{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":216,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":216,"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":"8e06b9c4de61","filters":{"topic":"Authorship Attribution and Profiling"}},"results":[{"id":"W1014449310","doi":"10.1609/icwsm.v6i1.14340","title":"Homophily and Latent Attribute Inference: Inferring Latent Attributes of Twitter Users from Neighbors","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":319,"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":"Homophily; Assortativity; Inference; Computer science; Context (archaeology); Instant messaging; Machine learning; Artificial intelligence; World Wide Web; Psychology; Social psychology; Geography; Complex network","retraction":null,"screen_n_in":null,"score":{"opus":0.06759890956918559,"gpt":0.2797267150628564,"spread":0.2121278054936708,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002835799,0.0001557913,0.0002668564,0.00007748565,0.0001276178,0.0001668561,0.0006006878,0.0001156518,0.00004156724],"category_scores_gemma":[0.0004721835,0.0001240655,0.00008119512,0.0001934587,0.0001668547,0.0002964834,0.0005901051,0.0002536535,0.000002357492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003724108,"about_ca_system_score_gemma":0.0001367587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002544428,"about_ca_topic_score_gemma":0.00001204436,"domain_scores_codex":[0.9986137,0.00002073573,0.0003513226,0.0003165691,0.0005167096,0.000180966],"domain_scores_gemma":[0.9984953,0.0002644082,0.0002944828,0.0000818162,0.0007906391,0.00007338984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00005046131,0.0001106058,0.3894997,0.00006844409,0.0001776707,0.000003395635,0.009969378,0.000004071659,0.0516297,0.5429531,0.0003374815,0.005196017],"study_design_scores_gemma":[0.001989599,0.0001188095,0.7092719,0.0007762314,0.00008450683,0.00001326719,0.002073355,0.01328657,0.1558644,0.1147543,0.001106438,0.0006606209],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856766,0.00008954042,0.0004475163,0.01257758,0.0005703629,0.00008278795,0.00008499351,0.00002850094,0.0004420959],"genre_scores_gemma":[0.998622,0.0002022863,0.0006283386,0.0003357081,0.0001142235,0.000007183379,0.00001391926,0.000005899416,0.00007046562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4281988,"threshold_uncertainty_score":0.5059243,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170770919","doi":"10.1109/cmpsac.2004.1342667","title":"N-gram-based detection of new malicious code","year":2004,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Code (set theory); Signature (topology); Computer virus; Software; Malware; Data mining; Artificial intelligence; Programming language; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.03563911430917237,"gpt":0.2790708994228318,"spread":0.2434317851136594,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001541375,0.00005213299,0.00006771457,0.00005308651,0.00004251918,0.00002276137,0.0002241401,0.00004410304,0.00001942312],"category_scores_gemma":[0.00002557983,0.00004639497,0.00004018671,0.0002790417,0.00001333351,0.000102695,0.00002852289,0.0000587536,0.00005255271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000309627,"about_ca_system_score_gemma":0.0001101884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002256456,"about_ca_topic_score_gemma":0.00008341792,"domain_scores_codex":[0.9994814,0.00001884677,0.0001267822,0.000131836,0.000125593,0.0001155512],"domain_scores_gemma":[0.9996167,0.00001860502,0.00004752533,0.0002088605,0.00004006846,0.00006822806],"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":[0.00003967142,0.0001613697,0.001183379,0.00004165634,0.00002110171,0.00001299625,0.00109182,0.01663573,0.1257725,0.6714969,0.0002633476,0.1832795],"study_design_scores_gemma":[0.0005689012,0.0001038576,0.001067538,0.00001037473,0.000002677768,0.000005396307,0.00001086112,0.01916517,0.9617191,0.01508415,0.002162652,0.00009934643],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02769797,0.0000251966,0.9698327,0.001287091,0.0001709062,0.00005734242,5.724077e-7,0.000167478,0.0007607087],"genre_scores_gemma":[0.9467121,7.358576e-7,0.05256765,0.0004133739,0.00002062714,0.000001142209,7.595425e-7,0.000002442463,0.0002811704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9190142,"threshold_uncertainty_score":0.1891932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025882237","doi":"10.1093/llc/fqm023","title":"Bigrams of Syntactic Labels for Authorship Discrimination of Short Texts","year":2007,"lang":"en","type":"article","venue":"Literary and Linguistic Computing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bigram; Library science; History; Computer science; Media studies; Artificial intelligence; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.03613429507286367,"gpt":0.3221275605100855,"spread":0.2859932654372218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001768939,0.0001133119,0.0002188706,0.0001405238,0.0001230173,0.00004447315,0.0002384513,0.00007293835,0.000001705877],"category_scores_gemma":[0.0009336573,0.0001090485,0.00006195995,0.0002952953,0.00004834296,0.00009917378,0.0001177393,0.0001207636,3.176784e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001152079,"about_ca_system_score_gemma":0.00002947087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007942479,"about_ca_topic_score_gemma":0.000001508049,"domain_scores_codex":[0.9987777,0.0000608036,0.00051015,0.0002562767,0.0001559971,0.0002391083],"domain_scores_gemma":[0.9981607,0.001165709,0.0001860576,0.0002005784,0.000200797,0.00008621241],"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":[0.00005050294,0.00009908898,0.01356507,0.0007849694,0.00002864339,0.000009259262,0.01657419,0.00002538156,0.001605839,0.5971708,0.000006987048,0.3700792],"study_design_scores_gemma":[0.001245464,0.0008945992,0.09015773,0.002131891,0.000132652,0.00007672492,0.0003259668,0.5982283,0.06466258,0.2374502,0.003743768,0.0009501211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2262995,0.000434484,0.7719418,0.00004814701,0.0004536559,0.0001619965,0.000005612556,0.00004867072,0.0006060609],"genre_scores_gemma":[0.9360153,0.000002009279,0.06371047,0.00004027513,0.0001665833,0.000001146627,0.00001274404,0.000006005603,0.00004546303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7097158,"threshold_uncertainty_score":0.4446867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2284070151","doi":"","title":"What's in a Name? Using First Names as Features for Gender Inference in Twitter","year":2013,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":168,"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":"Classifier (UML); Inference; Computer science; Artificial intelligence; Social media; Natural language processing; Baseline (sea); Information retrieval; Machine learning; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.2696613820475069,"gpt":0.4140428855734447,"spread":0.1443815035259378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007564912,0.000221959,0.0002251841,0.0004307184,0.0001577659,0.0008565188,0.0007394249,0.0001806797,0.0003452779],"category_scores_gemma":[0.001184518,0.0002191452,0.00006773289,0.0006438184,0.00009315644,0.001575068,0.0001197377,0.0003809399,0.0003485966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000224015,"about_ca_system_score_gemma":0.0004374832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002697832,"about_ca_topic_score_gemma":0.0003640529,"domain_scores_codex":[0.9977378,0.0001164857,0.0005473691,0.0005889277,0.0005698897,0.0004395349],"domain_scores_gemma":[0.9980236,0.0008139715,0.0001446928,0.0002376325,0.0006765059,0.0001036131],"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":[0.00003038254,0.000120014,0.0006435221,0.00001765581,0.000005344865,0.000003860294,0.002334476,0.007276491,0.0005901304,0.9589701,0.00005722823,0.02995074],"study_design_scores_gemma":[0.00005930999,0.00005802558,0.003060196,0.0001343322,0.000001187667,0.000003195648,0.000715495,0.4526847,0.007317478,0.5355757,0.0001269691,0.0002633804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1411749,0.0001654101,0.842651,0.01142354,0.001181064,0.001256201,0.000008435592,0.0001093411,0.002030144],"genre_scores_gemma":[0.9894788,0.00003751522,0.008753578,0.001350547,0.00007497396,0.0001620183,0.000009792398,0.000009419875,0.0001233978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8483039,"threshold_uncertainty_score":0.8936483,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125962012","doi":"10.1016/j.diin.2010.03.003","title":"Mining writeprints from anonymous e-mails for forensic investigation","year":2010,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Exploit; Cluster analysis; Stylometry; Anonymity; Identification (biology); Classifier (UML); Cybercrime; Focus (optics); Writing style; Information retrieval; World Wide Web; Data science; Data mining; Artificial intelligence; Computer security; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.04413737110212299,"gpt":0.2634196282676218,"spread":0.2192822571654988,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003341767,0.0001614536,0.0001402622,0.0001026572,0.0001876683,0.0006696037,0.0004055627,0.0001531518,0.00001189089],"category_scores_gemma":[0.0007522777,0.000168913,0.0000697007,0.0003239246,0.0001402299,0.002037882,0.0001057196,0.0001846063,0.0001303682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002984679,"about_ca_system_score_gemma":0.0001217407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001931326,"about_ca_topic_score_gemma":0.00001778493,"domain_scores_codex":[0.9986975,0.00002920694,0.0003275427,0.0004459692,0.0002385128,0.0002612886],"domain_scores_gemma":[0.9987534,0.0002491746,0.0001839559,0.000396068,0.0001908895,0.0002264662],"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":[0.0000285302,0.00005564861,0.1132916,0.0000602072,0.0000579792,0.000006662077,0.005682026,0.00009695774,0.1805705,0.5242626,0.006318494,0.1695687],"study_design_scores_gemma":[0.0008776979,0.00008836336,0.0259203,0.0000635148,0.00001404073,0.000009856008,0.000117442,0.1159823,0.3197247,0.5314464,0.005185666,0.0005697375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7538234,0.00001039264,0.2428554,0.001226217,0.0008300653,0.0002652686,0.00003638771,0.0002606181,0.0006922781],"genre_scores_gemma":[0.9068083,3.703437e-7,0.09158251,0.0006663078,0.0002057282,0.00004538142,0.00043433,0.00001346206,0.0002436071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.168999,"threshold_uncertainty_score":0.6888072,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2250194349","doi":"10.18653/v1/d13-1114","title":"Gender Inference of Twitter Users in Non-English Contexts","year":2013,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Public Safety Canada","keywords":"Inference; Computer science; Orthography; Natural language processing; Social media; Artificial intelligence; Data science; Linguistics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04556533857021437,"gpt":0.2934247514939073,"spread":0.2478594129236929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002205355,0.00006690097,0.0001061987,0.00007729817,0.00001802109,0.00004982403,0.0003814931,0.00005279855,0.0002994787],"category_scores_gemma":[0.00007982866,0.00005575074,0.00002667136,0.0002491148,0.00002589838,0.0004742309,0.000125589,0.0001075363,0.000143659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001467069,"about_ca_system_score_gemma":0.00004721198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001671888,"about_ca_topic_score_gemma":0.00001061396,"domain_scores_codex":[0.9992994,0.0000412744,0.0001928363,0.0001666478,0.0001261118,0.0001737402],"domain_scores_gemma":[0.9994141,0.00008393952,0.00004704237,0.0002463966,0.0001518343,0.000056619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007405512,0.0001588889,0.5918897,0.0000729868,0.00002591508,0.00000813286,0.02360607,0.0002297304,0.005180593,0.3428503,0.008530436,0.02743978],"study_design_scores_gemma":[0.001225585,0.00008615777,0.8529966,0.00005761323,0.000003170776,0.000001976052,0.0008574027,0.08881617,0.03298506,0.02066654,0.001776726,0.0005269443],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4039092,0.00001748096,0.576124,0.0003786599,0.0002757159,0.0001780399,3.975521e-7,0.00006621695,0.01905032],"genre_scores_gemma":[0.9901167,0.000001830925,0.008836996,0.0006408455,0.00001429373,0.000009330334,7.020573e-7,0.000002310373,0.0003770276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5862074,"threshold_uncertainty_score":0.3279082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123407642","doi":"10.1016/j.diin.2008.05.001","title":"A novel approach of mining write-prints for authorship attribution in e-mail forensics","year":2008,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Authorship attribution; Suspect; Computer science; Attribution; Decision tree; Support vector machine; Quality (philosophy); Information retrieval; Data mining; Data science; Computer security; Artificial