{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08166997,0.0021979036,0.0049633463,0.037814427,0.0017183613,0.000024574045,0.00014518757,0.00004198592,0.8714244],"genre_scores_gemma":[0.95128745,0.000976029,0.0008923644,0.007965862,0.00044823257,0.000036359525,0.00011487087,0.00007835112,0.038200386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977133,0.001157356,0.00004611577,0.00031957464,0.00048088992,0.00028279147],"domain_scores_gemma":[0.9979717,0.0007423792,0.00028514606,0.00027231855,0.00048372793,0.00024464054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021286742,0.00043108832,0.0003606497,0.0008921518,0.003519794,0.004095302,0.00052881043,0.0021981846,0.010522943],"category_scores_gemma":[0.0063989838,0.00019707394,0.0002261778,0.00047564073,0.013751469,0.005271436,0.002649994,0.003796558,0.0012201727],"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":[0.0001251133,0.000035822184,0.0023312254,0.00008295463,0.000024897547,0.00050946936,0.033893924,0.000079962854,0.0012642306,0.91748375,0.021828962,0.022339579],"study_design_scores_gemma":[0.000027110365,0.00007994668,0.009554291,0.0002757319,0.000051268544,0.0012745719,0.048083313,0.00027704085,0.00079531246,0.6439109,0.2956101,0.000060324135],"about_ca_topic_score_codex":0.0022628186,"about_ca_topic_score_gemma":0.0029211435,"teacher_disagreement_score":0.010522943,"about_ca_system_score_codex":0.001266228,"about_ca_system_score_gemma":0.0007389213,"threshold_uncertainty_score":0.03520274},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15328962,0.0038133769,0.012660825,0.002060849,0.0014091664,0.0028463718,0.7849947,0.0013776415,0.037547484],"genre_scores_gemma":[0.16890982,0.0020045,0.037946265,0.000595154,0.00067757186,0.011300784,0.75620127,0.00097651384,0.021388186],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933882,0.002102099,0.0009297793,0.000986039,0.0021727653,0.0004211104],"domain_scores_gemma":[0.97713,0.011069866,0.0020079166,0.0013149652,0.0076015065,0.000875668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033790378,0.0009980648,0.0008003631,0.01088201,0.0034112905,0.0018984565,0.0010759768,0.0019218031,0.01125415],"category_scores_gemma":[0.0225212,0.00041288312,0.0004529581,0.01390172,0.0013890815,0.0017580421,0.0028126729,0.0012907966,0.007974826],"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":[0.000695024,0.00048132168,0.016751388,0.008363558,0.0000801545,0.002996758,0.0438268,0.0007939021,0.012298384,0.008675121,0.68360144,0.2214362],"study_design_scores_gemma":[0.00010457518,0.00008086271,0.054906834,0.0012471633,0.00004469753,0.0007618596,0.012436815,0.0013377499,0.0037136977,0.0015021182,0.9237455,0.00011812561],"about_ca_topic_score_codex":0.023073733,"about_ca_topic_score_gemma":0.040609393,"teacher_disagreement_score":0.023073733,"about_ca_system_score_codex":0.0025027273,"about_ca_system_score_gemma":0.0041159745,"threshold_uncertainty_score":0.045878887},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22865206,0.5967579,0.003536199,0.0065613007,0.0019821944,0.00031413653,0.017648658,0.00011618592,0.14443141],"genre_scores_gemma":[0.45613825,0.49669892,0.007606928,0.0019862477,0.0013204904,0.0006066802,0.017840968,0.00047989882,0.017321652],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789137,0.0006252921,0.00045751163,0.00037695756,0.0004933599,0.00015560914],"domain_scores_gemma":[0.98540753,0.008924354,0.0013011168,0.0007667011,0.0032772443,0.00032299018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004874973,0.00037853955,0.0005810407,0.016418086,0.0014182134,0.0037641276,0.0009914162,0.0005006495,0.0037695928],"category_scores_gemma":[0.014131519,0.00041761145,0.00034530705,0.021944027,0.0035955103,0.003073996,0.0018484481,0.0008817116,0.0011326832],"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":[0.00022323235,0.000106311534,0.038172204,0.03539594,0.00027418198,0.0013515442,0.08632171,0.00026762477,0.0035262685,0.015815124,0.05264447,0.7659014],"study_design_scores_gemma":[0.000012561329,0.00005368649,0.15796378,0.018525383,0.00023097574,0.0008959216,0.040043715,0.00007487586,0.0012650887,0.0009481987,0.77993107,0.00005475382],"about_ca_topic_score_codex":0.03510381,"about_ca_topic_score_gemma":0.08825837,"teacher_disagreement_score":0.03510381,"about_ca_system_score_codex":0.0033990669,"about_ca_system_score_gemma":0.007449004,"threshold_uncertainty_score":0.06979895},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94136107,0.000689283,0.0018634067,0.0010257298,0.00011129155,0.00006105873,0.00045700886,0.000035557518,0.054395482],"genre_scores_gemma":[0.9942636,0.00025654753,0.0006088961,0.0001485619,0.000019861898,0.000023128043,0.00017472879,0.0000523204,0.0044523966],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99830616,0.0006929379,0.00010801057,0.00024291211,0.00034232455,0.00030760313],"domain_scores_gemma":[0.9979595,0.00077339774,0.0004360229,0.0001320801,0.00043632448,0.00026264985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015736193,0.00025971455,0.00034005326,0.0012351272,0.002318201,0.0025332395,0.0004510459,0.00039163182,0.0029167926],"category_scores_gemma":[0.0031699664,0.00018111666,0.00013903381,0.001512283