{"meta":{"query_hash":"594a330a2161","filters":{"venue":"Corpus Pragmatics"},"cohort_total":7,"direct_labels_cover":0,"predictions_cover":7,"exported":7,"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/594a330a2161","api":"https://metacan.xera.ac/api/v1/cohort?venue=Corpus+Pragmatics"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02734421908443559,"score_gpt":0.32079454567369875,"score_spread":0.2934503265892632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596760369","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":[0.46909955,0.00005079795,0.0019312549,0.0002046922,0.0014333556,0.00018620904,0.00000899058,0.00006571254,0.52701944],"genre_scores_gemma":[0.9889311,0.0000084424655,0.0007275027,0.00064243405,0.00022098221,0.000032263375,0.000008005542,0.00002123884,0.009408019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992404,0.00007558529,0.00016186787,0.00017923723,0.00014205907,0.00020084398],"domain_scores_gemma":[0.9987397,0.00022395427,0.00022219367,0.0006976965,0.000057495392,0.00005894918],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018510556,0.00011394319,0.00014627444,0.00004458533,0.0003451731,0.000101863814,0.00026779497,0.000089175745,0.00082538195],"category_scores_gemma":[0.00056062633,0.00009813654,0.00005513033,0.000030096242,0.00008546183,0.000089570436,0.00004414281,0.0001688714,0.001804235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001366493,0.00034858813,0.0021608516,0.000047521262,0.00017941423,0.00019959826,0.01819299,0.000002299925,0.00034662188,0.795927,0.012176998,0.1702815],"study_design_scores_gemma":[0.004246898,0.00085823453,0.09568735,0.0003136084,0.00028956975,0.00007531767,0.004407838,0.0004314922,0.0061152037,0.8727202,0.01394489,0.00090939406],"about_ca_topic_score_codex":0.000044984037,"about_ca_topic_score_gemma":0.000022715272,"teacher_disagreement_score":0.51983154,"about_ca_system_score_codex":0.000018924586,"about_ca_system_score_gemma":0.000013682238,"threshold_uncertainty_score":0.99897295},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01791365588722305,"score_gpt":0.27367386310372693,"score_spread":0.2557602072165039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983553948","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":[0.4410268,0.002796414,0.53754866,0.010463622,0.0044092378,0.0030533618,0.00015137254,0.00019362128,0.00035692262],"genre_scores_gemma":[0.9582819,0.004210837,0.03187308,0.003831039,0.00018147404,0.00014744661,0.0001402689,0.00005424596,0.0012797335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985368,0.000118855845,0.00046411363,0.0002602881,0.0003362112,0.0002837253],"domain_scores_gemma":[0.9970734,0.0012850666,0.00045548048,0.00094670325,0.0001638232,0.00007548882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059422106,0.00017105848,0.00031774555,0.00011646721,0.0003581258,0.00019666583,0.00085725513,0.00007263638,0.000004212741],"category_scores_gemma":[0.00014236943,0.00010510221,0.00014203427,0.0007229765,0.00008691279,0.00016113819,0.0002969687,0.00015397854,0.000009539275],"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":[0.00019927419,0.00061122543,0.054755375,0.00025850156,0.002745102,0.0000022508727,0.0028978698,0.0017344775,0.0014350372,0.023508478,0.009122631,0.90272975],"study_design_scores_gemma":[0.001760254,0.0005349913,0.027992696,0.00009561893,0.00050387374,0.000011408248,0.00049203023,0.8316038,0.0009477969,0.002786022,0.13294043,0.0003310854],"about_ca_topic_score_codex":0.00009558499,"about_ca_topic_score_gemma":0.00016180117,"teacher_disagreement_score":0.9023987,"about_ca_system_score_codex":0.000039108814,"about_ca_system_score_gemma":0.00004741317,"threshold_uncertainty_score":0.42859438},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Orality; Irish; History; Linguistics; Literature; Sociology; Art; Philosophy; Literacy; Pedagogy","score_opus":0.09385365034648183,"score_gpt":0.27789481671517985,"score_spread":0.18404116636869802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104004966","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":[0.62261117,0.2572745,0.0006768489,0.017701363,0.0040400103,0.0039455146,0.00042989626,0.00070423493,0.09261648],"genre_scores_gemma":[0.