intelligence; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1382981898189501,"gpt":0.2774152743910965,"spread":0.1391170845721464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005880459,0.0001257471,0.0001803054,0.0001582565,0.00009686949,0.00007408536,0.0002830893,0.0001295457,7.224609e-7],"category_scores_gemma":[0.0005785129,0.0001338602,0.00007016669,0.0006446182,0.0001327723,0.001096047,0.00008485364,0.0001150394,0.00000662319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000777742,"about_ca_system_score_gemma":0.0001436396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009026015,"about_ca_topic_score_gemma":0.000001829795,"domain_scores_codex":[0.9987491,0.00003488433,0.000414119,0.000314331,0.0002379934,0.0002495415],"domain_scores_gemma":[0.9991412,0.0001406906,0.000196482,0.0002310603,0.0001834964,0.0001070769],"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":[0.00005850515,0.0002287331,0.1257036,0.0002279938,0.00002654836,0.000004039815,0.01060731,0.001692689,0.009140586,0.8330095,0.0005534271,0.01874704],"study_design_scores_gemma":[0.002330024,0.0002683406,0.1286588,0.0002232274,0.00001214232,0.00009550866,0.0003589574,0.6942624,0.0834083,0.08865802,0.0009366552,0.0007875805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3699315,0.00001494146,0.6291485,0.0001587332,0.000096752,0.000205598,0.00002208031,0.00005546317,0.0003665125],"genre_scores_gemma":[0.8657624,9.330669e-7,0.1337858,0.00007093789,0.00003114073,0.00003234204,0.0001841592,0.000007344503,0.0001249667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7443514,"threshold_uncertainty_score":0.545866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041413176","doi":"10.3115/1073445.1073470","title":"Language and task independent text categorization with simple language models","year":2003,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":112,"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; Natural language processing; Categorization; Artificial intelligence; Task (project management); Language identification; Simple (philosophy); Language model; Variety (cybernetics); Independence (probability theory); Selection (genetic algorithm); Identification (biology); Feature (linguistics); Character (mathematics); Text categorization; Feature selection; Natural language; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01593452888467338,"gpt":0.2515908326777858,"spread":0.2356563037931124,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002379267,0.00008534313,0.00007814626,0.00004994899,0.00008711831,0.0001071991,0.000141336,0.00004545386,0.00005039508],"category_scores_gemma":[0.00001805354,0.00006398735,0.00001164753,0.0002208868,0.00001569756,0.000388713,0.00004631644,0.00008308241,0.00001962629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001771107,"about_ca_system_score_gemma":0.00003953505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008874888,"about_ca_topic_score_gemma":0.00005149088,"domain_scores_codex":[0.9992825,0.00006397082,0.00009506159,0.0002270485,0.0001625569,0.0001688437],"domain_scores_gemma":[0.9996035,0.00002709719,0.00003623074,0.0002199286,0.00003279169,0.00008048732],"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":[0.000004735944,0.00002881481,0.001470014,0.00001237244,0.0000111244,0.00002832031,0.0107516,0.0008562603,0.002419902,0.9759377,0.0001292703,0.00834992],"study_design_scores_gemma":[0.003604861,0.0004599752,0.003996884,0.00003995566,0.00004312044,0.0003638258,0.01516041,0.7476608,0.1628135,0.05916029,0.004911079,0.001785251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09488712,0.0001526375,0.8963147,0.0001246709,0.00003360818,0.00009696659,0.000001678957,0.0001279539,0.008260651],"genre_scores_gemma":[0.9864028,0.000004270036,0.01227799,0.0002752402,0.00001060228,0.00000503322,0.000009604252,0.000005716617,0.001008773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9167774,"threshold_uncertainty_score":0.2609329,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2251433042","doi":"10.3115/v1/w14-5904","title":"Automatic Identification of Arabic Language Varieties and Dialects in Social Media","year":2014,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Arabic; Computer science; Identification (biology); Natural language processing; Social media; Language identification; Linguistics; Artificial intelligence; Natural language; World Wide Web; Botany","retraction":null,"screen_n_in":null,"score":{"opus":0.01806990496924178,"gpt":0.2669399753216908,"spread":0.248870070352449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005985352,0.00003657915,0.00007804584,0.00006591412,0.00003636081,0.00003320113,0.0001313435,0.0000342019,0.00001483933],"category_scores_gemma":[0.0002158419,0.00003282684,0.00001139274,0.0001800882,0.00002983721,0.0001350854,0.00004327439,0.00004242925,0.000007857997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007361419,"about_ca_system_score_gemma":0.00001332793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001025789,"about_ca_topic_score_gemma":0.00002312639,"domain_scores_codex":[0.9994767,0.00009281488,0.0001573857,0.0000984178,0.0000990163,0.00007568901],"domain_scores_gemma":[0.9996451,0.0001666841,0.00005830095,0.0000917605,0.00002008665,0.00001811251],"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":[0.000001608596,0.00002499004,0.002692583,0.00006307833,0.00000331345,6.736884e-7,0.02794758,0.000003698021,0.009705025,0.8734931,0.00009503261,0.08596925],"study_design_scores_gemma":[0.000508209,0.00002808967,0.4067477,0.00001990227,0.000006199344,0.000003081491,0.0007042645,0.4361685,0.05490325,0.1006279,0.00006679268,0.0002161238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6319823,0.00004221478,0.3666908,0.0003863426,0.0001099523,0.00004478879,4.491545e-7,0.00006265768,0.0006804711],"genre_scores_gemma":[0.9976742,0.000001416254,0.002205154,0.00003997825,0.00002416253,0.000002758614,0.000001689475,0.000001454991,0.00004923321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7728653,"threshold_uncertainty_score":0.133864,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2085509246","doi":"10.1016/j.diin.2009.01.004","title":"Towards an integrated e-mail forensic analysis framework","year":2009,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Phishing; Spamming; Law enforcement; Harassment; Computer security; Context (archaeology); Child pornography; Cybercrime; Digital forensics; The Internet; Internet privacy; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.03798295588258519,"gpt":0.2880873846024712,"spread":0.250104428719886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002311663,0.0001255887,0.0001494762,0.000206129,0.0001018549,0.000688683,0.0003761431,0.0001111314,0.00001422563],"category_scores_gemma":[0.0002872856,0.0001145014,0.00009015462,0.002139533,0.00005512112,0.002042421,0.00003375033,0.000168618,0.00008157668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005004487,"about_ca_system_score_gemma":0.00007761065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001135336,"about_ca_topic_score_gemma":0.000002633054,"domain_scores_codex":[0.9989496,0.00005360303,0.000229686,0.0003187199,0.0002504198,0.0001979876],"domain_scores_gemma":[0.9991353,0.00003196781,0.00009501688,0.0003859373,0.0001505129,0.0002013287],"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":[0.000005758928,0.00004469769,0.006586044,0.000002972199,0.00006274341,0.000006022293,0.00128625,0.0007015635,0.0002011506,0.7246276,0.000350485,0.2661248],"study_design_scores_gemma":[0.0001119591,0.0001966119,0.04583871,0.00002657517,0.00004863188,0.00000406819,0.00009120795,0.2462537,0.008506199,0.6971607,0.001412983,0.0003486867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1341965,0.00002011327,0.8617458,0.0017729,0.0001305507,0.00006923142,0.000008893135,0.0003340959,0.001721968],"genre_scores_gemma":[0.9376775,9.21371e-7,0.06059181,0.001291037,0.00004440931,0.000002651659,0.0002595776,0.00000350133,0.0001285751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.803481,"threshold_uncertainty_score":0.6640986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2914961791","doi":"10.1145/3292577","title":"Code Authorship Attribution","year":2019,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"New Brunswick Innovation Foundation","keywords":"Computer science; Malware; Attribution; Authorship attribution; Code (set theory); Field (mathematics); Cryptovirology; Categorization; Data science; Artificial intelligence; Computer security; Programming language; Set (abstract data type); Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2631097808434538,"gpt":0.4126861586154646,"spread":0.1495763777720108,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01443954,0.0007719353,0.002152507,0.0003905072,0.0004080609,0.0005132472,0.005102199,0.0008885746,0.00003054734],"category_scores_gemma":[0.001610826,0.000704967,0.000784378,0.001785992,0.00006250454,0.0003140622,0.002604799,0.001526444,0.002859301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003329267,"about_ca_system_score_gemma":0.0006925351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002581374,"about_ca_topic_score_gemma":0.000004489772,"domain_scores_codex":[0.9888555,0.006786379,0.001256316,0.001429466,0.0006436016,0.001028697],"domain_scores_gemma":[0.9924223,0.002997805,0.001008965,0.003039711,0.0002540975,0.0002771552],"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":[3.364588e-7,0.00002297432,0.00006948755,0.003072562,0.00006612136,0.00001245296,0.00007192702,0.00001210268,8.196163e-8,0.01567518,0.0006988361,0.9802979],"study_design_scores_gemma":[0.0001430598,0.00004583589,0.0001817917,0.0048154,0.0001270849,0.0000762621,0.000001625119,0.00348795,0.000002456137,0.001090271,0.9891325,0.0008957197],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001763441,0.5221747,0.4743885,0.00007985062,0.002185051,0.0004288448,0.00003976428,0.0005278745,0.0001736194],"genre_scores_gemma":[0.0003167765,0.9761572,0.02084606,0.0001113877,0.0005666109,0.00001634357,0.0006909194,0.00009227046,0.001202426],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9884337,"threshold_uncertainty_score":0.9995402,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129364433","doi":"10.1016/j.diin.2014.03.012","title":"OBA2: An Onion approach to Binary code Authorship Attribution","year":2014,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","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":"Concordia University","funders":"","keywords":"Computer science; Authorship attribution; Code (set theory); Binary number; Attribution; Information retrieval; World Wide Web; Programming language; Natural language processing; Arithmetic; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07222085393703048,"gpt":0.2798793971174146,"spread":0.2076585431803841,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009937354,0.0001779352,0.0001489577,0.0001602676,0.0002304155,0.000677212,0.0005473612,0.0001491552,0.000002743032],"category_scores_gemma":[0.0005108945,0.0001798672,0.00005104386,0.0007670402,0.00006560437,0.002513693,0.0001542032,0.0001862003,0.000384707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001041006,"about_ca_system_score_gemma":0.00008344285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008290155,"about_ca_topic_score_gemma":9.614563e-7,"domain_scores_codex":[0.9982418,0.0002218187,0.0002969232,0.0005435988,0.0003620927,0.0003337482],"domain_scores_gemma":[0.9985574,0.00005382679,0.0001131771,0.0005182567,0.0001495875,0.0006077177],"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":[0.00001204352,0.00009800873,0.004844332,0.00002440474,0.000006133404,8.050258e-7,0.001313953,0.001360012,0.003482696,0.9604365,0.001413136,0.02700797],"study_design_scores_gemma":[0.0005158249,0.0006384119,0.04800925,0.00008075844,0.00001118833,0.0000296922,0.00009013802,0.7429405,0.02823541,0.1463987,0.03209421,0.0009558902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2290798,0.000009047469,0.7648439,0.001625399,0.0002953795,0.0002117937,0.00001545037,0.0004465427,0.00347268],"genre_scores_gemma":[0.9715136,4.012456e-7,0.02625104,0.001151063,0.0001409001,0.00002817931,0.0005148539,0.00001288448,0.0003871366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8140377,"threshold_uncertainty_score":0.7334773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035395173","doi":"10.1145/1774088.1774428","title":"e-mail authorship verification for forensic investigation","year":2010,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","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":"Concordia University","funders":"","keywords":"Computer science; Suspect; Phishing; Spamming; NIST; Matching (statistics); Context (archaeology); The Internet; Plagiarism detection; Sample (material); Computer security; Data mining; Information retrieval; World Wide Web; Natural language