{"meta":{"query_hash":"4c2cc3b5088f","filters":{"venue":"Corpora"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/4c2cc3b5088f","api":"https://metacan.xera.ac/api/v1/cohort?venue=Corpora"},"results":[{"id":"W1970536639","doi":"10.3366/cor.2007.2.1.97","title":"The Wenzhou Spoken Corpus","year":2007,"lang":"en","type":"article","venue":"Corpora","topic":"China's Ethnic Minorities and Relations","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"XPath; Markup language; XML; Computer science; Transcription (linguistics); Natural language processing; Information retrieval; Linguistics; Artificial intelligence; World Wide Web; XML database","score_opus":0.026061586547180323,"score_gpt":0.3246620743798674,"score_spread":0.29860048783268706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970536639","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1976643,0.002682412,0.0011705995,0.005785887,0.0028485467,0.00026341586,0.0000040274344,0.00013279979,0.789448],"genre_scores_gemma":[0.9483617,0.00051214825,0.00011124212,0.00014561704,0.00066499814,0.0000025114987,0.000001963986,0.0000058491214,0.050193995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993089,0.000037420203,0.0001220152,0.00008437252,0.00020986557,0.00023743411],"domain_scores_gemma":[0.9993307,0.00032496647,0.00006667541,0.00014383733,0.000047987414,0.00008583321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010251527,0.000045313638,0.00005070275,0.000017975572,0.0012135573,0.00005227198,0.00019416142,0.000066478664,0.00015482026],"category_scores_gemma":[0.00012246455,0.000031182964,0.000048495778,0.00018068007,0.00033655632,0.000053120144,0.000027350623,0.00011764313,0.00013060917],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010544087,0.000019902602,0.015793132,0.000001771108,0.000010300102,0.000014219694,0.0083625475,0.0000034642042,0.000025100187,0.87927294,0.03024545,0.066240646],"study_design_scores_gemma":[0.00007746948,0.000009375982,0.035012588,0.0000042786855,0.0000055400546,0.0000012126961,0.0038912625,0.00000952455,0.00001217289,0.021844331,0.9390701,0.00006211467],"about_ca_topic_score_codex":0.0014774266,"about_ca_topic_score_gemma":0.0067260438,"teacher_disagreement_score":0.9088247,"about_ca_system_score_codex":0.000050958817,"about_ca_system_score_gemma":0.00009689081,"threshold_uncertainty_score":0.93338245},"labels":[],"label_agreement":null},{"id":"W2077469553","doi":"10.3366/cor.2013.0032","title":"Challenges in cross-linguistic corpus-assisted discourse studies","year":2013,"lang":"en","type":"article","venue":"Corpora","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corpus linguistics; Linguistics; Focus (optics); Population; Contrastive linguistics; Sociology; Applied linguistics; Computer science; Philosophy","score_opus":0.16594680154034003,"score_gpt":0.36325899686749796,"score_spread":0.19731219532715794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077469553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.574764,0.051251594,0.0000029669584,0.0018283142,0.0016384574,0.00038352623,0.000017549455,0.0001816742,0.36993188],"genre_scores_gemma":[0.9868029,0.001517536,0.000053579763,0.00014119675,0.00077190675,0.0001383589,0.000011169542,0.000029103998,0.0105343],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99857616,0.000060133018,0.0003992026,0.00036876745,0.00024233865,0.0003533808],"domain_scores_gemma":[0.9988181,0.00015936485,0.00019062198,0.00041671484,0.00035781102,0.000057383248],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022515011,0.00024585397,0.00046151748,0.00017992026,0.0002522221,0.0002220934,0.00025818747,0.000035553705,0.0014026904],"category_scores_gemma":[0.00033385848,0.00018849543,0.00011653213,0.000064166285,0.0010907061,0.00026328771,0.00015095223,0.00015681337,0.00065055204],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025858257,0.0005823436,0.016934028,0.000287393,0.00093005144,0.00029009295,0.21257347,0.000027501184,0.0000398951,0.663621,0.0098437825,0.0948446],"study_design_scores_gemma":[0.002366269,0.00036272348,0.14134684,0.00090971787,0.00052807987,0.000020599084,0.6324573,0.00027939153,0.00007503039,0.114311524,0.10527578,0.0020667154],"about_ca_topic_score_codex":0.00038057624,"about_ca_topic_score_gemma":0.007979228,"teacher_disagreement_score":0.5493095,"about_ca_system_score_codex":0.000056503202,"about_ca_system_score_gemma":0.000023548742,"threshold_uncertainty_score":0.99951017},"labels":[],"label_agreement":null},{"id":"W2516495486","doi":"10.3366/cor.2016.0091","title":"Discourse