{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":12,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":12,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"8953a914060a","filters":{"venue":"Data Intelligence"}},"results":[{"id":"W2988998130","doi":"10.1162/dint_r_00024","title":"FAIR Principles: Interpretations and Implementation Considerations","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":459,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Biotechnology and Biological Sciences Research Council; European Regional Development Fund; Horizon 2020 Framework Programme; Innovative Medicines Initiative; National Institutes of Health; National Science Foundation; Ministerio de Economía y Competitividad; Common Fund; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; European Commission; Universidad Politécnica de Madrid","keywords":"Implementation; Interoperability; Computer science; Reusability; USable; Fair use; Reuse; Stakeholder; Convergence (economics); Risk analysis (engineering); Data science; Management science; Software engineering; World Wide Web; Business; Engineering; Political science; Public relations; Software; Law; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.2135019208723,"gpt":0.4376810240360997,"spread":0.2241791031637997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007842351,0.00008590251,0.00007872999,0.0001283835,0.00011522,0.002064488,0.001949318,0.00001759932,0.0002291715],"category_scores_gemma":[0.0004908955,0.00008303223,0.000009426699,0.0002384644,0.00004974555,0.030371,0.002955171,0.0001136881,0.000360954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002022336,"about_ca_system_score_gemma":0.00007753687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000130014,"about_ca_topic_score_gemma":0.0002163334,"domain_scores_codex":[0.9986019,0.0000916307,0.0002488604,0.0005908955,0.0002738547,0.0001928906],"domain_scores_gemma":[0.9972207,0.0004851563,0.00009904593,0.002053975,0.00007327079,0.00006787247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001215918,0.00001942568,0.002299073,0.00002128371,0.00002152211,0.000004526263,0.0003904269,0.00005609429,0.0001139016,0.9754397,0.001223473,0.02040932],"study_design_scores_gemma":[0.0002949834,0.0002883842,0.01424445,0.00008083291,0.00003394667,0.00006811807,0.00421137,0.5950091,0.00350402,0.02948134,0.3520832,0.0007002397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003090768,0.00007946233,0.9898286,0.002583777,0.0001631397,0.0004797537,0.0001615506,0.00008211775,0.003530796],"genre_scores_gemma":[0.8926328,0.000568666,0.1052161,0.0005619911,0.00001901996,0.00003034075,0.0005144855,0.000006780319,0.0004498043],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9459584,"threshold_uncertainty_score":0.9989715,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3017715546","doi":"10.1162/dint_a_00058","title":"The Semantic Data Dictionary – An Approach for Describing and Annotating Data","year":2020,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"CARE Canada; Privacy Analytics (Canada)","funders":"National Institute of Environmental Health Sciences","keywords":"Computer science; Natural language processing; Data dictionary; Information retrieval; Artificial intelligence; World Wide Web; Metadata","retraction":null,"screen_n_in":null,"score":{"opus":0.3725294609797752,"gpt":0.3740642515334556,"spread":0.001534790553680387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006288765,0.000100361,0.0000899005,0.000006989841,0.0002559689,0.00008880169,0.002943313,0.00007203253,0.000001490444],"category_scores_gemma":[0.001786921,0.00007213671,0.000007798151,0.00006580591,0.0002396104,0.00002846826,0.003565083,0.00009581059,0.000001584401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001521155,"about_ca_system_score_gemma":0.00004350666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002456848,"about_ca_topic_score_gemma":0.00001774558,"domain_scores_codex":[0.998675,0.0000474742,0.0001815064,0.0008076727,0.0000980488,0.0001903007],"domain_scores_gemma":[0.9974102,0.0001049195,0.00005673081,0.002309199,0.00002812066,0.00009083242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001168812,0.00005674204,0.0010786,0.00008757353,0.00008999468,0.000003050153,0.000192302,0.