9109588,0.009925168,0.010766516,0.06406863,0.0030450565,0.000110489076,0.000070421804,0.0001381728,0.0009167345],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856496,0.00012497719,0.0006545072,0.00021526832,0.00022152897,0.00021876788],"domain_scores_gemma":[0.99897885,0.00009931981,0.0002732841,0.00022877933,0.00027080104,0.0001489693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000324487,0.0001802912,0.00052563054,0.00008025735,0.00010033429,0.000040457395,0.00021464349,0.000042683576,0.00023794014],"category_scores_gemma":[0.0010690044,0.00015786052,0.00011605695,0.0002546822,0.00017461702,0.00014512413,0.00012586864,0.00020366984,0.0000122498195],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000863841,0.00048631427,0.01350065,0.035702482,0.00021610493,0.00010806154,0.44406074,0.000037278867,0.00015795571,0.036468677,0.46236417,0.0068112006],"study_design_scores_gemma":[0.0004886712,0.0002558744,0.0003613904,0.0062257885,0.00015412287,0.0000019545682,0.0039845696,0.00018621786,0.00007065252,0.0012971992,0.9864994,0.0004741596],"about_ca_topic_score_codex":0.00034238916,"about_ca_topic_score_gemma":0.0001923121,"teacher_disagreement_score":0.52413523,"about_ca_system_score_codex":0.000093341216,"about_ca_system_score_gemma":0.00005812159,"threshold_uncertainty_score":0.64373654},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Göteborgs Universitet","keywords":"Irish; Politeness; Linguistics; Index (typography); Proposition; History; Digression; Meaning (existential); Sociology; Psychology; Computer science; Philosophy","score_opus":0.030970538150724085,"score_gpt":0.25943387350388897,"score_spread":0.22846333535316488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281645291","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":[0.25951326,0.0014314898,0.00002679833,0.00077675853,0.002165555,0.0005821898,0.00013060123,0.00036858226,0.7350048],"genre_scores_gemma":[0.9783548,0.000087683686,0.00033370926,0.0008377064,0.00042060725,0.00016142635,0.00012087482,0.000054014563,0.019629177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981206,0.0003416188,0.0005162541,0.00024406744,0.00041584639,0.00036162068],"domain_scores_gemma":[0.9983237,0.00030166583,0.00025971915,0.0009029221,0.00013912247,0.00007290231],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055459654,0.00022102702,0.00029593857,0.00017832019,0.00057029846,0.0003453643,0.0007924599,0.000043723692,0.007259348],"category_scores_gemma":[0.00011182326,0.0002202396,0.00008688947,0.00014521154,0.00025223038,0.0003115088,0.0004607774,0.0005713595,0.00017079778],"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":[0.00003866336,0.0007382133,0.0014581016,0.00014038419,0.000075469994,0.00006218611,0.32545325,0.00057426695,0.000037862956,0.47834256,0.19085631,0.0022227373],"study_design_scores_gemma":[0.0006150786,0.00011992772,0.00030128003,0.000030414454,0.000033019212,0.0000068345994,0.112605184,0.0006770608,0.000025288857,0.00525566,0.8799662,0.00036408217],"about_ca_topic_score_codex":0.00021256988,"about_ca_topic_score_gemma":0.0016653759,"teacher_disagreement_score":0.71884155,"about_ca_system_score_codex":0.00012731442,"about_ca_system_score_gemma":0.00013380084,"threshold_uncertainty_score":0.9936482},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.022198717270504785,"score_gpt":0.2591112480562162,"score_spread":0.23691253078571142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293072906","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":[0.9466617,0.0008201709,0.00008306294,0.00707875,0.00037034703,0.00060530315,0.00030018802,0.00005346917,0.04402699],"genre_scores_gemma":[0.99445665,0.0000132848845,0.00062265305,0.0006289675,0.00008555539,0.00018243838,0.000028451206,0.000017157603,0.003964839],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99875104,0.00031748012,0.0002629459,0.00016055875,0.000329672,0.0001783236],"domain_scores_gemma":[0.9987632,0.0006617716,0.00011423203,0.0002917782,0.000108011016,0.00006100858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042954576,0.00012341166,0.0001765588,0.00014011875,0.00043872008,0.00014509888,0.00024285584,0.000016854856,0.000782049],"category_scores_gemma":[0.0003465465,0.000116