relations and evaluation","year":2016,"lang":"en","type":"article","venue":"Corpora","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Simon Fraser University","keywords":"Adjective; Polarity (international relations); Linguistics; Noun; Adverb; Verb; Rhetorical question; Appraisal theory; Relation (database); Interpretation (philosophy); Negation; Psychology; Discourse marker; Social psychology; Computer science; Philosophy","score_opus":0.05206585222861549,"score_gpt":0.3048947820211111,"score_spread":0.2528289297924956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516495486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59575576,0.0011979967,0.00025666194,0.0044493442,0.00034453045,0.0001556858,0.00002685574,0.00006232236,0.39775085],"genre_scores_gemma":[0.9770394,0.00002116558,0.000036831945,0.00004984595,0.00027438055,0.000018458788,0.000005083362,0.000006066617,0.022548772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99955624,0.000026675023,0.00008999408,0.00011049776,0.00014167464,0.00007491959],"domain_scores_gemma":[0.9996556,0.00004747181,0.00005557386,0.00012573536,0.00009388608,0.000021745262],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017474609,0.000056087945,0.00007116069,0.000046506426,0.00017531446,0.000045377736,0.000039280312,0.000010030368,0.0048476555],"category_scores_gemma":[0.00006375704,0.000032045693,0.000026269148,0.000015329077,0.0003240747,0.00020366452,0.000026122128,0.000019440877,0.00021399681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040628056,0.000031144573,0.004511719,0.0000030416206,0.00009003186,0.000002592413,0.013598585,0.0000015889998,0.000087621294,0.8550373,0.023210507,0.10342183],"study_design_scores_gemma":[0.0031187113,0.00023596366,0.0352727,0.00037403227,0.002040246,0.000008780463,0.10079714,0.0008980383,0.00020665453,0.37154853,0.48424193,0.0012572701],"about_ca_topic_score_codex":0.000023333376,"about_ca_topic_score_gemma":0.0004370375,"teacher_disagreement_score":0.48348874,"about_ca_system_score_codex":0.000015681951,"about_ca_system_score_gemma":0.000015024695,"threshold_uncertainty_score":0.99606204},"labels":[],"label_agreement":null},{"id":"W2606816378","doi":"10.3366/cor.2017.0108","title":"Subtopic annotation and automatic segmentation for news texts in Brazilian Portuguese","year":2017,"lang":"en","type":"article","venue":"Corpora","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Annotation; Computer science; Segmentation; Natural language processing; Portuguese; Artificial intelligence; Process (computing); Rhetorical question; Computational linguistics; Brazilian Portuguese; Linguistics","score_opus":0.02239593382287337,"score_gpt":0.309573640430716,"score_spread":0.28717770660784264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606816378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49513292,0.0012791662,0.5006858,0.0014854698,0.00024251564,0.0006429128,0.0000025896102,0.00033925794,0.00018936624],"genre_scores_gemma":[0.6603045,0.000009340177,0.3394023,0.00013239338,0.000020125168,0.000030969695,0.000005273665,0.000004115213,0.00009101433],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99945647,0.000014447694,0.0001357508,0.0002003443,0.0000853545,0.00010760836],"domain_scores_gemma":[0.99936277,0.000028889748,0.00019552498,0.00033782257,0.00004317405,0.000031807776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016416698,0.00006936518,0.00008854741,0.00007869677,0.00011586024,0.0002387529,0.00037172873,0.000041704632,0.0000012682851],"category_scores_gemma":[0.000109378285,0.00006430315,0.0000140217435,0.000056969322,0.000032524516,0.00087462843,0.000088933324,0.00004941125,0.0000020127559],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034611674,0.000014863278,0.0076584346,0.000059793823,0.0000016103235,0.0000119228325,0.00040757132,3.7017185e-7,0.004801407,0.00761992,0.000301563,0.97911906],"study_design_scores_gemma":[0.0013827903,0.00020370554,0.42173392,0.00024186315,0.000010537743,0.00002536721,0.00006470013,0.10476488,0.024907926,0.44594556,0.00026276795,0.00045600146],"about_ca_topic_score_codex":0.00006164037,"about_ca_topic_score_gemma":0.000070671915,"teacher_disagreement_score":0.9786631,"about_ca_system_score_codex":0.000025995536,"about_ca_system_score_gemma":0.00003219913,"threshold_uncertainty_score":0.26222065},"labels":[],"label_agreement":null}]}