00002838982,0.009267421,0.000160715,0.04346825,0.9454501],"study_design_scores_gemma":[0.00009489647,0.0002253617,0.0001493209,0.00001716744,0.00004184507,0.00002564718,0.002287391,0.7125035,0.001492657,0.00007274091,0.2828795,0.0002099846],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005820891,0.004310057,0.983942,0.001306311,0.0001128483,0.0002144352,0.004183926,0.00003595827,0.00007356018],"genre_scores_gemma":[0.6566525,0.002302815,0.2389399,0.001357423,0.0009804609,0.00001998055,0.09966188,0.00003631598,0.00004877497],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9452401,"threshold_uncertainty_score":0.5469457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2985716559","doi":"10.1162/dint_a_00039","title":"The FAIR Funding Model: Providing a Framework for Research Funders to Drive the Transition toward FAIR Data Management and Stewardship Practices","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institutes of Health Research; Stroke Association","keywords":"RDM; Stewardship (theology); Metadata; Business; Work (physics); Process management; Knowledge management; Data curation; Public relations; Computer science; Political science; Data science; Engineering; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.6366391164030468,"gpt":0.5222957442909713,"spread":0.1143433721120756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.01791815,0.0002219901,0.0001731686,0.0002385108,0.001122773,0.008857303,0.02123163,0.00006908304,0.000005284168],"category_scores_gemma":[0.004552661,0.0001462236,0.00002717739,0.001127894,0.0002170825,0.02980392,0.0165792,0.0007369742,0.00009459711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001035649,"about_ca_system_score_gemma":0.0001357348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001669852,"about_ca_topic_score_gemma":0.0001573083,"domain_scores_codex":[0.9946018,0.0005481746,0.0004079823,0.001893983,0.001564014,0.0009840013],"domain_scores_gemma":[0.9839373,0.006520191,0.0003140147,0.00881659,0.0002186712,0.0001932544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001467061,0.00005758339,0.00004987448,0.0003140494,0.0001484991,0.000009037091,0.002330796,0.001637217,0.00003175993,0.905736,0.008088593,0.08144993],"study_design_scores_gemma":[0.0000776429,0.000187382,0.00004585335,0.0001692774,0.00003192381,0.000004542175,0.01516157,0.8042773,0.0001248011,0.0503703,0.1293103,0.0002391201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003935784,0.0003360057,0.9507126,0.0437279,0.0002657209,0.003477137,0.0002849869,0.0000856823,0.0007163619],"genre_scores_gemma":[0.5451079,0.005273304,0.4464852,0.001122645,0.0001846525,0.0005004188,0.000525199,0.00004724578,0.0007534878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8553656,"threshold_uncertainty_score":0.9921716,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2988604061","doi":"10.1162/dint_a_00029","title":"Ontology-based Access Control for FAIR Data","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Metadata; Computer science; Ontology; Access control; Data access; Metadata repository; Database; World Wide Web; Information retrieval; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.5944593014190421,"gpt":0.5293744523263445,"spread":0.06508484909269763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01004135,0.0001601267,0.0003069869,0.0002374163,0.0001572851,0.001295984,0.02443566,0.00005429002,0.001173045],"category_scores_gemma":[0.008245149,0.0001199009,0.00004595707,0.0007129614,0.0001309705,0.001747872,0.005540103,0.000111249,0.003059511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001812379,"about_ca_system_score_gemma":0.0001356654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001399566,"about_ca_topic_score_gemma":0.00024211,"domain_scores_codex":[0.9955063,0.0001264602,0.0007087005,0.002220654,0.001034978,0.0004028915],"domain_scores_gemma":[0.9816203,0.00370273,0.0002810382,0.01402942,0.0002547548,0.0001117299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008661739,0.00009426459,0.007199517,0.00001814175,0.00002488346,0.000003750117,0.00002643152,0.002296967,0.00002071644,0.004119201,0.6875322,0.2985773],"study_design_scores_gemma":[0.0001477793,0.00002937397,0.000702539,0.00001129573,0.00001201113,8.585429e-7,0.0001048161,0.5210217,0.0000597101,0.00367129,0.4741215,0.0001171986],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00173027,0.00008323089,0.9822123,0.001909632,0.002943168,0.0007439051,0.008568696,0.00007782882,0.001730937],"genre_scores_gemma":[0.9691374,0.000005367906,0.01836051,0.002751429,0.000181567,0.0000194478,0.006961357,0.00001630442,0.00256662],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9674071,"threshold_uncertainty_score":0.9997408,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2987816848","doi":"10.1162/dint_a_00051","title":"Considerations