processing; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04174213818809263,"gpt":0.2857227118872353,"spread":0.2439805736991427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008173602,0.00007189254,0.00006428885,0.00005889561,0.0001569506,0.0001136507,0.0003318698,0.0001056027,0.00002705809],"category_scores_gemma":[0.0002924147,0.00006532212,0.00004134787,0.0002276132,0.0000364969,0.0003787457,0.0000352209,0.0001495935,0.00008083692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001195668,"about_ca_system_score_gemma":0.00006434125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006854739,"about_ca_topic_score_gemma":0.00002369,"domain_scores_codex":[0.9992848,0.00003316284,0.0001542165,0.0002379358,0.0001184537,0.0001714388],"domain_scores_gemma":[0.9992398,0.0001121704,0.00006488647,0.0003436557,0.0001315931,0.0001078736],"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":[0.000002172263,0.000004447696,0.0006419741,0.000005527312,0.000001683469,8.0539e-8,0.0002586154,0.000002469232,0.02184465,0.9582587,0.001096308,0.01788336],"study_design_scores_gemma":[0.000371823,0.00006426375,0.01161563,0.000006711027,0.000006577262,0.000007016306,0.00002745634,0.1919556,0.3204099,0.4455962,0.02964812,0.0002907265],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06351005,0.000004700403,0.9289823,0.004777634,0.0009133672,0.0002193105,0.000001652188,0.0002813503,0.001309628],"genre_scores_gemma":[0.7531718,3.194992e-7,0.2454953,0.0004320538,0.00008978779,0.00003565639,0.0000189053,0.000004151161,0.0007520575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6896617,"threshold_uncertainty_score":0.2663759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2576057564","doi":"10.1002/dac.3259","title":"Authorship verification using deep belief network systems","year":2017,"lang":"en","type":"article","venue":"International Journal of Communication Systems","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; University of Victoria","funders":"","keywords":"Computer science; Merge (version control); Bernoulli's principle; Gaussian; Word error rate; Basis (linear algebra); Artificial intelligence; Block (permutation group theory); Natural language processing; Data mining; Theoretical computer science; Algorithm; Information retrieval; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.09828633259928508,"gpt":0.3644836674045816,"spread":0.2661973348052965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00387107,0.000140356,0.0002740407,0.0001871878,0.0006793104,0.001934318,0.005737888,0.000135383,0.00000564303],"category_scores_gemma":[0.000445938,0.0001326557,0.0001277166,0.0001168582,0.00008066616,0.001693791,0.0004343135,0.0003900018,0.00002930353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002515867,"about_ca_system_score_gemma":0.0001603071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001323095,"about_ca_topic_score_gemma":0.000004244558,"domain_scores_codex":[0.9971159,0.0006664798,0.001000339,0.0001640669,0.0008511263,0.0002021498],"domain_scores_gemma":[0.9934529,0.0002244149,0.002852749,0.001478049,0.0018533,0.0001385885],"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":[0.00006761828,0.0001053317,0.01211222,0.00001567852,0.0003394105,0.000026631,0.001610542,0.1311155,0.000690338,0.8454764,0.001085727,0.007354599],"study_design_scores_gemma":[0.000931877,0.00006312626,0.01153522,0.000867132,0.00003511418,0.0006194124,0.000314118,0.9171084,0.0002333189,0.005628145,0.06230814,0.0003560578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01312815,0.005524485,0.9681215,0.002611927,0.008133923,0.0001954984,0.000004026901,0.00005364825,0.002226817],"genre_scores_gemma":[0.9870492,0.0002792901,0.01164362,0.00005395079,0.0007929284,0.000006604002,0.000007278164,0.00001178836,0.0001553017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9739211,"threshold_uncertainty_score":0.9996415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045244401","doi":"10.1016/j.jcss.2014.12.019","title":"Authorship verification of e-mail and tweet messages applied for continuous authentication","year":2014,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Stylometry; Word error rate; Support vector machine; Set (abstract data type); Feature selection; Feature (linguistics); Authentication (law); Writing style; Information retrieval; Selection (genetic algorithm); Block (permutation group theory); Artificial intelligence; Natural language processing; Data mining; Computer security; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02652990645237236,"gpt":0.2698352296278049,"spread":0.2433053231754325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00413637,0.0000752035,0.000247461,0.0001426171,0.0001734628,0.0001817924,0.0003664197,0.00004667902,4.072448e-7],"category_scores_gemma":[0.00004068232,0.00005503892,0.00004075607,0.0001845284,0.0001180687,0.0002851509,0.00004887332,0.00005759099,4.27215e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001009331,"about_ca_system_score_gemma":0.00004296212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001260397,"about_ca_topic_score_gemma":2.030061e-7,"domain_scores_codex":[0.998867,0.0001401081,0.0004418359,0.0001683248,0.0002617046,0.0001210134],"domain_scores_gemma":[0.9987534,0.0003124766,0.0005419783,0.0001125252,0.0001970116,0.00008261473],"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":[0.00002612086,0.00002975175,0.002855386,0.0002810204,0.00002304299,4.525858e-7,0.003358453,0.00008782426,0.003420687,0.9125776,0.0002487685,0.07709089],"study_design_scores_gemma":[0.001508959,0.00126607,0.04632816,0.000478277,0.00006372771,0.0002393608,0.0009823507,0.9150955,0.008330076,0.02284226,0.002505281,0.0003599958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1021254,0.0001964953,0.8964209,0.0004823898,0.0003826036,0.0001136596,8.636358e-7,0.00001491198,0.0002627919],"genre_scores_gemma":[0.9364153,0.000006203518,0.06342796,0.00002781664,0.0001053825,0.000002179662,2.931965e-7,0.00000183212,0.00001307687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9150077,"threshold_uncertainty_score":0.2244422,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2251483280","doi":"10.18653/v1/d15-1088","title":"Mr. Bennet, his coachman, and the Archbishop walk into a bar but only one of them gets recognized: On The Difficulty of Detecting Characters in Literary Texts","year":2015,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":59,"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":"Character (mathematics); Archbishop; Computer science; Bar (unit); State (computer science); Artificial intelligence; Natural language processing; History; Mathematics; Algorithm; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.06396051724858276,"gpt":0.2615950096518417,"spread":0.197634492403259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002435059,0.0001441699,0.0002813302,0.00007717333,0.0000954986,0.00006034935,0.0006044189,0.00007248666,0.00001617114],"category_scores_gemma":[0.000536355,0.00007763837,0.00006351388,0.0002614587,0.0001708732,0.0002104212,0.000277445,0.0003079834,0.000009528722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003713601,"about_ca_system_score_gemma":0.00007157357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00027245,"about_ca_topic_score_gemma":0.0001046461,"domain_scores_codex":[0.9982638,0.000483272,0.000423337,0.0002881769,0.0003126553,0.0002287188],"domain_scores_gemma":[0.9980657,0.001063013,0.0002273483,0.0004323667,0.0001238682,0.00008777896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001353358,0.000650548,0.0247703,0.0002267485,0.0001952728,0.0000262454,0.1583995,0.00003352841,0.014904,0.1625521,0.000315178,0.6365732],"study_design_scores_gemma":[0.01668429,0.001531748,0.1726014,0.00185186,0.0001115703,0.0001660185,0.009773524,0.178366,0.3903488,0.2249554,0.001691092,0.001918276],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988996,0.0002141221,0.0041874,0.004776502,0.000107335,0.0003436684,0.000004213297,0.00004060837,0.001330148],"genre_scores_gemma":[0.9970677,0.00003242638,0.002058168,0.0005777082,0.00002812788,0.00001261742,0.000003056351,0.000006757623,0.0002134771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6346549,"threshold_uncertainty_score":0.3166001,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103195385","doi":"10.1145/2632188.2632207","title":"Automatic identification of arabic dialects in social media","year":2014,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Arabic; Classifier (UML); Hidden Markov model; Naive Bayes classifier; Modern Standard Arabic; Social media; Language identification; Context (archaeology); Probabilistic logic; n-gram; Language model; Linguistics; Natural language; Support vector machine; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03165082704362224,"gpt":0.2818454130505005,"spread":0.2501945860068783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007717822,0.00003840466,0.00008451216,0.00008545243,0.00003579799,0.00002416368,0.000255316,0.00003760742,0.00003020515],"category_scores_gemma":[0.0002878828,0.00003536914,0.00002213629,0.0003383825,0.00001906297,0.0001534363,0.00003894428,0.00004892544,0.00005048511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001534581,"about_ca_system_score_gemma":0.00002255356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003822063,"about_ca_topic_score_gemma":0.00001332049,"domain_scores_codex":[0.9993135,0.0001137485,0.0002275434,0.0001129694,0.000135597,0.00009665063],"domain_scores_gemma":[0.9995559,0.0001752243,0.00008278434,0.0001312418,0.00003366086,0.00002119056],"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":[9.96418e-7,0.00003549113,0.001944598,0.00002909764,0.000002229918,3.379294e-7,0.003567009,0.00001339222,0.006466446,0.8833908,0.0002069221,0.1043427],"study_design_scores_gemma":[0.0003152362,0.00001442697,0.2233046,0.0000141152,0.00000265935,0.00000104529,0.00004636181,0.6302121,0.04816441,0.09765476,0.0001332028,0.0001371375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3019966,0.000009169578,0.6954324,0.0006451992,0.0002478326,0.00005498928,3.202263e-7,0.00008855527,0.001524908],"genre_scores_gemma":[0.9965912,5.711649e-7,0.003271307,0.00005077335,0.0000361012,0.000003774664,0.000001738301,0.000001596672,0.00004299353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.785736,"threshold_uncertainty_score":0.1442312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220816919","doi":"10.1126/sciadv.abm2463","title":"Based on billions of words on the internet, <scp>people</scp> = <scp>men</scp>","year":2022,"lang":"en","type":"article","venue":"Science Advances","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University","keywords":"Similarity (geometry); Context (archaeology); Measure (data warehouse); The Internet; Linguistics; Computer science; Psychology; Similarity measure; Social psychology; Natural language processing; Sociology; World Wide Web; Artificial intelligence; History","retraction":null,"screen_n_in":null,"score":{"opus":0.02511934123538057,"gpt":0.2815690368670433,"spread":0.2564496956316628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00274411,0.0001922938,0.0001978764,0.0003768955,0.001039841,0.0001780962,0.003174092,0.00002994758,0.00003856389],"category_scores_gemma":[0.001773738,0.0001345331,0.0001043321,0.004008009,0.0005240139,0.0007100282,0.0006268037,0.0004247681,0.00006470218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001283026,"about_ca_system_score_gemma":0.00034579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001568851,"about_ca_topic_score_gemma":0.000009859368,"domain_scores_codex":[0.9967327,0.000258245,0.0003176921,0.0006980012,0.001404262,0.0005891206],"domain_scores_gemma":[0.9963141,0.002281462,0.0002803182,0.0008460188,0.0001260741,0.0001520357],"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":[0.00001518009,0.0007792441,0.01806073,0.00005380275,0.00002207028,0.00002594748,0.01733627,0.1066281,0.01406526,0.7897803,0.01125558,0.04197757],"study_design_scores_gemma":[0.0007810757,0.002175279,0.01254502,0.0001697897,0.00001615127,0.00002056885,0.01145414,0.3841404,0.2808532,0.02815505,0.2794432,0.0002461158],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5923707,0.0009301143,0.3312088,0.006800101,0.004569426,0.001052725,0.00007340944,0.0005304521,0.0624642],"genre_scores_gemma":[0.993859,0.00001107618,0.002704908,0.001462139,0.00004097851,0.00007535,0.000002798907,0.00000811503,0.001835653],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7616252,"threshold_uncertainty_score":0.7997724,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891582949","doi":"10.18653/v1/d18-1294","title":"Syntax Encoding with Application in Authorship Attribution","year":2018,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"National Key Research and Development Program of China; Beijing Advanced Innovation Center for Big Data and Brain Computing; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Computer science; Syntax; Natural language processing; Sentence; Encoding (memory); Artificial intelligence; Abstract syntax; Embedding; Parsing; ENCODE; Abstract syntax tree; Word (group theory); Representation (politics); Parse tree; Tree (set theory); Lossless compression; Linguistics; Data