{"meta":{"query_hash":"28b6cc5f6b26","filters":{"venue":"Studies in corpus linguistics"},"cohort_total":12,"direct_labels_cover":0,"predictions_cover":12,"exported":12,"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/28b6cc5f6b26","api":"https://metacan.xera.ac/api/v1/cohort?venue=Studies+in+corpus+linguistics"},"results":[{"id":"W2476135460","doi":"10.1075/scl.67.03dar","title":"At the crossroads of change","year":2015,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Possession (linguistics); Newspaper; Negation; History; Language change; Geography; Linguistics; Media studies; Sociology","score_opus":0.3719527862548491,"score_gpt":0.4396158681615569,"score_spread":0.06766308190670778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2476135460","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015517735,0.013862189,0.0000040593395,0.00032106185,0.01296826,0.00038097927,0.000105621635,0.000031555057,0.9723108],"genre_scores_gemma":[0.034396376,0.010104586,0.0002400277,0.00048769242,0.010181588,0.000034993103,0.000028622593,0.00004977379,0.94447637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983953,0.000074119445,0.0004791456,0.00026199,0.000503649,0.00028577988],"domain_scores_gemma":[0.9965805,0.0007533143,0.00045473242,0.00034090097,0.0018049057,0.000065668915],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012782366,0.0002105627,0.0005097408,0.000090528214,0.0003376577,0.000011161185,0.0003522981,0.00030797892,0.00022193327],"category_scores_gemma":[0.022748481,0.00016584636,0.000090326495,0.000060256767,0.0021341636,0.000004917898,0.00038849976,0.00030069126,0.00007801916],"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":[0.000018156634,0.000011202083,0.00027151717,0.00004003171,0.00007925662,0.000048846607,0.026799288,0.0000017482031,1.4559555e-7,0.94624853,0.025677064,0.00080419844],"study_design_scores_gemma":[0.0001812427,0.000037277387,0.000017429555,0.00010060948,0.00006975848,9.152464e-7,0.0008450462,0.00000172656,8.7987496e-7,0.106101714,0.8924902,0.00015318417],"about_ca_topic_score_codex":0.00092294,"about_ca_topic_score_gemma":0.012034068,"teacher_disagreement_score":0.8668132,"about_ca_system_score_codex":0.00047138915,"about_ca_system_score_gemma":0.0003159261,"threshold_uncertainty_score":0.98548335},"labels":[],"label_agreement":null},{"id":"W2485877726","doi":"10.1075/scl.67.07mey","title":"Passives of so-called ‘ditransitives’ in nineteenth century and present-day Canadian English","year":2015,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"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":"Complement (music); Dominance (genetics); Linguistics; Matching (statistics); Literature; History; Art; Philosophy; Mathematics; Chemistry","score_opus":0.0688148870694358,"score_gpt":0.3428270208740393,"score_spread":0.27401213380460354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2485877726","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010647891,0.013451754,0.0000069510525,0.000240271,0.0090853665,0.00055064895,0.0002726004,0.000029237377,0.97625667],"genre_scores_gemma":[0.84361136,0.048715062,0.0009310167,0.00035907223,0.011577266,0.000042035528,0.00013411012,0.00011313757,0.09451693],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805254,0.00016143346,0.00059048436,0.00038808526,0.00037239923,0.00043503504],"domain_scores_gemma":[0.996722,0.00083597086,0.00028411264,0.00019359807,0.0017283015,0.00023601137],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00096076797,0.00027151222,0.0007204984,0.00038520925,0.00017538523,0.000022110256,0.00021903042,0.00040861007,0.0000653831],"category_scores_gemma":[0.026668375,0.00028892452,0.000058403188,0.00008489535,0.0014437385,0.000011515471,0.000109188266,0.00043781538,0.0000037692198],"study_design_candidate":"not_applicable","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":[0.000028704355,0.000027991033,0.0019603926,0.00009833002,0.00015324086,0.00033155025,0.10227489,0.00001661288,2.55443e-7,0.88853,0.0055370177,0.0010409702],"study_design_scores_gemma":[0.00062842964,0.000052907228,0.00024413843,0.00029076776,0.00007048951,5.1033453e-7,0.0060155448,0.000011272979,5.8614455e-7,0.032094575,0.960297,0.00029379103],"about_ca_topic_score_codex":0.041579407,"about_ca_topic_score_gemma":0.4812623,"teacher_disagreement_score":0.95475996,"about_ca_system_score_codex":0.000448491,"about_ca_system_score_gemma":0.0013334451,"threshold_uncertainty_score":0.9999563},"labels":[],"label_agreement":null},{"id":"W2498427696","doi":"10.1075/scl.13.11bri","title":"Subject