269363,0.0009111961,0.00016942284,0.00092379533,0.0000029294506,0.00043933053,0.0000054011075,0.0010808271],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991291,0.000001948864,0.00015683212,0.00018774987,0.00032677685,0.00019755926],"domain_scores_gemma":[0.9995371,0.000023853516,0.00008332559,0.00019512637,0.000078890866,0.00008170452],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00029867067,0.00006120263,0.000054080978,0.000107557935,0.0007667891,0.0030974508,0.0008317063,0.000003119873,0.000048041693],"category_scores_gemma":[0.00007477966,0.00004698223,0.00002793282,0.0000508993,0.00039538962,0.012295721,0.00021021375,0.00006432678,0.000026888503],"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":[0.000025037858,0.00020514654,0.00056635804,0.00002411439,0.000020653735,0.000011624153,0.0014966541,0.00008172121,0.00002172711,0.8512712,0.0042694323,0.1420063],"study_design_scores_gemma":[0.0011976707,0.0004221939,0.07667181,0.00021983423,0.00003272942,0.00013799871,0.00066145393,0.00077577855,0.000045070934,0.48555672,0.43385467,0.0004240657],"about_ca_topic_score_codex":0.000004467136,"about_ca_topic_score_gemma":0.000018490171,"teacher_disagreement_score":0.5611857,"about_ca_system_score_codex":0.00003085606,"about_ca_system_score_gemma":0.00010279451,"threshold_uncertainty_score":0.99793744},"labels":[],"label_agreement":null},{"id":"W2154198926","doi":"10.2481/dsj.14-047","title":"Data-PE: A Framework for Evaluating Data Publication Policies at Scholarly Journals","year":2015,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","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 Toronto","funders":"","keywords":"Computer science; Scope (computer science); Usability; Transparency (behavior); Metadata; Open data; Data science; Data publishing; Implementation; Reuse; Publishing; World Wide Web; Political science; Software engineering; Engineering","score_opus":0.7646680752783171,"score_gpt":0.5850843913237225,"score_spread":0.17958368395459468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154198926","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":[0.0013011756,0.0008485469,0.9456808,0.04713186,0.0010693796,0.00045951785,0.0026949558,0.00007401028,0.00073977094],"genre_scores_gemma":[0.0053080944,0.001001022,0.98801386,0.0017219802,0.0010145885,0.000011075013,0.002550244,0.00002000188,0.0003591258],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905491,0.00042406045,0.0008371482,0.0018985457,0.005167422,0.0011237204],"domain_scores_gemma":[0.9675272,0.0012521758,0.0017250257,0.024741137,0.0033221045,0.0014323688],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.098324955,0.00021014523,0.00024247343,0.00089990126,0.0022009625,0.07931364,0.09842829,0.000069545684,0.00004324852],"category_scores_gemma":[0.14051557,0.00017239536,0.000023273013,0.0031313251,0.0004518173,0.5295488,0.06948273,0.0010273644,0.00013086287],"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":[0.00006281883,0.0002409634,0.002266322,0.000031320164,0.00010006745,0.000046614958,0.00053045823,0.000085088875,0.0013760143,0.10263835,0.7540167,0.13860527],"study_design_scores_gemma":[0.00052229787,0.00016184313,0.0017822242,0.000088594585,0.00003761835,0.0006855375,0.0004032616,0.41100353,0.000044639273,0.009835939,0.5751445,0.00028998495],"about_ca_topic_score_codex":0.000065074266,"about_ca_topic_score_gemma":0.00004087663,"teacher_disagreement_score":0.4502352,"about_ca_system_score_codex":0.00035734547,"about_ca_system_score_gemma":0.0031448358,"threshold_uncertainty_score":0.99909806},"labels":[],"label_agreement":null},{"id":"W2585472482","doi":"10.5334/dsj-2017-003","title":"Legal and Ethical Issues around Incorporating Traditional Knowledge in Polar Data Infrastructures","year":2017,"lang":"en","type":"article","venue":"Data Science Journal","topic":"International Maritime Law Issues","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Traditional knowledge; Acknowledgement; Knowledge management; Interoperability; Context (archaeology); Sociology of scientific knowledge; Knowledge sharing; Inclusion (mineral); Body of knowledge; Computer science; Engineering ethics; Indigenous; Sociology; Social science; World Wide Web; Engineering; Computer security; Geography","score_opus":0.07870823258626229,"score_gpt":0.3662956398552014,"score_spread":0.2875874072689391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2585472482","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":[0.96432656,0.00015427168,0.00023846021,0.006707413,0.0007382738,0.00010966289,0.00075204927,0.0000147654,0.026958548],"genre_scores_gemma":[0.98317885,0.000032546384,0.015949314,0.00022296452,0.00043052944,6.0687296e-7,0.0001260281,0.0000061465016,0.000053001862],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99789655,0.000059695194,0.00029668654,0.0005651304,0.0008864232,0.00029551657],"domain_scores_gemma":[0.9982844,0.00007926808,0.00023171092,0.0011952486,0.000028330596,0.00018105982],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0035750156,0.00012040697,0.00013434