{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":518,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":518,"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":"56a0dbac733f","filters":{"topic":"Advanced Graph Neural Networks"}},"results":[{"id":"W2604314403","doi":"10.1007/978-3-319-93417-4_38","title":"Modeling Relational Data with Graph Convolutional Networks","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":5060,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; National Science Foundation","keywords":"Computer science; Inference; Predicate (mathematical logic); Encoder; Relational database; Convolutional neural network; Graph; Information retrieval; Artificial intelligence; Knowledge base; Data mining; Theoretical computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03535772873792242,"gpt":0.252253383566264,"spread":0.2168956548283416,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007681181,0.0006121119,0.0004742202,0.0006603496,0.0004673292,0.0003539504,0.006063338,0.0003688993,0.0000319963],"category_scores_gemma":[0.00004709822,0.0005214535,0.00008209667,0.001018824,0.001360402,0.001782121,0.003144118,0.001227933,0.00002523183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001719601,"about_ca_system_score_gemma":0.0005449088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008044485,"about_ca_topic_score_gemma":0.0001203488,"domain_scores_codex":[0.994661,0.00003528019,0.0005562094,0.00253365,0.00138349,0.0008303549],"domain_scores_gemma":[0.9956374,0.0004520337,0.0002761165,0.002968356,0.00044508,0.0002210061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001144802,0.00001060956,0.00003541482,0.000005164904,0.00001408733,0.00004118119,0.0000529457,0.9210442,0.000001553652,0.03621203,0.00005141084,0.04252],"study_design_scores_gemma":[0.0001953924,0.0001020144,0.00002358673,0.0002430425,0.000007436596,0.0001150836,3.546405e-8,0.7764413,0.000002911738,0.2220209,0.0003417445,0.0005065341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002666134,0.0007429385,0.9961635,0.0004068004,0.00146417,0.0003345865,0.00001432637,0.0002175902,0.0006293725],"genre_scores_gemma":[0.07327548,0.00007553532,0.9234707,0.00145396,0.001415579,0.000007555131,0.0001038296,0.00005590375,0.0001414632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1858089,"threshold_uncertainty_score":0.9997237,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2387462954","doi":"10.1145/2939672.2939751","title":"Asymmetric Transitivity Preserving Graph Embedding","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1293,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Transitive relation; Embedding; Scalability; Computer science; Theoretical computer science; Transitive reduction; Graph embedding; Directed graph; Graph; Vertex (graph theory); Mathematics; Algorithm; Combinatorics; Artificial intelligence; Voltage graph; Line graph","retraction":null,"screen_n_in":null,"score":{"opus":0.01410138418591184,"gpt":0.2541467789611533,"spread":0.2400453947752415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001855131,0.0001215902,0.0001202382,0.0002105182,0.0000975041,0.00005778226,0.0007687859,0.0000446415,0.00002012008],"category_scores_gemma":[0.00003533483,0.00007532592,0.00008576269,0.001240615,0.0000336105,0.001285154,0.0001977992,0.00007907399,0.0000334281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001776028,"about_ca_system_score_gemma":0.000007850421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004510398,"about_ca_topic_score_gemma":0.00000570543,"domain_scores_codex":[0.9988051,0.00005989656,0.0001452728,0.0004007168,0.0002242594,0.000364778],"domain_scores_gemma":[0.9988832,0.0003832317,0.00004189938,0.0005404552,0.00004386131,0.0001072863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005528248,0.00003874509,0.001205095,0.000005934585,0.00001392651,0.00003090854,0.00006050359,0.0004084796,0.00963637,0.1040683,0.004030056,0.8804961],"study_design_scores_gemma":[0.004302527,0.0005527012,0.04630502,0.0004028023,0.00002172393,0.0002023058,0.00002763438,0.2027131,0.1425067,0.5383683,0.06157785,0.003019265],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005411739,0.0002177888,0.98656,0.001207244,0.0002378009,0.00009132877,6.410031e-7,0.0004237212,0.00584974],"genre_scores_gemma":[0.8990439,0.0001146673,0.1001169,0.000287431,0.00004750992,0.000007532952,1.101589e-7,0.000008483535,0.000373462],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8936322,"threshold_uncertainty_score":0.3071702,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766453196","doi":"10.17863/cam.48429","title":"Graph Attention Networks","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":947,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; HEC Montréal","funders":"","keywords":"Computer science; Graph; Attention network; Theoretical computer science; Artificial neural network; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.06497125518221562,"gpt":0.1940901129282144,"spread":0.1291188577459987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001964022,0.0004162483,0.0003835599,0.0002626527,0.0004755677,0.000299891,0.003951175,0.000459204,0.000009016185],"category_scores_gemma":[0.00002102762,0.0004894316,0.0004222105,0.0004320547,0.000204777,0.0008351289,0.003506084,0.001076412,0.0000531378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001046382,"about_ca_system_score_gemma":0.00006197824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000450914,"about_ca_topic_score_gemma":0.00004192836,"domain_scores_codex":[0.997492,0.00012826,0.0002084662,0.001517468,0.0001005124,0.0005532499],"domain_scores_gemma":[0.9960863,0.00007648709,0.0005491457,0.002908958,0.0001567702,0.0002223599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001593019,0.0000429439,0.003533151,0.00002272295,0.00007294442,0.0004770939,0.00001745243,0.8202468,0.00000747131,0.1714703,0.0008701301,0.003222975],"study_design_scores_gemma":[0.000319943,0.00003239765,0.004440421,0.0001160521,0.00004693823,0.000007392797,0.000004590968,0.8028061,0.000006359943,0.1911885,0.0004847323,0.0005465256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03046469,0.0002026525,0.9639569,0.0001243775,0.00223189,0.000297249,0.000004475698,0.0004854827,0.002232296],"genre_scores_gemma":[0.9946767,0.0007305532,0.002224071,0.0001041016,0.0002077796,0.000001361992,0.0000218705,0.00002557834,0.00200796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9642121,"threshold_uncertainty_score":0.9997557,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2604942799","doi":"10.1609/aaai.v31i1.10488","title":"Community Preserving Network Embedding","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":929,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Tencent","keywords":"Computer science; Embedding; Correctness; Community structure; Modularity (biology); Theoretical computer science; Exploit; Variety (cybernetics); Representation (politics); Feature (linguistics); Feature learning; Artificial intelligence; Non-negative matrix factorization; Matrix decomposition; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1242917882980847,"gpt":0.342916314103725,"spread":0.2186245258056403,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009223125,0.0002626042,0.0003059997,0.00006304219,0.002222575,0.000862438,0.008760423,0.000105977,0.00002512496],"category_scores_gemma":[0.0009485787,0.0002032686,0.0001533051,0.0003457654,0.0005018287,0.001301335,0.002772944,0.0009041574,0.00003343441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003409009,"about_ca_system_score_gemma":0.0000439013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008734123,"about_ca_topic_score_gemma":0.00004273838,"domain_scores_codex":[0.9980026,0.00004852661,0.0005021336,0.0004227916,0.000473536,0.0005504522],"domain_scores_gemma":[0.9969682,0.000179929,0.000861347,0.001350219,0.0005251751,0.0001151403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003454955,0.00007893779,0.0009864944,0.00003062855,0.00001553142,6.92391e-7,0.0007696782,0.001821659,0.005473856,0.9332857,0.0006002812,0.05690203],"study_design_scores_gemma":[0.00002661243,0.0001305293,0.001725413,0.0004520589,0.000009113089,0.000004940029,0.0002023415,0.22726,0.0900929,0.6796217,0.0001874027,0.0002870076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5627143,0.0001270557,0.2638744,0.02052963,0.004588694,0.001854868,0.000008494451,0.0007573134,0.1455452],"genre_scores_gemma":[0.988738,0.00003147297,0.01048179,0.000229982,0.0001583147,0.00002013513,1.779351e-7,0.00001558315,0.000324525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4260237,"threshold_uncertainty_score":0.9990764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2811124557","doi":"","title":"Hierarchical graph representation learning with differentiable pooling","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":909,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Pooling; Differentiable function; Computer science; Graph; Artificial intelligence; Theoretical computer science; Benchmark (surveying); Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01436539982481925,"gpt":0.2542677497504681,"spread":0.2399023499256489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001651346,0.0001767938,0.0001812941,0.0002423849,0.0005921056,0.001018532,0.0004278021,0.00006966793,0.000002477582],"category_scores_gemma":[0.00004286081,0.0001370011,0.00003596345,0.001055383,0.000105529,0.006705186,0.00009762873,0.000313997,0.00003131398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002900195,"about_ca_system_score_gemma":0.00003525498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001874307,"about_ca_topic_score_gemma":0.000001961984,"domain_scores_codex":[0.9983741,0.00008778108,0.0004565172,0.0002489161,0.0004756595,0.0003570017],"domain_scores_gemma":[0.998807,0.00005368688,0.0003993753,0.0002770845,0.0003608446,0.0001019986],"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":[0.0002776074,0.00008291481,0.01850492,0.0007891597,0.00007176631,0.00001929322,0.01337988,0.4461404,0.001943386,0.03035438,0.00157034,0.4868659],"study_design_scores_gemma":[0.0003673677,0.000193696,0.001300387,0.0001478849,0.000005570128,0.0001128967,0.0001888706,0.9946876,0.0006129457,0.0004838727,0.00167681,0.0002221476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09989683,0.00006930816,0.8968416,0.0001827826,0.0003858469,0.0002489224,4.558408e-7,0.0006126785,0.00176153],"genre_scores_gemma":[0.9933959,0.000003703287,0.006001749,0.0001964555,0.000187731,0.00003394411,0.00001583894,0.00001030895,0.0001543273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8934991,"threshold_uncertainty_score":0.9821725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2808284704","doi":"10.24963/ijcai.2018/611","title":"Bootstrapping Entity Alignment with Knowledge Graph Embedding","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":531,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Toronto","keywords":"Bootstrapping (finance); Embedding; Computer science; Knowledge graph; Graph; Artificial intelligence; Process (computing); Graph embedding; Training set; Labeled data; Natural language processing; Theoretical computer science; Machine learning; Data mining; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01614141661547361,"gpt":0.2765177001588361,"spread":0.2603762835433625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001114579,0.0001479696,0.0001196108,0.00009945327,0.0002107897,0.0001110188,0.0005979502,0.00003544901,0.00002871811],"category_scores_gemma":[0.000002975131,0.0001125588,0.0000465208,0.0006652426,0.0001280662,0.0005987342,0.0002281272,0.00009829026,0.00007930532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002540701,"about_ca_system_score_gemma":0.00001722656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004897905,"about_ca_topic_score_gemma":0.00003582381,"domain_scores_codex":[0.9988249,0.00003070416,0.0001471167,0.0004363218,0.00018654,0.0003744017],"domain_scores_gemma":[0.9991964,0.00004244644,0.00005574018,0.0005072362,0.0000844642,0.0001137563],"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":[0.00005428535,0.0004462474,0.007083551,0.00004614039,0.0001869087,0.00009744034,0.003112948,0.003412135,0.01090616,0.8041527,0.02771713,0.1427843],"study_design_scores_gemma":[0.003792512,0.002736947,0.01133228,0.0005391015,0.00004384431,0.0003101587,0.0003449382,0.5469335,0.1254375,0.114098,0.190967,0.003464171],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01775737,0.0001365876,0.9652267,0.0001192544,0.0003479177,0.0001257015,1.978452e-7,0.0003394749,0.01594678],"genre_scores_gemma":[0.9195716,0.00002179262,0.07960327,0.0002657497,0.0001415637,0.000009726657,4.116958e-7,0.000009061542,0.0003768736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9018142,"threshold_uncertainty_score":0.4590015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3120491054","doi":"10.1145/3424672","title":"Knowledge