clitics in English","year":2004,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":12,"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 British Columbia","funders":"","keywords":"Subject (documents); History; Linguistics; Computer science; Philosophy; World Wide Web","score_opus":0.08111191884132003,"score_gpt":0.36748845532521995,"score_spread":0.28637653648389993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498427696","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035090892,0.002541086,0.000012757717,0.000085054795,0.02137974,0.0003800599,0.000056142002,0.000115535106,0.97539455],"genre_scores_gemma":[0.34782928,0.030436384,0.00346463,0.0013548312,0.030440047,0.000057066914,0.00009624392,0.00020244045,0.58611906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976154,0.00008708573,0.00078776595,0.00048891996,0.0004618293,0.0005589772],"domain_scores_gemma":[0.99671155,0.0010965794,0.00031258064,0.00031524774,0.0014633745,0.00010065743],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010989531,0.00034059543,0.0007444315,0.00034129308,0.00022959262,0.000032002055,0.00035161435,0.0006048523,0.0001743157],"category_scores_gemma":[0.06406682,0.00038668097,0.00010879345,0.00011852596,0.0010514061,0.000009364798,0.00018756256,0.0008059283,0.00006281477],"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":[0.000012069374,0.000030590258,0.00075743767,0.00006571775,0.000047088368,0.0004913255,0.029113362,0.000024646642,3.6867497e-8,0.9680707,0.0011353168,0.00025172383],"study_design_scores_gemma":[0.00042641594,0.00003722221,0.000034101588,0.0003185412,0.000041174062,5.251541e-7,0.0015798574,0.0000016126911,4.6652656e-7,0.34231812,0.6549395,0.0003025018],"about_ca_topic_score_codex":0.0010723964,"about_ca_topic_score_gemma":0.016871748,"teacher_disagreement_score":0.6538041,"about_ca_system_score_codex":0.0013055175,"about_ca_system_score_gemma":0.0010270671,"threshold_uncertainty_score":0.9998585},"labels":[],"label_agreement":null},{"id":"W2505386209","doi":"10.1075/scl.13.04tag","title":"Have to, gotta, must?","year":2004,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":37,"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 Toronto","funders":"","keywords":"History","score_opus":0.1029219713045221,"score_gpt":0.39003760022818473,"score_spread":0.2871156289236626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505386209","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000051870406,0.0015616199,0.000087556204,0.0004871384,0.017473731,0.0004903022,0.000067006404,0.000107218184,0.97972023],"genre_scores_gemma":[0.038270354,0.004627327,0.0049850233,0.002476231,0.015307372,0.0000397571,0.000034163033,0.00010955412,0.9341502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977733,0.000049655115,0.0006136863,0.00053536386,0.00051218347,0.00051583495],"domain_scores_gemma":[0.9972527,0.00057293574,0.00027707068,0.00036489684,0.0013460909,0.0001862998],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069757114,0.00035425602,0.0006779968,0.00027675697,0.0004113232,0.00003587369,0.00040272702,0.00048362074,0.0004161803],"category_scores_gemma":[0.0322886,0.00038561597,0.00012021238,0.00007363339,0.0007691891,0.0000062907225,0.0002658579,0.0005341309,0.00040990935],"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":[0.00001232826,0.00001869923,0.000086110194,0.000040157447,0.000083780076,0.00033795388,0.017399885,0.00003595394,1.4215696e-7,0.97115535,0.00998928,0.0008403808],"study_design_scores_gemma":[0.00022832063,0.000051004947,0.000010522977,0.00023563122,0.000060640235,9.2620337e-7,0.0010057954,0.0000010227125,7.73237e-7,0.25673535,0.74135494,0.00031508494],"about_ca_topic_score_codex":0.0011148445,"about_ca_topic_score_gemma":0.01045867,"teacher_disagreement_score":0.7313657,"about_ca_system_score_codex":0.0010431141,"about_ca_system_score_gemma":0.00073255773,"threshold_uncertainty_score":0.9998596},"labels":[],"label_agreement":null},{"id":"W3011686062","doi":"10.1075/scl.96.10bri","title":"The