667,0.00008433343,0.0014514893,0.0018652009,0.005788098,0.00007899713,0.0005766268],"category_scores_gemma":[0.0013132092,0.0001037132,0.000010011894,0.00012958802,0.002577154,0.007557402,0.004914184,0.00084277027,0.00006335417],"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":[0.000045757937,0.00017041665,0.82157475,0.000013301937,0.000017468987,0.00030449312,0.0007296831,0.00015770781,0.014332329,0.100350074,0.03898946,0.023314577],"study_design_scores_gemma":[0.00030020002,0.00003393197,0.91689503,0.000055489676,0.000006026657,0.00073321396,0.0001517237,0.0313087,0.00014869834,0.026919557,0.023250122,0.00019728045],"about_ca_topic_score_codex":0.0019787347,"about_ca_topic_score_gemma":0.002346664,"teacher_disagreement_score":0.09532033,"about_ca_system_score_codex":0.00013903108,"about_ca_system_score_gemma":0.00016140842,"threshold_uncertainty_score":0.9998485},"labels":[],"label_agreement":null},{"id":"W2610869427","doi":"10.5334/dsj-2017-024","title":"All or Nothing: The False Promise of Anonymity","year":2017,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Ethics in Clinical Research","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":"Juvenile Diabetes Research Foundation","funders":"","keywords":"Anonymity; Data sharing; Computer science; Identification (biology); Data anonymization; Process (computing); Internet privacy; State (computer science); Computer security; Information privacy; Medicine","score_opus":0.8656067754571136,"score_gpt":0.6914985035282208,"score_spread":0.17410827192889278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610869427","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":[0.8206691,0.00011472739,0.0005255033,0.16516627,0.0010817013,0.00053278205,0.000121805206,0.00001480764,0.0117732985],"genre_scores_gemma":[0.9883703,0.00074025965,0.007724615,0.0014574885,0.00041036494,0.0000010911048,0.000003229516,0.000006837964,0.0012857929],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968384,0.000044132907,0.00036057286,0.00028525785,0.0021520876,0.00031956285],"domain_scores_gemma":[0.99274886,0.0019658704,0.00043363028,0.0036659783,0.00079872285,0.00038693557],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031516477,0.00005958479,0.00016501031,0.00006552825,0.0011227439,0.00045209372,0.0059122625,0.00007475684,0.00023785411],"category_scores_gemma":[0.1409741,0.000027514732,0.00003663931,0.00014363449,0.003676838,0.0011498168,0.0021118475,0.0019652592,0.000027298276],"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":[0.005482406,0.0030716795,0.4390132,0.0008889219,0.0003766928,0.0028614625,0.009198436,0.000011334152,0.22278854,0.027395554,0.10743288,0.18147889],"study_design_scores_gemma":[0.0053700656,0.0015804396,0.76935124,0.001694214,0.00020525976,0.002718841,0.0014580642,0.008160527,0.018750338,0.031154381,0.15917689,0.00037974797],"about_ca_topic_score_codex":0.00007090837,"about_ca_topic_score_gemma":0.000097452576,"teacher_disagreement_score":0.33033803,"about_ca_system_score_codex":0.00004366994,"about_ca_system_score_gemma":0.003104599,"threshold_uncertainty_score":0.99946624},"labels":[],"label_agreement":null},{"id":"W2765696161","doi":"10.5334/dsj-2017-048","title":"The Northern Voice: Listening to Indigenous and Northern Perspectives on Management of Data in Canada","year":2017,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Indigenous Studies and Ecology","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":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Indigenous; Interoperability; Active listening; Class (philosophy); The Internet; Geography; World Wide Web; Computer science; Sociology; Ecology","score_opus":0.08398072553422269,"score_gpt":0.4148932033926937,"score_spread":0.330912477858471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765696161","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":[0.99378735,0.00023979915,0.000014290962,0.0024906565,0.0005455817,0.00034091872,0.00020182537,0.0000017660095,0.0023778],"genre_scores_gemma":[0.9985251,0.0007912348,0.0002978756,0.00015618297,0.00011114733,0.0000044195144,0.0000066537473,0.0000056637477,0.00010176102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99817425,0.000061183055,0.00029835073,0.00032785453,0.00038924368,0.0007491359],"domain_scores_gemma":[0.99755645,0.00012480219,0.0003525574,0.0016664758,0.00018163318,0.00011810164],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0039546317,0.00007643382,0.00014360007,0.000060577837,0.016278379,0.00008110194,0.0038500254,0.00001945129,0.000009181359],"category_scores_gemma":[0.00033607997,0.00004859612,0.0000054704115,0.00011472997,0.0002358414,0.00049722067,0.004155916,0.00040077438,0.00001116165],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004296388,0.000026675852,0.89403343,0.000023054248,0.00003112597,0.000071886,0.081981055,0.000022882608,0.00000657582,0.00007346623,0.00054029294,0.023146564],"study_design_scores_gemma":[0.00020104312,0.00005237883,0.6729949,0.00007919507,0.000007682805,0.000008783264,0.31718558,0.00012146173,3.293725e-7,0.000019292944,0.009267185,0.000062182036],"about_ca_topic_score_codex":0.78434485,"about_ca_topic_score_gemma":0.9988107,"teacher_disagreement_score":0.23520452,"about_ca_system_score_codex":0.0007870976,"about_ca_system_score_gemma":0.002968389,"threshold_uncertainty_score":0.9850023},"labels":[],"label_agreement":null},{"id":"W2785284360","doi":"10.5334/dsj-2018-001","title":"Science