Graph Embedding for Link Prediction","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":476,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Variety (cybernetics); Embedding; Link (geometry); Graph; Scale (ratio); Knowledge graph; Data science; Machine learning; Data mining; Artificial intelligence; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06056504407758513,"gpt":0.3279314449345395,"spread":0.2673664008569543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002133534,0.0003577867,0.0003477269,0.0002117096,0.0005394758,0.000414845,0.003276558,0.0001848815,0.00003135046],"category_scores_gemma":[0.0001068433,0.0003702025,0.0002399618,0.00121148,0.00008668724,0.004089874,0.0002935379,0.0004600264,0.00009209829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007979282,"about_ca_system_score_gemma":0.0001961013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000742349,"about_ca_topic_score_gemma":0.000169494,"domain_scores_codex":[0.9971006,0.0001379858,0.0004704845,0.001565388,0.0002143044,0.0005112423],"domain_scores_gemma":[0.993304,0.00121803,0.0001063144,0.004986697,0.0002151427,0.0001698342],"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":[0.0001508381,0.001734705,0.0001213666,0.0001072459,0.00050923,0.00003732799,0.001234431,0.008586855,0.005688496,0.009830159,0.01995179,0.9520476],"study_design_scores_gemma":[0.00508147,0.0005496453,0.001496757,0.0008657019,0.0004141126,0.00007229965,0.0003356835,0.4892126,0.04378241,0.1320297,0.3239738,0.002185876],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001027492,0.00301986,0.9866519,0.0007681875,0.003832516,0.0003725753,0.003594005,0.0003885637,0.0003448755],"genre_scores_gemma":[0.5396911,0.00286968,0.4436336,0.0005275857,0.001953292,0.0004599357,0.006690711,0.0001821905,0.003991902],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9498617,"threshold_uncertainty_score":0.999875,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963384510","doi":"10.1109/msp.2018.2887284","title":"Learning Graphs From Data: A Signal Representation Perspective","year":2019,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":408,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Theoretical computer science; Inference; Viewpoints; Graph; Visualization; Topological graph theory; Data visualization; Signal processing; Perspective (graphical); Graph theory; Representation (politics); Artificial intelligence; Machine learning; Voltage graph; Mathematics; Digital signal processing; Line graph","retraction":null,"screen_n_in":null,"score":{"opus":0.0284040847330043,"gpt":0.2936060278097968,"spread":0.2652019430767925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002452544,0.000267149,0.0002932978,0.0001752157,0.0002255601,0.0003766466,0.001480529,0.0000925725,0.00007434527],"category_scores_gemma":[0.0000330474,0.0002567836,0.00007146555,0.001131499,0.00008946448,0.002917942,0.0003714703,0.000592878,0.0002929926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006016209,"about_ca_system_score_gemma":0.0001292295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000481838,"about_ca_topic_score_gemma":0.00001304346,"domain_scores_codex":[0.9972859,0.0001424791,0.0003243014,0.001249117,0.0005587398,0.000439454],"domain_scores_gemma":[0.9982972,0.0002371962,0.0002934471,0.000770549,0.0002798175,0.0001218444],"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":[0.0003489772,0.0003499788,0.0128329,0.0001081852,0.0001959046,0.0002862388,0.005160903,0.1047607,0.3141436,0.01044706,0.004794819,0.5465708],"study_design_scores_gemma":[0.0009879373,0.0002782687,0.002892862,0.0001744913,0.0000307355,0.0000308091,0.0002705246,0.9088818,0.003907331,0.08094843,0.0009751739,0.0006216001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06727533,0.0009122111,0.92558,0.0005519082,0.000438379,0.0003545633,0.00001101269,0.0006343292,0.004242284],"genre_scores_gemma":[0.9613016,0.00001782213,0.03747826,0.000254612,0.0002596798,0.000007882843,0.0000485908,0.00003175877,0.0005998176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8940263,"threshold_uncertainty_score":0.9999884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3097986917","doi":"10.18653/v1/2020.emnlp-main.541","title":"Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":358,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"NIH Office of the Director; Office of Naval Research; National Science Foundation; Office of the Director of National Intelligence; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Intelligence Advanced Research Projects Activity","keywords":"Timestamp; Computer science; ENCODE; Inference; Autoregressive model; Event (particle physics); Graph; Artificial intelligence; Task (project management); Machine learning; Data mining; Theoretical computer science; Real-time computing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02230392439341087,"gpt":0.2709334823829315,"spread":0.2486295579895207,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000660146,0.0003104248,0.0002914,0.0000529018,0.0001594642,0.0001231945,0.001190159,0.0001155859,0.0001138607],"category_scores_gemma":[0.00003336879,0.0002406006,0.0001475204,0.0009338587,0.00007400312,0.0005811932,0.0006850857,0.0004549638,0.00005321064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000031691,"about_ca_system_score_gemma":0.0000825923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003378883,"about_ca_topic_score_gemma":0.00004437532,"domain_scores_codex":[0.9979629,0.00011121,0.000345701,0.0007074258,0.0002962446,0.0005765276],"domain_scores_gemma":[0.9987471,0.00008642569,0.0001734302,0.0005074951,0.000116438,0.0003690844],"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":[0.00004860102,0.00009364819,0.008628541,0.00004116244,0.00007769126,0.00007606022,0.001985698,0.0237062,0.0001187295,0.6869318,0.1185716,0.1597203],"study_design_scores_gemma":[0.001071648,0.0005958984,0.009423153,0.0001092324,0.00001917071,0.00002316623,0.00002931385,0.7404276,0.0005168811,0.1893815,0.05730991,0.001092627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01166058,0.00329456,0.9736903,0.003870131,0.002838206,0.0006279959,0.00001040773,0.001145962,0.002861873],"genre_scores_gemma":[0.9607199,0.00005158392,0.03699186,0.001644178,0.0004029167,0.00001181365,0.0000120332,0.00001753137,0.0001481568],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9490594,"threshold_uncertainty_score":0.9811406,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963782635","doi":"10.17863/cam.40744","title":"Deep Graph Infomax","year":2018,"lang":"en","type":"article","venue":"Apollo (University of Cambridge)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":332,"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":"European Commission","keywords":"Infomax; Computer science; Graph; Artificial intelligence; Unsupervised learning; Node (physics); Machine learning; Competitive learning; Feature learning; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.007093247053127333,"gpt":0.1900923582138747,"spread":0.1829991111607473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008044065,0.0001136067,0.0001655972,0.000176318,0.0002223118,0.0000176838,0.001082178,0.0000649166,0.00001999597],"category_scores_gemma":[0.000009924687,0.0001396278,0.000117959,0.0008358596,0.0003538836,0.0007690304,0.0003777371,0.0001082004,0.0001049521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002030007,"about_ca_system_score_gemma":0.00002876399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001234585,"about_ca_topic_score_gemma":0.0001038034,"domain_scores_codex":[0.999079,0.000034435,0.00009147411,0.0002964449,0.0002233129,0.0002752614],"domain_scores_gemma":[0.9990119,0.0000494685,0.000117594,0.0005648716,0.0001367991,0.0001193191],"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":[0.0001398992,0.0001794688,0.007804719,0.000043259,0.0001861899,0.0002436717,0.003360854,0.0004668763,0.004503023,0.7513056,0.0384293,0.1933371],"study_design_scores_gemma":[0.008340055,0.003078154,0.342762,0.0002556915,0.0001963015,0.0003187968,0.002696672,0.3437509,0.01211974,0.05162951,0.2311527,0.003699483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09580417,0.00007230847,0.8915676,0.0008272559,0.0003331904,0.00009517803,0.000001847085,0.0001740056,0.01112446],"genre_scores_gemma":[0.9478074,0.00003553079,0.05057031,0.0002590503,0.00005891996,8.413227e-8,0.000001710196,0.000006267819,0.001260729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8520032,"threshold_uncertainty_score":0.5693854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4317931697","doi":"10.1561/2200000096","title":"Graph Neural Networks for Natural Language Processing: A Survey","year":2023,"lang":"en","type":"article","venue":"Foundations and Trends® in Machine Learning","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":269,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial neural network; Graph; Natural language processing; Artificial intelligence; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02218011106607913,"gpt":0.3132030583237363,"spread":0.2910229472576571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004010958,0.0001494033,0.0001590386,0.0004905671,0.0003983113,0.0002372915,0.0002618385,0.00004614914,0.000005090649],"category_scores_gemma":[0.0001051326,0.0001373723,0.00005240774,0.00253222,0.00004476559,0.0004846486,0.0001417122,0.0004108706,0.000001856612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001244848,"about_ca_system_score_gemma":0.00000700551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001138449,"about_ca_topic_score_gemma":0.001170855,"domain_scores_codex":[0.998814,0.0001247629,0.000203375,0.0003833499,0.0001094397,0.0003651143],"domain_scores_gemma":[0.9992976,0.0003446491,0.00009363133,0.0001671376,0.00004186119,0.00005516925],"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":[0.00001521786,0.00001634353,0.04142061,0.000009573794,0.000007945108,0.00001203613,0.0004861213,0.1449712,0.00001140312,0.001282503,0.0001126507,0.8116544],"study_design_scores_gemma":[0.0003487748,0.00003447829,0.145578,0.000009764044,0.000002708388,0.000007073322,0.00002116462,0.8530216,5.776513e-7,0.0003851457,0.000455411,0.0001353023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2345864,0.00437303,0.7559283,0.00203922,0.001001239,0.0004018529,0.00001755818,0.001346328,0.0003060319],"genre_scores_gemma":[0.9943288,0.00002672311,0.004321828,0.00007846946,0.00006052289,0.00004168501,0.0004142009,0.00001744899,0.0007103286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8115191,"threshold_uncertainty_score":0.5601879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2808466528","doi":"10.24963/ijcai.2018/438","title":"ANRL: Attributed Network Representation Learning via Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Zhejiang University; National Natural Science Foundation of China","keywords":"Computer science; Autoencoder; Node (physics); Representation (politics); Focus (optics); Artificial intelligence; Feature learning; Encoder; Network structure; Artificial neural network; Data mining; Theoretical computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01612407182908719,"gpt":0.2656443981401106,"spread":0.2495203263110234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002841354,0.0002398707,0.0002409315,0.00007653472,0.0005095619,0.0001941746,0.0008496185,0.0001267307,0.00006784766],"category_scores_gemma":[0.00005684449,0.0002217179,0.00010582,0.00180715,0.0001369004,0.001021004,0.0004840186,0.0004361139,0.00006887647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003185858,"about_ca_system_score_gemma":0.000007026389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000202279,"about_ca_topic_score_gemma":0.00007687607,"domain_scores_codex":[0.9975877,0.0002411072,0.0003612884,0.0007116987,0.0002984093,0.0007998142],"domain_scores_gemma":[0.9984745,0.0002478894,0.0001826836,0.0007049468,0.0002069794,0.0001829773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000227436,0.00001731604,0.01252744,0.000001350969,0.00002039043,0.00002197757,0.00007604847,0.802838,0.00008273436,0.005085252,0.002553251,0.1767535],"study_design_scores_gemma":[0.0002649456,0.0001837705,0.007967066,0.000005625561,0.000006216864,0.00003842746,0.000007741878,0.9853053,0.0001412057,0.004279433,0.001533861,0.0002663794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005089123,0.0001716455,0.9904985,0.0004712715,0.001352085,0.0002148742,8.970723e-8,0.0009666655,0.001235708],"genre_scores_gemma":[0.9348665,0.0000193712,0.06228542,0.001249427,0.001197232,0.00001530543,0.00001518095,0.00002514328,0.0003263762],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9297774,"threshold_uncertainty_score":0.9041392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809156873","doi":"10.1145/3219819.3219969","title":"Arbitrary-Order