compression; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02970367137682244,"gpt":0.2849840804760073,"spread":0.2552804090991848,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008438492,0.00008919665,0.00008998968,0.0001144509,0.0001290234,0.00007677135,0.0003547639,0.00007734694,0.00002729806],"category_scores_gemma":[0.00003412848,0.00007262977,0.00001681179,0.0008092781,0.00004903388,0.0004040794,0.00007653777,0.0001354957,0.0002479499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008485674,"about_ca_system_score_gemma":0.00005006333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006443288,"about_ca_topic_score_gemma":0.0001516265,"domain_scores_codex":[0.9989942,0.00008379408,0.0001680303,0.0003172499,0.0001788508,0.0002578896],"domain_scores_gemma":[0.9993992,0.00004959178,0.00006148371,0.0003150095,0.00009743528,0.00007725124],"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":[0.00001461148,0.00002589744,0.02973184,0.000006153302,0.000002822916,0.000002521807,0.0005877079,0.00001424139,0.002085232,0.9482435,0.00006548641,0.01921999],"study_design_scores_gemma":[0.001622688,0.0007124224,0.1660605,0.0001793436,0.00001345015,0.0001020565,0.0002472305,0.4954273,0.2473245,0.06177415,0.02526328,0.001273114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04913354,0.00001096477,0.9438195,0.001449983,0.00009453468,0.0001570983,5.813239e-7,0.0002140341,0.005119742],"genre_scores_gemma":[0.9686971,0.000001147637,0.03074434,0.0002175502,0.00007483821,0.00002343847,0.000005065869,0.000004031773,0.0002324864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9195636,"threshold_uncertainty_score":0.3186978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2250174871","doi":"","title":"Classifying English Documents by National Dialect","year":2013,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"British National Corpus; Linguistics; Variety (cybernetics); Variation (astronomy); Computer science; Natural language processing; Intuition; Artificial intelligence; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02166335923556349,"gpt":0.2665022127154754,"spread":0.2448388534799119,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002444758,0.00006443385,0.00005549936,0.00003901409,0.0001102983,0.0002569431,0.0003517751,0.00004236296,0.0006524492],"category_scores_gemma":[0.0001277445,0.00005582872,0.00002795958,0.0001955826,0.00001333118,0.0008339738,0.0001046633,0.0000900025,0.0006638333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004696336,"about_ca_system_score_gemma":0.00004252946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002710032,"about_ca_topic_score_gemma":8.550903e-7,"domain_scores_codex":[0.9991755,0.00004691334,0.000122797,0.0001862708,0.0002878393,0.0001807146],"domain_scores_gemma":[0.9994938,0.0000775975,0.00003390923,0.0001178814,0.0001965837,0.00008027923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001215081,0.00005884449,0.005659017,0.000007626721,0.0000216611,8.470569e-7,0.0008861108,0.00001431188,0.003871561,0.4910548,0.4689103,0.02951371],"study_design_scores_gemma":[0.001674227,0.0001323745,0.0114124,0.00003501853,0.000006452818,0.000009737974,0.0001927053,0.1847794,0.06328899,0.1274454,0.6097474,0.001275874],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007998296,0.0000650834,0.8574371,0.002313665,0.0007927798,0.000172955,0.000002185905,0.0004242751,0.1307937],"genre_scores_gemma":[0.9783517,0.000003331272,0.01424098,0.00140422,0.00008776251,0.00002361749,0.000008458018,0.000003336275,0.005876655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9703534,"threshold_uncertainty_score":0.8532455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1543116020","doi":"","title":"Web-based inference detection","year":2007,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":41,"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; Inference; Salient; Information retrieval; Identification (biology); Web application; Data science; Data mining; Artificial intelligence; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03315902922342352,"gpt":0.3023352610639297,"spread":0.2691762318405062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005928863,0.00004709698,0.00003946081,0.00006938739,0.00007974906,0.00004775402,0.0002188304,0.00004277931,0.00005249038],"category_scores_gemma":[0.00006547499,0.00004120167,0.00002302258,0.0003260128,0.00001163513,0.0001602996,0.00003538182,0.00008012124,0.0001819489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002382931,"about_ca_system_score_gemma":0.00004259564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008924729,"about_ca_topic_score_gemma":0.00004734389,"domain_scores_codex":[0.9994625,0.00002061849,0.0001020039,0.0001362694,0.0001188883,0.0001596699],"domain_scores_gemma":[0.9995679,0.0001093641,0.00002646273,0.0001818404,0.00004996483,0.00006450943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001917713,0.00005288539,0.008753471,0.00001147899,0.000004372271,0.00001482378,0.0001654515,0.0001845776,0.05746993,0.3604361,0.0001626215,0.5727251],"study_design_scores_gemma":[0.0003863171,0.00006211945,0.01108668,0.000006044925,0.000001372794,0.000003692088,0.00001294019,0.2866819,0.6834812,0.003276351,0.01481843,0.0001829987],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02229671,0.000007980821,0.9681411,0.0003029304,0.0002646336,0.00003827997,1.270046e-7,0.0003380552,0.008610214],"genre_scores_gemma":[0.9680954,3.534276e-7,0.03105232,0.0005857792,0.0000243933,0.000001221899,4.470533e-7,0.000001581147,0.0002384975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9457987,"threshold_uncertainty_score":0.2338646,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2251370914","doi":"","title":"Robust, Lexicalized Native Language Identification","year":2012,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":40,"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; Artificial intelligence; Natural language processing; Classifier (UML); Training set; Task (project management); Identification (biology); Set (abstract data type); Language identification; Test set; Natural language","retraction":null,"screen_n_in":null,"score":{"opus":0.0716369537548322,"gpt":0.3186020371403878,"spread":0.2469650833855556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005647785,0.00004990636,0.00005343889,0.00004052407,0.00007568853,0.00005858438,0.0002531325,0.00003548089,0.0001639523],"category_scores_gemma":[0.00007521956,0.00004119327,0.00002906689,0.0002291733,0.00001401086,0.000564221,0.00007121514,0.00006554546,0.000436244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002202698,"about_ca_system_score_gemma":0.00001172572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009779776,"about_ca_topic_score_gemma":9.221241e-7,"domain_scores_codex":[0.9993818,0.00007737321,0.0001153837,0.0001159432,0.0001325172,0.0001769671],"domain_scores_gemma":[0.9995786,0.00005010972,0.00004212587,0.000210366,0.00003763281,0.00008117479],"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":[0.000001693961,0.00003607146,0.0009647023,0.000003253877,0.00000557799,5.538233e-7,0.002879409,0.00001153591,0.002862545,0.9825211,0.001147884,0.009565718],"study_design_scores_gemma":[0.001405691,0.00006277749,0.06588208,0.00002769661,0.0000252066,0.00004503394,0.002324586,0.1895361,0.6741552,0.01836945,0.04698553,0.001180645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009520771,0.0001530306,0.9786502,0.0008841382,0.0003210735,0.00006443274,8.297577e-7,0.0002164195,0.01018913],"genre_scores_gemma":[0.9673473,0.000001773087,0.02851614,0.0003404263,0.00007103536,0.000006506721,0.000005354024,0.000002465761,0.003709016],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9641516,"threshold_uncertainty_score":0.5607179,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1595390009","doi":"","title":"Cybergenre: automatic identification of home pages on the web","year":2004,"lang":"en","type":"article","venue":"Journal of Web Engineering","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Web page; Home page; Computer science; World Wide Web; Classifier (UML); Information retrieval; Static web page; Web development; The Internet; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01742234240319396,"gpt":0.2319652182478575,"spread":0.2145428758446635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009166237,0.00006649196,0.0001164013,0.0001343593,0.00003683809,0.0000456255,0.0004245586,0.00003166237,0.000007305181],"category_scores_gemma":[0.0001765336,0.00004607565,0.00007893566,0.0002991605,0.000009031046,0.0002121655,0.00003010009,0.0001845991,0.00001190241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005262182,"about_ca_system_score_gemma":0.00007286236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.999406e-7,"about_ca_topic_score_gemma":1.436199e-7,"domain_scores_codex":[0.9991562,0.00002519527,0.000394335,0.00006069526,0.0002593119,0.0001042282],"domain_scores_gemma":[0.9993175,0.0001034577,0.0002662639,0.0001848883,0.00008422934,0.00004369283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006743806,0.0001022107,0.0003001731,0.0001221658,0.0001095107,0.00003300303,0.001374622,0.3078537,0.4626285,0.2198997,0.0004764139,0.007093282],"study_design_scores_gemma":[0.0008904863,0.0002185661,0.02084105,0.0005574423,0.00003349299,0.000194929,0.0001156061,0.7145824,0.2571731,0.003853625,0.001230772,0.0003084721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5975638,0.0002492008,0.3986022,0.002727661,0.0007237258,0.00004772744,9.687284e-7,0.00004096941,0.00004365709],"genre_scores_gemma":[0.9950804,0.00005709081,0.004741661,0.00003043736,0.00006999556,9.348668e-7,1.372431e-7,0.000004921963,0.0000144743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4067287,"threshold_uncertainty_score":0.187891,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155085300","doi":"10.1109/hicss.2008.53","title":"An Examination of Genre Attributes for Web Page Classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Web page; Set (abstract data type); Information retrieval; Identification (biology); World Wide Web; Recall; Precision and recall","retraction":null,"screen_n_in":null,"score":{"opus":0.1191895850919988,"gpt":0.3147126104816039,"spread":0.1955230253896051,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005013195,0.0000565495,0.00008024336,0.00006574737,0.0001217839,0.00001728182,0.000295289,0.00005717626,0.00002107166],"category_scores_gemma":[0.00006297715,0.00005129018,0.00003484879,0.0002261315,0.00002685344,0.0004111712,0.00002187944,0.00003575945,0.00001068265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001967465,"about_ca_system_score_gemma":0.00004948181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001819051,"about_ca_topic_score_gemma":0.00000150074,"domain_scores_codex":[0.9993198,0.00007005782,0.0001783378,0.0001847306,0.0001325476,0.0001145057],"domain_scores_gemma":[0.9993023,0.00009592275,0.00008769635,0.0002707737,0.0001959528,0.00004734474],"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":[0.00000887428,0.0001605089,0.00637047,0.00003595642,0.000009572142,0.000001160411,0.001324053,0.00002773279,0.2686871,0.6588916,0.001103525,0.06337943],"study_design_scores_gemma":[0.0003828858,0.0001834002,0.2689103,0.000006025618,0.000004055675,0.000008485316,0.0001202982,0.6106579,0.1168075,0.001012725,0.001745716,0.0001607419],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1983922,0.00002208527,0.8000523,0.0003309383,0.00008248141,0.000148389,0.000007904335,0.0001086135,0.0008551795],"genre_scores_gemma":[0.9466976,0.000007920488,0.05270319,0.00006390784,0.00002973235,0.00001674236,0.0000418643,0.000003156733,0.0004358841],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7483054,"threshold_uncertainty_score":0.2091553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2527936838","doi":"10.63317/4e2puhxuby8y","title":"Discriminating Similar Languages: Evaluations and Explorations","year":2016,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Oracle; Digital subscriber line; Annotation; Machine learning; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05894784463913573,"gpt":0.3522310635662659,"spread":0.2932832189271302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003175111,0.00004710782,0.00004298691,0.00004167205,0.0001519248,0.00006306978,0.0001377647,0.00002085842,0.0000759934],"category_scores_gemma":[0.0002286041,0.00002868275,0.00001418011,0.0001198366,0.00002245264,0.0005167871,0.00008819117,0.00002696246,0.00006256654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001253738,"about_ca_system_score_gemma":0.00002362057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003133642,"about_ca_topic_score_gemma":0.000009753458,"domain_scores_codex":[0.9994872,0.0000573865,0.00009351038,0.0001492925,0.0001082345,0.0001043453],"domain_scores_gemma":[0.9995335,0.000161132,0.00002489163,0.0001755204,0.00005328725,0.00005165697],"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":[3.384702e-7,0.000009018626,0.0006990941,0.000002539588,0.000003264069,0.000001037033,0.001212486,0.000002501529,0.004799888,0.8629068,0.000425797,0.1299372],"study_design_scores_gemma":[0.00361607,0.0004348472,0.05848316,0.0004145932,0.00008778973,0.00009292092,0.01099549,0.2487957,0.1825489,0.4597653,0.03250932,0.002255897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005238437,0.00005141726,0.9755489,0.01394276,0.00005626042,0.00006114755,0.000002078726,0.0001517237,0.004947328],"genre_scores_gemma":[0.9471333,0.000009738751,0.05127956,0.0002852516,0.0000249649,0.0000132672,0.000001361649,0.000002466761,0.001250089],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9418949,"threshold_uncertainty_score":0.1169648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963515066","doi":"10.1145/3209978.3210008","title":"SynTF","year":2018,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":33,"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":"European