development and pragmatic function of a non-inference marker","year":2020,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":1,"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 British Columbia","funders":"","keywords":"Grammaticalization; Inference; Linguistics; Divergence (linguistics); Function (biology); Reading (process); Context (archaeology); Drama; History; Literature; Philosophy; Art; Epistemology","score_opus":0.05131447241279757,"score_gpt":0.32952148696499123,"score_spread":0.27820701455219365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011686062","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038933777,0.01648387,0.00066206447,0.000030257232,0.005593039,0.00047106305,0.000029352097,0.00002938588,0.9763116],"genre_scores_gemma":[0.68067694,0.007634733,0.0038054315,0.00051754183,0.0026929204,0.00025543786,0.00011087945,0.00016283564,0.30414325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987689,0.000036334834,0.00054465147,0.00028726112,0.00019959248,0.00016320782],"domain_scores_gemma":[0.99814767,0.0008656501,0.0003398744,0.0002262696,0.00038747748,0.000033052125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003253542,0.00024191075,0.00041737128,0.0000673446,0.00012649855,0.000012459783,0.00011372835,0.0001516161,0.00004392353],"category_scores_gemma":[0.0020887733,0.00017756312,0.00004569347,0.000040107232,0.00028973378,0.000004191401,0.00014384155,0.00031892298,0.000049337694],"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":[0.00061699626,0.000078370846,0.0009065004,0.0014172975,0.00252424,0.00021271167,0.037060678,9.67151e-7,0.000006279858,0.7536831,0.0056753964,0.19781747],"study_design_scores_gemma":[0.0013085328,0.000468484,0.0034181848,0.0016936098,0.00084040116,0.0000089411105,0.008586427,0.000036417117,0.00001834329,0.20137236,0.7814385,0.00080975005],"about_ca_topic_score_codex":0.000006745955,"about_ca_topic_score_gemma":0.00017076575,"teacher_disagreement_score":0.77576315,"about_ca_system_score_codex":0.000047203757,"about_ca_system_score_gemma":0.0000707371,"threshold_uncertainty_score":0.72408146},"labels":[],"label_agreement":null},{"id":"W4379415672","doi":"10.1075/scl.109.09gei","title":"DocuScope Write &amp; Audit as an early feedback machine ingenre-based writing","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Audit; Context (archaeology); Computer science; Focus (optics); Report writing; Management; History; Library science","score_opus":0.09666553958224774,"score_gpt":0.34309553982103885,"score_spread":0.2464300002387911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379415672","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055553106,0.015101991,0.000008858632,0.00011808104,0.0071504083,0.0004549043,0.0007356557,0.0004656865,0.9754089],"genre_scores_gemma":[0.047731925,0.004029132,0.0006950091,0.0006082523,0.014311516,0.000081198494,0.0005162051,0.00046449373,0.93156224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958405,0.000076292934,0.0013467352,0.0010559806,0.000893446,0.0007870452],"domain_scores_gemma":[0.995511,0.0009171566,0.0007465618,0.0010426684,0.0016491071,0.00013351838],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00072478753,0.0010368295,0.0016464759,0.00072596455,0.00093607674,0.000366349,0.0006944454,0.00025249802,0.0012321597],"category_scores_gemma":[0.0038318508,0.0009857205,0.00039977318,0.00009128701,0.0019381773,0.00006441017,0.00068382773,0.001118653,0.0014704101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008640348,0.000102037106,0.00031927248,0.00066232256,0.0022558784,0.0011032405,0.029442115,0.00011571146,5.9679206e-7,0.951077,0.010853032,0.003982398],"study_design_scores_gemma":[0.0007296183,0.00039035588,0.000021888156,0.0027017733,0.0010968812,0.0000022708564,0.0067336196,0.00006052615,0.0000023066148,0.07848414,0.9081492,0.001627456],"about_ca_topic_score_codex":0.0009065993,"about_ca_topic_score_gemma":0.042618554,"teacher_disagreement_score":0.89729613,"about_ca_system_score_codex":0.00028077932,"about_ca_system_score_gemma":0.00015190846,"threshold_uncertainty_score":0.9996809},"labels":[],"label_agreement":null},{"id":"W4385228274","doi":"10.1075/scl.110.03cot","title":"The <i>Phonologie du français contemporain</i> projectin Quebec","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Pronunciation; Variety (cybernetics); Representation (politics); Linguistics; French; Subject (documents); Relevance (law); Variation (astronomy); History; Computer science; Artificial intelligence; Philosophy; Political science; Library science","score_opus":0.11830890903078506,"score_gpt":0.36347782692427305,"score_spread":0.245168917893488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385228274","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000097735965,0.0027845867,0.000021272299,0.0016563309,0.03290689,0.0007450812,0.00006348719,0.0003321027,0.9614805],"genre_scores_gemma":[0.015993468,0.021114346,0.00020688797,0.00060824427,0.009070278,0.000086826294,0.000025564068,0.00009592204,0.9527985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974706,0.00015952831,0.00076666503,0.0005135541,0.00051091315,0.0005787084],"domain_scores_gemma":[0.99286604,0.0045731934,0.0004974233,0.00044846127,0.0015343722,0.00008049107],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0021205482,0.0003663699,0.00064474216,0.00015250823,0.0013682361,0.00008630386,0.00062507106,0.00053207966,0.00003315608],"category_scores_gemma":[0.086675055,0.0002934735,0.00015291509,0.0001376698,0.0023280005,0.000008461993,0.00038254165,0.0007514182,0.0003333563],"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":[0.000024540803,0.000011775296,0.00029604282,0.00003053802,0.0001671977,0.00022898287,0.018791946,0.0000019300899,9.229294e-8,0.92155534,0.057023417,0.001868203],"study_design_scores_gemma":[0.0002572501,0.000037636964,0.000034900426,0.00013023455,0.000055429933,8.2874885e-7,0.0044508693,0.000004127729,6.477941e-7,0.113067955,0.8816674,0.00029273803],"about_ca_topic_score_codex":0.018009076,"about_ca_topic_score_gemma":0.29302746,"teacher_disagreement_score":0.82464397,"about_ca_system_score_codex":0.00047587347,"about_ca_system_score_gemma":0.0011242061,"threshold_uncertainty_score":0.9999517},"labels":[],"label_agreement":null},{"id":"W4387736150","doi":"10.1075/scl.113.06lab","title":"run away!","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Categorization, perception, and language","field":"Psychology","cited_by":0,"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":"Vocabulary; Verb; Path (computing); Motion (physics); Word (group theory); Computer science; Expression (computer science); Linguistics; Translation (biology); Natural language processing; Artificial intelligence; Chemistry; Philosophy; Programming language","score_opus":0.12279469422098577,"score_gpt":0.3941716250231471,"score_spread":0.27137693080216135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387736150","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054481094,0.0064034336,0.000045350764,0.000023740446,0.026839007,0.00030051457,0.00017744007,0.0002798076,0.9658762],"genre_scores_gemma":[0.0067057265,0.0064458284,0.00010995324,0.00017709027,0.007333707,0.000036314177,0.00026016642,0.0001801026,0.9787511],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981376,0.00002789454,0.0006145896,0.00057552574,0.00027324198,0.00037114962],"domain_scores_gemma":[0.99814963,0.0004025569,0.00024135628,0.0006109693,0.0005355606,0.00005991767],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002619421,0.00041608972,0.0006352111,0.00032164727,0.00015031004,0.00001839459,0.00024741274,0.00044146267,0.0011780742],"category_scores_gemma":[0.0015294406,0.00043096778,0.00013996694,0.000100771525,0.0003774014,0.0000056404433,0.00017019063,0.00052625925,0.002461151],"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":[0.000032116066,0.000033890472,0.0006540391,0.00016106029,0.00037894677,0.0005135519,0.014568646,0.0000083023815,7.3132105e-7,0.90931636,0.07192268,0.0024096859],"study_design_scores_gemma":[0.00042832617,0.00008625618,0.0007034983,0.00024118784,0.00016293631,0.00000851754,0.0018687891,0.000004066995,4.0470132e-7,0.087020405,0.90893185,0.00054373883],"about_ca_topic_score_codex":0.00013979367,"about_ca_topic_score_gemma":0.0013019644,"teacher_disagreement_score":0.8370092,"about_ca_system_score_codex":0.00018537203,"about_ca_system_score_gemma":0.00006335333,"threshold_uncertainty_score":0.9998142},"labels":[],"label_agreement":null},{"id":"W4405077419","doi":"10.1075/scl.118.09mil","title":"Modeling