379124,0.000017531942,0.00007460998,0.00007768075,0.00011957533,0.00022069483,0.00023759034,0.000006280215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079005695,0.00010170863,0.003039126,0.000030306575,0.00003656405,0.000028641913,0.21903828,0.00022843221,0.000009338889,0.7743887,0.0027883544,0.00023159274],"study_design_scores_gemma":[0.0029906991,0.0005583904,0.041502975,0.00010614474,0.00009935209,0.00012921706,0.51503515,0.0028747844,0.000010841485,0.06428575,0.3714515,0.0009551673],"about_ca_topic_score_codex":0.20720094,"about_ca_topic_score_gemma":0.8529426,"teacher_disagreement_score":0.7101029,"about_ca_system_score_codex":0.0003258781,"about_ca_system_score_gemma":0.0006477703,"threshold_uncertainty_score":0.85628885},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019183666781653366,"score_gpt":0.2799128157519163,"score_spread":0.26072914897026295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389053094","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":[0.96172017,0.00089957414,0.00013101634,0.00020071273,0.0018579301,0.0005276672,0.0020247737,0.00030386113,0.032334313],"genre_scores_gemma":[0.997698,0.000072756775,0.00015509188,0.00016974942,0.000254493,0.000054756958,0.0001079705,0.000037976853,0.0014491902],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99661255,0.00026606012,0.0012111882,0.0003689789,0.0009863132,0.00055490015],"domain_scores_gemma":[0.99558514,0.0008170351,0.0011777254,0.001285454,0.0010481119,0.00008651836],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000956221,0.00038339113,0.0011887918,0.00025571184,0.00042799526,0.0001766094,0.00097357697,0.00010382847,0.00054707425],"category_scores_gemma":[0.00200724,0.00027503737,0.00090332964,0.0021933082,0.0013765811,0.00019342471,0.00039405495,0.00021369528,0.00003450592],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016738835,0.0016352461,0.15130575,0.0026389614,0.02176776,0.00007339628,0.38678432,0.025748763,0.00028320553,0.368375,0.028264541,0.012955665],"study_design_scores_gemma":[0.008835612,0.0010279064,0.07934637,0.0024163113,0.05056658,0.000006662298,0.4275432,0.23260488,0.0021975348,0.01369697,0.17785011,0.0039078835],"about_ca_topic_score_codex":0.0002683264,"about_ca_topic_score_gemma":0.008980558,"teacher_disagreement_score":0.35467803,"about_ca_system_score_codex":0.00010011341,"about_ca_system_score_gemma":0.00018678335,"threshold_uncertainty_score":0.9999702},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01697193502643659,"score_gpt":0.30662836815915295,"score_spread":0.2896564331327164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408463245","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":[0.7198947,0.0006745691,0.2768033,0.0006480901,0.00024281054,0.00048380633,0.0000026047644,0.000052013296,0.0011981118],"genre_scores_gemma":[0.9545585,0.00022770908,0.04453454,0.00023141412,0.000010955668,0.000032223958,0.000020452877,0.000010192477,0.0003740379],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967241,0.00016542169,0.0017966839,0.00054201076,0.00043824007,0.0003335292],"domain_scores_gemma":[0.9975557,0.0003356153,0.00083337264,0.0009856379,0.00020314775,0.00008653747],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011812428,0.0002490548,0.00085059257,0.001471487,0.000056884284,0.00014974464,0.0004667333,0.00013421754,0.00001492519],"category_scores_gemma":[0.00032428678,0.0002502375,0.0001706316,0.004235455,0.0000731369,0.0002797344,0.0003736148,0.00021663235,0.0000023847954],"study_design_candidate":"observational","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":[0.000014917633,0.0005863847,0.9746625,0.0002856325,0.0011947871,0.00020895345,0.00232501,0.002843142,0.0010676074,0.006861103,0.00037139846,0.009578553],"study_design_scores_gemma":[0.0013084003,0.000070665265,0.21651652,0.00048643132,0.00065392314,0.0000141621,0.00036925232,0.77462167,0.00235987,0.0029906356,0.0002483155,0.00036014157],"about_ca_topic_score_codex":0.00027705627,"about_ca_topic_score_gemma":0.0010375616,"teacher_disagreement_score":0.7717785,"about_ca_system_score_codex":0.00009645176,"about_ca_system_score_gemma":0.00019447993,"threshold_uncertainty_score":0.999995},"labels":[],"label_agreement":null}]}