{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":7,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":7,"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":"594a330a2161","filters":{"venue":"Corpus Pragmatics"}},"results":[{"id":"W2983553948","doi":"10.1007/s41701-019-00065-w","title":"The SFU Opinion and Comments Corpus: A Corpus for the Analysis of Online News Comments","year":2019,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Simon Fraser University; Nvidia","keywords":"Computer science; Corpus linguistics; Focus (optics); Meaning (existential); Newspaper; Negation; Linguistics; Constructive; Interpretation (philosophy); Annotation; Natural language processing; Artificial intelligence; Psychology; Process (computing); Sociology; Media studies","retraction":null,"screen_n_in":null,"score":{"opus":0.01791365588722305,"gpt":0.2736738631037269,"spread":0.2557602072165039,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005942211,0.0001710585,0.0003177456,0.0001164672,0.0003581258,0.0001966658,0.0008572551,0.00007263638,0.000004212741],"category_scores_gemma":[0.0001423694,0.0001051022,0.0001420343,0.0007229765,0.00008691279,0.0001611382,0.0002969687,0.0001539785,0.000009539275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003910881,"about_ca_system_score_gemma":0.00004741317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009558499,"about_ca_topic_score_gemma":0.0001618012,"domain_scores_codex":[0.9985368,0.0001188558,0.0004641136,0.0002602881,0.0003362112,0.0002837253],"domain_scores_gemma":[0.9970734,0.001285067,0.0004554805,0.0009467033,0.0001638232,0.00007548882],"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":[0.0001992742,0.0006112254,0.05475537,0.0002585016,0.002745102,0.000002250873,0.00289787,0.001734477,0.001435037,0.02350848,0.009122631,0.9027297],"study_design_scores_gemma":[0.001760254,0.0005349913,0.0279927,0.00009561893,0.0005038737,0.00001140825,0.0004920302,0.8316038,0.0009477969,0.002786022,0.1329404,0.0003310854],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4410268,0.002796414,0.5375487,0.01046362,0.004409238,0.003053362,0.0001513725,0.0001936213,0.0003569226],"genre_scores_gemma":[0.9582819,0.004210837,0.03187308,0.003831039,0.000181474,0.0001474466,0.0001402689,0.00005424596,0.001279733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9023987,"threshold_uncertainty_score":0.4285944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2596760369","doi":"10.1007/s41701-017-0006-y","title":"On Being Negative","year":2017,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Simon Fraser University","keywords":"Rhetorical question; Adjective; Negativity effect; Computer science; Taxonomy (biology); Natural language processing; Newspaper; Linguistics; Focus (optics); Corpus linguistics; Adverb; Artificial intelligence; Rhetorical device; Semantics (computer science); Expression (computer science); Psychology; Noun; Sociology; Cognitive psychology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02734421908443559,"gpt":0.3207945456736987,"spread":0.2934503265892632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001851056,0.0001139432,0.0001462744,0.00004458533,0.0003451731,0.0001018638,0.000267795,0.00008917574,0.000825382],"category_scores_gemma":[0.0005606263,0.00009813654,0.00005513033,0.00003009624,0.00008546183,0.00008957044,0.00004414281,0.0001688714,0.001804235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001892459,"about_ca_system_score_gemma":0.00001368224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004498404,"about_ca_topic_score_gemma":0.00002271527,"domain_scores_codex":[0.9992404,0.00007558529,0.0001618679,0.0001792372,0.0001420591,0.000200844],"domain_scores_gemma":[0.9987397,0.0002239543,0.0002221937,0.0006976965,0.00005749539,0.00005894918],"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":[0.0001366493,0.0003485881,0.002160852,0.00004752126,0.0001794142,0.0001995983,0.01819299,0.000002299925,0.0003466219,0.795927,0.012177,0.1702815],"study_design_scores_gemma":[0.004246898,0.0008582345,0.09568735,0.0003136084,0.0002895698,0.00007531767,0.004407838,0.0004314922,0.006115204,0.8727202,0.01394489,0.0009093941],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4690996,0.00005079795,0.001931255,0.0002046922,0.001433356,0.000186209,0.00000899058,0.00006571254,0.5270194],"genre_scores_gemma":[0.9889311,0.000008442466,0.0007275027,0.0006424341,0.0002209822,0.00003226338,0.000008005542,0.00002123884,0.009408019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5198315,"threshold_uncertainty_score":0.998973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4293072906","doi":"10.1007/s41701-022-00120-z","title":"Responses to Thanks in Ireland, England and Canada: A Variational Pragmatic Perspective","year":2022,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Leuphana Universität Lüneburg","keywords":"Irish; Varieties of English; British English; Linguistics; Perspective (graphical); Variety (cybernetics); Corpus linguistics; Point (geometry); Psychology; Universality (dynamical systems); Sociology; Computer science; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02219871727050478,"gpt":0.2591112480562162,"spread":0.2369125307857114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004295458,0.0001234117,0.0001765588,0.0001401187,0.0004387201,0.0001450989,0.0002428558,0.00001685486,0.000782049],"category_scores_gemma":[0.0003465465,0.0001163791,0.00001753194,0.00007460998,0.00007768075,0.0001195753,0.0002206948,0.0002375903,0.000006280215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003258781,"about_ca_system_score_gemma":0.0006477703,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2072009,"about_ca_topic_score_gemma":0.8529426,"domain_scores_codex":[0.998751,0.0003174801,0.0002629459,0.0001605587,0.000329672,0.0001783236],"domain_scores_gemma":[0.9987632,0.0006617716,0.000114232,0.0002917782,0.000108011,0.00006100858],"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":[0.00007900569,0.0001017086,0.003039126,0.00003030658,0.00003656405,0.00002864191,0.2190383,0.0002284322,0.000009338889,0.7743887,0.002788354,0.0002315927],"study_design_scores_gemma":[0.002990699,0.0005583904,0.04150297,0.0001061447,0.00009935209,0.0001292171,0.5150352,0.002874784,0.00001084149,0.06428575,0.3714515,0.0009551673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9466617,0.0008201709,0.00008306294,0.00707875,0.000370347,0.0006053032,0.000300188,0.00005346917,0.04402699],"genre_scores_gemma":[0.9944566,0.00001328488,0.0006226531,0.0006289675,0.00008555539,0.0001824384,0.00002845121,0.0000171576,0.003964839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7101029,"threshold_uncertainty_score":0.8562889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408463245","doi":"10.1007/s41701-025-00185-6","title":"Attitude in Reported and Non-reported News: A Critique of Sentiment Analysis in Corpus Pragmatics","year":2025,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Simon Fraser University","funders":"Australian Research Data Commons; Simon Fraser University; University of Sydney","keywords":"Pragmatics; Sentiment analysis; Linguistics; Corpus linguistics; Psychology; Computer science; Natural language processing; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01697193502643659,"gpt":0.306628368159153,"spread":0.2896564331327164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001181243,0.0002490548,0.0008505926,0.001471487,0.00005688428,0.0001497446,0.0004667333,0.0001342175,0.00001492519],"category_scores_gemma":[0.0003242868,0.0002502375,0.0001706316,0.004235455,0.0000731369,0.0002797344,0.0003736148,0.0002166324,0.000002384795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009645176,"about_ca_system_score_gemma":0.0001944799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002770563,"about_ca_topic_score_gemma":0.001037562,"domain_scores_codex":[0.9967241,0.0001654217,0.001796684,0.0005420108,0.0004382401,0.0003335292],"domain_scores_gemma":[0.9975557,0.0003356153,0.0008333726,0.0009856379,0.0002031477,0.00008653747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001491763,0.0005863847,0.9746625,0.0002856325,0.001194787,0.0002089535,0.00232501,0.002843142,0.001067607,0.006861103,0.0003713985,0.009578553],"study_design_scores_gemma":[0.0013084,0.00007066526,0.2165165,0.0004864313,0.0006539231,0.0000141621,0.0003692523,0.7746217,0.00235987,0.002990636,0.0002483155,0.0003601416],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7198947,0.0006745691,0.2768033,0.0006480901,0.0002428105,0.0004838063,0.000002604764,0.0000520133,0.001198112],"genre_scores_gemma":[0.9545585,0.0002277091,0.04453454,0.0002314141,0.00001095567,0.00003222396,0.00002045288,0.00001019248,0.0003740379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7717785,"threshold_uncertainty_score":0.999995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4281645291","doi":"10.1007/s41701-022-00121-y","title":"“Well He’s Sick Anyway Like”: Anyway in Irish English","year":2022,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Göteborgs Universitet","keywords":"Irish; Politeness; Linguistics; Index (typography); Proposition; History; Digression; Meaning (existential); Sociology; Psychology; Computer science; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03097053815072408,"gpt":0.259433873503889,"spread":0.2284633353531649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005545965,0.000221027,0.0002959386,0.0001783202,0.0005702985,0.0003453643,0.0007924599,0.00004372369,0.007259348],"category_scores_gemma":[0.0001118233,0.0002202396,0.00008688947,0.0001452115,0.0002522304,0.0003115088,0.0004607774,0.0005713595,0.0001707978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273144,"about_ca_system_score_gemma":0.0001338008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002125699,"about_ca_topic_score_gemma":0.001665376,"domain_scores_codex":[0.9981206,0.0003416188,0.0005162541,0.0002440674,0.0004158464,0.0003616207],"domain_scores_gemma":[0.9983237,0.0003