{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"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":"4c2cc3b5088f","filters":{"venue":"Corpora"}},"results":[{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Corpus linguistics; Linguistics; Focus (optics); Population; Contrastive linguistics; Sociology; Applied linguistics; Computer science; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.16594680154034,"gpt":0.363258996867498,"spread":0.1973121953271579,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002251501,0.000245854,0.0004615175,0.0001799203,0.0002522221,0.0002220934,0.0002581875,0.0000355537,0.00140269],"category_scores_gemma":[0.0003338585,0.0001884954,0.0001165321,0.00006416628,0.001090706,0.0002632877,0.0001509522,0.0001568134,0.000650552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000565032,"about_ca_system_score_gemma":0.00002354874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003805762,"about_ca_topic_score_gemma":0.007979228,"domain_scores_codex":[0.9985762,0.00006013302,0.0003992026,0.0003687674,0.0002423386,0.0003533808],"domain_scores_gemma":[0.9988181,0.0001593648,0.000190622,0.0004167148,0.000357811,0.00005738325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002585826,0.0005823436,0.01693403,0.000287393,0.0009300514,0.000290093,0.2125735,0.00002750118,0.0000398951,0.663621,0.009843783,0.0948446],"study_design_scores_gemma":[0.002366269,0.0003627235,0.1413468,0.0009097179,0.0005280799,0.00002059908,0.6324573,0.0002793915,0.00007503039,0.1143115,0.1052758,0.002066715],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.574764,0.05125159,0.000002966958,0.001828314,0.001638457,0.0003835262,0.00001754946,0.0001816742,0.3699319],"genre_scores_gemma":[0.9868029,0.001517536,0.00005357976,0.0001411968,0.0007719068,0.0001383589,0.00001116954,0.000029104,0.0105343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5493095,"threshold_uncertainty_score":0.9995102,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05206585222861549,"gpt":0.3048947820211111,"spread":0.2528289297924956,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001747461,0.00005608795,0.00007116069,0.00004650643,0.0001753145,0.00004537774,0.00003928031,0.00001003037,0.004847656],"category_scores_gemma":[0.00006375704,0.00003204569,0.00002626915,0.00001532908,0.0003240747,0.0002036645,0.00002612213,0.00001944088,0.0002139968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001568195,"about_ca_system_score_gemma":0.0000150247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002333338,"about_ca_topic_score_gemma":0.0004370375,"domain_scores_codex":[0.9995562,0.00002667502,0.00008999408,0.0001104978,0.0001416746,0.00007491959],"domain_scores_gemma":[0.9996556,0.00004747181,0.00005557386,0.0001257354,0.00009388608,0.00002174526],"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":[0.000004062806,0.00003114457,0.004511719,0.000003041621,0.00009003186,0.000002592413,0.01359858,0.000001589,0.00008762129,0.8550373,0.02321051,0.1034218],"study_design_scores_gemma":[0.003118711,0.0002359637,0.0352727,0.0003740323,0.002040246,0.000008780463,0.1007971,0.0008980383,0.0002066545,0.3715485,0.4842419,0.00125727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5957558,0.001197997,0.0002566619,0.004449344,0.0003445304,0.0001556858,0.00002685574,0.00006232236,0.3977509],"genre_scores_gemma":[0.9770394,0.00002116558,0.00003683195,0.00004984595,0.0002743806,0.00001845879,0.000005083362,0.000006066617,0.02254877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4834887,"threshold_uncertainty_score":0.996062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02606158654718032,"gpt":0.3246620743798674,"spread":0.2986004878326871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001025153,0.00004531364,0.00005070275,0.00001797557,0.001213557,0.00005227198,0.0001941614,0.00006647866,0.0001548203],"category_scores_gemma":[0.0001224646,0.00003118296,0.00004849578,0.0001806801,0.0003365563,0.00005312014,0.00002735062,0.0001176431,0.0001306092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005095882,"about_ca_system_score_gemma":0.00009689081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001477427,"about_ca_topic_score_gemma":0.006726044,"domain_scores_codex":[0.9993089,0.0000374202,0.0001220152,0.00008437252,0.0002098656,0.0002374341],"domain_scores_gemma":[0.9993307,0.0003249665,0.00006667541,0.0001438373,0.00004798741,0.00008583321],"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":[0.00001054409,0.0000199026,0.01579313,0.000001771108,0.0000103001,0.00001421969,0.008362547,0.000003464204,0.00002510019,0.8792729,0.03024545,0.06624065],"study_design_scores_gemma":[0.00007746948,0.000009375982,0.03501259,0.000004278686,0.000005540055,0.000001212696,0.003891262,0.00000952455,0.00001217289,0.02184433,0.9390701,0.00006211467],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1976643,0.002682412,0.001170599,0.005785887,0.002848547,0.0002634159,0.000004027434,0.0001327998,0.789448],"genre_scores_gemma":[0.9483617,0.0005121483,0.0001112421,0.000145617,0.0006649981,0.000002511499,0.000001963986,0.000005849121,0.050194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9088247,"threshold_uncertainty_score":0.9333825,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02239593382287337,"gpt":0.309573640430716,"spread":0.2871777066078426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000164167,0.00006936518,0.00008854741,0.00007869677,0.0001158602,0.0002387529,0.0003717287,0.00004170463,0.000001268285],"category_scores_gemma":[0.0001093783,0.00006430315,0.00001402174,0.00005696932,0.00003252452,0.0008746284,0.00008893332,0.00004941125,0.000002012756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002599554,"about_ca_system_score_gemma":0.00003219913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006164037,"about_ca_topic_score_gemma":0.00007067191,"domain_scores_codex":[0.9994565,0.00001444769,0.0001357508,0.0002003443,0.0000853545,0.0001076084],"domain_scores_gemma":[0.9993628,0.00002888975,0.000195525,0.0003378226,0.00004317405,0.00003180778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003461167,0.00001486328,0.007658435,0.00005979382,0.000001610323,0.00001192283,0.0004075713,3.701718e-7,0.004801407,0.00761992,0.000301563,0.9791191],"study_design_scores_gemma":[0.00138279,0.0002037055,0.4217339,0.0002418631,0.00001053774,0.00002536721,0.00006470013,0.1047649,0.02490793,0.4459456,0.0002627679,0.0004560015],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4951329,0.001279166,0.5006858,0.00148547,0.0002425156,0.0006429128,0.00000258961,0.0003392579,0.0001893662],"genre_scores_gemma":[0.6603045,0.000009340177,0.3394023,0.0001323934,0.00002012517,0.0000309697,0.000005273665,0.000004115213,0.00009101433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9786631,"threshold_uncertainty_score":0.2622207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}