Metadata Management, Interoperability and Data Citations of the National Institute of Polar Research, Japan","year":2018,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","field":"Computer Science","cited_by":5,"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":"Metadata; Data management plan; Interoperability; Directory; Stewardship (theology); Data center; Meta Data Services; Open science; Data management; Data mapping; Library science; Data as a service; Research center; World Wide Web; Metadata management; Computer science; Metadata repository; Database; Political science; Business; Service (business)","score_opus":0.478091744716791,"score_gpt":0.5185561253619065,"score_spread":0.04046438064511554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785284360","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":[0.46104184,0.00037806743,0.45709926,0.031661745,0.0038592094,0.0019983447,0.004233794,0.00006445283,0.039663285],"genre_scores_gemma":[0.8977801,0.00034272185,0.10148978,0.00011067996,0.00007961562,0.0000013882867,0.000029846311,0.0000033820265,0.00016247676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9929287,0.00027898268,0.00047145784,0.0010700554,0.004750406,0.00050041755],"domain_scores_gemma":[0.9908152,0.00021423967,0.00038063983,0.0062418957,0.002130767,0.00021720963],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","sts","scholarly_communication","open_science"],"category_scores_codex":[0.052924737,0.00009198726,0.00012689155,0.0012968966,0.0019019814,0.0048768427,0.05046319,0.000014799254,0.000010725594],"category_scores_gemma":[0.012497359,0.00006125085,0.000013910766,0.0076894853,0.013653349,0.19567987,0.054906044,0.00041738048,0.0000052934424],"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":[0.000019505638,0.0003055972,0.007960822,0.00006809953,0.00006865123,0.000004177844,0.0005141192,0.000008422713,0.022201587,0.94053924,0.010204416,0.018105369],"study_design_scores_gemma":[0.0012376994,0.0006465832,0.48730743,0.00040078853,0.00006800935,0.00033095627,0.0025381139,0.13155991,0.0061558797,0.02218223,0.34701514,0.000557267],"about_ca_topic_score_codex":0.000107386666,"about_ca_topic_score_gemma":0.00013766304,"teacher_disagreement_score":0.918357,"about_ca_system_score_codex":0.00010056001,"about_ca_system_score_gemma":0.0019524379,"threshold_uncertainty_score":0.9993974},"labels":[],"label_agreement":null},{"id":"W2891686592","doi":"10.5334/dsj-2018-020","title":"Using Classified and Unclassified Land Cover Data to Estimate the Footprint of Human Settlement","year":2018,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Impact of Light on Environment and Health","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Esri (Canada)","funders":"","keywords":"Geography; Population; Footprint; Land cover; Cartography; Settlement (finance); Orthophoto; Ancillary data; Georeference; Census; Remote sensing; Land use; Computer science; Physical geography; Archaeology; Ecology; World Wide Web; Demography","score_opus":0.23874262984261077,"score_gpt":0.43696381670121914,"score_spread":0.19822118685860837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891686592","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":[0.9942934,0.000010946137,0.0014887337,0.0019072123,0.00018515064,0.0001635429,0.00014637702,0.000005286494,0.001799365],"genre_scores_gemma":[0.9908052,0.000016814467,0.008605475,0.00036614205,0.00013243523,3.809013e-7,0.000020305804,0.000006514644,0.000046702375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99794245,0.00004319806,0.00030506102,0.00041476218,0.00083050923,0.00046404472],"domain_scores_gemma":[0.9981157,0.000026845422,0.0002048832,0.0013188085,0.000011233652,0.00032251858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004134521,0.00010825348,0.00012885623,0.000057997415,0.0011015433,0.00019562778,0.0025272942,0.000023594192,0.00064760284],"category_scores_gemma":[0.0001035781,0.000067285444,0.0000094889565,0.00027601133,0.0014524778,0.001020496,0.0029377243,0.0001646692,0.000059048172],"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":[0.000049019676,0.00012999738,0.6243751,0.000008937919,0.000015028447,0.000006882702,0.00096756505,0.00016220538,0.35936794,0.00023534683,0.006989289,0.0076927003],"study_design_scores_gemma":[0.00037948397,0.00026334522,0.9581269,0.00003374194,0.000028020457,0.0000809878,0.00014397684,0.012178664,0.0032969057,0.00021287028,0.025088364,0.00016673979],"about_ca_topic_score_codex":0.00016155232,"about_ca_topic_score_gemma":0.00017708156,"teacher_disagreement_score":0.35607103,"about_ca_system_score_codex":0.00015993461,"about_ca_system_score_gemma":0.00008982723,"threshold_uncertainty_score":0.84722924},"labels":[],"label_agreement":null},{"id":"W2908272686","doi":"10.5334/dsj-2019-001","title":"Understanding