Proximity Preserved Network Embedding","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Embedding; Scalability; Computer science; Node (physics); Order (exchange); Decomposition; Mathematical optimization; Algorithm; Theoretical computer science; Topology (electrical circuits); Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01815734829812609,"gpt":0.2724486667270325,"spread":0.2542913184289064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002058798,0.0001708681,0.0001571347,0.00004238753,0.0002554064,0.000135885,0.001130857,0.00007518391,0.00008649187],"category_scores_gemma":[0.00004194432,0.0001420304,0.00006072486,0.001024483,0.0001092594,0.001279613,0.0005656839,0.000207868,0.0001095972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001534176,"about_ca_system_score_gemma":0.00003010747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009261385,"about_ca_topic_score_gemma":0.00004055307,"domain_scores_codex":[0.9983571,0.00006608864,0.0002176339,0.000521432,0.0002417787,0.0005959402],"domain_scores_gemma":[0.9987007,0.0001028287,0.00007621677,0.0008311621,0.0001503244,0.0001387614],"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":[0.00006408397,0.0001947084,0.01215853,0.00002927892,0.0000960321,0.00006395377,0.0004806558,0.01789076,0.0006341799,0.7893223,0.1224016,0.056664],"study_design_scores_gemma":[0.0003188853,0.0001790692,0.002627184,0.00002808134,0.000004234845,0.00001599816,0.000005114658,0.8275427,0.001591255,0.1461324,0.02115357,0.0004014884],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009019885,0.000106408,0.9628316,0.0006643133,0.0007722194,0.0002512958,2.429153e-7,0.0006904825,0.02566358],"genre_scores_gemma":[0.3470154,0.00001138612,0.6483314,0.002106842,0.0009057585,0.00002150537,0.000001172049,0.00001709382,0.00158942],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.809652,"threshold_uncertainty_score":0.5791833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4290876096","doi":"10.1145/3534678.3542609","title":"Graph Neural Networks: Foundation, Frontiers and Applications","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":199,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Artificial neural network; Graph; Data science; Machine learning; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03770490372849548,"gpt":0.2782985551746336,"spread":0.2405936514461382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003555207,0.0002032714,0.0002273656,0.0001207559,0.0007946666,0.0003824415,0.00324499,0.0000361137,0.000003222108],"category_scores_gemma":[0.0001206159,0.0001678639,0.00003867832,0.000754197,0.0002480087,0.002169034,0.005525639,0.0003156053,3.630306e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001828384,"about_ca_system_score_gemma":0.00004453577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002730111,"about_ca_topic_score_gemma":0.000002661866,"domain_scores_codex":[0.9984468,0.00002807363,0.000282191,0.0007437796,0.0002131321,0.000285997],"domain_scores_gemma":[0.9985559,0.0001633192,0.0002908393,0.0007919492,0.000113484,0.00008451331],"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":[0.0001498218,0.0002504425,0.03522674,0.0001409971,0.0001046302,0.000001233439,0.002136364,0.0008640502,0.0006801515,0.5683152,0.009062334,0.383068],"study_design_scores_gemma":[0.001152333,0.0004309291,0.006649479,0.0001697622,0.0001062268,0.00006651128,0.004052238,0.8650205,0.0002639098,0.1143224,0.006838687,0.0009270489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4039814,0.006861685,0.5699207,0.005549035,0.002742286,0.002835027,0.0002926435,0.0004590279,0.007358172],"genre_scores_gemma":[0.9925666,0.0001862333,0.00661786,0.0001979954,0.00008905234,0.0001166801,0.00003053986,0.0000131404,0.0001818751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8641565,"threshold_uncertainty_score":0.6887314,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389098833","doi":"10.1145/3633518","title":"A Survey on Graph Representation Learning Methods","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Graph; Representation (politics); Data science; Theoretical computer science; Artificial intelligence; Information retrieval; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.064175238834068,"gpt":0.3603229334070372,"spread":0.2961476945729692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005332108,0.0001625039,0.0002264386,0.001051619,0.000298354,0.0000659392,0.0005572364,0.000191973,0.000003498869],"category_scores_gemma":[0.0001671394,0.0001488676,0.00005545084,0.003188073,0.00008683033,0.0001323441,0.00003234819,0.0004906798,0.00006498137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000245365,"about_ca_system_score_gemma":0.00000919433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001166333,"about_ca_topic_score_gemma":0.00003327793,"domain_scores_codex":[0.9984047,0.0003064582,0.0002933437,0.0005455688,0.0001557069,0.0002942358],"domain_scores_gemma":[0.9980923,0.0008673823,0.00009941137,0.0008015992,0.00008180087,0.00005750635],"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":[0.00002016575,0.00005934093,0.001641766,0.00001768602,0.00007962138,0.00002287301,0.0001766854,0.0681385,0.0006900128,0.02413607,0.0002075976,0.9048097],"study_design_scores_gemma":[0.001589257,0.004591323,0.01859578,0.0006641391,0.00008221978,0.0003476502,0.002682921,0.6421313,0.09022924,0.2047723,0.0319145,0.002399421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009868124,0.0002183629,0.9866185,0.0009157736,0.0008621002,0.0002665773,0.000003184044,0.00119035,0.00005703495],"genre_scores_gemma":[0.9864365,0.0008970474,0.01175307,0.0000401614,0.00001601196,0.0001384741,0.000006754372,0.00002019699,0.0006918065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9765683,"threshold_uncertainty_score":0.6070646,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890848214","doi":"10.1109/icassp.2018.8462291","title":"A Graph-CNN for 3D Point Cloud Classification","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Upsampling; Point cloud; Graph; Pooling; Theoretical computer science; Convolutional neural network; Topological graph theory; Artificial intelligence; Line graph; Voltage graph","retraction":null,"screen_n_in":null,"score":{"opus":0.03146337179556759,"gpt":0.2832721333078607,"spread":0.2518087615122931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001324605,0.00009454395,0.0000865853,0.00006807096,0.0001383226,0.00006206814,0.0005259987,0.00004688062,0.00001283036],"category_scores_gemma":[0.00002557632,0.00007816387,0.00006341984,0.0004130455,0.00008153637,0.0003956301,0.00008827349,0.00005746508,0.00007026896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001418003,"about_ca_system_score_gemma":0.00001355307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000244316,"about_ca_topic_score_gemma":0.00001308833,"domain_scores_codex":[0.9991007,0.00001952606,0.0001591433,0.0003508669,0.0001176285,0.000252119],"domain_scores_gemma":[0.9991072,0.00009273009,0.00006680845,0.0005286792,0.0001345545,0.00006998582],"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":[0.0000157786,0.00003418587,0.0001110263,0.000004602909,0.000008444341,7.307085e-7,0.0001389744,0.00002072133,0.001515641,0.8363355,0.02451079,0.1373036],"study_design_scores_gemma":[0.0005894491,0.0004874213,0.002264607,0.00001362969,0.000006432867,0.00001216251,0.00002507454,0.5666329,0.005463091,0.3441329,0.08001437,0.0003579478],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001088948,0.00002338545,0.9897592,0.001813096,0.000795636,0.0002556259,7.014788e-7,0.00029801,0.005965367],"genre_scores_gemma":[0.4071323,0.000007835086,0.5900615,0.001577865,0.0004270179,0.00004973548,0.00000227149,0.000009413449,0.0007320063],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5666122,"threshold_uncertainty_score":0.318743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962850650","doi":"","title":"SimplE embedding for link prediction in knowledge graphs","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":178,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Simple (philosophy); Embedding; Computer science; Theoretical computer science; Factorization; Link (geometry); Graph embedding; Tying; Artificial intelligence; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02168659529710737,"gpt":0.3003203198068173,"spread":0.27863372450971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003382379,0.0001626694,0.0001795096,0.0003575355,0.0003109568,0.0005038888,0.0004398424,0.0001064824,0.000001056869],"category_scores_gemma":[0.0000691809,0.0001498582,0.00004940466,0.001006254,0.00005224878,0.006686699,0.00007773079,0.0001504785,0.00002672463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006709254,"about_ca_system_score_gemma":0.00005089178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007569638,"about_ca_topic_score_gemma":0.000007739756,"domain_scores_codex":[0.9985301,0.00004079078,0.0006532276,0.0002180791,0.0001974543,0.0003602885],"domain_scores_gemma":[0.9988908,0.0000748382,0.0003206202,0.000251087,0.0003907993,0.00007185132],"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":[0.00009740683,0.00006952354,0.003545981,0.001556536,0.00001874737,0.000002030862,0.01340123,0.08046452,0.0008012298,0.06124602,0.01022983,0.828567],"study_design_scores_gemma":[0.0004187043,0.0001225259,0.000532401,0.0001265729,0.000002219791,0.00001783845,0.0001017201,0.983013,0.000222323,0.002052741,0.01324004,0.0001499333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02226669,0.0003883015,0.9722034,0.0001727736,0.002134607,0.0008684399,0.000009198498,0.0006227779,0.001333859],"genre_scores_gemma":[0.9957992,0.000003738752,0.0034264,0.0001812624,0.0003334615,0.0001521039,0.00002666869,0.000009648454,0.0000674784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9735326,"threshold_uncertainty_score":0.6111039,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964105372","doi":"10.1109/tsp.2017.2752689","title":"On the Shift Operator, Graph Frequency, and Optimal Filtering in Graph Signal Processing","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":163,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graph energy; Adjacency matrix; Laplacian matrix; Spectral graph theory; Mathematics; Voltage graph; Line graph; Algorithm; Graph; Discrete mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02521948641295206,"gpt":0.2665720012858287,"spread":0.2413525148728766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003917146,0.0003824275,0.0002885081,0.000322833,0.002449482,0.001412388,0.001239487,0.0001336377,0.0000187576],"category_scores_gemma":[0.000006228344,0.0002980788,0.0001056825,0.0005606972,0.0003672598,0.002345104,0.00001687119,0.0009141908,0.000005401555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004770896,"about_ca_system_score_gemma":0.0001070586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002655133,"about_ca_topic_score_gemma":0.00005134472,"domain_scores_codex":[0.9976649,0.0001000951,0.0003953629,0.0007979823,0.000454144,0.0005874761],"domain_scores_gemma":[0.9987877,0.0001944517,0.0002365944,0.0005516753,0.00007964365,0.0001499375],"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":[0.0001595428,0.0003303059,0.0003142688,0.0001551548,0.00003902524,0.0001767326,0.002650911,0.1934841,0.01597328,0.00196506,0.0000184811,0.7847331],"study_design_scores_gemma":[0.002470583,0.0009594843,0.003938649,0.003041725,0.00006523603,0.0001741923,0.0003038764,0.8435616,0.07815627,0.06519718,0.00004207994,0.002089089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1223793,0.0002520276,0.8757675,0.000807456,0.0001302864,0.0002656698,0.000003786646,0.000151852,0.0002421097],"genre_scores_gemma":[0.9870023,0.00002339117,0.01232578,0.0004627442,0.000051769,0.00008054812,3.642756e-7,0.00003459322,0.00001857181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.864623,"threshold_uncertainty_score":0.9999471,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2893944917","doi":"","title":"Deep Graph Infomax.","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":156,"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":"Infomax; Computer science; Graph; Artificial intelligence; Node (physics); Unsupervised learning; Machine learning; Competitive learning; Feature learning; Random