for the Conduction and Interpretation of FAIRness Evaluations","year":2019,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institutes of Health; Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Metadata; Interpretation (philosophy); Computer science; Maturity (psychological); Software; Psychology; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.3344731620481542,"gpt":0.4639573840777451,"spread":0.1294842220295909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001494225,0.00004863153,0.0000630218,0.00006423175,0.0001018516,0.0006657765,0.001297401,0.00001461041,0.00003312522],"category_scores_gemma":[0.002474113,0.00003607065,0.00001029853,0.0001705648,0.00007635682,0.01503998,0.0007868434,0.00006013861,0.00002020985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000840621,"about_ca_system_score_gemma":0.00005703436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005970784,"about_ca_topic_score_gemma":0.00003958477,"domain_scores_codex":[0.9991319,0.00008219641,0.0001826174,0.0003018903,0.0002131783,0.00008828349],"domain_scores_gemma":[0.9957891,0.002431141,0.0001141801,0.001455265,0.0001913816,0.00001891971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000745235,0.00002304072,0.0001511016,0.00004287186,0.00003662192,1.523611e-7,0.0003885734,0.001045423,0.0006324688,0.9252445,0.001255688,0.07117212],"study_design_scores_gemma":[0.0000463453,0.00005111175,0.0003607399,0.00001423039,0.00001572069,0.000003572361,0.0004270641,0.9732703,0.001679793,0.01887706,0.00520323,0.00005085141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001017434,0.0001432831,0.9947752,0.002787072,0.000228382,0.0006621737,0.0001115842,0.00001645876,0.0002584281],"genre_scores_gemma":[0.9632362,0.0003051998,0.0360461,0.0001026657,0.00001356748,0.00004368914,0.0001086855,0.000002832317,0.0001410831],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9722248,"threshold_uncertainty_score":0.9987361,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400522920","doi":"10.1162/dint_a_00255","title":"FAIR Enough: Develop and Assess a FAIR-Compliant Dataset for Large Language Model Training?","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; Toronto Metropolitan University; Vector Institute","funders":"Government of Canada; Canadian Institute for Advanced Research","keywords":"Stewardship (theology); Computer science; Context (archaeology); Interoperability; Frame (networking); Process (computing); Work (physics); Engineering ethics; Knowledge management; Process management; Accreditation; Checklist; Data science; Risk analysis (engineering); Political science; Business; Engineering; Psychology; World Wide Web; Medical education; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.3962006214895893,"gpt":0.4654284737358328,"spread":0.0692278522462435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00269819,0.0002052829,0.0001878785,0.0001562742,0.000180138,0.004148574,0.006409768,0.000049338,0.00001993199],"category_scores_gemma":[0.001224741,0.0001822166,0.0000197869,0.0006260299,0.00006392137,0.02551872,0.005568637,0.000263095,0.000108036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003186255,"about_ca_system_score_gemma":0.0002529285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000757524,"about_ca_topic_score_gemma":0.0001289749,"domain_scores_codex":[0.9972439,0.00007975441,0.0003179701,0.001306568,0.000460068,0.0005917808],"domain_scores_gemma":[0.9961771,0.0007432081,0.00006632492,0.002793728,0.00006557247,0.0001540747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001469289,0.00008869802,0.00001089966,0.0004503621,0.0001062552,0.0002261223,0.002427848,0.00009579117,0.0002428567,0.7147921,0.1145727,0.1669717],"study