Human Mobility Patterns in a Developing Country Using Mobile Phone Data","year":2019,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":47,"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 Calgary","funders":"","keywords":"TRIPS architecture; Mobile phone; Phone; Computer science; Destinations; Centroid; Entropy (arrow of time); Statistics; Geography; Mathematics; Telecommunications","score_opus":0.33013340903309646,"score_gpt":0.4317011090950576,"score_spread":0.10156770006196114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908272686","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":[0.97482574,0.000043588978,0.02355181,0.00023626504,0.0003423913,0.00023146022,0.00017563892,0.000019377905,0.00057370134],"genre_scores_gemma":[0.9986168,0.00007916093,0.00080898503,0.00014082798,0.00017748901,0.0000013456856,0.00015148807,0.000005709075,0.00001815265],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688315,0.00022146491,0.00046452158,0.00069794705,0.0011718118,0.0005610907],"domain_scores_gemma":[0.9978449,0.00013435689,0.00022921101,0.0014753703,0.00012937702,0.0001868156],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01463965,0.000110905654,0.00020945432,0.00034677412,0.0021315543,0.0008474777,0.0039940285,0.00006115107,0.00080303435],"category_scores_gemma":[0.0004206378,0.00010754928,0.000022983204,0.0017351534,0.0007786518,0.004630253,0.00084441015,0.00037206602,0.00002626227],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013734418,0.00029869433,0.9740191,0.00006309094,0.0000319434,0.000023197521,0.0114536965,0.002882206,0.0026253748,0.006210117,0.00044397116,0.0019348923],"study_design_scores_gemma":[0.002670481,0.0001389009,0.17649207,0.0014451296,0.00018836626,0.00007157381,0.36885378,0.4096285,0.00024433434,0.011608545,0.02640326,0.002255055],"about_ca_topic_score_codex":0.011265857,"about_ca_topic_score_gemma":0.047235217,"teacher_disagreement_score":0.797527,"about_ca_system_score_codex":0.0015774902,"about_ca_system_score_gemma":0.0026358706,"threshold_uncertainty_score":0.99916756},"labels":[],"label_agreement":null},{"id":"W2955083888","doi":"10.5334/dsj-2019-027","title":"Developing a Model Guidelines Addressing Legal Impediments to Open Access to Publicly Funded Research Data in Malaysia","year":2019,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","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":"","keywords":"Data access; Computer science; Business; Knowledge management; Database","score_opus":0.8726138537959646,"score_gpt":0.6560074045530535,"score_spread":0.21660644924291106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955083888","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":[0.10887103,0.000054876138,0.7881599,0.09499923,0.00089559413,0.0020152717,0.00025013194,0.0000492368,0.0047046924],"genre_scores_gemma":[0.11481516,0.00023501104,0.87836015,0.0049913367,0.00023459636,0.00003306465,0.00016699391,0.00002584154,0.0011378622],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9897661,0.00037729065,0.0008711441,0.0025339692,0.004717786,0.0017336644],"domain_scores_gemma":[0.9877329,0.0002715608,0.00027633173,0.009509586,0.0013400593,0.0008695852],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.06316291,0.00020857298,0.0002867829,0.0027242962,0.000960773,0.1387359,0.1754812,0.000040549116,0.000043729324],"category_scores_gemma":[0.0125229815,0.00017960029,0.000013461474,0.009334749,0.00015236213,0.44698343,0.2792544,0.0009194107,0.000276133],"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":[0.00029717945,0.00051346974,0.05038571,0.0001336461,0.000088166125,0.00064796157,0.0009614271,0.030649228,0.011721232,0.12980376,0.59110713,0.18369107],"study_design_scores_gemma":[0.0005050562,0.000075974305,0.0064132325,0.00034577973,0.000002260421,0.00008665122,0.00035740397,0.8766887,0.00021250104,0.0010822989,0.11385876,0.00037134998],"about_ca_topic_score_codex":0.0019412035,"about_ca_topic_score_gemma":0.00092276454,"teacher_disagreement_score":0.8460395,"about_ca_system_score_codex":0.00054202357,"about_ca_system_score_gemma":0.004801103,"threshold_uncertainty_score":0.99579495},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["open_science","scholarly_communication"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3048186973","doi":"10.5334/dsj-2020-043","title":"The CARE Principles for Indigenous Data Governance","year":2020,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","field":"Computer Science","cited_by":1206,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"Rural Development Administration; European Commission","keywords":"Indigenous; Sovereignty; Data governance; Data sharing; Corporate governance; Stewardship (theology); Political science; Public administration; Public relations; Sociology; Law; Business; Medicine; Data