016658,0.0002597191,0.0009029221,0.0001391225,0.00007290231],"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":[0.00003866336,0.0007382133,0.001458102,0.0001403842,0.00007546999,0.00006218611,0.3254533,0.0005742669,0.00003786296,0.4783426,0.1908563,0.002222737],"study_design_scores_gemma":[0.0006150786,0.0001199277,0.00030128,0.00003041445,0.00003301921,0.000006834599,0.1126052,0.0006770608,0.00002528886,0.00525566,0.8799662,0.0003640822],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2595133,0.00143149,0.00002679833,0.0007767585,0.002165555,0.0005821898,0.0001306012,0.0003685823,0.7350048],"genre_scores_gemma":[0.9783548,0.00008768369,0.0003337093,0.0008377064,0.0004206072,0.0001614263,0.0001208748,0.00005401456,0.01962918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7188416,"threshold_uncertainty_score":0.9936482,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389053094","doi":"10.1007/s41701-023-00159-6","title":"Eh Across Englishes: A Corpus-Pragmatic Analysis of the Corpus of Global Web-Based English","year":2023,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Christian-Albrechts-Universität zu Kiel","keywords":"Punctuation; Linguistics; Variety (cybernetics); Variation (astronomy); Interrogative; Sentence; Contrast (vision); Computer science; Corpus linguistics; Discourse marker; Narrative; Natural language processing; Artificial intelligence; Philosophy; Astrophysics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01918366678165337,"gpt":0.2799128157519163,"spread":0.2607291489702629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000956221,0.0003833911,0.001188792,0.0002557118,0.0004279953,0.0001766094,0.000973577,0.0001038285,0.0005470742],"category_scores_gemma":[0.00200724,0.0002750374,0.0009033296,0.002193308,0.001376581,0.0001934247,0.000394055,0.0002136953,0.00003450592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001134,"about_ca_system_score_gemma":0.0001867833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002683264,"about_ca_topic_score_gemma":0.008980558,"domain_scores_codex":[0.9966125,0.0002660601,0.001211188,0.0003689789,0.0009863132,0.0005549002],"domain_scores_gemma":[0.9955851,0.0008170351,0.001177725,0.001285454,0.001048112,0.00008651836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001673884,0.001635246,0.1513058,0.002638961,0.02176776,0.00007339628,0.3867843,0.02574876,0.0002832055,0.368375,0.02826454,0.01295566],"study_design_scores_gemma":[0.008835612,0.001027906,0.07934637,0.002416311,0.05056658,0.000006662298,0.4275432,0.2326049,0.002197535,0.01369697,0.1778501,0.003907884],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9617202,0.0008995741,0.0001310163,0.0002007127,0.00185793,0.0005276672,0.002024774,0.0003038611,0.03233431],"genre_scores_gemma":[0.997698,0.00007275677,0.0001550919,0.0001697494,0.000254493,0.00005475696,0.0001079705,0.00003797685,0.00144919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.354678,"threshold_uncertainty_score":0.9999702,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3104004966","doi":"10.1007/s41701-020-00092-y","title":"Review of Orality in Written Texts: Using Historical Corpora to Investigate Irish English 1700–1900","year":2020,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Orality; Irish; History; Linguistics; Literature; Sociology; Art; Philosophy; Literacy; Pedagogy","retraction":null,"screen_n_in":null,"score":{"opus":0.09385365034648183,"gpt":0.2778948167151798,"spread":0.184041166368698,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000324487,0.0001802912,0.0005256305,0.00008025735,0.0001003343,0.00004045739,0.0002146435,0.00004268358,0.0002379401],"category_scores_gemma":[0.001069004,0.0001578605,0.000116057,0.0002546822,0.000174617,0.0001451241,0.0001258686,0.0002036698,0.00001224982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009334122,"about_ca_system_score_gemma":0.00005812159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003423892,"about_ca_topic_score_gemma":0.0001923121,"domain_scores_codex":[0.998565,0.0001249772,0.0006545072,0.0002152683,0.000221529,0.0002187679],"domain_scores_gemma":[0.9989789,0.00009931981,0.0002732841,0.0002287793,0.000270801,0.0001489693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000863841,0.0004863143,0.01350065,0.03570248,0.0002161049,0.0001080615,0.4440607,0.00003727887,0.0001579557,0.03646868,0.4623642,0.006811201],"study_design_scores_gemma":[0.0004886712,0.0002558744,0.0003613904,0.006225789,0.0001541229,0.000001954568,0.00398457,0.0001862179,0.00007065252,0.001297199,0.9864994,0.0004741596],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6226112,0.2572745,0.0006768489,0.01770136,0.00404001,0.003945515,0.0004298963,0.0007042349,0.09261648],"genre_scores_gemma":[0.9109588,0.009925168,0.01076652,0.06406863,0.003045056,0.0001104891,0.0000704218,0.0001381728,0.0009167345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5241352,"threshold_uncertainty_score":0.6437365,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}