fine-grained sociolinguistic variation","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"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":"Variation (astronomy); Computer science; Linguistics; Astrophysics; Physics; Philosophy","score_opus":0.05598935463493161,"score_gpt":0.3361349588186589,"score_spread":0.2801456041837273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405077419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026046737,0.18107603,0.40772545,0.00029704825,0.0192116,0.00071520486,0.0000697275,0.0028445597,0.38805777],"genre_scores_gemma":[0.057068154,0.004320861,0.7210215,0.00041288717,0.008390671,0.000074113705,0.00006396321,0.00028381046,0.20836405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730986,0.000019587795,0.0008055975,0.0009245004,0.00052036805,0.0004200984],"domain_scores_gemma":[0.997212,0.0004099994,0.00024941599,0.0007691456,0.0012964748,0.000062967076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054301065,0.00058466644,0.0007333011,0.00047930883,0.00016563621,0.00017014341,0.0010846897,0.00044951722,0.0000046260116],"category_scores_gemma":[0.0072144833,0.0005577249,0.00016484484,0.00016449798,0.00017005086,0.000033737844,0.0011915965,0.001206819,0.00006477448],"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":[0.000004432369,0.000008669983,7.3770485e-7,0.0004953811,0.00011298801,0.0005061615,0.00189718,0.0003319981,0.0000029217365,0.9939799,0.00065735256,0.0020023186],"study_design_scores_gemma":[0.000094533374,0.000045217846,7.093905e-8,0.0015367557,0.00008629936,0.000010285628,0.000009869757,0.13504396,0.0000083690875,0.84649575,0.01615477,0.0005141268],"about_ca_topic_score_codex":0.000030646006,"about_ca_topic_score_gemma":0.000076008626,"teacher_disagreement_score":0.31329602,"about_ca_system_score_codex":0.0005516561,"about_ca_system_score_gemma":0.00022117667,"threshold_uncertainty_score":0.99968743},"labels":[],"label_agreement":null},{"id":"W4416401069","doi":"10.1075/scl.122.14joa","title":"Examining coherence and cohesion errors in writing Catalan as an additional language","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université TÉLUQ","funders":"","keywords":"Catalan; Cohesion (chemistry); Coherence (philosophical gambling strategy); Perception; Error analysis; Language proficiency","score_opus":0.06872773850521371,"score_gpt":0.37796157656266277,"score_spread":0.3092338380574491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416401069","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014468305,0.031094197,0.000004232613,0.000016367203,0.0021931038,0.00032537334,0.0007320844,0.00010535049,0.951061],"genre_scores_gemma":[0.5199057,0.000717341,0.0020230594,0.0047403728,0.0035965308,0.00016269617,0.004023688,0.00018121813,0.46464938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822253,0.000095887786,0.0005573745,0.0006151707,0.00019615237,0.00031291196],"domain_scores_gemma":[0.997765,0.001402151,0.00025282803,0.00032877657,0.0001849175,0.00006633175],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039583634,0.0003419166,0.0005396439,0.00041062894,0.00012828862,0.000027091883,0.0001708612,0.00027364373,0.010464923],"category_scores_gemma":[0.0032202448,0.00038098617,0.00003748333,0.00007668008,0.00027581686,0.00001771423,0.0001829912,0.00086696254,0.00006802995],"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":[0.0005675898,0.00035176103,0.009436989,0.0015778797,0.0009643253,0.033710916,0.1851365,0.00004578441,0.00003459655,0.58056164,0.05480689,0.13280515],"study_design_scores_gemma":[0.0067534386,0.0017349538,0.016830172,0.020864228,0.00048220117,0.0006122852,0.2984866,0.00024343409,0.00002391541,0.03443831,0.6150007,0.0045297774],"about_ca_topic_score_codex":0.00018796012,"about_ca_topic_score_gemma":0.00046735167,"teacher_disagreement_score":0.5601938,"about_ca_system_score_codex":0.00012667362,"about_ca_system_score_gemma":0.00007216476,"threshold_uncertainty_score":0.9998642},"labels":[],"label_agreement":null},{"id":"W4416401093","doi":"10.1075/scl.122.04gag","title":"Crosslinguistic