quality","score_opus":0.3437787918939087,"score_gpt":0.4254753768765994,"score_spread":0.08169658498269072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048186973","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":[0.0015069378,0.0030434958,0.9333755,0.05633418,0.0011302325,0.0008137605,0.0019504057,0.00008380703,0.0017617004],"genre_scores_gemma":[0.18816039,0.031801775,0.76883113,0.006244382,0.0031101126,0.00004126283,0.0010628107,0.00005429417,0.0006938366],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963055,0.00007221621,0.00031086727,0.0009715131,0.0016631427,0.0006767356],"domain_scores_gemma":[0.9930814,0.00035788614,0.0004000109,0.0055403477,0.00026985124,0.0003504913],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.0068816002,0.000107464744,0.000100379526,0.000045398636,0.0025999951,0.016631553,0.0692704,0.000016150067,0.000003322821],"category_scores_gemma":[0.0075646196,0.00006919435,0.000018080422,0.001027167,0.0003855879,0.105846316,0.023864495,0.00036182388,0.000027413933],"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":[0.00007383252,0.000084838844,0.0022948033,0.0000964118,0.00007883446,0.00016979195,0.0040458953,0.00024486193,0.0008598361,0.2047193,0.09816121,0.68917036],"study_design_scores_gemma":[0.00016361463,0.000084677915,0.0021488762,0.000010094387,0.000006029367,0.000039139355,0.0004993922,0.074632965,0.00008463098,0.000106277825,0.92211825,0.00010604477],"about_ca_topic_score_codex":0.000020736361,"about_ca_topic_score_gemma":0.000058257618,"teacher_disagreement_score":0.823957,"about_ca_system_score_codex":0.00008139827,"about_ca_system_score_gemma":0.0013922415,"threshold_uncertainty_score":0.9986985},"labels":[],"label_agreement":null},{"id":"W3111376437","doi":"10.5334/dsj-2020-047","title":"39 Hints to Facilitate the Use of Semantics for Data on Agriculture and Nutrition","year":2020,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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":"Agriculture and Agri-Food Canada; Rural Development Administration; Agence Nationale de la Recherche; Ministry of Agriculture of the People's Republic of China; Department for International Development; Bill and Melinda Gates Foundation","keywords":"Computer science; Semantic interoperability; Interoperability; Conceptualization; Linked data; Knowledge management; Data science; Semantics (computer science); World Wide Web; Data sharing; Standardization; Semantic Web","score_opus":0.29656193485514376,"score_gpt":0.34992526355676146,"score_spread":0.053363328701617696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111376437","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":[0.84240884,0.0008228849,0.08568249,0.06267826,0.00048704044,0.00055106846,0.0073239985,0.000012706904,0.000032707343],"genre_scores_gemma":[0.89669275,0.0014373641,0.09337672,0.0059624733,0.00078357576,0.000004925877,0.0016256318,0.000009126178,0.00010742525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999363,0.000015629625,0.00010602674,0.00024067496,0.00015982283,0.00011486633],"domain_scores_gemma":[0.9993479,0.00002865791,0.000051365405,0.00040047345,0.000067295055,0.00010427198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043803712,0.00004694858,0.00006122729,0.000013767467,0.00014578046,0.000081637234,0.0010298708,0.00003244594,0.0000012686311],"category_scores_gemma":[0.001631234,0.000025118024,0.00000977222,0.00010982173,0.00025464196,0.000022583088,0.0006291388,0.00007208018,7.3205496e-7],"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":[0.000130384,0.00005291786,0.0002454911,0.000029756542,0.000017504926,0.0000021386982,0.00025726113,0.000017251827,0.4129091,0.000026220172,0.53798175,0.04833025],"study_design_scores_gemma":[0.00024234877,0.0005657869,0.0011190581,0.000030631876,0.0000122842885,0.00003567033,0.00034199125,0.0026430208,0.009223532,0.000023806364,0.98569405,0.00006784405],"about_ca_topic_score_codex":0.000005255373,"about_ca_topic_score_gemma":0.0000063377606,"teacher_disagreement_score":0.4477123,"about_ca_system_score_codex":0.0000022750944,"about_ca_system_score_gemma":0.000045452973,"threshold_uncertainty_score":0.19528572},"labels":[],"label_agreement":null},{"id":"W3127642832","doi":"10.5334/dsj-2021-007","title":"Stewardship Maturity Assessment Tools for Modernization of Climate Data Management","year":2021,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Climate variability and models","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Environment and Climate Change Canada; Centrum fÖr Personcentrerad Vård; National Centers for Environmental Information; National Oceanic and Atmospheric Administration; Grains Research and Development Corporation; National Aeronautics and Space Administration","keywords":"Stewardship (theology); Data management; Maturity (psychological); Scope (computer science); Data quality; Computer science; Process (computing); Quality (philosophy); Usability; Process management; Environmental resource management; Business; Data science; Database; Environmental science; Political