Commission","keywords":"Computer science; Information retrieval; Authorship attribution; Vector space model; Suspect; Task (project management); Term (time); Obfuscation; Identity (music); Stylometry; Contrast (vision); Data mining; Artificial intelligence; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.02695464514839649,"gpt":0.2845048336781714,"spread":0.257550188529775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001350132,0.00002396088,0.00002385657,0.00001700819,0.00006280756,0.00003778176,0.000246986,0.00001146829,0.0002382127],"category_scores_gemma":[0.00002225038,0.00001891975,0.00001144488,0.000133784,0.00001889925,0.0001249596,0.00007281901,0.00002402718,0.001689556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004758098,"about_ca_system_score_gemma":0.00001245671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002890959,"about_ca_topic_score_gemma":0.000001406348,"domain_scores_codex":[0.9997073,0.00001367624,0.00004293796,0.00009107782,0.00005755597,0.00008742932],"domain_scores_gemma":[0.9997357,0.00001700489,0.000008909255,0.0001677111,0.00003602952,0.00003468924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[3.162045e-7,0.00000309851,0.0003876058,4.112898e-7,9.46453e-7,6.474368e-7,0.000097576,9.163863e-8,0.0002918049,0.9754167,0.002134057,0.02166675],"study_design_scores_gemma":[0.0003079446,0.0002530488,0.009443466,0.00001211047,0.000002569338,0.00003553872,0.0000492921,0.1218557,0.2750071,0.09256982,0.5000317,0.0004317146],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003417851,0.000006745659,0.9098802,0.0009919797,0.0002868177,0.00001538464,7.637041e-8,0.0001840109,0.08521697],"genre_scores_gemma":[0.9395141,3.416037e-7,0.0567597,0.0007315793,0.00008623254,6.805623e-7,1.438756e-7,8.933625e-7,0.002906333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9360963,"threshold_uncertainty_score":0.9990878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2773782067","doi":"","title":"Chat Disentanglement: Identifying Semantic Reply Relationships with Random Forests and Recurrent Neural Networks","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":33,"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":"Computer science; Thread (computing); Random forest; Recurrent neural network; Classifier (UML); Artificial intelligence; Machine learning; Artificial neural network; Natural language processing; Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.06351610469634573,"gpt":0.3261799200032158,"spread":0.2626638153068701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004761584,0.0001983031,0.0001829313,0.0001295117,0.0008634407,0.001760102,0.00068506,0.00005331276,0.00001652081],"category_scores_gemma":[0.0004774898,0.0001523613,0.00004901228,0.0000807584,0.00009931863,0.001359139,0.0002829728,0.0005359756,0.000005553384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000624452,"about_ca_system_score_gemma":0.00004417979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003073478,"about_ca_topic_score_gemma":0.0001091905,"domain_scores_codex":[0.9984443,0.00008767071,0.0002896837,0.0004708306,0.0004439235,0.0002636003],"domain_scores_gemma":[0.9986967,0.00007818523,0.0004329815,0.0003594735,0.0003307344,0.0001019514],"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":[0.0005283774,0.0001295612,0.07985589,0.0001836141,0.0001427683,0.0004323967,0.005701865,0.0005740831,0.0005999653,0.07409701,0.0001143733,0.8376401],"study_design_scores_gemma":[0.001048524,0.00003836445,0.06042236,0.0006673621,0.00001405092,0.00006222261,0.0002591027,0.9357601,0.0004636142,0.0009616104,0.00003605854,0.0002666046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2682411,0.003101033,0.7092617,0.01348873,0.002784909,0.0005871138,0.00001102582,0.0003443387,0.002180026],"genre_scores_gemma":[0.9964262,0.00002452403,0.002806823,0.000272959,0.0002055276,0.00001753665,0.00003254463,0.00001079683,0.0002031295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.935186,"threshold_uncertainty_score":0.9992762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148429219","doi":"10.1214/10-aoas378","title":"Detecting multiple authorship of United States Supreme Court legal decisions using function words","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":30,"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":"Supreme court; Style (visual arts); Function (biology); Legal writing; Writing style; Statistical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.2448864315332253,"gpt":0.347889792177648,"spread":0.1030033606444227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001597384,0.0001464091,0.000225333,0.0001780299,0.0002397907,0.00003781238,0.0005782854,0.00007915979,0.00002569788],"category_scores_gemma":[0.0004497444,0.0001176751,0.00004922659,0.0007180744,0.000137919,0.000123432,0.0001866112,0.0002411137,0.000007192675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001042418,"about_ca_system_score_gemma":0.00007469267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002269908,"about_ca_topic_score_gemma":0.0000271622,"domain_scores_codex":[0.9984819,0.0001352508,0.000512569,0.0002114445,0.0003552064,0.0003036731],"domain_scores_gemma":[0.9975441,0.001074565,0.0004155559,0.0004674293,0.0004032359,0.00009510239],"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":[0.0006720368,0.0001814138,0.0006507174,0.00006238949,0.0001641758,0.000005641329,0.0165386,0.009733577,0.008798529,0.9210965,0.0006005215,0.04149589],"study_design_scores_gemma":[0.0004153797,0.0002156012,0.003629248,0.00006710214,0.00007154745,0.00000518637,0.00147629,0.6351608,0.09820084,0.2595783,0.0008729588,0.0003068008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1376094,0.00003082987,0.861544,0.00006308993,0.0001563047,0.0001529222,0.0001098097,0.00005291263,0.0002807587],"genre_scores_gemma":[0.8363841,0.00001700424,0.1633866,0.0001352786,0.00002110706,0.000003563279,0.00002683284,0.00001101431,0.00001451759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6987748,"threshold_uncertainty_score":0.4798653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392238204","doi":"10.3390/info15030131","title":"Authorship Attribution Methods, Challenges, and Future Research Directions: A Comprehensive Survey","year":2024,"lang":"en","type":"article","venue":"Information","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; York University","funders":"York University","keywords":"Attribution; Data science; Authorship attribution; Survey research; Computer science; Psychology; Applied psychology; Natural language processing; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.255335490359698,"gpt":0.4439869260173184,"spread":0.1886514356576204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006477717,0.000110447,0.0001195865,0.000422393,0.0003220787,0.0005312987,0.0002317666,0.0001784506,0.00001070133],"category_scores_gemma":[0.0002437121,0.0001002404,0.00003428416,0.0009611699,0.00005068777,0.00278857,0.0001628621,0.0005157868,0.0002240458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078133,"about_ca_system_score_gemma":0.00009814072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005369659,"about_ca_topic_score_gemma":0.00001387741,"domain_scores_codex":[0.9975359,0.001317538,0.0002963639,0.000213408,0.0003533997,0.0002833617],"domain_scores_gemma":[0.9983243,0.0007426882,0.00004941578,0.0002633976,0.0005087826,0.0001114661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005483165,0.000003765698,0.00002229535,0.00007645704,0.00000932068,8.015173e-7,0.00384928,0.000001469757,0.00002001766,0.3187766,0.0005280499,0.6767064],"study_design_scores_gemma":[0.00009801654,0.00005187717,0.04189099,0.00005680429,0.000003246692,0.00003754794,0.0003982336,0.02903129,0.0003783291,0.01477879,0.9131227,0.0001521356],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001884121,0.04724769,0.933224,0.01115819,0.002541073,0.0004421913,0.00003357407,0.0007759606,0.002693209],"genre_scores_gemma":[0.7658799,0.06171361,0.167598,0.0008859063,0.001836219,0.0003187487,0.001038869,0.00004267048,0.0006861094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9125947,"threshold_uncertainty_score":0.5123326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2250418537","doi":"","title":"Author Verification Using Common N-Gram Profiles of Text Documents","year":2014,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; n-gram; Natural language processing; Artificial intelligence; Classifier (UML); Set (abstract data type); Class (philosophy); Identification (biology); Information retrieval; Language model","retraction":null,"screen_n_in":null,"score":{"opus":0.04998160390730941,"gpt":0.3299500645796463,"spread":0.2799684606723369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006286454,0.00007428353,0.0001167324,0.00006465892,0.00009283494,0.00005754299,0.0003914578,0.00005597857,0.00003800663],"category_scores_gemma":[0.00005475475,0.00006469634,0.00003647517,0.0002627148,0.00003001938,0.0002955906,0.00009827406,0.00007001748,0.000048028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002291673,"about_ca_system_score_gemma":0.00002694605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005512061,"about_ca_topic_score_gemma":0.000002053345,"domain_scores_codex":[0.9991032,0.0001330671,0.0002325032,0.0001932689,0.0001904423,0.0001475443],"domain_scores_gemma":[0.9993031,0.00005583279,0.0001289439,0.0003816454,0.00007353876,0.0000569406],"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":[0.000007900388,0.00007494116,0.01094826,0.00004102874,0.00001188836,3.479472e-7,0.0005088106,0.0001914763,0.02668149,0.8865303,0.0005051162,0.07449844],"study_design_scores_gemma":[0.0003195123,0.00009755305,0.01101636,0.00004337673,0.000009608407,0.00000546335,0.00005447866,0.7385574,0.2253108,0.0142758,0.01005809,0.0002515303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1116635,0.00001506267,0.8843619,0.0005573091,0.0002275171,0.0001222878,9.268531e-7,0.0001111195,0.002940353],"genre_scores_gemma":[0.9115201,6.482445e-7,0.08782717,0.00009041251,0.00002517142,0.000003539105,0.000004590915,0.000003672514,0.0005246841],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8722545,"threshold_uncertainty_score":0.263824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011672789","doi":"10.1075/ssol.4.1.02nic","title":"Toward a science of science fiction","year":2014,"lang":"en","type":"article","venue":"Scientific Study of Literature","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"University of British Columbia; John Templeton Foundation","keywords":"Operationalization; Fantasy; Test (biology); Fiction theory; Literary fiction; Literature; Techno-thriller; Humanism; Literary criticism; Computer science; Linguistics; Epistemology; Art; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03059280971897983,"gpt":0.2935062790963196,"spread":0.2629134693773398,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006382177,0.0001213494,0.0001986752,0.0009246613,0.0008455442,0.000711059,0.002342854,0.00004252759,0.000007369335],"category_scores_gemma":[0.0006021245,0.00009976349,0.00005044538,0.009577925,0.002079819,0.001360068,0.0005348197,0.0001740798,0.000006589327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004219192,"about_ca_system_score_gemma":0.0003180855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005992157,"about_ca_topic_score_gemma":0.000001014764,"domain_scores_codex":[0.9968029,0.00009572747,0.0003738138,0.0008112596,0.001547823,0.0003684421],"domain_scores_gemma":[0.9971969,0.00006052426,0.0002467212,0.001033083,0.001320911,0.0001418613],"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":[0.00003432599,0.001385785,0.008163824,0.0001569288,0.00001642624,0.000005016868,0.1752421,0.0002825934,0.4834087,0.3101733,0.001013299,0.02011772],"study_design_scores_gemma":[0.002900384,0.002739783,0.100604,0.0007012846,0.00004415669,0.00005749351,0.008703898,0.1224517,0.7370293,0.01671509,0.006886674,0.001166157],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.950893,0.0001102623,0.04258282,0.0001623966,0.003430336,0.0003080816,0.000005698338,0.00007611984,0.002431222],"genre_scores_gemma":[0.9938267,5.606034e-7,0.005856293,0.00001727021,0.00003149457,0.000004566295,0.000001382182,0.000002888406,0.0002588807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2934582,"threshold_uncertainty_score":0.7663178,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147608180","doi":"10.1109/hicss.2009.68","title":"An N-Gram Based Approach to Automatically Identifying Web Page Genre","year":2009,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Killam Trusts","keywords":"Computer science; Web page; Feature (linguistics); Information retrieval; Set (abstract data type); Front page; Listing (finance); World Wide Web; Static web page; Artificial intelligence; Web navigation","retraction":null,"screen_n_in":null,"score":{"opus":0.04993646941629454,"gpt":0.3202699916950935,"spread":0.270333522278799,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007536707,0.0001298896,0.0001381227,0.0001223625,0.0001691482,0.000410032,0.0008932836,0.00007693878,0.00004606179],"category_scores_gemma":[0.00005406319,0.0001126932,0.00005952144,0.0005838343,0.00001136912,0.0004453001,0.00006067337,0.0001339979,0.0002211623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003328372,"about_ca_system_score_gemma":0.00008090861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003236446,"about_ca_topic_score_gemma":0.000001312562,"domain_scores_codex":[0.9985586,0.0001257606,0.0002364774,0.0004132708,0.0003204145,0.0003454365],"domain_scores_gemma":[0.9989344,0.00003833833,0.00003790193,0.0006149353,0.00006718533,0.000307237],"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":[0.00001107135,0.0005810052,0.0004761112,0.00004067349,0.00001051956,0.00002209418,0.001300096,0.00176788,0.03596777,0.8573684,0.002149876,0.1003045],"study_design_scores_gemma":[0.0001650262,0.00009976138,0.003334024,0.00001137341,0.000002752937,0.000005256276,0.00004101189,0.9898438,0.00339517,0.002429693,0.0004666562,0.0002054714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01087582,0.000009769008,0.9701905,0.001726158,0.0001129213,0.0002018054,0.000001194926,0.0009239122,0.01595798],"genre_scores_gemma":[0.5951361,1.855218e-7,0.4014055,0.003208908,0.00002633615,0.000005143579,0.000004962484,0.000003357683,0.000209461],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9880759,"threshold_uncertainty_score":0.4595497,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066783897","doi":"10.1145/2699910","title":"A Visualizable Evidence-Driven Approach for Authorship Attribution","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Information and System Security","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stylometry; Computer science; Authorship attribution; Context (archaeology); Identification (biology); Attribution; The Internet; Data science; Information retrieval; World Wide Web; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.1074829618696274,"gpt":0.3201323593290201,"spread":0.2126493974593927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001748583,0.0001612432,0.0002047594,0.0002053154,0.0004246479,0.0003418422,0.0004328761,0.0001849517,0.000003704434],"category_scores_gemma":[0.0001709927,0.0001495321,0.00008742707,0.0004382213,0.00003025527,0.002880933,0.00001964547,0.0001956099,0.0000494502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001939499,"about_ca_system_score_gemma":0.0001348829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003171996,"about_ca_topic_score_gemma":0.000002637227,"domain_scores_codex":[0.9984832,0.0001966533,0.0004794727,0.0002208713,0.0003542414,0.0002654939],"domain_scores_gemma":[0.9985381,0.0001617761,0.0001821597,0.0004701126,0.0003752467,0.0002725393],"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":[0.0004364303,0.0002467674,0.000467691,0.001912679,0.0001134435,0.000001301153,0.03972296,0.01056269,0.00002910094,0.8981628,0.002059563,0.04628462],"study_design_scores_gemma":[0.001084608,0.000279772,0.00009446839,0.0001461769,0.00002664017,0.0000519191,0.002121,0.9821213,0.0008884027,0.002821016,0.01004858,0.0003160809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002414159,0.00007180223,0.9948112,0.0006885426,0.0004349641,0.0006839707,0.00004742468,0.0003911222,0.000456781],"genre_scores_gemma":[0.9641103,0.00001245033,0.03537202,0.0001831525,0.00003304584,0.0001861586,0.00005364829,0.000004782203,0.00004450315],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9715586,"threshold_uncertainty_score":0.6097744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3047361733","doi":"10.1002/nem.2130","title":"De‐anonymizing Ethereum blockchain smart contracts through code attribution","year":2020,"lang":"en","type":"article","venue":"International Journal of Network Management","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan; University of New Brunswick","funders":"","keywords":"Computer science; Blockchain; Anonymity; Database transaction; Stylometry; Computer security; Code (set theory); Field (mathematics); Source code; Smart contract; World Wide Web; Artificial intelligence; Database; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04856664035440313,"gpt":0.3014062167132896,"spread":0.2528395763588865,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001074793,0.0001216586,0.0001744554,0.00005554977,0.00008684894,0.0002230815,0.001151649,0.00005336494,0.00005041654],"category_scores_gemma":[0.00005945971,0.0001156565,0.0001339581,0.0002406418,0.00002147368,0.000302692,0.0002910346,0.0002879743,0.0000337663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001666824,"about_ca_system_score_gemma":0.0000493978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003155008,"about_ca_topic_score_gemma":0.000001282634,"domain_scores_codex":[0.9982796,0.0001332333,0.0005090898,0.0001799661,0.0006230109,0.0002751435],"domain_scores_gemma":[0.9988679,0.0000987692,0.0004614956,0.0001235549,0.00031105,0.0001372853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002710506,0.0001313395,0.003603977,0.0000259585,0.0009874105,0.001120614,0.001819343,0.1312533,0.0003479224,0.758103,0.03162779,0.07070829],"study_design_scores_gemma":[0.002199736,0.0002543141,0.004598481,0.0003177779,0.00007174263,0.0002181865,0.0001766249,0.2112089,0.0009713687,0.03420848,0.7453856,0.0003887886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00480607,0.0003951578,0.9593597,0.03139023,0.001569982,0.00009951438,0.000002944844,0.00005111555,0.00232529],"genre_scores_gemma":[0.9151881,0.0001576039,0.07443635,0.008826188,0.001240745,0.000002879994,0.000004156625,0.000009313484,0.0001347122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.910382,"threshold_uncertainty_score":0.4716335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3179438688","doi":"10.1109/access.2021.3095967","title":"Authorship Classification in a Resource Constraint Language Using Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Athabasca University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Word2vec; Artificial intelligence; Convolutional neural network; Embedding; Classifier (UML); Hyperparameter; Natural language processing; Pattern recognition (psychology); Document classification; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1227674961873143,"gpt":0.3669254085632319,"spread":0.2441579123759176,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006302499,0.0001087011,0.0001352249,0.00009539042,0.000125002,0.0003066427,0.0005851753,0.0001248943,0.00003839599],"category_scores_gemma":[0.0001174671,0.0001167938,0.00005056558,0.0007885741,0.00006359712,0.0005194409,0.0001494881,0.0003431697,0.000006714903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040192,"about_ca_system_score_gemma":0.0001485713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003336845,"about_ca_topic_score_gemma":0.00003306949,"domain_scores_codex":[0.9984868,0.0003444468,0.000275288,0.0003705977,0.0002145326,0.0003083281],"domain_scores_gemma":[0.9992077,0.0001612245,0.0001068198,0.0003315204,0.00009298404,0.00009979738],"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":[0.0001064081,0.0004645659,0.1299238,0.0001338425,0.00007874428,0.001430901,0.00719157,0.242851,0.03707789,0.4856053,0.002204614,0.09293143],"study_design_scores_gemma":[0.0002360202,0.000004968083,0.01651797,0.0000284299,0.000003390499,0.00006287551,0.0001329021,0.9790977,0.002504376,0.0009796404,0.0002790105,0.0001527707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2824127,0.0002533088,0.7149097,0.001269652,0.000495061,0.00008513412,0.000003708098,0.00009345207,0.0004773376],"genre_scores_gemma":[0.9958555,0.000002062801,0.003082541,0.00079289,0.0001526475,0.000007227365,0.0000216727,0.000006680383,0.00007884963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7362466,"threshold_uncertainty_score":0.4762712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2344088191","doi":"10.5220/0005710103540361","title":"Authorship Attribution using Variable Length Part-of-Speech Patterns","year":2016,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Variable (mathematics); Computer science; Speech recognition; Artificial intelligence; Natural language processing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07725854955679153,"gpt":0.2956823975046892,"spread":0.2184238479478977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001294002,0.0001407619,0.0001872916,0.0000969668,0.0001308799,0.00005596986,0.0005398362,0.0001419315,0.0004028938],"category_scores_gemma":[0.0001401099,0.00009597656,0.00006951868,0.0004323812,0.00003670919,0.0005958212,0.0002106626,0.0001084251,0.00008359479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008667973,"about_ca_system_score_gemma":0.0001126342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006024542,"about_ca_topic_score_gemma":0.000003731679,"domain_scores_codex":[0.998365,0.00020327,0.0003632861,0.0003626907,0.0003045632,0.000401227],"domain_scores_gemma":[0.9988133,0.0001821444,0.0001592329,0.000517775,0.000186466,0.0001410226],"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":[0.000009553947,0.00003999576,0.02093698,0.00002526819,0.0000209971,0.000005184139,0.0001337048,0.00001947249,0.01909209,0.8991325,0.0002468305,0.06033736],"study_design_scores_gemma":[0.001901687,0.0002775704,0.009193522,0.0006406955,0.00005058627,0.0001071482,0.00005684077,0.07008346,0.7649601,0.07916342,0.07226305,0.00130188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05493203,0.00002796183,0.9421096,0.001142709,0.0006452706,0.000110591,0.00001990949,0.0002037991,0.0008081568],"genre_scores_gemma":[0.9256362,0.000009330391,0.07277083,0.0001084,0.0001379015,0.000004145666,0.000004535902,0.000008385194,0.001320295],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8707042,"threshold_uncertainty_score":0.4411404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901907079","doi":"10.1145/3236391","title":"Arabic Authorship Attribution","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":23,"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":"Cybercrime; Computer science; Anonymity; Authorship attribution; The Internet; Identity (music); Cyberspace; Online identity; Stylometry; Artificial intelligence; Computer security; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01375791771308319,"gpt":0.2626968309772169,"spread":0.2489389132641337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005789272,0.0001973875,0.0001523469,0.000327985,0.0008525276,0.0005619516,0.0004946513,0.0001716695,0.0001046991],"category_scores_gemma":[0.00009618451,0.0001844036,0.0000606067,0.0007340889,0.0001197871,0.002390307,0.00002382237,0.0003666255,0.0002565452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006354148,"about_ca_system_score_gemma":0.00007338056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007455498,"about_ca_topic_score_gemma":0.000005488002,"domain_scores_codex":[0.9985982,0.00009553627,0.0003876652,0.000244209,0.0003193708,0.0003550326],"domain_scores_gemma":[0.9989685,0.00004908616,0.0001798685,0.0004660046,0.0001434386,0.0001931313],"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":[0.00002663063,0.00002658871,0.00002610321,0.00006514576,0.000008228041,0.000001766444,0.02132571,0.00004127606,0.0001777628,0.002119878,0.0000557575,0.9761251],"study_design_scores_gemma":[0.007274581,0.00167656,0.01300594,0.002138456,0.0001949817,0.0008314048,0.03869624,0.4627397,0.1870938,0.01030223,0.2716025,0.004443602],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01895288,0.0000735268,0.974395,0.002918742,0.0001487705,0.0001747228,0.00001211309,0.0004736571,0.002850567],"genre_scores_gemma":[0.9840354,0.0000037786,0.01374333,0.00172192,0.00008897152,0.00001731835,0.00003139912,0.000008987851,0.0003489027],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9716815,"threshold_uncertainty_score":0.7519762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3095732274","doi":"10.1007/978-3-030-60290-1_17","title":"DeepStyle: User Style Embedding for Authorship Attribution of Short Texts","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Task (project management); Salient; Authorship attribution; Embedding; Word embedding; Style (visual arts); Word (group theory); Artificial intelligence; Natural language processing; Attribution; Writing style; Information