_design_scores_gemma":[0.00003771304,0.00002775039,0.000009180864,0.00004941401,0.00001073402,0.00001699268,0.000521019,0.6087494,0.000216032,0.001386255,0.3888081,0.0001673479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001305821,0.0008504866,0.9582657,0.00201164,0.0001810255,0.0004458553,0.03762138,0.0001686807,0.000324657],"genre_scores_gemma":[0.157155,0.001880926,0.7866951,0.001313735,0.0001756158,0.0001988503,0.0514195,0.00005579933,0.001105479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7134058,"threshold_uncertainty_score":0.998966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3128327914","doi":"10.1162/dint_a_00086","title":"Implementation of an Open Science Instruction Program for Undergraduates","year":2021,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Transparency (behavior); Curriculum; Context (archaeology); Best practice; Political science; Undergraduate research; Subject (documents); Medical education; Public relations; Engineering ethics; Pedagogy; Engineering; Library science; Sociology; Computer science; Medicine; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.4297001939532424,"gpt":0.566531096562857,"spread":0.1368309026096147,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00800633,0.00007853307,0.0001434633,0.0002031577,0.0003043875,0.001796128,0.007762128,0.00001551574,0.0001822561],"category_scores_gemma":[0.002926831,0.00006535561,0.00001951796,0.002180117,0.0002923254,0.002709247,0.004877346,0.00003913296,0.00003023475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002669313,"about_ca_system_score_gemma":0.0003751633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003642582,"about_ca_topic_score_gemma":0.0008492616,"domain_scores_codex":[0.9968271,0.00007595629,0.0006004564,0.00121624,0.001055495,0.0002247959],"domain_scores_gemma":[0.9953358,0.0003121794,0.0002644254,0.003165444,0.0008366208,0.00008559757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006586048,0.00008754764,0.0004699044,0.00000494292,0.000004159124,7.377477e-7,0.0001085229,0.00008088726,0.0005524742,0.0133612,0.003356514,0.9819666],"study_design_scores_gemma":[0.0005341182,0.0006954909,0.01448792,0.00005261578,0.00004564849,0.00002851885,0.03813607,0.2675488,0.2381046,0.2196857,0.2201939,0.0004866743],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3737818,0.00005269259,0.6177576,0.001324053,0.002642539,0.001672,0.00148604,0.00008744765,0.001195864],"genre_scores_gemma":[0.8259382,0.000009141147,0.172618,0.00007262376,0.00004421727,0.00002947855,0.001094454,0.000005420278,0.0001885102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9814798,"threshold_uncertainty_score":0.9992401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394770144","doi":"10.1162/dint_a_00251","title":"LLaMA-LoRA Neural Prompt Engineering: A Deep Tuning Framework for Automatically Generating Chinese Text Logical Reasoning Thinking Chains","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Language model; Artificial intelligence; Natural language processing; Comprehension; Benchmark (surveying); Inference; Logical reasoning; Question answering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05625293307651095,"gpt":0.3232568566701648,"spread":0.2670039235936538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001106047,0.0003176679,0.0002914296,0.0001431361,0.0002597574,0.00139777,0.003377257,0.0001547546,0.00002633889],"category_scores_gemma":[0.002502077,0.0002659875,0.00008478696,0.0006251409,0.00003783749,0.00116193,0.001742609,0.0006127355,0.00003385982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006460859,"about_ca_system_score_gemma":0.00008712547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001609691,"about_ca_topic_score_gemma":0.000005948466,"domain_scores_codex":[0.9971735,0.00004941391,0.0005659973,0.001151621,0.0004398119,0.0006196663],"domain_scores_gemma":[0.9970775,0.0009889175,0.00008214969,0.00161837,0.00007446998,0.0001586336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004448858,0.00003139543,0.0001003634,0.0002606503,0.00004426127,0.0001054448,0.003939926,0.1015982,0.0006395959,0.672863,0.00006469194,0.220348],"study_design_scores_gemma":[0.00002344289,0.0000465099,0.000037527,0.0004467017,0.00001000195,0.0000722141,0.00004989273,0.9839883,0.0001097163,0.01449052,0.0004102202,0.0003149078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007559526,0.0009479024,0.9880491,0.0008340873,0.001095698,0.0003753329,0.00002087379,0.001071877,0.00004562119],"genre_scores_gemma":[0.3681177,0.00001030696,0.6310749,0.0002167997,0.0004560454,0.00004028619,0.00004478011,0.00002491692,0.00001428715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8823901,"threshold_uncertainty_score":0.9999793,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380629788","doi":"10.1162/dint_a_00209","title":"MillenniumDB: An Open-Source Graph Database System","year":2023,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Agencia Nacional de Investigación y Desarrollo; Pontificia Universidad Católica de Chile; Universidad de Chile; University of Waterloo; University of Toronto; University of Galway; National University of Ireland; Universidad Técnica Federico Santa María","keywords":"Computer science; Graph database; Query language; Query optimization; Graph; Search engine indexing; Information retrieval; Theoretical computer science; Joins; Database; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.103571274253965,"gpt":0.3299497707628121,"spread":0.2263784965088471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001874576,0.0002059854,0.0002093294,0.0002375164,0.0003381568,0.0006767775,0.0155489,0.00005682358,0.00002909577],"category_scores_gemma":[0.00009347333,0.0001879071,0.00002957113,0.001927036,0.0001098597,0.003488056,0.007432122,0.0002000332,0.00165006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001533166,"about_ca_system_score_gemma":0.00005207317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001941676,"about_ca_topic_score_gemma":0.00002540352,"domain_scores_codex":[0.9974902,0.0002118335,0.0003376935,0.001140662,0.0003452529,0.0004743551],"domain_scores_gemma":[0.9940581,0.0001832105,0.00009789443,0.005356268,0.0000672674,0.0002372038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001925341,0.0001714429,0.0001001733,0.0001110828,0.0000444868,0.0003081641,0.00106277,0.0005354655,0.0009888925,0.7422851,0.01861267,0.2357605],"study_design_scores_gemma":[0.0001716082,0.0002415073,0.0001827919,0.000250942,0.00002045112,0.0001612239,0.002411721,0.8856417,0.007564248,0.01378729,0.08866376,0.0009027428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002325875,0.0001515445,0.9937018,0.0001651721,0.0008273906,0.0002953785,0.0006439297,0.001033535,0.0008554342],"genre_scores_gemma":[0.8434447,0.0006604272,0.1464206,0.001248544,0.0004747573,0.0001395158,0.006068058,0.0001101151,0.001433295],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8851063,"threshold_uncertainty_score":0.9991273,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400831116","doi":"10.3724/2096-7004.di.2024.0002","title":"Risk Factors Categorizations of Ischemic Heart Disease in South-Western Bangladesh","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Disease; Voting; Population; Actuarial science; Medicine; Geography; Environmental health; Demography; Business; Political science; Pathology; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.2185347216657957,"gpt":0.4789780423696013,"spread":0.2604433207038056,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008533082,0.0002296059,0.0003237283,0.0002957312,0.0002707774,0.00002712318,0.001035535,0.0001959523,0.0007866237],"category_scores_gemma":[0.001837219,0.0002072089,0.00005707052,0.0009464119,0.0001807115,0.000534165,0.0005769018,0.001083101,0.001403114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001474459,"about_ca_system_score_gemma":0.0007300884,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008654701,"about_ca_topic_score_gemma":0.003002798,"domain_scores_codex":[0.9967209,0.0004176026,0.001186698,0.0007420441,0.0003395486,0.0005932105],"domain_scores_gemma":[0.9962932,0.001522759,0.0001883891,0.001551704,0.0001677157,0.0002761695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002772244,0.00005084317,0.9782073,0.0006021496,0.00001332718,0.00001402946,0.01327852,0.0003386103,0.0001212701,0.00162432,0.004749198,0.0009727202],"study_design_scores_gemma":[0.0002010191,0.0003273332,0.2351964,0.007615672,0.0004091508,0.000004250732,0.07226726,0.2986672,0.009782171,0.0198892,0.3529499,0.002690479],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9501914,0.002907013,0.03113542,0.001526163,0.00263298,0.001608851,0.009215719,0.0003408202,0.0004416289],"genre_scores_gemma":[0.9972646,0.0002587005,0.0002424946,0.0002304005,0.0002209851,0.00007487992,0.001310215,0.00004810042,0.000349586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7430109,"threshold_uncertainty_score":0.9993744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390025222","doi":"10.1162/dint_a_00240","title":"BIKAS: Bio-Inspired Knowledge Acquisition and Simulacrum—A Knowledge Database to Support Multifunctional Design Concept Generation","year":2023,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Design Education and Practice","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Simulacrum; Computer science; Knowledge acquisition; Knowledge management; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2012791044468487,"gpt":0.3756119567879984,"spread":0.1743328523411497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007918277,0.0001922468,0.0001389144,0.0002457061,0.000148409,0.0001352672,0.0003937603,0.00007711719,0.000670239],"category_scores_gemma":[0.0003494569,0.0002094464,0.00001722395,0.0007623706,0.00004825576,0.0009595189,0.0002037131,0.0001407047,0.005074508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006204692,"about_ca_system_score_gemma":0.00009950766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001465293,"about_ca_topic_score_gemma":0.00002893878,"domain_scores_codex":[0.9986792,0.0001135252,0.0003122772,0.0004767966,0.0001466207,0.0002715675],"domain_scores_gemma":[0.9984293,0.0004761004,0.00003617004,0.0007370008,0.0001247289,0.0001966898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004596557,0.0001657273,0.00008901494,0.0001052193,0.00007011827,0.0000123691,0.003451882,0.03906659,0.03409231,0.001032961,0.676435,0.2454328],"study_design_scores_gemma":[0.000108069,0.00007699613,0.0002681648,0.00002961492,0.0000299167,0.00001202073,0.0003567434,0.7340699,0.02203241,0.00003667229,0.2426665,0.0003129389],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004702853,0.0006878944,0.9886681,0.0002387371,0.002476477,0.0005494689,0.001118079,0.0006619183,0.0008964891],"genre_scores_gemma":[0.9663575,0.0006595974,0.0162229,0.0003714528,0.001026551,0.0001110527,0.01369883,0.00007553224,0.001476563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9724452,"threshold_uncertainty_score":0.9957002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312713146","doi":"10.1162/dint_x_00187","title":"About The Author","year":2022,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.1516575294259257,"gpt":0.4242079873297074,"spread":0.2725504579037817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001573716,0.00004118665,0.00004544771,0.00002101269,0.001533936,0.00007043342,0.001888933,0.00001446785,0.003235935],"category_scores_gemma":[0.0006013521,0.00003140588,0.00001702371,0.0003388726,0.0001424404,0.00017327,0.0007434152,0.0002924177,0.0002095983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002935025,"about_ca_system_score_gemma":0.0003226913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007426509,"about_ca_topic_score_gemma":0.0003980868,"domain_scores_codex":[0.9988583,0.0002820373,0.0001052358,0.0001912649,0.0003683763,0.0001947591],"domain_scores_gemma":[0.9991383,0.0001906107,0.00004510198,0.0005531164,0.00002097639,0.00005191869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007914538,0.00004504317,0.0009678985,0.000002449335,0.0000101073,0.000009833828,0.01003417,0.000212101,0.00001012899,0.1549231,0.07502278,0.7587545],"study_design_scores_gemma":[0.000005525534,0.00001390125,0.00002627609,0.00000154925,0.000003438201,0.000001081489,0.03227407,0.0008010985,0.0000107745,0.001299652,0.9655135,0.00004910568],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.07775372,0.01181031,0.06315175,0.2782787,0.01296564,0.002565631,0.003020818,0.001474303,0.5489792],"genre_scores_gemma":[0.9687074,0.0004387457,0.003691026,0.002312992,0.001128927,0.00004778073,0.0005663466,0.00001878722,0.02308803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8909537,"threshold_uncertainty_score":0.9997659,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}