science","score_opus":0.13297788638193198,"score_gpt":0.36953920862532325,"score_spread":0.23656132224339127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127642832","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":[0.22658762,0.00012285927,0.7437834,0.0023945644,0.0015558333,0.0009831034,0.008196896,0.00004619704,0.016329518],"genre_scores_gemma":[0.6832484,0.0024176042,0.312406,0.00024125894,0.00008525471,0.0000067125156,0.0015234066,0.000012955822,0.000058413658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978228,0.00003834646,0.00036330865,0.00060510833,0.0008156914,0.00035473588],"domain_scores_gemma":[0.99761957,0.00011549808,0.00018728542,0.0018944909,0.00005420211,0.00012896961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00494847,0.00008953389,0.00013859192,0.000041261035,0.00045824223,0.000427813,0.0026607357,0.000029424764,0.0006552727],"category_scores_gemma":[0.00030463695,0.00007914195,0.000024236855,0.00040941214,0.0002788423,0.0051779095,0.0049042483,0.00012769418,0.000012335709],"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":[0.00023506844,0.0034585593,0.082526915,0.0008736347,0.00020663963,0.00012561367,0.00092652,0.122751325,0.07437627,0.029288413,0.02493816,0.66029286],"study_design_scores_gemma":[0.0006390645,0.00004659519,0.056096498,0.0000632916,0.000106863605,0.00008169524,0.0005826178,0.9182319,0.0008006504,0.003402154,0.019718748,0.0002299384],"about_ca_topic_score_codex":0.0000140904995,"about_ca_topic_score_gemma":0.000036851463,"teacher_disagreement_score":0.79548055,"about_ca_system_score_codex":0.00015657248,"about_ca_system_score_gemma":0.00012569969,"threshold_uncertainty_score":0.7174777},"labels":[],"label_agreement":null},{"id":"W4301396488","doi":"10.5334/dsj-2022-017","title":"A Survey on Publicly Available Open Datasets Derived From Electronic Health Records (EHRs) of Patients with Neuroblastoma","year":2022,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Neuroblastoma Research and Treatments","field":"Medicine","cited_by":9,"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":"Neuroblastoma; Computer science; Health records; Open science; License; The Internet; Electronic health record; Open data; World Wide Web; Internet privacy; Medicine; Information retrieval; Data mining; Political science; Mathematics; Statistics; Health care","score_opus":0.07305559528067233,"score_gpt":0.3504970068041415,"score_spread":0.27744141152346913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301396488","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":[0.9797359,0.00004012203,0.000016941445,0.00066296215,0.00012907841,0.000570018,0.018705366,0.000009823865,0.0001297909],"genre_scores_gemma":[0.98907214,0.000072375595,0.00047229647,0.0008504962,0.000024975385,0.000010168631,0.009386744,0.000020367184,0.00009043954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99595815,0.00036549632,0.00035063556,0.00070804957,0.0018347014,0.000782961],"domain_scores_gemma":[0.9972745,0.00012104836,0.00037096912,0.0014344697,0.00020282436,0.0005961609],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028570574,0.00014935827,0.00032222274,0.00033727268,0.00090120675,0.00028547406,0.0027419995,0.000011490333,0.0014529999],"category_scores_gemma":[0.00049174746,0.00010930303,0.00002019123,0.001281552,0.00022504393,0.0016055442,0.0024347277,0.00069991924,0.000043827524],"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":[0.008404824,0.00473583,0.6944162,0.000017032367,0.00018629867,0.00027551482,0.00008853035,0.000025323781,0.0015451256,0.000014213309,0.27174625,0.01854486],"study_design_scores_gemma":[0.0047388417,0.010359891,0.9714262,0.00004344098,0.000016773465,0.000085299514,0.00003786686,0.00033088328,0.0005484685,0.0000127575195,0.012283739,0.000115850686],"about_ca_topic_score_codex":0.00360217,"about_ca_topic_score_gemma":0.0016346319,"teacher_disagreement_score":0.27701,"about_ca_system_score_codex":0.00040260685,"about_ca_system_score_gemma":0.005009867,"threshold_uncertainty_score":0.9994598},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4380538161","doi":"10.5334/dsj-2023-015","title":"Legal Regulation of State Electronic Services: Relevant Issues and Ways of Improvement","year":2023,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Corruption and Economic Development","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":"Government (linguistics); Business; Politics; Public relations; Public sector; Quality (philosophy); State (computer science); Order (exchange); Service (business); Public administration; The Republic; Political science; Marketing; Computer