retrieval; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04678901294171871,"gpt":0.3068086415893817,"spread":0.260019628647663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002092926,0.0005503878,0.0007529877,0.000613928,0.0003271959,0.0003291671,0.002861776,0.0005642915,0.00002084022],"category_scores_gemma":[0.0003955839,0.0005386369,0.0002726455,0.0008852493,0.0004556195,0.0006323708,0.001081743,0.0009114053,0.00002286537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003116817,"about_ca_system_score_gemma":0.0006343873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004737485,"about_ca_topic_score_gemma":0.00001350902,"domain_scores_codex":[0.9957114,0.00007501298,0.0008466722,0.001604242,0.001008402,0.0007542237],"domain_scores_gemma":[0.9969665,0.0007759786,0.0003984139,0.001030014,0.000523088,0.000305977],"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":[0.0000494783,0.0000513042,0.0004003929,0.0003205956,0.00004479363,0.0000324,0.001886141,0.01946283,0.001612534,0.4722857,0.00009310459,0.5037607],"study_design_scores_gemma":[0.0003603272,0.0003607981,0.000214169,0.0005535161,0.00002860212,0.0000339338,4.903294e-7,0.8063197,0.02443904,0.1602596,0.006469103,0.0009607813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001174284,0.0003412447,0.9952165,0.001317647,0.001601764,0.0007706378,0.00004244444,0.0002033998,0.0003889284],"genre_scores_gemma":[0.5214359,0.00001461753,0.4769435,0.0007663643,0.0004841979,0.00002136328,0.00003990914,0.00004133032,0.0002528331],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7868568,"threshold_uncertainty_score":0.9997065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2774157693","doi":"10.1109/icdmw.2017.51","title":"Estimating Personality from Social Media Posts","year":2017,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Personality psychology; Personality; Lexicon; Computer science; Repertoire; Social media; Artificial intelligence; Negotiation; Arabic; Robot; Natural language processing; Social psychology; Linguistics; Psychology; World Wide Web; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.09161803524495755,"gpt":0.3393627365054629,"spread":0.2477447012605054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003558079,0.00006282225,0.00008563403,0.0000114815,0.0008655878,0.0003965063,0.000833265,0.0000525497,0.0001705791],"category_scores_gemma":[0.0004071797,0.00005562198,0.00004361158,0.00002615593,0.00004640648,0.0004262506,0.0002829068,0.0001033724,0.0001524881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001815356,"about_ca_system_score_gemma":0.0000360507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002021628,"about_ca_topic_score_gemma":0.00004626742,"domain_scores_codex":[0.9993157,0.0000430338,0.000100925,0.0002042302,0.0001826134,0.0001535442],"domain_scores_gemma":[0.9993361,0.0001232836,0.00009700711,0.000336121,0.00004564492,0.00006187512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000009561994,0.00004915598,0.03162403,0.00001095605,0.00003369023,0.00002883545,0.01873287,0.000005354341,0.001236875,0.6799189,0.003759689,0.2645901],"study_design_scores_gemma":[0.0004628091,0.000009813527,0.5682653,0.00001785871,0.000007406626,0.000003299721,0.0001279334,0.3422056,0.003469447,0.08403467,0.00103831,0.0003575984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1597127,0.00001405404,0.820609,0.007470174,0.00106809,0.00003629312,0.000009980908,0.0001900601,0.01088958],"genre_scores_gemma":[0.8588879,1.276546e-7,0.1404355,0.0002293,0.0003270411,0.000001194494,0.000004977396,0.000002114841,0.0001119217],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6991751,"threshold_uncertainty_score":0.6657489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213077949","doi":"10.1037/cep0000273","title":"Bridging people and perspectives: General and language-specific social network structure predict mentalizing across diverse sociolinguistic contexts.","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Betweenness centrality; Mentalization; Psychology; Cognitive psychology; PsycINFO; Social cognition; Cognition; Bridging (networking); Context (archaeology); Developmental psychology; Computer science; Neuroscience; Biology; MEDLINE","retraction":null,"screen_n_in":null,"score":{"opus":0.03936839491776121,"gpt":0.320760304366242,"spread":0.2813919094484807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0009643028,0.0003116876,0.0004264612,0.0002273105,0.001693978,0.0001793334,0.000866935,0.0001404117,0.000261778],"category_scores_gemma":[0.00005219671,0.0003651447,0.000129684,0.0003699305,0.0004028269,0.0002665048,0.0002462947,0.000767012,0.000001809663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001293246,"about_ca_system_score_gemma":0.0002063742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001758008,"about_ca_topic_score_gemma":0.005305377,"domain_scores_codex":[0.9971291,0.0003519245,0.0004882221,0.0006822239,0.0001362875,0.001212277],"domain_scores_gemma":[0.9982343,0.00005953401,0.0003764907,0.0003250214,0.00007076999,0.0009338412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003653681,0.0002715388,0.0837822,0.00003432681,0.0004660464,0.003761105,0.7499211,0.0003106541,0.08575257,0.02638249,0.03312294,0.01582962],"study_design_scores_gemma":[0.01200009,0.003460868,0.2930261,0.0001850397,0.0001162484,0.02473972,0.6320686,0.002311804,0.005303024,0.006173332,0.01763639,0.00297875],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783205,0.01507459,0.001968976,0.001411045,0.002460946,0.0002450179,0.0002148504,0.00003618796,0.000267897],"genre_scores_gemma":[0.9948755,0.0000396283,0.002748916,0.001494936,0.000709289,0.00001807651,0.00002156958,0.0000307661,0.00006132168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2092439,"threshold_uncertainty_score":0.9998801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W112115809","doi":"","title":"Herbert west: deanonymizer","year":2011,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":19,"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":"Anonymity; Computer science; Selection (genetic algorithm); Face (sociological concept); Quality (philosophy); Simple (philosophy); Internet privacy; Data science; World Wide Web; Computer security; Artificial intelligence; Sociology; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.07896113860058249,"gpt":0.254769367506567,"spread":0.1758082289059845,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002609656,0.00004947405,0.0000481696,0.00002666276,0.00004638666,0.00003265347,0.0003633106,0.00003873671,0.0008470298],"category_scores_gemma":[0.00001708448,0.00003931133,0.00002877865,0.0001353027,0.0000162793,0.0002116204,0.0001002458,0.00006333026,0.0009750059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006282939,"about_ca_system_score_gemma":0.00002302089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002307906,"about_ca_topic_score_gemma":0.000002180773,"domain_scores_codex":[0.9995247,0.0000497973,0.00008040522,0.0001382495,0.00007820342,0.0001287119],"domain_scores_gemma":[0.9996311,0.00003312339,0.00001773142,0.0002304497,0.00002417363,0.000063399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000171775,0.00001799851,0.002727452,0.000001390842,0.000003444396,0.000008411504,0.0007040232,3.406382e-7,0.00008692905,0.984633,0.00118754,0.01062772],"study_design_scores_gemma":[0.001920911,0.0002815207,0.1492324,0.00004965493,0.00002043044,0.0002176822,0.0002454354,0.04088332,0.2312941,0.2219234,0.3521667,0.001764417],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001267033,0.00001443413,0.7207366,0.0002151762,0.0001953509,0.0000237923,8.66418e-8,0.0001789198,0.2773686],"genre_scores_gemma":[0.8631378,0.000002033369,0.1315335,0.0006301216,0.00002481697,0.000002820184,2.885402e-7,0.000002691878,0.004665891],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8618708,"threshold_uncertainty_score":0.9998028,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042368861","doi":"10.1109/vast.2012.6400484","title":"Relative N-gram signatures: Document visualization at the level of character N-grams","year":2012,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Boeing","keywords":"Visualization; n-gram; Computer science; Classifier (UML); Character (mathematics); Artificial intelligence; Gram; Data visualization; Natural language processing; Pattern recognition (psychology); Information retrieval; Mathematics; Language model","retraction":null,"screen_n_in":null,"score":{"opus":0.09470629678166564,"gpt":0.341107670361583,"spread":0.2464013735799173,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007839651,0.00009171454,0.00009484315,0.00003741444,0.0001490488,0.00003685847,0.0003199817,0.00007708369,0.0002059389],"category_scores_gemma":[0.00006229294,0.00005478708,0.0000584341,0.0002897487,0.00004404999,0.0006709194,0.0002143117,0.0001109966,0.0001384462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005403149,"about_ca_system_score_gemma":0.00001950914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000167798,"about_ca_topic_score_gemma":0.000005920038,"domain_scores_codex":[0.998993,0.0001635407,0.0002060968,0.000143096,0.0002681786,0.0002261204],"domain_scores_gemma":[0.9992584,0.0001594127,0.000135376,0.0002923433,0.00008675083,0.00006769566],"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":[0.000005834834,0.0000379335,0.002384942,0.000005984162,0.00001773641,1.795279e-7,0.003019311,0.00001232819,0.001579716,0.9869825,0.0009352801,0.005018246],"study_design_scores_gemma":[0.001450797,0.0003449866,0.1431516,0.0001215709,0.00007367831,0.00002643631,0.0006418147,0.02852874,0.5830364,0.03410595,0.2073529,0.001165155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01605085,0.0002277029,0.9789082,0.001309888,0.0004764066,0.0002091309,0.000004097276,0.00007485859,0.002738819],"genre_scores_gemma":[0.9887531,0.00001039962,0.004486207,0.000655498,0.00006248894,0.00001021178,0.00001571719,0.000004719334,0.006001601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.974422,"threshold_uncertainty_score":0.2254886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W93917463","doi":"","title":"Authorship Attribution for Small Texts: Literary and Forensic Experiments.","year":2007,"lang":"en","type":"article","venue":"PAN","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Attribution; Authorship attribution; Psychology; History; Computer science; Linguistics; Social psychology; Natural language processing; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.06904991508512409,"gpt":0.319997208466426,"spread":0.2509472933813019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001175599,0.0001124578,0.0001143644,0.00008176929,0.0001885893,0.0001117561,0.0002232674,0.00009777526,0.000005718395],"category_scores_gemma":[0.00007638892,0.0001068048,0.00004856023,0.0001955924,0.00003457522,0.0002334142,0.0001034189,0.0001024149,0.00001617978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003976349,"about_ca_system_score_gemma":0.00002368554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005185549,"about_ca_topic_score_gemma":0.000004936879,"domain_scores_codex":[0.9989814,0.00004580063,0.0002085573,0.0003018053,0.0001086113,0.0003538654],"domain_scores_gemma":[0.9993307,0.0001568639,0.00006706926,0.0002312142,0.00007125972,0.0001428908],"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":[0.00005656956,0.00005521609,0.008344149,0.00004698769,0.0000190589,0.000008300689,0.004095279,6.86738e-7,0.004578747,0.5027884,0.0005219747,0.4794846],"study_design_scores_gemma":[0.002642514,0.0006802083,0.1004363,0.0001647012,0.00003487742,0.00009130782,0.0002458584,0.02088549,0.4522551,0.2671742,0.1541177,0.001271694],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09698763,0.0008351506,0.9004582,0.0006276012,0.0003554869,0.0002442994,0.000006903789,0.0001535805,0.0003311602],"genre_scores_gemma":[0.938266,0.000004471939,0.0607088,0.0003948457,0.0001220108,0.00001859224,0.00002900303,0.000007422647,0.0004488931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8412783,"threshold_uncertainty_score":0.4355373,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119140562","doi":"10.1007/s10032-007-0060-2","title":"Genre as noise: noise in genre","year":2007,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Noise (video); Perspective (graphical); Hierarchy; Feature (linguistics); Word error rate; Natural language processing; Artificial intelligence; Emphasis (telecommunications); Speech recognition; Selection (genetic algorithm); Pattern recognition (psychology); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02048356387265479,"gpt":0.317666999386885,"spread":0.2971834355142302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001893853,0.000174775,0.0002342474,0.001375255,0.0001640828,0.0005850069,0.0005228295,0.0001015651,0.000676151],"category_scores_gemma":[0.0001036044,0.0001491242,0.000254129,0.0008399211,0.00003054987,0.0006595626,0.0001129938,0.000411899,0.0001970449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001982498,"about_ca_system_score_gemma":0.00005374489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006036781,"about_ca_topic_score_gemma":0.00006776847,"domain_scores_codex":[0.997752,0.0001250738,0.0006543931,0.0003481379,0.0008372884,0.0002830891],"domain_scores_gemma":[0.9987441,0.0001436138,0.0003308768,0.0001500186,0.0003988502,0.000232578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005302676,0.000638478,0.09753013,0.00001326795,0.002851851,0.001587889,0.002168062,0.0009108754,0.002091705,0.02460363,0.0006022611,0.8664716],"study_design_scores_gemma":[0.009411152,0.001034442,0.7406067,0.0006664636,0.001060225,0.001720765,0.001709514,0.02540914,0.04034439,0.1440464,0.03126677,0.002723983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7320476,0.0002571719,0.2585337,0.004357609,0.001117268,0.0001140931,0.00001022206,0.00004839269,0.00351395],"genre_scores_gemma":[0.9931297,0.0004812803,0.003487832,0.001619392,0.0003282775,0.000003878053,0.00005294586,0.000007230431,0.0008894525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8637476,"threshold_uncertainty_score":0.740338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2477122767","doi":"10.1109/bracis.2016.071","title":"Authorship