walk; Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05111203280535453,"gpt":0.1820539192501569,"spread":0.1309418864448024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001424832,0.0004315816,0.0003642382,0.0003918306,0.0002137661,0.0001380632,0.003439264,0.0003991819,0.00003476044],"category_scores_gemma":[0.00002630271,0.0004991917,0.0003224283,0.001239226,0.0002819135,0.0006458379,0.003889688,0.0008001484,0.0002321202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001138158,"about_ca_system_score_gemma":0.00008952164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000291548,"about_ca_topic_score_gemma":0.00005290884,"domain_scores_codex":[0.9975002,0.0001184318,0.0002279499,0.001460707,0.0001230837,0.0005695939],"domain_scores_gemma":[0.9969502,0.0001091317,0.0003100222,0.002153957,0.0002138474,0.0002628195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004061171,0.0001020584,0.003985114,0.00006596207,0.0001593225,0.0009110627,0.0002446578,0.5719948,0.00001779361,0.4166835,0.002468221,0.003326877],"study_design_scores_gemma":[0.0003240814,0.00007332709,0.001221933,0.00006436456,0.00003682529,0.00001043715,0.00001253072,0.5841883,0.00007504043,0.4117925,0.001543052,0.0006576431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05677074,0.000113871,0.9363599,0.00007635994,0.001454459,0.000268027,0.00000366624,0.0006289853,0.004323926],"genre_scores_gemma":[0.987857,0.0002504559,0.01055972,0.0003149946,0.0001962245,0.000001154807,0.00001110146,0.00002676664,0.0007825446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9310863,"threshold_uncertainty_score":0.999746,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963702033","doi":"10.1109/tsipn.2017.2742940","title":"Characterization and Inference of Graph Diffusion Processes From Observations of Stationary Signals","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Laplacian matrix; Null graph; Voltage graph; Graph; Computer science; Strength of a graph; Eigenvalues and eigenvectors; Theoretical computer science; Mathematics; Algorithm; Line graph","retraction":null,"screen_n_in":null,"score":{"opus":0.01979981599724482,"gpt":0.2345992929744548,"spread":0.21479947697721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005728815,0.0001109102,0.0001616899,0.0001208119,0.0001610774,0.00005807042,0.0005877308,0.00005497782,0.00001626253],"category_scores_gemma":[0.0007816778,0.0001112862,0.00003047261,0.0009213754,0.0002721108,0.0006155941,0.0003044519,0.00007619381,0.000001400829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007976928,"about_ca_system_score_gemma":0.00008342611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001392676,"about_ca_topic_score_gemma":0.0002534568,"domain_scores_codex":[0.9982923,0.0006737923,0.0003527465,0.0003155422,0.000238829,0.0001267726],"domain_scores_gemma":[0.9951357,0.00137725,0.0004343387,0.0006486101,0.002341778,0.0000622877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001316431,0.0003612536,0.03850893,0.0000881269,0.00002545591,5.760376e-7,0.01012902,0.00003607278,0.7608551,0.1205951,0.00003245694,0.06935474],"study_design_scores_gemma":[0.0004642297,0.000003653586,0.3401005,0.000912073,0.00001530128,0.000001740748,0.00006071742,0.06096447,0.5651037,0.0315027,0.000606814,0.000264152],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4586267,0.00009367281,0.5402039,0.0007262407,0.00002781229,0.00009302978,0.00002379199,0.00004021955,0.0001646256],"genre_scores_gemma":[0.8986323,0.0003113246,0.1006942,0.00005473085,0.000007443373,0.00001095694,0.0001329704,0.000007365253,0.0001486398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4400056,"threshold_uncertainty_score":0.4538121,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2907079035","doi":"10.48550/arxiv.1901.01484","title":"LanczosNet: Multi-Scale Deep Graph Convolutional Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Computer science; Graph; Scale (ratio); Artificial intelligence; Theoretical computer science; Cartography; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.05126511466307922,"gpt":0.1852913280843273,"spread":0.1340262134212481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001785895,0.0005323555,0.0005222161,0.0003095172,0.0002143966,0.0001168342,0.002831206,0.0005810281,0.00003166224],"category_scores_gemma":[0.00001249066,0.0006237194,0.0004349037,0.0009729741,0.0002265372,0.0005433225,0.002804748,0.001344493,0.0001661161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001818087,"about_ca_system_score_gemma":0.0001131195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004539332,"about_ca_topic_score_gemma":0.0001115856,"domain_scores_codex":[0.9968526,0.000180075,0.000293324,0.001777935,0.0001450782,0.0007509367],"domain_scores_gemma":[0.9970763,0.0001901841,0.0003775552,0.001867003,0.0002090086,0.0002799756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002247654,0.00007592396,0.009610408,0.00002432225,0.00006972579,0.0001369567,0.00004188165,0.9468793,0.00000824954,0.04227466,0.0004303335,0.0004257835],"study_design_scores_gemma":[0.0007217391,0.00003871593,0.005876459,0.0000697651,0.00003896664,0.000009982529,0.00001445289,0.9685754,0.00001062229,0.02349776,0.0004737284,0.0006724026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01912174,0.0005135802,0.9762119,0.00006568091,0.002265628,0.0004787651,0.00001583405,0.0005017431,0.0008251299],"genre_scores_gemma":[0.9809318,0.0004623001,0.01640219,0.0003222918,0.0001940815,0.000002411216,0.00005737918,0.0000381911,0.001589406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.96181,"threshold_uncertainty_score":0.9996214,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3099845049","doi":"10.18653/v1/2020.emnlp-main.462","title":"TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Samsung; Compute Canada; Canadian Institute for Advanced Research","keywords":"Leverage (statistics); Computer science; Knowledge graph; Message passing; Graph; Temporal database; Machine learning; Artificial intelligence; Theoretical computer science; Data mining; Distributed computing","retraction":null,"screen_n_in":null,"score":{"opus":0.05205755584159759,"gpt":0.2873606080580615,"spread":0.2353030522164639,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001745065,0.0002428449,0.0002995332,0.00009159333,0.0002757325,0.0001753278,0.0008264858,0.00008376721,0.00001598015],"category_scores_gemma":[0.00003742893,0.00021452,0.0001888279,0.0008593232,0.00007844214,0.0007867138,0.0002735007,0.0001890857,0.00003529605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002549329,"about_ca_system_score_gemma":0.00004235146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001002776,"about_ca_topic_score_gemma":0.00002767255,"domain_scores_codex":[0.9982554,0.00007415263,0.0003652531,0.0006511991,0.0002103522,0.0004436611],"domain_scores_gemma":[0.9989406,0.0001630355,0.0001393438,0.0003888426,0.0001157314,0.0002523935],"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":[0.0002371105,0.0005362382,0.02633952,0.0004192477,0.0001604479,0.00009069603,0.00319468,0.002839762,0.01269898,0.5665865,0.2249403,0.1619565],"study_design_scores_gemma":[0.002303487,0.0007412569,0.002982217,0.00007250892,0.00002254856,0.00002067401,0.0001195692,0.770487,0.003974853,0.04271487,0.1753782,0.001182875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002394414,0.0002002267,0.9882629,0.005413607,0.0004003498,0.0004822804,0.000005539085,0.0007456642,0.002095007],"genre_scores_gemma":[0.8022373,0.000004144016,0.1956631,0.001606114,0.0002305871,0.00003978235,0.00002223808,0.00002230307,0.0001744413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7998428,"threshold_uncertainty_score":0.8747872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035403290","doi":"10.1145/3397271.3401172","title":"DGL-KE","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speedup; Parallel computing; Overhead (engineering); Locality; Computation; Key (lock); Theoretical computer science; Algorithm; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02202193411362178,"gpt":0.2137706386130928,"spread":0.191748704499471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00001490288,0.00004774539,0.00004990508,0.000009533606,0.0000276381,0.00003223411,0.0004724646,0.00001481623,0.0000300559],"category_scores_gemma":[0.0000104141,0.00003892617,0.00002576371,0.0002998346,0.00001087813,0.0002574583,0.0001654907,0.00006457363,0.0001999286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002407085,"about_ca_system_score_gemma":0.000005067897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.09005e-7,"about_ca_topic_score_gemma":5.709658e-7,"domain_scores_codex":[0.9995364,0.000008691884,0.00006150358,0.0001852866,0.00008508192,0.0001230666],"domain_scores_gemma":[0.9996759,0.00002352269,0.0000140365,0.0001776554,0.00001204006,0.00009679147],"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":[0.000004258785,0.00001580407,0.0007189794,0.000005235368,0.000007677682,0.00005932851,0.0003495964,0.00223339,0.002081692,0.7800138,0.05269178,0.1618184],"study_design_scores_gemma":[0.0004055058,0.0001943937,0.001589382,0.000004779026,0.000002162603,0.00001472802,0.00001567056,0.7470914,0.007872963,0.03498253,0.2074185,0.0004079164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008572211,0.00004011218,0.9732301,0.01107244,0.0001045145,0.00003753136,9.401587e-8,0.0003805564,0.01427747],"genre_scores_gemma":[0.8094523,0.000006976646,0.1723628,0.01770611,0.0001010577,0.000002303537,2.549008e-7,0.000004465406,0.0003637595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8085951,"threshold_uncertainty_score":0.2569744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2997940961","doi":"10.1609/aaai.v34i05.6214","title":"Multi-Agent Actor-Critic with Hierarchical Graph Attention Network","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Reinforcement learning; Transferability; Artificial intelligence; Graph; Attention network; Machine learning; Representation (politics); Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.08352121217448213,"gpt":0.2864564552276392,"spread":0.2029352430531571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002181491,0.0003064178,0.0003199169,0.00007086475,0.0002692723,0.0002295004,0.002138225,0.00009424359,0.00002099354],"category_scores_gemma":[0.0001810886,0.0002138314,0.0001611526,0.001406889,0.0004128126,0.0005429893,0.0004570289,0.0005984541,0.00004911654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002655787,"about_ca_system_score_gemma":0.00005474318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005988029,"about_ca_topic_score_gemma":0.000006369633,"domain_scores_codex":[0.9975576,0.00003181171,0.0005196764,0.0007381691,0.0006049341,0.000547848],"domain_scores_gemma":[0.9985725,0.0001022457,0.0003275037,0.0003058063,0.000454162,0.0002377776],"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":[0.0002449884,0.0002143829,0.002034546,0.00007340454,0.0000434366,0.000005303037,0.001014262,0.002527829,0.03741798,0.9134746,0.0003256316,0.04262361],"study_design_scores_gemma":[0.00021074,0.001604385,0.0041034,0.0008009342,0.0000592807,0.00002439012,0.0004523215,0.6460729,0.1099743,0.2353493,0.0002986167,0.001049425],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1571909,0.00006782122,0.8213138,0.01816193,0.0006619019,0.000990135,0.000004898774,0.0003822694,0.001226321],"genre_scores_gemma":[0.9681262,0.00003933704,0.03050352,0.00108666,0.0001565844,0.00002912308,6.268437e-7,0.00001958799,0.0000383004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8109353,"threshold_uncertainty_score":0.8719791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3215602957","doi":"10.6339/22-jds1047","title":"A Review on Graph Neural Network Methods in Financial Applications","year":2022,"lang":"en","type":"review","venue":"Journal of Data Science","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Computer science; Graph; Categorization; Artificial neural network; Financial modeling; Data mining; Data science; Finance; Artificial intelligence; Theoretical computer science; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.1986486505103352,"gpt":0.4830799741744901,"spread":0.2844313236641549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.008679627,0.0003693613,0.001622374,0.0007738631,0.0003662109,0.0001683249,0.01754633,0.00007852393,0.00001720684],"category_scores_gemma":[0.000818335,0.0002770015,0.0003575596,0.01228257,0.0003722827,0.002926539,0.003467009,0.001947128,0.000005432031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000192838,"about_ca_system_score_gemma":0.001434484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001098083,"about_ca_topic_score_gemma":0.000002019792,"domain_scores_codex":[0.9949133,0.0007972986,0.001611287,0.001010732,0.001032551,0.0006348083],"domain_scores_gemma":[0.9932342,0.001200383,0.002246106,0.002967555,0.0001117206,0.0002400809],"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":[9.706417e-7,0.00003529955,3.55876e-7,0.001148327,0.000004318325,0.00003809642,0.000003137934,0.0002788379,8.907303e-8,0.002781851,0.004370948,0.9913378],"study_design_scores_gemma":[0.0000603741,0.000107142,0.000002681441,0.01173269,0.00007091598,0.0005201115,5.282834e-7,0.0007659727,4.351135e-8,0.002017345,0.9844719,0.0002502631],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.153501e-8,0.7810344,0.2173125,0.0001428599,0.0008427524,0.0005586838,0.00002019664,0.00001597319,0.0000726935],"genre_scores_gemma":[4.259521e-8,0.7644638,0.2341639,0.001017343,0.0002775799,0.00004983789,0.00001131376,0.00001198004,0.000004180936],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9910875,"threshold_uncertainty_score":0.9999682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2903329593","doi":"10.1109/bigdata.2018.8621910","title":"dynnode2vec: Scalable Dynamic Network Embedding","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Embedding; Computer science; Graph embedding; Scalability; Random walk; Theoretical computer science; Timestamp; Dynamic network analysis; Graph; Representation (politics); Vector space; Artificial intelligence; Mathematics; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.008102776568752312,"gpt":0.2681077697511505,"spread":0.2600049931823982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001630482,0.0001541587,0.0001454892,0.00005605984,0.0002771257,0.0001354226,0.000938989,0.00006357204,0.00006106209],"category_scores_gemma":[0.00001419464,0.0001337942,0.00005775713,0.0009285896,0.0001053183,0.0007086765,0.0004325416,0.0001443443,0.0004009897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003428194,"about_ca_system_score_gemma":0.00001803102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000557235,"about_ca_topic_score_gemma":0.00004208951,"domain_scores_codex":[0.9984993,0.00003587051,0.0001928944,0.000466871,0.0001997136,0.0006052982],"domain_scores_gemma":[0.9989454,0.00008266478,0.00006314339,0.0007058908,0.00008341279,0.0001195245],"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":[0.00002550868,0.00008621869,0.001604628,0.00001256064,0.00006231782,0.00006149849,0.0002893,0.05436325,0.001461568,0.4302184,0.06606928,0.4457454],"study_design_scores_gemma":[0.0001307808,0.00007940767,0.0003597562,0.00001748106,0.000002165484,0.00002119911,0.000004052027,0.9443309,0.0002198773,0.04161473,0.01300943,0.0002101668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003294204,0.0001481813,0.9687508,0.0004141314,0.001065979,0.0001033566,2.245262e-7,0.0006279487,0.02559516],"genre_scores_gemma":[0.6449018,0.00001819042,0.3512163,0.001314643,0.0003028837,0.000006788565,9.605775e-7,0.00001455585,0.00222385],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8899677,"threshold_uncertainty_score":0.545597,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396506525","doi":"10.1109/tnnls.2024.3389714","title":"Reconstructed Graph Neural Network With Knowledge Distillation for Lightweight Anomaly Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Computer science; Graph; Theoretical computer science; Data mining; Distributed computing; Anomaly detection; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.009916444358123496,"gpt":0.2235279266217746,"spread":0.2136114822636511,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002987634,0.0004097969,0.0003774038,0.0002588071,0.001025578,0.0006758489,0.0002464777,0.0002029291,0.000002312348],"category_scores_gemma":[0.000004936839,0.000329139,0.0001576286,0.001670248,0.0001048879,0.0007704226,0.000004796904,0.0009938926,0.000002820186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005265055,"about_ca_system_score_gemma":0.0000218741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002096999,"about_ca_topic_score_gemma":0.00009227453,"domain_scores_codex":[0.9975242,0.0003259043,0.0004509005,0.0008850569,0.0001950046,0.0006189035],"domain_scores_gemma":[0.9983736,0.0008270279,0.0001495768,0.0003226642,0.0001405561,0.0001866071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008513292,0.00001373675,0.00007689701,0.00006529845,0.00006018372,0.0000115081,0.00008429529,0.8488079,0.00005172192,0.0004794309,0.00006672487,0.1501971],"study_design_scores_gemma":[0.0003833099,0.0007612254,0.0002481132,0.0002624163,0.0000592053,0.0003177494,0.00002370288,0.9947713,0.00004854809,0.00008177458,0.002637337,0.0004053042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03727333,0.002963168,0.9526713,0.0001169046,0.005163908,0.0007458831,0.00000392406,0.00100335,0.00005826422],"genre_scores_gemma":[0.9971959,0.0001299097,0.001227635,0.00003036382,0.0007239949,0.0001886326,0.000006109197,0.00006301251,0.0004344226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9599226,"threshold_uncertainty_score":0.9999161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034239155","doi":"10.60692/6b5x9-hbn81","title":"Inductive Relation Prediction by Subgraph Reasoning","year":2019,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Embedding; Inductive bias; Knowledge graph; Artificial intelligence; Relation (database); Theoretical computer science; Holy Grail; Graph; Set (abstract data type); Machine learning; Multi-task learning; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.008794174846235568,"gpt":0.2066363655234487,"spread":0.1978421906772131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006135638,0.0004133295,0.0003428299,0.0002875429,0.0007234998,0.0001162026,0.0009752965,0.0003480102,0.00003631558],"category_scores_gemma":[0.0001937789,0.0004362447,0.0001844157,0.001549101,0.00006548164,0.004525717,0.0003953509,0.001178014,0.0003163641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003880626,"about_ca_system_score_gemma":0.0000166053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004917146,"about_ca_topic_score_gemma":0.00001497871,"domain_scores_codex":[0.9965015,0.0003215329,0.000540253,0.001222894,0.0007099676,0.0007038585],"domain_scores_gemma":[0.9978266,0.0002273656,0.0003729895,0.001079426,0.0002208409,0.0002727702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006117034,0.0001364132,0.004783762,0.00002447507,0.0000913534,0.00002157266,0.00001419375,0.001810342,0.08625355,0.7550784,0.00004718058,0.1516776],"study_design_scores_gemma":[0.006116406,0.001894052,0.05662287,0.0008189649,0.0001524839,0.000336825,0.00017095,0.04416228,0.1663369,0.5737271,0.1452639,0.004397247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9750349,0.0001688255,0.001108065,0.00007041734,0.001726948,0.0007125403,0.0001333772,0.0009946004,0.02005034],"genre_scores_gemma":[0.982352,0.00006415401,0.01626407,0.0003655552,0.00003639797,0.0000464481,0.00004351571,0.00006068914,0.0007671216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1813513,"threshold_uncertainty_score":0.9998089,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3092206109","doi":"10.1609/aaai.v35i11.17203","title":"GraphMix: Improved Training of GNNs for Semi-Supervised Learning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Graph; Convolutional neural network; Theoretical computer science; Artificial intelligence; Machine learning; Regularization (linguistics); Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.0913165739348398,"gpt":0.2977802692848069,"spread":0.2064636953499671,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004273824,0.0002451866,0.000412499,0.0001226395,0.0002243913,0.0001271181,0.001587176,0.0001102488,0.00001999958],"category_scores_gemma":[0.0008843141,0.0002030836,0.0002768224,0.001122928,0.0002497361,0.0003571576,0.0003607503,0.0003930716,0.000003326778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002112245,"about_ca_system_score_gemma":0.0001424169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006782543,"about_ca_topic_score_gemma":0.000007896771,"domain_scores_codex":[0.9978869,0.00002501325,0.0006710651,0.000601068,0.0003605714,0.0004553932],"domain_scores_gemma":[0.9975364,0.0002946698,0.0005201087,0.0003221782,0.001229952,0.00009674401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005126948,0.00005989534,0.0001189382,0.00006257864,0.00002136346,4.412337e-7,0.001789458,0.0005152652,0.3524923,0.5363854,0.00002248447,0.1084806],"study_design_scores_gemma":[0.00004864394,0.0002101657,0.00004593157,0.000196474,0.00001280261,0.000004765016,0.001052029,0.2203877,0.6262359,0.1515493,0.00007330107,0.0001829988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3177175,0.000171639,0.66965,0.004306404,0.001186839,0.001181897,0.00001470474,0.0002772779,0.005493795],"genre_scores_gemma":[0.976676,0.0000564165,0.02280969,0.0001561426,0.00006044444,0.0000404213,0.000001044797,0.00001857262,0.0001812941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6589585,"threshold_uncertainty_score":0.8281507,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382203390","doi":"10.1609/aaai.v37i8.26168","title":"Neighbor Contrastive Learning on Learnable Graph Augmentation","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Francis Xavier University","funders":"Hainan University; National Natural Science Foundation of China","keywords":"Computer science; Graph; Artificial intelligence; False positive paradox; Theoretical computer science; Machine learning; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.06447864412558238,"gpt":0.2998504342094437,"spread":0.2353717900838614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004202993,0.0002423352,0.0002430909,0.0002555019,0.0003708744,0.0002208231,0.001411703,0.0000844712,0.00003153111],"category_scores_gemma":[0.0004461638,0.0001883943,0.0001315503,0.001978894,0.0002238014,0.0005499142,0.0002888663,0.0005382906,0.0002618652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004276095,"about_ca_system_score_gemma":0.00004196818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001335741,"about_ca_topic_score_gemma":0.000003743386,"domain_scores_codex":[0.9978957,0.00003166946,0.0004371316,0.0005796561,0.0005789479,0.0004768943],"domain_scores_gemma":[0.9985871,0.0002630008,0.0003992374,0.0002255142,0.0004316144,0.00009349437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009572519,0.00006117134,0.0002844968,0.00001579763,0.00001565224,0.000001550978,0.0007982133,0.008028104,0.02900827,0.8832076,0.0002998025,0.07818359],"study_design_scores_gemma":[0.00006568144,0.0005973697,0.001034288,0.000263206,0.00001037699,0.000002724067,0.0008869664,0.2171897,0.3919635,0.3875067,0.0001615365,0.0003178723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7442043,0.0000492645,0.1942111,0.01480492,0.002849577,0.002194039,0.00001081158,0.00183613,0.03983991],"genre_scores_gemma":[0.997947,0.00007710137,0.0008812204,0.0002607041,0.00006543646,0.00004083528,0.000001113657,0.00001714878,0.0007094091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4957009,"threshold_uncertainty_score":0.7682496,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3003775208","doi":"10.1109/tip.2020.2969052","title":"Point Cloud Denoising via Feature Graph Laplacian Regularization","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Point cloud; Laplacian matrix; Artificial intelligence; Computer science; Noise reduction; Fidelity; Algorithm; Regularization (linguistics); Graph; Mathematics; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01133680422635431,"gpt":0.234045933363947,"spread":0.2227091291375927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009268169,0.0002603825,0.0002059661,0.0001604818,0.0007052039,0.0004005485,0.0005319114,0.0001210194,0.000007686279],"category_scores_gemma":[0.000008353994,0.0002636494,0.0001239348,0.001653517,0.00008646793,0.001985697,0.000005599111,0.0005794853,0.00002473335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004493123,"about_ca_system_score_gemma":0.00004175485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001709112,"about_ca_topic_score_gemma":0.000004774053,"domain_scores_codex":[0.9983272,0.00006954528,0.0002518031,0.000640123,0.0003331579,0.0003781659],"domain_scores_gemma":[0.9991339,0.0000429228,0.000143841,0.000335406,0.0001403473,0.0002035681],"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":[0.0001285969,0.000169886,0.000009348397,0.0002044094,0.00004328658,0.0001124293,0.002844797,0.06697539,0.1183551,0.0004641588,0.0005416928,0.8101509],"study_design_scores_gemma":[0.0009616503,0.0002322863,0.00004132291,0.0002502589,0.00005671779,0.0001260474,0.0001022614,0.6776763,0.3106171,0.008410759,0.0006830121,0.0008423744],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004826839,0.0001703224,0.9922899,0.005506159,0.0004265032,0.0002046202,0.000002911587,0.0006989701,0.0002179368],"genre_scores_gemma":[0.7819886,0.00001904054,0.2155663,0.002120339,0.0001511243,0.0000165026,0.000002407913,0.00003948884,0.00009623646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8093085,"threshold_uncertainty_score":0.9999816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081963674","doi":"","title":"Contrastive