science; Law; Finance","score_opus":0.05167142070269107,"score_gpt":0.3291735194967818,"score_spread":0.2775020987940907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380538161","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":[0.99325943,0.00004156477,0.00011991506,0.0052578007,0.0002292367,0.00008061459,0.000022357304,0.000013374922,0.0009757307],"genre_scores_gemma":[0.9974339,0.0014766034,0.00046911777,0.00017218279,0.000058382353,5.66561e-7,0.000012024168,0.000002218717,0.00037499485],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989079,0.000017362405,0.00026247738,0.00015426126,0.00039552682,0.00026244155],"domain_scores_gemma":[0.9994328,0.00001900965,0.00020483755,0.0001734121,0.000099123565,0.00007078946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039565586,0.000038711856,0.00008365617,0.00015229311,0.00033318327,0.0001137984,0.0005497718,0.0000147962555,0.000087937566],"category_scores_gemma":[0.000056450885,0.000034254066,0.000010199253,0.00043187296,0.00028259135,0.001272763,0.00020551209,0.000078135046,0.000010104418],"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":[0.00007934333,0.00010906601,0.01775118,0.0001322055,0.000057706893,0.000009594992,0.05337938,0.0003022764,0.16440149,0.06989039,0.00730984,0.68657756],"study_design_scores_gemma":[0.00081468065,0.0003012698,0.15525462,0.00015867333,0.000022338983,0.000022910752,0.025683524,0.018449498,0.0060734074,0.01516942,0.77769524,0.00035442694],"about_ca_topic_score_codex":0.00075574545,"about_ca_topic_score_gemma":0.0007673367,"teacher_disagreement_score":0.7703854,"about_ca_system_score_codex":0.0000988856,"about_ca_system_score_gemma":0.00063144683,"threshold_uncertainty_score":0.256261},"labels":[],"label_agreement":null},{"id":"W4382141301","doi":"10.5334/dsj-2023-018","title":"Polar Data Forum IV – An Ocean of Opportunities","year":2023,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Inuvialuit Regional Corporation; Nunavut Research Institute; University of Calgary","funders":"LifeWatch – Niclas Öberg Foundation; Belgian Federal Science Policy Office","keywords":"Interoperability; Polar; Data management; Computer science; Library science; World Wide Web; Data science; Database","score_opus":0.5412294111931125,"score_gpt":0.46077708226501984,"score_spread":0.08045232892809268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382141301","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":[0.13478158,0.0007322101,0.7074738,0.11750337,0.006402428,0.0011272922,0.011252196,0.00085922977,0.019867856],"genre_scores_gemma":[0.7515243,0.01730854,0.21960275,0.002106031,0.0009529655,0.0000028158333,0.0058683385,0.00005537063,0.0025788373],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956493,0.00016258124,0.0003922172,0.0008428774,0.0022253788,0.0007276489],"domain_scores_gemma":[0.9908743,0.00015288006,0.00035123402,0.007964422,0.00022919365,0.0004279974],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.018040523,0.00011133259,0.00014574129,0.0009064993,0.00074401434,0.00653685,0.051074214,0.000021006266,0.00003188833],"category_scores_gemma":[0.0021682724,0.000092578994,0.000015436563,0.0024287964,0.00061286683,0.2749197,0.02690796,0.00032382054,0.00004998841],"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":[0.00002371671,0.00041565878,0.012172206,0.0000623186,0.00007394336,0.0009971892,0.00055270706,0.00009248458,0.0032442787,0.2372533,0.5734704,0.1716418],"study_design_scores_gemma":[0.0003182186,0.00027627463,0.011687615,0.000053052554,0.000015869871,0.0003168738,0.004246083,0.40340614,0.0002224879,0.0025943043,0.5765502,0.00031287188],"about_ca_topic_score_codex":0.00009234218,"about_ca_topic_score_gemma":0.000031347627,"teacher_disagreement_score":0.61674273,"about_ca_system_score_codex":0.00003045955,"about_ca_system_score_gemma":0.0010333975,"threshold_uncertainty_score":0.99449444},"labels":[{"model":"gemma","categories":["scholarly_communication"],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4386830764","doi":"10.5334/dsj-2023-035","title":"Umbrella Data Management Plans to Integrate FAIR Data: Lessons From the ISIDORe and BY-COVID Consortia for Pandemic Preparedness","year":2023,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Preparedness; Data management; Computer science; Multidisciplinary approach; Plan (archaeology); Download; Process (computing); Data management plan; Data science; Process management; Knowledge management; Engineering management; World Wide Web; Business; Engineering; Political science; Geography; Database","score_opus":0.43034568833391706,"score_gpt":0.48834636250226554,"score_spread":0.058000674168348476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386830764","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":[0.007924392,0.00038265844,0.89552104,0.045440495,0.0011632221,0.0012496094,0.04769893,0.00019640458,0.00042322715],"genre_scores_gemma":[0.33050996,0.07910057,0.46854258,0.020395124,0.002579436,0.00031218547,0.09261571,0.00020590032,0.0057385247],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99460465,0.00019630945,0.00045698564,0.0023845981,0.0015051971,0.0008522715],"domain_scores_gemma":[0.9871954,0.0010694292,0.00029233177,0.01085734,0.00011681157,0.0004686951],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.018114448,0.00020920412,0.00020698682,0.00029965286,0.0014741666,0.01234649,0.0605602,0.000033724227,0.000011258881],"category_scores_gemma":[0.0030227124,0.00014068585,0.000015441365,0.0019156693,0.00052056194,0.057475705,0.058726847,0.0004146619,0.00006275514],"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":[0.000038122475,0.00004640682,0.0015623563,0.000025442028,0.000098170545,0.00008164605,0.00046501172,0.00004189485,0.0005124847,0.0082652075,0.92726743,0.0615958],"study_design_scores_gemma":[0.00047026496,0.000054778648,0.0037388315,0.00008534134,0.000055969584,0.00006942753,0.003096505,0.15674263,0.000019872927,0.0012562539,0.8341447,0.00026538182],"about_ca_topic_score_codex":0.0002910757,"about_ca_topic_score_gemma":0.00064453273,"teacher_disagreement_score":0.42697847,"about_ca_system_score_codex":0.00008032258,"about_ca_system_score_gemma":0.00053901714,"threshold_uncertainty_score":0.9998258},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4401463404","doi":"10.5334/dsj-2024-042","title":"Decentralised