influences and L3/Ln teaching","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Set (abstract data type); Language proficiency; Error analysis; Catalan; German; Language acquisition; Romance languages","score_opus":0.09240474182370162,"score_gpt":0.3478189198680716,"score_spread":0.25541417804437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416401093","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002200042,0.022414654,0.000008692254,0.000043893277,0.007548819,0.0001866337,0.000071469025,0.0001747174,0.96933115],"genre_scores_gemma":[0.11117721,0.0026810062,0.0007546781,0.00041355347,0.007868852,0.000014340288,0.000028916496,0.000085870386,0.8769756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99797225,0.00006492587,0.0007069507,0.0005760437,0.00028977575,0.00039003819],"domain_scores_gemma":[0.9972916,0.0014444411,0.0003530881,0.00033632538,0.0005133674,0.00006117603],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007190007,0.00054260384,0.0008432408,0.00033649354,0.0012115205,0.0002596839,0.0002678614,0.00019930216,0.00008236908],"category_scores_gemma":[0.015385459,0.00050984306,0.0001102355,0.000013099048,0.0013020232,0.000018568622,0.00038306005,0.0019018927,0.000028958599],"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":[0.000014363863,0.000014575869,0.00040985402,0.0006214333,0.00021977721,0.00013242371,0.036618713,0.000025001691,1.3591219e-7,0.9515504,0.005183786,0.005209499],"study_design_scores_gemma":[0.00020452189,0.000081877406,0.00001021181,0.0026270233,0.00017861095,0.0000025570596,0.00221323,0.000058062626,2.0195006e-7,0.08892542,0.905208,0.0004903102],"about_ca_topic_score_codex":0.00028571603,"about_ca_topic_score_gemma":0.0012364791,"teacher_disagreement_score":0.9000242,"about_ca_system_score_codex":0.00013666344,"about_ca_system_score_gemma":0.00010365243,"threshold_uncertainty_score":0.9997353},"labels":[],"label_agreement":null},{"id":"W612974530","doi":"10.1075/scl.67","title":"Grammatical Change in English World-Wide","year":2015,"lang":"en","type":"book","venue":"Studies in corpus linguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":104,"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":"Computer science; Linguistics; Natural language processing; Philosophy","score_opus":0.16084686923901154,"score_gpt":0.4076607891824785,"score_spread":0.24681391994346696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W612974530","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012742057,0.0035887668,0.000010099912,0.00024344996,0.027352838,0.0006618017,0.000042444222,0.00013574181,0.96795213],"genre_scores_gemma":[0.019526653,0.0047370917,0.0024151078,0.001832837,0.042529136,0.00024144277,0.00012956095,0.000117662305,0.9284705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970986,0.00029048973,0.00080139627,0.0004825596,0.0006600766,0.00066682714],"domain_scores_gemma":[0.9949437,0.0021758634,0.00032030285,0.00032957233,0.0020525004,0.00017806179],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002170336,0.00034087314,0.000905847,0.000521778,0.00017361395,0.00003992313,0.0004464948,0.0004663333,0.000084568535],"category_scores_gemma":[0.15815264,0.0003645657,0.00008543517,0.00039240907,0.0009992694,0.000015167045,0.00029744586,0.0008528282,0.00008742859],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021508084,0.00007111216,0.0037870416,0.00012977207,0.00005562962,0.0005583731,0.093782485,0.0000025459647,6.0505276e-9,0.77081746,0.12996973,0.00080434245],"study_design_scores_gemma":[0.00041963882,0.000030866257,0.00008087783,0.00032972434,0.000046606452,3.1856044e-7,0.0017785712,0.000011990593,6.630773e-8,0.1530014,0.84398186,0.0003180878],"about_ca_topic_score_codex":0.0011827345,"about_ca_topic_score_gemma":0.07831777,"teacher_disagreement_score":0.71401215,"about_ca_system_score_codex":0.0017666889,"about_ca_system_score_gemma":0.0013011512,"threshold_uncertainty_score":0.9998806},"labels":[],"label_agreement":null}]}