,0.0030184975,0.0016803226,0.002257656,0.0011080271,0.0003727967],"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":[0.0003085432,0.00008466347,0.045193233,0.000569082,0.000028659906,0.001699913,0.85823715,0.00007651546,0.017142791,0.016538365,0.0066161677,0.053504974],"study_design_scores_gemma":[0.000010788532,0.00007261492,0.09554728,0.00040843774,0.000027553475,0.0016459618,0.7628524,0.00023557231,0.0021729583,0.0008087388,0.13613527,0.000082439954],"about_ca_topic_score_codex":0.03222174,"about_ca_topic_score_gemma":0.066381745,"teacher_disagreement_score":0.03222174,"about_ca_system_score_codex":0.0022366021,"about_ca_system_score_gemma":0.0016452319,"threshold_uncertainty_score":0.06406838},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9298602,0.0012945451,0.0013814382,0.0016922917,0.000031660013,0.00010894558,0.0019946347,0.000027485481,0.0636088],"genre_scores_gemma":[0.9945469,0.0003661054,0.0006737583,0.00012621791,0.000004348009,0.000047643523,0.0005866855,0.000028790555,0.0036195887],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9973111,0.0007629716,0.00007688284,0.00033431945,0.00068772,0.0008269618],"domain_scores_gemma":[0.9946732,0.002354427,0.00033651807,0.00021691454,0.0020421972,0.00037681445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030665188,0.00038881987,0.0006447395,0.0025607029,0.0056519117,0.0065241894,0.0015316557,0.00069886283,0.0049372846],"category_scores_gemma":[0.010000863,0.00034079578,0.00029604827,0.0055431607,0.0056682117,0.001692301,0.0035724165,0.0013426873,0.00030845715],"study_design_candidate":"observational","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":[0.00057760254,0.000116392344,0.11942882,0.0007435125,0.00014287289,0.0012159678,0.7069795,0.0020725022,0.0049819592,0.091663904,0.0077138776,0.06436316],"study_design_scores_gemma":[0.000023579041,0.000036616224,0.24608496,0.00036148963,0.00007251084,0.00021360855,0.69628876,0.0016302225,0.0010286617,0.004248079,0.04984488,0.00016657615],"about_ca_topic_score_codex":0.98675364,"about_ca_topic_score_gemma":0.99146175,"teacher_disagreement_score":0.053834632,"about_ca_system_score_codex":0.053834632,"about_ca_system_score_gemma":0.0357249,"threshold_uncertainty_score":0.39059943},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9666621,0.0012989963,0.0065641515,0.0004626101,0.000067930705,0.0003290004,0.0060641873,0.0000694613,0.018481487],"genre_scores_gemma":[0.98014385,0.0005832671,0.008039972,0.00011374377,0.00004771953,0.00046197313,0.0074143526,0.00018267993,0.003012397],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99762326,0.0012595241,0.00022888451,0.00038875706,0.00036134425,0.00013822241],"domain_scores_gemma":[0.98734134,0.009472457,0.00061444216,0.0007379742,0.0015838565,0.00024988488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031239886,0.0003216965,0.00042462384,0.0045575285,0.0019031578,0.0020149078,0.000393506,0.00037792118,0.0031116533],"category_scores_gemma":[0.008653863,0.00017531677,0.0002065796,0.0062606996,0.0020200529,0.0013086406,0.0025651143,0.0007602355,0.0003288378],"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":[0.0009559507,0.00065295765,0.05761469,0.0041193427,0.00016195122,0.0033409123,0.6097466,0.0010889563,0.0458727,0.026842928,0.013909791,0.23569328],"study_design_scores_gemma":[0.00014790792,0.00023004734,0.3593022,0.0008474822,0.00017246451,0.0017115937,0.34576705,0.0026498472,0.015827855,0.0041163834,0.2690924,0.00013483824],"about_ca_topic_score_codex":0.008758514,"about_ca_topic_score_gemma":0.020494517,"teacher_disagreement_score":0.008758514,"about_ca_system_score_codex":0.0011138306,"about_ca_system_score_gemma":0.0008871331,"threshold_uncertainty_score":0.017415047},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12736501,0.03681369,0.46170214,0.19468081,0.006474646,0.0017138809,0.0042542526,0.00082459155,0.16617101],"genre_scores_gemma":[0.8906721,0.0060205995,0.08166127,0.010167201,0.0029227398,0.0030652552,0.0010329108,0.0006542145,0.0038037861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.863775,0.100130245,0.0052709556,0.0076098605,0.022462048,0.0007518464],"domain_scores_gemma":[0.5063269,0.42110816,0.012422917,0.017401295,0.041386068,0.0013546125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1601577,0.0010373628,0.0020741068,0.0137945535,0.006742345,0.0119091235,0.004423451,0.0022096026,0.0033258402],"category_scores_gemma":[0.34974143,0.0011983304,0.0012503577,0.01359198,0.03068677,0.014865241,0.005770417,0.0044778353,0.00076291885],"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":[0.0005898843,0.00011917331,0.014414001,0.005951683,0.00081621186,0.00042154195,0.09167764,0.0016074664,0.0022484425,0.6527308,0.039995093,0.189428],"study_design_scores_gemma":[0.00031827224,0.00018123213,0.04366848,0.0075390413,0.00058385404,0.00074701174,0.058285292,0.026314888,0.0045332387,0.5998558,0.25758323,0.00038977613],"about_ca_topic_score_codex":0.03605639,"about_ca_topic_score_gemma":0.028361676,"teacher_disagreement_score":0.1601577,"about_ca_system_score_codex":0.011453082,"about_ca_system_score_gemma":0.0062767514,"threshold_uncertainty_score":0.847005},"labels":[],"label_agreement":null}]}