Semantics: A Semantic Engine User Perspective","year":2024,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"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":"Canada First Research Excellence Fund","keywords":"Computer science; Perspective (graphical); Semantics (computer science); Information retrieval; Semantic computing; World Wide Web; Semantic Web; Programming language; Artificial intelligence","score_opus":0.040953870980605905,"score_gpt":0.3302790571581251,"score_spread":0.28932518617751923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401463404","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":[0.034157045,0.0043866695,0.9296539,0.022678563,0.0063946336,0.00019549,0.000034367364,0.00055070274,0.0019486361],"genre_scores_gemma":[0.92006165,0.00057987496,0.078302726,0.00041678202,0.00045684344,0.0000014408967,0.0000044409244,0.000011866394,0.0001643617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997281,0.00004127291,0.00028471622,0.0007868195,0.0009294889,0.000676701],"domain_scores_gemma":[0.9979569,0.00012730538,0.00006870571,0.0013413115,0.0002451685,0.00026061275],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002198078,0.00016844872,0.00018267627,0.0004687434,0.0004819443,0.0034966914,0.006216246,0.00004078367,0.000053088406],"category_scores_gemma":[0.00054296886,0.0001230149,0.000059204798,0.0017019354,0.00040439196,0.0071179494,0.0013836221,0.00040908245,0.00018042926],"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":[0.000017212673,0.0002724361,0.0031861996,0.000103534316,0.00019479092,0.0042387117,0.010366614,0.00029682732,0.01349351,0.79741937,0.095570974,0.074839845],"study_design_scores_gemma":[0.00054025673,0.00016864289,0.010839489,0.00040472133,0.00007521008,0.006940324,0.0027521343,0.88224393,0.0038691498,0.025999397,0.06540945,0.0007572723],"about_ca_topic_score_codex":0.000041036354,"about_ca_topic_score_gemma":0.000018637713,"teacher_disagreement_score":0.8859046,"about_ca_system_score_codex":0.00017176814,"about_ca_system_score_gemma":0.0009449071,"threshold_uncertainty_score":0.9991606},"labels":[],"label_agreement":null},{"id":"W4402883940","doi":"10.5334/dsj-2024-046","title":"Knowledge Infrastructures Are Growing Up: The Case for Institutional (Data) Repositories 10 Years After the Holdren Memo","year":2024,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Research Data Management Practices","field":"Computer Science","cited_by":5,"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":"University at Buffalo; University of Minnesota","keywords":"Computer science; Business; World Wide Web; Data science","score_opus":0.13277524692396442,"score_gpt":0.407377605795062,"score_spread":0.2746023588710976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402883940","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":[0.08161543,0.01645269,0.7887615,0.07082103,0.030632913,0.0021133951,0.0053322227,0.00040169235,0.0038690965],"genre_scores_gemma":[0.97022635,0.00058557116,0.024389286,0.0005651977,0.0029286363,0.00003884304,0.00016500254,0.000017635217,0.0010834704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731934,0.00014329882,0.00029008157,0.0007977821,0.0009836063,0.0004658871],"domain_scores_gemma":[0.9955194,0.0005715686,0.00014336784,0.0034215697,0.00020050662,0.00014358832],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.009147289,0.00012888218,0.0000949206,0.00023987488,0.0020611666,0.025484992,0.017621446,0.000026653779,0.000026356012],"category_scores_gemma":[0.0024214832,0.00006868741,0.00003661862,0.0013690771,0.0009493338,0.10358251,0.008841521,0.0005360123,0.0000277457],"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":[0.00007762791,0.000063966094,0.00050167966,0.00011377502,0.00021094504,0.007416906,0.0024728652,0.00025008604,0.0005179262,0.16718715,0.6434868,0.17770028],"study_design_scores_gemma":[0.00013203204,0.000033173237,0.0045434977,0.00008413425,0.000038017304,0.010682979,0.00068244594,0.08267478,0.00008837073,0.0018399305,0.89903635,0.0001642667],"about_ca_topic_score_codex":0.00004153354,"about_ca_topic_score_gemma":0.0000939319,"teacher_disagreement_score":0.8886109,"about_ca_system_score_codex":0.00009268914,"about_ca_system_score_gemma":0.0010384906,"threshold_uncertainty_score":0.999238},"labels":[],"label_agreement":null}]}