Multi-View Representation Learning on Graphs","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graph; Artificial intelligence; Node (physics); Binary classification; Theoretical computer science; Representation (politics); Machine learning; Binary number; Feature learning; Mathematics; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.0770792012378027,"gpt":0.3372805158083014,"spread":0.2602013145704987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001522118,0.0002445394,0.0002257642,0.0001535464,0.0002095139,0.0002338881,0.0008605075,0.00006341645,0.0001535984],"category_scores_gemma":[0.0006670758,0.0002326806,0.0001123928,0.0003890457,0.00005172377,0.000474949,0.0001995629,0.00119807,0.0002194052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004097548,"about_ca_system_score_gemma":0.00002700934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002390996,"about_ca_topic_score_gemma":0.000006278411,"domain_scores_codex":[0.9979013,0.0002855075,0.0003062326,0.0006966816,0.0005412354,0.0002690123],"domain_scores_gemma":[0.9988784,0.0002999784,0.0002682701,0.0001790637,0.0002167252,0.0001575597],"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":[0.0002292611,0.0001084401,0.02034041,0.00001079763,0.0001044555,0.0001244421,0.001433963,0.2469853,0.003115409,0.5278226,0.00009991682,0.199625],"study_design_scores_gemma":[0.0008034695,0.0004578842,0.00434363,0.00008603114,0.000004458516,0.000007104474,0.00006856927,0.9870999,0.0004398571,0.002757545,0.003670356,0.0002611371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01559951,0.0001261289,0.9499592,0.01729796,0.0007490451,0.0003538746,0.000006462586,0.000821946,0.01508591],"genre_scores_gemma":[0.9900829,0.0001542669,0.006856175,0.0022562,0.0001107278,0.00002051155,0.00004290639,0.00002030975,0.0004560052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9744834,"threshold_uncertainty_score":0.9488441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963885834","doi":"10.1609/aaai.v32i1.11299","title":"TIMERS: Error-Bounded SVD Restart on Dynamic Networks","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Tencent","keywords":"Singular value decomposition; Computer science; Margin (machine learning); Reset (finance); Algorithm; Bounded function; Dynamic network analysis; Singular value; Upper and lower bounds; Process (computing); Mathematical optimization; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.06146482267875695,"gpt":0.3112352360366101,"spread":0.2497704133578532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004529529,0.0003850048,0.0003620001,0.0001887459,0.000443421,0.0003136184,0.003241183,0.0001670202,0.00007164253],"category_scores_gemma":[0.000268719,0.0002936291,0.0001765127,0.001361673,0.0008909035,0.0006027083,0.0005655158,0.0006223216,0.0002938427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008331666,"about_ca_system_score_gemma":0.00007254721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001514569,"about_ca_topic_score_gemma":0.00003436308,"domain_scores_codex":[0.9970735,0.00003327473,0.0006453972,0.0008865638,0.0006678785,0.0006934074],"domain_scores_gemma":[0.9977326,0.0001696832,0.00051189,0.0006918475,0.0007585818,0.000135329],"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":[0.000187438,0.0001490439,0.00006108017,0.00001235725,0.00002127385,0.000001516298,0.0005158018,0.0009029052,0.007171585,0.9271912,0.0007101653,0.06307565],"study_design_scores_gemma":[0.00004190247,0.0008457993,0.0001971332,0.0003203122,0.00001212233,0.000007550454,0.0001462284,0.5731317,0.07987756,0.3447128,0.0003102294,0.0003966047],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.411348,0.0001256615,0.5048404,0.01615683,0.006042202,0.002454574,0.00001174513,0.001133871,0.05788669],"genre_scores_gemma":[0.9931258,0.00004112457,0.005236852,0.0009000125,0.000193134,0.00002534298,6.730331e-7,0.00002676106,0.0004502778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5824784,"threshold_uncertainty_score":0.9999516,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2942315111","doi":"10.1613/jair.1.13225","title":"Graph Kernels: A Survey","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Graph; Theoretical computer science; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.2937579756576601,"gpt":0.4530306973098932,"spread":0.1592727216522331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005932336,0.0001313063,0.0002923237,0.0005245474,0.0002471808,0.0004011359,0.001673191,0.0000953419,0.00007247613],"category_scores_gemma":[0.002417294,0.000113768,0.0001952814,0.003884023,0.0002445156,0.0008178765,0.0004490283,0.001252211,0.00009820436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007678657,"about_ca_system_score_gemma":0.0005069221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003182423,"about_ca_topic_score_gemma":0.0001489597,"domain_scores_codex":[0.9954671,0.001229742,0.0008241069,0.0003450659,0.001472941,0.0006610096],"domain_scores_gemma":[0.9936244,0.001825964,0.000230737,0.0005942302,0.003416764,0.0003079031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000191096,0.0006307015,0.002183001,0.00002463211,0.0001033111,0.002795389,0.001025244,0.008257848,0.02388133,0.1759886,0.003962173,0.7809566],"study_design_scores_gemma":[0.00007061201,0.00073601,0.003380781,0.0001638076,0.000006068954,0.0007620552,0.0007063636,0.03056114,0.2816873,0.6793451,0.002210115,0.0003706135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0593299,0.001484775,0.936141,0.001601682,0.000964521,0.0000914292,0.000001964303,0.00002496145,0.0003597436],"genre_scores_gemma":[0.9697821,0.000918965,0.02864277,0.0001110994,0.0003663133,0.000002479239,8.875746e-7,0.00001520837,0.0001602534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9104521,"threshold_uncertainty_score":0.5440301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4293107948","doi":"10.1007/s10601-022-09327-y","title":"Learning the travelling salesperson problem requires rethinking generalization","year":2022,"lang":"en","type":"article","venue":"Constraints","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Generalization; Computer science; Pipeline (software); Artificial intelligence; Artificial neural network; Machine learning; Deep learning; Graph; Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02172918509130155,"gpt":0.2412136384714505,"spread":0.2194844533801489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000524291,0.0001108779,0.0000946998,0.00006179079,0.001047752,0.0001170487,0.0007477321,0.00002790903,0.00005511045],"category_scores_gemma":[0.00003440845,0.00009372955,0.00005621498,0.0005172986,0.0001543085,0.0002495194,0.0002873269,0.0005028095,0.000005218551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005210691,"about_ca_system_score_gemma":0.00004599964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003441044,"about_ca_topic_score_gemma":0.000002296532,"domain_scores_codex":[0.9985901,0.0002784274,0.0001933396,0.0003343824,0.0003209557,0.0002828456],"domain_scores_gemma":[0.9993632,0.0001502913,0.0001379421,0.0002730745,0.00003446001,0.0000409638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007471302,0.00002276766,0.00112077,0.00001119954,0.00002361223,0.00006339452,0.01461189,0.4026646,0.005781813,0.2249688,0.0004061267,0.3503176],"study_design_scores_gemma":[0.0006056878,0.0002368774,0.0006049322,0.00006157962,0.00001537568,0.0003878188,0.001636048,0.8832058,0.001382614,0.09897213,0.01228695,0.0006041623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04000819,0.0003143734,0.9539479,0.001825218,0.0005286228,0.0003126648,0.000001359788,0.000373249,0.002688438],"genre_scores_gemma":[0.9733128,0.00002183902,0.02572163,0.0005948363,0.00007327329,0.00003110972,0.00000588286,0.00001259546,0.0002260552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9333046,"threshold_uncertainty_score":0.8058565,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173856251","doi":"10.1109/tkde.2021.3090664","title":"Hierarchical Multi-View Graph Pooling with Structure Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Pooling; Theoretical computer science; Graph; Upsampling; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01904280756439184,"gpt":0.2570408665654081,"spread":0.2379980590010163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006299529,0.0001844163,0.0001786393,0.0001191377,0.0001883586,0.00009779711,0.0004188205,0.00006308717,0.000006090596],"category_scores_gemma":[0.000007490387,0.0001647212,0.00003089637,0.0006317936,0.00002572537,0.0005929618,0.00002067054,0.0006366213,0.000003522664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001188804,"about_ca_system_score_gemma":0.00003249869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001359171,"about_ca_topic_score_gemma":0.00003612683,"domain_scores_codex":[0.9989044,0.00003303893,0.0001431506,0.0005460316,0.0001113307,0.0002620336],"domain_scores_gemma":[0.9989986,0.0001429391,0.00002164683,0.0006604624,0.00004785588,0.0001285413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001216634,0.0001080078,0.00004547948,0.0001375093,0.0001010179,0.0001289342,0.0005057104,0.7960659,0.005525045,0.001056878,0.00002537219,0.196288],"study_design_scores_gemma":[0.0005480915,0.00006780569,0.000233104,0.0002341144,0.00002887175,0.0002198717,0.00001487988,0.9883364,0.006607865,0.0000669059,0.003286783,0.0003553196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004413978,0.00168592,0.99318,0.00005616011,0.0003290222,0.00006331563,0.00002141247,0.0002352056,0.00001497586],"genre_scores_gemma":[0.8424382,0.0005158379,0.1568389,0.00003615573,0.00005313014,0.000005902796,0.0000187862,0.0000240918,0.00006908045],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8380241,"threshold_uncertainty_score":0.6717135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2546973305","doi":"10.14778/3007263.3007267","title":"GraphJet","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Graph; Exploit; Theoretical computer science; Clique-width; Line graph; Voltage graph","retraction":null,"screen_n_in":null,"score":{"opus":0.006945037593673362,"gpt":0.1942015750778655,"spread":0.1872565374841921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001270792,0.0001117197,0.0001149063,0.00005739829,0.00007183212,0.00002657684,0.001375176,0.00002789134,0.000005593214],"category_scores_gemma":[0.00004104294,0.00005280023,0.0001070718,0.0004153,0.00008620361,0.0004296556,0.0005368768,0.00006220458,0.000009251295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002751165,"about_ca_system_score_gemma":0.000007783081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002165058,"about_ca_topic_score_gemma":4.576678e-7,"domain_scores_codex":[0.9990023,0.000003686069,0.0001844942,0.0002588848,0.0003002628,0.0002503177],"domain_scores_gemma":[0.9994096,0.00004418859,0.0001711645,0.0002176061,0.0001020161,0.00005547066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001332902,0.0000679858,0.008830296,0.0000215225,0.00003033988,5.88333e-7,0.0001888085,0.000007053108,0.2449301,0.6714856,0.008027935,0.06639641],"study_design_scores_gemma":[0.0008428018,0.000148359,0.008774417,0.0002095142,0.00001223295,0.00002730149,0.00002031485,0.0002668115,0.6893929,0.2864514,0.01356909,0.0002848869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7553497,0.00109715,0.1230906,0.06280648,0.004206116,0.002636927,0.00001438138,0.001310947,0.04948776],"genre_scores_gemma":[0.9898244,0.00006108803,0.00931329,0.0002652331,0.00004214833,0.00002559076,2.24152e-8,0.000007289595,0.0004609141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4444628,"threshold_uncertainty_score":0.2555442,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966459188","doi":"10.24963/ijcai.2019/268","title":"TransMS: Knowledge Graph Embedding for Complex Relations by Multidirectional Semantics","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":76,"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 Key Research and Development Program of China; Science and Technology Commission of Shanghai Municipality","keywords":"Embedding; Computer science; Knowledge graph; Scalability; Theoretical computer science; Graph; Semantics (computer science); Natural language processing; Artificial intelligence; Programming language; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.01942765360007787,"gpt":0.2909674769819032,"spread":0.2715398233818254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009854264,0.0001306034,0.0001408004,0.00009478035,0.0001828843,0.00005171825,0.0003697295,0.00006130763,0.0000566116],"category_scores_gemma":[0.000007671435,0.000122229,0.0001230231,0.0004559511,0.0000316318,0.0004616047,0.00004970382,0.0001152364,0.00008373745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002209579,"about_ca_system_score_gemma":0.00001513792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002037661,"about_ca_topic_score_gemma":0.000008808145,"domain_scores_codex":[0.9990122,0.00002674187,0.000201263,0.0003678785,0.0001215483,0.0002704224],"domain_scores_gemma":[0.9990984,0.0003909388,0.00005121119,0.0002901127,0.0000974576,0.00007192513],"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":[0.00002850936,0.0003865324,0.003772775,0.00006224909,0.0001005057,0.000001390516,0.0009112876,0.04528391,0.04095864,0.6762626,0.1917723,0.04045925],"study_design_scores_gemma":[0.0005981849,0.00006086098,0.0006685545,0.00001410428,0.000004262198,0.000006312472,0.00001713557,0.8955997,0.001008791,0.01127871,0.09051019,0.0002331944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002630108,0.0001693193,0.9921805,0.0006092403,0.0005637279,0.0004006077,0.000009881688,0.0003154115,0.003121188],"genre_scores_gemma":[0.4802833,0.00002277106,0.5152469,0.0002110975,0.00005317,0.00003557837,0.00002710849,0.00001742674,0.004102649],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8503158,"threshold_uncertainty_score":0.4984353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2949865801","doi":"","title":"LanczosNet: Multi-Scale Deep Graph Convolutional Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Computer science; Graph; Theoretical computer science; Laplacian matrix; Deep learning; Adjacency matrix; Algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.05126511466307922,"gpt":0.1852913280843273,"spread":0.1340262134212481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001785895,0.0005323555,0.0005222161,0.0003095172,0.0002143966,0.0001168342,0.002831206,0.0005810281,0.00003166224],"category_scores_gemma":[0.00001249066,0.0006237194,0.0004349037,0.0009729741,0.0002265372,0.0005433225,0.002804748,0.001344493,0.0001661161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001818087,"about_ca_system_score_gemma":0.0001131195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004539332,"about_ca_topic_score_gemma":0.0001115856,"domain_scores_codex":[0.9968526,0.000180075,0.000293324,0.001777935,0.0001450782,0.0007509367],"domain_scores_gemma":[0.9970763,0.0001901841,0.0003775552,0.001867003,0.0002090086,0.0002799756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002247654,0.00007592396,0.009610408,0.00002432225,0.00006972579,0.0001369567,0.00004188165,0.9468793,0.00000824954,0.04227466,0.0004303335,0.0004257835],"study_design_scores_gemma":[0.0007217391,0.00003871593,0.005876459,0.0000697651,0.00003896664,0.000009982529,0.00001445289,0.9685754,0.00001062229,0.02349776,0.0004737284,0.0006724026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01912174,0.0005135802,0.9762119,0.00006568091,0.002265628,0.0004787651,0.00001583405,0.0005017431,0.0008251299],"genre_scores_gemma":[0.9809318,0.0004623001,0.01640219,0.0003222918,0.0001940815,0.000002411216,0.00005737918,0.0000381911,0.001589406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.96181,"threshold_uncertainty_score":0.9996214,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3093694263","doi":"","title":"FLAG: Adversarial Data Augmentation for Graph Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Graph; Adversarial system; Flag (linear algebra); Node (physics); Code (set theory); Artificial neural network; Artificial intelligence; Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1152999739681295,"gpt":0.2230016270728497,"spread":0.1077016531047202,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002514266,0.0004413393,0.000434371,0.0002203499,0.0002801364,0.000292833,0.004356369,0.0003872931,0.00001184414],"category_scores_gemma":[0.00004812176,0.0005458182,0.0003091143,0.0009500299,0.0001194488,0.00157019,0.005759543,0.0007478122,0.000003330202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001217038,"about_ca_system_score_gemma":0.00012533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005645959,"about_ca_topic_score_gemma":0.0001352892,"domain_scores_codex":[0.9965618,0.000184675,0.0003092655,0.002234203,0.0001245701,0.0005855128],"domain_scores_gemma":[0.9957509,0.0002902925,0.0004018392,0.003130662,0.0002178375,0.0002084383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007571671,0.00005072591,0.0003038615,0.00003601486,0.000107688,0.000185317,0.00005423891,0.9761512,0.00001157165,0.01890181,0.00147206,0.00264977],"study_design_scores_gemma":[0.0009620178,0.00005277412,0.0001942873,0.00005021267,0.000118129,0.000005945754,0.00005045446,0.9816434,0.0000211068,0.01607986,0.0002929144,0.0005289065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0179874,0.0001990332,0.9746874,0.000138319,0.005793934,0.0007076515,0.00005820067,0.000331455,0.0000966056],"genre_scores_gemma":[0.9823207,0.0002770975,0.01520445,0.0002915099,0.0004721562,0.000004111822,0.001055108,0.00003644204,0.0003384103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9643333,"threshold_uncertainty_score":0.9996994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3185513611","doi":"10.1109/tkde.2022.3220948","title":"Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Randomness; Computer science; Adjacency matrix; Correlation clustering; Feature (linguistics); Graph; Clustering coefficient; Encoder; Data mining; Pattern recognition (psychology); Theoretical computer science; Artificial intelligence; Algorithm; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05141376820259933,"gpt":0.2706461837856772,"spread":0.2192324155830779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003528534,0.000233311,0.0002231956,0.0003506531,0.0006529049,0.00009500977,0.001091345,0.00005885577,0.000004616655],"category_scores_gemma":[0.000004540154,0.0002619003,0.00008619091,0.000832136,0.00002186541,0.001176553,0.00007943263,0.0004862723,0.000001239713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004772844,"about_ca_system_score_gemma":0.00002582185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005519607,"about_ca_topic_score_gemma":0.00001865789,"domain_scores_codex":[0.9984136,0.00003806743,0.0002618097,0.0007018227,0.0001804668,0.0004042282],"domain_scores_gemma":[0.9985359,0.0002682478,0.00004702292,0.0009876703,0.00004439318,0.0001168222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001359659,0.00005254314,6.150192e-7,0.00004043485,0.00004012481,0.000005441871,0.0004926433,0.9754489,0.0005475667,0.001219682,0.0001978839,0.02194056],"study_design_scores_gemma":[0.0004471912,0.00009033839,0.000004075422,0.00003327492,0.00002352833,0.00004821858,0.0000146287,0.9925967,0.0004326911,0.00399357,0.002020407,0.0002953717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004127463,0.0006584151,0.9963865,0.00009538344,0.001355463,0.0003141962,0.0002332014,0.0005118487,0.00003226931],"genre_scores_gemma":[0.8858261,0.0001517802,0.1134845,0.00009370599,0.0000544348,0.0002174664,0.00005488359,0.00004628066,0.00007092352],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8854133,"threshold_uncertainty_score":0.9999833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391884321","doi":"10.1145/3648358","title":"Distributed Graph Neural Network Training: A Survey","year":2024,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Microsoft Research Asia; Beijing Nova Program; Hong Kong University of Science and Technology; Shanghai Jiao Tong University; National Natural Science Foundation of China; Microsoft Research; National Science and Technology Major Project; National Science Foundation","keywords":"Computer science; Workload; Distributed computing; Partition (number theory); Graph; Artificial neural network; Artificial intelligence; Machine learning; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1308699428806917,"gpt":0.357007057581011,"spread":0.2261371147003193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.008114265,0.001476238,0.003344601,0.000435383,0.0004666983,0.0009192008,0.007375132,0.0006290384,0.000004448195],"category_scores_gemma":[0.001195807,0.001237915,0.001339601,0.007613379,0.0001907446,0.0003494359,0.004498805,0.002454827,0.0001658274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001400429,"about_ca_system_score_gemma":0.0003592945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007639192,"about_ca_topic_score_gemma":0.0001182793,"domain_scores_codex":[0.9859574,0.007213378,0.001745617,0.002395666,0.0007218652,0.001966091],"domain_scores_gemma":[0.9880466,0.006897188,0.0008986993,0.003535852,0.0002049788,0.0004166715],"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":[8.785722e-7,0.00002179507,0.00007715708,0.001344902,0.0002441114,0.0002048749,0.00005656602,0.002906627,6.521021e-9,0.0007606849,0.01040028,0.9839821],"study_design_scores_gemma":[0.00038594,0.000234439,0.002282476,0.01781055,0.0007330959,0.0007040743,0.000005306525,0.07095128,5.324044e-8,0.01186453,0.8908889,0.004139373],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000005771005,0.7096337,0.2832311,0.00004243376,0.004946974,0.0005832603,0.0001431665,0.001376406,0.00003723357],"genre_scores_gemma":[0.0006420878,0.9811278,0.01493288,0.0001226727,0.001291531,0.00003590123,0.001520179,0.0002335673,0.00009337796],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9798427,"threshold_uncertainty_score":0.9998466,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156954687","doi":"10.1609/aaai.v25i1.7917","title":"Learning Structured Embeddings of Knowledge Bases","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":66,"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":"WordNet; Computer science; Artificial intelligence; Natural language processing; Process (computing); Knowledge extraction; Natural language; Information retrieval; Information extraction; Word (group theory); Annotation","retraction":null,"screen_n_in":null,"score":{"opus":0.08527527762667422,"gpt":0.2914836337513474,"spread":0.2062083561246732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003085425,0.0002472731,0.0003283961,0.000168415,0.0001635778,0.00005770248,0.002341258,0.00009766917,0.00007885647],"category_scores_gemma":[0.0004117554,0.0001850229,0.0001585325,0.0009975332,0.0004063898,0.0005152524,0.0005454783,0.000427662,0.00002317752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002232362,"about_ca_system_score_gemma":0.00005868882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002187504,"about_ca_topic_score_gemma":0.000007483732,"domain_scores_codex":[0.9981744,0.00002533684,0.0005963441,0.0004871307,0.0003532179,0.0003636302],"domain_scores_gemma":[0.9981018,0.0001183222,0.0006202456,0.0003120666,0.000756362,0.00009116604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006335795,0.0001081398,0.0008752369,0.00004311907,0.00001527021,4.408329e-7,0.004130788,0.0001002028,0.04865031,0.8481479,0.00005030123,0.0978149],"study_design_scores_gemma":[0.00002223591,0.0003110669,0.0005914764,0.0002006265,0.00001020274,0.000004338323,0.0004276515,0.03277687,0.7511393,0.214264,0.00005640421,0.0001958565],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8428326,0.0001322495,0.09104174,0.000617197,0.001433087,0.0009293151,0.000005912993,0.0004020021,0.06260586],"genre_scores_gemma":[0.9890026,0.00003260486,0.01066502,0.00005071338,0.00003856541,0.00001137366,1.827143e-7,0.0000145055,0.0001844547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.702489,"threshold_uncertainty_score":0.7545015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3047456059","doi":"10.1109/infocom41043.2020.9155370","title":"Guardian: Evaluating Trust in Online Social Networks with Graph Convolutional Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Guardian; Scalability; Social graph; Graph; Social network (sociolinguistics); Viral marketing; Data science; Social media; Artificial intelligence; Theoretical computer science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03636358331498197,"gpt":0.2838109764218088,"spread":0.2474473931068268,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002409682,0.0002779991,0.0003430943,0.00008674374,0.0002163388,0.0001003089,0.0007869367,0.0001431965,0.00003515104],"category_scores_gemma":[0.00002996498,0.0002398317,0.000111577,0.001969661,0.0001363448,0.0005530054,0.0002884908,0.0006512267,0.000005917699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004739852,"about_ca_system_score_gemma":0.00007116775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001404671,"about_ca_topic_score_gemma":0.00009516077,"domain_scores_codex":[0.9976029,0.0001547784,0.000411723,0.0007076389,0.0004565277,0.0006664527],"domain_scores_gemma":[0.9990953,0.0001780762,0.0001525741,0.0002645949,0.0001114643,0.0001979929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007293272,0.00005175411,0.008279046,0.000004333629,0.0000247093,0.00004597981,0.0001803321,0.9443988,0.00001195911,0.02142481,0.001622054,0.02388326],"study_design_scores_gemma":[0.0009930934,0.000217007,0.01812339,0.00001866655,0.000007557437,0.00001186961,0.00005219812,0.9788727,0.000002816517,0.001182277,0.0001977657,0.000320649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01805815,0.0003011658,0.9753787,0.004847324,0.0002259684,0.000305237,0.000002555953,0.0003252403,0.0005556638],"genre_scores_gemma":[0.8985404,0.00002652291,0.09439442,0.006067003,0.0008506277,0.00002467641,0.00002953742,0.00002577891,0.00004098066],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8809843,"threshold_uncertainty_score":0.9780054,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035707368","doi":"10.18653/v1/2020.acl-main.526","title":"ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Embedding; Relation (database); Computer science; Theoretical computer science; Knowledge graph; Graph; Artificial intelligence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.01780149421137464,"gpt":0.2549994744631446,"spread":0.23719798025177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001072663,0.0002242948,0.000202057,0.00005056098,0.0003566454,0.0001701581,0.0003830218,0.0001009075,0.00001491263],"category_scores_gemma":[0.00002042769,0.0001831601,0.00009278322,0.001261919,0.00007928299,0.00332449,0.0001633309,0.0001787421,0.00003623201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091219,"about_ca_system_score_gemma":0.000045713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003532202,"about_ca_topic_score_gemma":0.00001634685,"domain_scores_codex":[0.9985391,0.00004550627,0.0004145146,0.00036282,0.0002468671,0.0003911221],"domain_scores_gemma":[0.998985,0.00007017511,0.000226483,0.0002850336,0.0002546445,0.0001786712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007549694,0.000005244506,0.0009470724,0.00003466628,0.00001875735,0.000001038999,0.0007341935,0.784871,0.00001434275,0.1254986,0.006124272,0.08167531],"study_design_scores_gemma":[0.0007016464,0.0002575539,0.004520314,0.00004418036,0.000007774646,0.00001342036,0.0001222673,0.972033,0.0000380645,0.01951522,0.002439796,0.0003068096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003944784,0.00008779384,0.9932275,0.0009071216,0.0003236676,0.000560738,0.000005911113,0.0005144813,0.0004280482],"genre_scores_gemma":[0.8076088,0.00001378974,0.1910859,0.0009350138,0.0002336657,0.0000424286,0.00006213765,0.000008449762,0.000009759401],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.803664,"threshold_uncertainty_score":0.7469052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4282913028","doi":"10.1109/tnnls.2022.3177775","title":"CLEAR: Cluster-Enhanced Contrast for Self-Supervised Graph Representation Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Theoretical computer science; Graph; Artificial intelligence; Feature learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01326984234264895,"gpt":0.2394135342971649,"spread":0.226143691954516,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005744438,0.0003276879,0.000411958,0.0002356946,0.002622792,0.0003261603,0.0004465113,0.0001076785,0.000009004866],"category_scores_gemma":[0.00001248983,0.0003410484,0.0002231664,0.0008941665,0.00005154894,0.0005346622,0.0000169538,0.001630639,0.000001774337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006917251,"about_ca_system_score_gemma":0.00001593906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004239481,"about_ca_topic_score_gemma":0.000007655632,"domain_scores_codex":[0.9965573,0.001049629,0.0005129658,0.0008585713,0.0004023304,0.000619179],"domain_scores_gemma":[0.9980805,0.000994209,0.0002877105,0.0003636808,0.00009928694,0.0001746104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000183068,0.00005751156,0.00005224867,0.00002660141,0.00005268988,0.000006011638,0.0005163839,0.961671,0.000274087,0.0001842509,0.00008897089,0.0368872],"study_design_scores_gemma":[0.001374576,0.001139357,0.00006027146,0.00003184702,0.00003316114,0.00007942789,0.0005485081,0.9950241,0.00006418158,0.00004007241,0.001240689,0.0003638212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04767253,0.0003698305,0.9474338,0.0002415202,0.002385568,0.001021009,0.000003729886,0.0008152138,0.00005683952],"genre_scores_gemma":[0.9965162,0.0001157818,0.001663367,0.0002267785,0.0001920864,0.0006078347,0.00001052582,0.00005636023,0.0006110562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9488437,"threshold_uncertainty_score":0.9999042,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3006053005","doi":"10.48550/arxiv.1911.06962","title":"Inductive Relation Prediction by Subgraph Reasoning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Relation (database); Inductive reasoning; Mathematics; Computer science; Artificial intelligence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03719935338676308,"gpt":0.171996814774414,"spread":0.1347974613876509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001659167,0.0003272686,0.0002831646,0.0002912068,0.0001707475,0.00009118531,0.001210265,0.0004705591,0.000007063972],"category_scores_gemma":[0.00002782357,0.0003987704,0.0001880722,0.00096688,0.00008924041,0.001121569,0.001192441,0.001110876,0.00005097181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002697503,"about_ca_system_score_gemma":0.00008568198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000615261,"about_ca_topic_score_gemma":0.000007288961,"domain_scores_codex":[0.9977604,0.0001678547,0.0002066385,0.001373506,0.0001293167,0.0003622846],"domain_scores_gemma":[0.9980032,0.0001034463,0.0003993619,0.001207934,0.0001546056,0.0001314824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003865603,0.00005911248,0.02997504,0.00003098146,0.0001034629,0.00005904136,0.0002368879,0.785209,0.0001309189,0.1809594,0.002082546,0.001114986],"study_design_scores_gemma":[0.0004713668,0.00008727206,0.009489422,0.00016168,0.00005676352,0.000005368493,0.00004143115,0.9021975,0.0001441796,0.08614918,0.0006463373,0.0005494659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1875885,0.0001047647,0.8085555,0.00005112989,0.001226368,0.0003635382,0.00002140527,0.0004218027,0.001666952],"genre_scores_gemma":[0.9942458,0.000233723,0.004130384,0.00006338395,0.00008202206,0.000001380273,0.00006785456,0.00002349222,0.00115201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8066572,"threshold_uncertainty_score":0.9998464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3165146808","doi":"10.1016/j.ailsci.2022.100036","title":"Understanding the performance of knowledge graph embeddings in drug discovery","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in the Life Sciences","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Ranking (information retrieval); Identification (biology); Context (archaeology); Domain knowledge; Machine learning; Hyperparameter; Graph; Drug discovery; Knowledge graph; Embedding; Process (computing); Data science; Artificial intelligence; Data mining; Theoretical computer science; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.11443593632942,"gpt":0.3198195361523598,"spread":0.2053835998229397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003733705,0.0001414939,0.0001708763,0.0003467387,0.0008747517,0.0001550534,0.003950549,0.0000194293,0.000009535069],"category_scores_gemma":[0.0001242613,0.00008729938,0.00007511507,0.005748517,0.0009749414,0.001178799,0.0006566236,0.0004626712,0.000004890317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006851977,"about_ca_system_score_gemma":0.0001268795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001115872,"about_ca_topic_score_gemma":0.0004270887,"domain_scores_codex":[0.9974962,0.0004287092,0.0005317043,0.000439749,0.0006425385,0.0004611003],"domain_scores_gemma":[0.9980692,0.001236604,0.0001956862,0.0004441248,0.00002172205,0.00003264945],"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":[0.00001709881,0.0001143636,0.004484168,0.00000700413,0.000002681423,0.000005042963,0.01787755,0.3020123,0.0001863174,0.6704233,0.0001169614,0.004753282],"study_design_scores_gemma":[0.00002485829,0.0001952908,0.0008506808,0.00004114207,0.000002890542,0.00001206502,0.02531899,0.5643408,0.00230529,0.4066226,0.00007813484,0.0002072309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8731111,0.0007075226,0.1195001,0.00371843,0.001105062,0.0004165116,0.00000197333,0.0000377804,0.001401539],"genre_scores_gemma":[0.9988279,0.00008242961,0.0005462537,0.0004329401,0.00003914139,0.0000478261,2.39324e-7,0.000004273698,0.00001904729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2638006,"threshold_uncertainty_score":0.7341169,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4377099260","doi":"10.1145/3597428","title":"The Evolution of Distributed Systems for Graph Neural Networks and Their Origin in Graph Processing and Deep Learning: A Survey","year":2023,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Deep learning; Categorization; Scalability; Artificial intelligence; Graph; Artificial neural network; Deep neural networks; Machine learning; Theoretical computer science; Data science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.06068414396664795,"gpt":0.3193867958571259,"spread":0.258702651890478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008779772,0.0005991183,0.001594136,0.0003577634,0.0006159074,0.0004056494,0.00155282,0.0003085422,2.168365e-8],"category_scores_gemma":[0.001386918,0.0004127028,0.0002207401,0.003537067,0.0002588217,0.000227855,0.001050212,0.0008863879,1.679464e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009574649,"about_ca_system_score_gemma":0.00009414516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004145098,"about_ca_topic_score_gemma":0.0005633297,"domain_scores_codex":[0.992421,0.004352861,0.001189655,0.0009912105,0.0002341359,0.000811101],"domain_scores_gemma":[0.984891,0.01277577,0.001187076,0.0007762028,0.000256432,0.0001134935],"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":[0.000005771188,0.00001383786,0.005678031,0.002812202,0.00006798218,0.000003662756,0.00006824991,0.04607738,4.524281e-8,0.000416191,0.00001798053,0.9448386],"study_design_scores_gemma":[0.0002878176,0.0001019908,0.01169157,0.00443159,0.00003845621,0.00004049309,0.00004317664,0.9793227,2.103602e-8,0.00115432,0.002376976,0.0005109425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002638209,0.53544,0.4630271,0.000006331858,0.0004036177,0.0007111322,0.00001693917,0.0001306469,4.25104e-7],"genre_scores_gemma":[0.08436555,0.9145521,0.0005867616,0.000003085967,0.0001275186,0.00007924037,0.0001924286,0.00008530406,0.000007991628],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9443277,"threshold_uncertainty_score":0.9998325,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2981898874","doi":"10.1109/tnnls.2020.3044146","title":"Hierarchical Representation Learning in Graph Neural Networks With Node Decimation Pooling","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Pooling; Decimation; Adjacency matrix; Computer science; Preprocessor; Graph; Theoretical computer science; Artificial intelligence; Pattern recognition (psychology); Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01764219419340182,"gpt":0.2414166420792822,"spread":0.2237744478858803,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003291244,0.0004052994,0.0004839016,0.0002504577,0.0007014863,0.0004384792,0.0003788139,0.0002029037,0.000002920699],"category_scores_gemma":[0.00002315304,0.0003647168,0.0001224716,0.001729352,0.0001030358,0.0009204397,0.00001240612,0.002786211,0.00000196008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004067346,"about_ca_system_score_gemma":0.00001364779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008328637,"about_ca_topic_score_gemma":0.000029882,"domain_scores_codex":[0.9964249,0.0008987493,0.0006155737,0.000957205,0.0004233405,0.000680265],"domain_scores_gemma":[0.998337,0.0007062057,0.0002847194,0.0002893359,0.00007707427,0.0003056157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001769571,0.00002556165,0.002385667,0.00002127112,0.00002253762,0.00006130514,0.0004339975,0.9609151,0.00004232649,0.00009775785,0.0000109643,0.03580654],"study_design_scores_gemma":[0.0008676651,0.0005230828,0.001301263,0.0001272053,0.00001962726,0.0001089264,0.0001647039,0.9964144,0.00001265486,0.00001252276,0.00006030121,0.0003876051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1061273,0.0004156747,0.8910305,0.000838596,0.0005999289,0.0004391798,4.842901e-7,0.0005193712,0.00002898633],"genre_scores_gemma":[0.9974545,0.0001643054,0.001488871,0.0004398136,0.0002782732,0.00007034463,0.000007557178,0.00005331995,0.00004303406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8913272,"threshold_uncertainty_score":0.9998805,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}