Attribution via Network Motifs Identification","year":2016,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":17,"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":"Automatic summarization; Authorship attribution; Identification (biology); Attribution; Function (biology); Style (visual arts); Motif (music)","retraction":null,"screen_n_in":null,"score":{"opus":0.02819452153527435,"gpt":0.2619039526048588,"spread":0.2337094310695844,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001548047,0.0001153677,0.0001069625,0.00005851124,0.0002235559,0.0001210503,0.0005714762,0.0001198017,0.0001596928],"category_scores_gemma":[0.00009990504,0.00007810001,0.00006615363,0.0005110457,0.00003542051,0.0006901561,0.0001399409,0.00008957429,0.001479676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008877501,"about_ca_system_score_gemma":0.00003652843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006225145,"about_ca_topic_score_gemma":0.000003997432,"domain_scores_codex":[0.9984654,0.0001960925,0.0003092603,0.000386544,0.0002582553,0.0003844425],"domain_scores_gemma":[0.9989249,0.0001276148,0.0001217713,0.0005409293,0.0001411692,0.0001435773],"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":[0.00000489629,0.00001886031,0.004454706,0.00000392221,0.000008171126,0.000001814633,0.00007872627,0.00004327461,0.008719998,0.8699288,0.003226273,0.1135106],"study_design_scores_gemma":[0.001054057,0.0001306385,0.1637861,0.000111375,0.00002312114,0.0000541876,0.00001150371,0.08385091,0.1385277,0.5392227,0.0721429,0.001084772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003320759,0.00004931428,0.9862412,0.008006854,0.000959632,0.0001310587,0.000002046369,0.0005211609,0.0007680108],"genre_scores_gemma":[0.9773546,0.000007061599,0.01670917,0.0002462583,0.0002161017,0.00001415964,0.000007382878,0.000006348837,0.005438905],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9740338,"threshold_uncertainty_score":0.9992978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W140340549","doi":"10.63317/2id75yrzanby","title":"Using the Complexity of the Distribution of Lexical Elements as a Feature in Authorship Attribution","year":2008,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Punctuation; Authorship attribution; Computer science; Artificial intelligence; Natural language processing; Feature (linguistics); Support vector machine; Noun; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2062589589989079,"gpt":0.3485729465110212,"spread":0.1423139875121133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001046712,0.000103624,0.0001696409,0.000033681,0.0002512768,0.00001462828,0.0006927329,0.000113256,0.00001644365],"category_scores_gemma":[0.0001801315,0.00005995562,0.0001067805,0.000929201,0.0003986393,0.000165327,0.0002739172,0.0003068031,0.000003089856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009730806,"about_ca_system_score_gemma":0.0001411463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002172437,"about_ca_topic_score_gemma":0.00003635118,"domain_scores_codex":[0.9983695,0.000428267,0.0003603963,0.0001952371,0.0004102092,0.0002364003],"domain_scores_gemma":[0.9990925,0.00007466409,0.0002198459,0.0004310639,0.0001375039,0.00004441907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002598195,0.00009773007,0.1018176,0.00001583825,0.00001025988,0.00000181042,0.0006843865,0.0002005489,0.002196193,0.8943657,0.0002302221,0.0003537316],"study_design_scores_gemma":[0.0007325177,0.00008785873,0.7071111,0.00009556694,0.00001482624,0.00008253819,0.0001290336,0.1496682,0.09043979,0.05020055,0.001209957,0.0002280796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5895334,0.00003683734,0.4068337,0.003075758,0.0001460903,0.0002032126,0.00001963789,0.00002154734,0.0001298223],"genre_scores_gemma":[0.9960437,0.000003455339,0.003720817,0.0001076719,0.00001908308,0.000002899315,0.0000175006,0.000002587624,0.0000823228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8441651,"threshold_uncertainty_score":0.2444919,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385572818","doi":"10.18653/v1/2022.emnlp-main.128","title":"AfroLID: A Neural Language Identification Tool for African Languages","year":2022,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Advanced Micro Devices","keywords":"Computer science; Domain (mathematical analysis); Identification (biology); Natural language processing; Set (abstract data type); Cover (algebra); Artificial intelligence; Exploit; Language identification; Natural language; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02260801631974186,"gpt":0.3036981982625557,"spread":0.2810901819428138,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005149168,0.00005848493,0.00006514207,0.0000698093,0.0002741216,0.00009698238,0.0004845684,0.00001428603,0.0001725663],"category_scores_gemma":[0.00005730874,0.00005652727,0.00005268414,0.0002890346,0.000008691049,0.0001742427,0.0001957641,0.00008285142,0.00001963097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003699193,"about_ca_system_score_gemma":0.00002374693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002137157,"about_ca_topic_score_gemma":0.000003544656,"domain_scores_codex":[0.9992269,0.00008007815,0.000137132,0.0002153316,0.0001716245,0.0001689805],"domain_scores_gemma":[0.9995174,0.00008068575,0.00005797152,0.0002837695,0.00002740967,0.0000327048],"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":[0.00004888692,0.0001486147,0.001084474,0.00003925016,0.00003027946,0.0000274118,0.01739077,0.0007679117,0.03839868,0.7653927,0.01299917,0.1636719],"study_design_scores_gemma":[0.001726007,0.0004195362,0.01085391,0.00000490501,0.00003154983,0.0001083783,0.01755714,0.7912219,0.06783877,0.009466828,0.09965388,0.001117166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07384464,0.0001548711,0.9192773,0.00401754,0.0003930416,0.0003448036,0.00004153753,0.0003955186,0.001530824],"genre_scores_gemma":[0.9871379,3.493598e-7,0.007614113,0.0006166471,0.00004772858,0.0001493148,0.00003609845,0.000005027568,0.004392821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9132932,"threshold_uncertainty_score":0.2305115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1970306474","doi":"10.1353/cjp.2011.0028","title":"Description, Disagreement, and Fictional Names","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Philosophy","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge","funders":"","keywords":"Fictional universe; Philosophy; Proper noun; Epistemology; Emptiness; Linguistics; Narrative","retraction":null,"screen_n_in":null,"score":{"opus":0.08777744241595391,"gpt":0.2282456605309692,"spread":0.1404682181150153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002689385,0.00006263198,0.0000830148,0.0001877396,0.0001495754,0.000062347,0.0002753473,0.0000349437,0.0001243404],"category_scores_gemma":[0.00004236426,0.00005715223,0.00004202258,0.0001365111,0.00006446252,0.0004761251,0.00001515189,0.0001303893,0.00001269186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004776983,"about_ca_system_score_gemma":0.0003050331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002360905,"about_ca_topic_score_gemma":0.0003434619,"domain_scores_codex":[0.9994356,0.00003805422,0.0001919919,0.00008669986,0.0001035485,0.000144094],"domain_scores_gemma":[0.9991823,0.00001273935,0.0001122904,0.00009905719,0.0001372932,0.0004562494],"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":[0.000005975641,0.00001156855,0.04348467,0.000008084731,0.00003245981,0.00008972688,0.002531192,0.00000282019,0.00005828845,0.9477259,0.001973008,0.004076341],"study_design_scores_gemma":[0.0006061679,0.000325983,0.1092911,0.00009763557,0.00002348311,0.000734148,0.00012456,0.0005784827,0.0006579419,0.8586191,0.02862269,0.0003186619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1661542,0.004706227,0.7601979,0.02004781,0.005097047,0.0002267814,0.00003985545,0.00005679632,0.04347339],"genre_scores_gemma":[0.9912751,0.000008940269,0.008019003,0.0004572667,0.0001789387,4.572942e-7,6.216836e-7,0.000003051298,0.00005665211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8251209,"threshold_uncertainty_score":0.23306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3110983064","doi":"10.1007/978-3-030-61675-5","title":"Machine Learning for Authorship Attribution and Cyber Forensics","year":2020,"lang":"en","type":"book","venue":"International series on computer entertainment and media technology","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Authorship attribution; Attribution; Computer forensics; Computer science; Computer security; Data science; Psychology; Internet privacy; Natural language processing; Digital forensics; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02230978867466325,"gpt":0.2477327119029573,"spread":0.225422923228294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002513415,0.0003578477,0.0003861217,0.0003464639,0.0001736758,0.0001577404,0.0006027383,0.0004913924,0.00001205841],"category_scores_gemma":[0.00009975713,0.0003478148,0.00008928045,0.00009482363,0.0001772485,0.0001961927,0.0007322142,0.000693058,0.00001285594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001689864,"about_ca_system_score_gemma":0.00006234742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001412973,"about_ca_topic_score_gemma":0.00000730038,"domain_scores_codex":[0.99825,0.00004443207,0.0003759412,0.0007098172,0.0003166111,0.0003031926],"domain_scores_gemma":[0.9990022,0.0002411174,0.000257161,0.0002104935,0.0001474113,0.0001416411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008814495,0.00001757107,0.000409588,0.00004860762,0.0001265355,0.00002534291,0.0004269263,0.0000104842,0.00001758395,0.8750533,0.003008472,0.1207674],"study_design_scores_gemma":[0.0008011995,0.000689302,0.00008992091,0.0001785859,0.00002714062,0.00007957694,0.00001499031,0.03420271,0.0004415974,0.1266966,0.8363767,0.0004016889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003325855,0.000613824,0.956806,0.03620004,0.002947829,0.0005923804,0.000105826,0.0005751584,0.001826341],"genre_scores_gemma":[0.2636174,0.008343012,0.4322345,0.01549066,0.008573931,0.00108714,0.0119103,0.0004583882,0.2582847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8333682,"threshold_uncertainty_score":0.9998974,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2250996967","doi":"","title":"Cognate and Misspelling Features for Natural Language Identification","year":2013,"lang":"en","type":"article","venue":"Workshop on Innovative Use of NLP for Building Educational Applications","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":14,"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":"Bigram; Computer science; Cognate; Natural language processing; Artificial intelligence; Classifier (UML); Natural language; Word (group theory); Identification (biology); Spelling; Syntax; Language identification; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04016925118674335,"gpt":0.347697391551569,"spread":0.3075281403648256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002985854,0.0001341796,0.0001367861,0.0002374369,0.0002917865,0.0001976263,0.000322163,0.00006890909,0.000008616888],"category_scores_gemma":[0.0004480996,0.0001314282,0.00004862241,0.000890872,0.00007392446,0.0004511646,0.00004568437,0.0001358297,0.000007760941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005168972,"about_ca_system_score_gemma":0.00008788993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009297542,"about_ca_topic_score_gemma":0.000001177307,"domain_scores_codex":[0.9989144,0.00002306261,0.000349987,0.0003835883,0.0001443136,0.00018463],"domain_scores_gemma":[0.9967404,0.001542678,0.000300702,0.0002941905,0.001070455,0.00005159171],"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":[0.000009355132,0.00007984566,0.000113372,0.00004204475,0.00002600465,7.732403e-9,0.0004405445,0.00009198696,0.01995312,0.9281286,0.004231504,0.04688362],"study_design_scores_gemma":[0.002106603,0.000194079,0.1308183,0.000627221,0.00008739412,0.00002025552,0.001771845,0.08365323,0.2036726,0.486727,0.08844929,0.001872165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0442637,0.0002813015,0.9408898,0.01235607,0.0002405623,0.001786059,0.00007078966,0.00006184285,0.00004990186],"genre_scores_gemma":[0.7602218,0.000008716002,0.2361488,0.0003857027,0.0001292208,0.00167934,0.0002178627,0.00001280803,0.00119575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7159581,"threshold_uncertainty_score":0.5359487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}