{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":12,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":12,"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","author_layer_release":"2026-06-26"},"query_hash":"28b6cc5f6b26","filters":{"venue":"Studies in corpus linguistics"}},"results":[{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Linguistics; Natural language processing; Philosophy","authors":[{"name":"Peter C. Collins","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1608468692390115,"gpt":0.4076607891824785,"spread":0.246813919943467,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004081069,0.0001471606,0.000163136,0.001158274,0.001283504,0.002717842,0.0002686595,0.0003211253,0.002142559],"category_scores_gemma":[0.0009502333,0.00009209843,0.0001133774,0.00167196,0.002301346,0.002185231,0.0009896146,0.0006508004,0.0002495821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001591213,"about_ca_system_score_gemma":0.0003825825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003348276,"about_ca_topic_score_gemma":0.005129461,"domain_scores_codex":[0.9995796,0.0001316838,0.00002075674,0.00007481943,0.0001468744,0.00004620305],"domain_scores_gemma":[0.9997159,0.0001350208,0.0000249217,0.00004064139,0.00007001553,0.00001355246],"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":[0.00001854872,0.00001970026,0.00332539,0.0001566097,0.00001249692,0.0004252557,0.08041542,0.0003575078,0.001190284,0.7384483,0.0251244,0.1505062],"study_design_scores_gemma":[0.000004138699,0.00002757621,0.01436014,0.0001703816,0.00001046667,0.0008776266,0.01762856,0.000445449,0.0005106622,0.06954728,0.8964021,0.00001562453],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.1798604,0.02401812,0.003232284,0.004991402,0.0007679398,0.00003130005,0.0003379963,0.0001326654,0.7866281],"genre_scores_gemma":[0.9093022,0.008525837,0.001532216,0.0004922982,0.0002715767,0.00002701229,0.0003813207,0.00009388968,0.07937358],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.003348276,"threshold_uncertainty_score":0.01154518,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"History","authors":[{"name":"Sali A. Tagliamonte","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1029219713045221,"gpt":0.3900376002281847,"spread":0.2871156289236626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004687412,0.0001984809,0.0001606976,0.0005940489,0.0009770003,0.00151308,0.0002063611,0.000290919,0.005709479],"category_scores_gemma":[0.0009469832,0.000124108,0.0001164642,0.0008007055,0.002736612,0.001769997,0.0004260344,0.0006949022,0.000763668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009091573,"about_ca_system_score_gemma":0.00060024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006093249,"about_ca_topic_score_gemma":0.02715401,"domain_scores_codex":[0.9996469,0.0001447578,0.00002124487,0.00004883602,0.0001060206,0.00003224719],"domain_scores_gemma":[0.9995826,0.0002007788,0.00006912702,0.00003578801,0.00006904453,0.00004275379],"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":[0.0001336172,0.00003369632,0.0241674,0.0004481407,0.0000287988,0.0004833846,0.08900049,0.0001657889,0.007025851,0.6133179,0.04959235,0.2156027],"study_design_scores_gemma":[0.00001136114,0.0001029524,0.1316375,0.000372961,0.00003954537,0.003608149,0.05037777,0.0009024533,0.002252239,0.1166294,0.6940152,0.00005036654],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2490728,0.008206421,0.01438201,0.005220631,0.0003831003,0.00003477706,0.0004553446,0.0001158793,0.722129],"genre_scores_gemma":[0.8913478,0.001775198,0.004909741,0.0004499635,0.00007289914,0.00001750333,0.0003219646,0.00008218076,0.1010228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006093249,"threshold_uncertainty_score":0.01910007,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Subject (documents); History; Linguistics; Computer science; Philosophy; World Wide Web","authors":[{"name":"Laurel J. Brinton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08111191884132003,"gpt":0.36748845532522,"spread":0.2863765364838999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006095422,0.0004428656,0.0002955753,0.001191914,0.002025686,0.00269943,0.0004129158,0.0005810811,0.004234417],"category_scores_gemma":[0.0009414805,0.0002378497,0.0002011096,0.001201292,0.003664563,0.00336055,0.001341412,0.001068291,0.0009961866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001906463,"about_ca_system_score_gemma":0.001421733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006235752,"about_ca_topic_score_gemma":0.00740253,"domain_scores_codex":[0.9995964,0.0001130322,0.00003597699,0.0000927545,0.0001097245,0.00005209998],"domain_scores_gemma":[0.999569,0.0001782718,0.000040824,0.00005941489,0.0001230532,0.00002936077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002392069,0.00002583667,0.00130137,0.0001492378,0.000005016014,0.0002039088,0.01691457,0.0001094511,0.001295559,0.937592,0.004199251,0.03817999],"study_design_scores_gemma":[0.00002755593,0.00007241516,0.002971753,0.0002400753,0.00001963556,0.0008142124,0.005859093,0.0005259492,0.002129796,0.2179365,0.7693749,0.00002812564],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1202829,0.01666976,0.0193772,0.002872544,0.0006732281,0.00007600276,0.0003162864,0.0003067899,0.8394252],"genre_scores_gemma":[0.885699,0.00714707,0.005086274,0.0005606866,0.0004349363,0.00006594106,0.0002917146,0.0002377266,0.1004766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006235752,"threshold_uncertainty_score":0.01416546,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Victoria","funders":"","keywords":"Possession (linguistics); Newspaper; Negation; History; Language change; Geography; Linguistics; Media studies; Sociology","authors":[{"name":"Alexandra D’Arcy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3719527862548491,"gpt":0.4396158681615569,"spread":0.06766308190670778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001130111,0.0001828323,0.0002639309,0.0009190198,0.007574129,0.005123753,0.000735928,0.0007974264,0.006178251],"category_scores_gemma":[0.002325732,0.0001866825,0.0001353591,0.001724246,0.0202711,0.004347155,0.002590972,0.002126826,0.0003316973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02064416,"about_ca_system_score_gemma":0.009768841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4657509,"about_ca_topic_score_gemma":0.5786963,"domain_scores_codex":[0.9985313,0.0004050992,0.00003640864,0.0002646587,0.0003906035,0.0003718643],"domain_scores_gemma":[0.9992656,0.0002826691,0.00005259214,0.0001019811,0.0002013112,0.0000959142],"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":[0.00003183991,0.000009366016,0.002496278,0.00007522395,0.00000705361,0.000340643,0.1923457,0.00009748711,0.0009537993,0.7517376,0.006277101,0.04562786],"study_design_scores_gemma":[0.000007218954,0.00002009705,0.02786783,0.0003270533,0.00001474305,0.0003335238,0.1438862,0.0001972405,0.0004941771,0.09538342,0.7314385,0.00003008127],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1683137,0.01008928,0.002315531,0.01406235,0.0003073341,0.00003226049,0.0001555488,0.00004358916,0.8046805],"genre_scores_gemma":[0.9649218,0.001985976,0.0005080819,0.0006409599,0.00004809739,0.00001200773,0.00005444829,0.00004956751,0.031779],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4657509,"threshold_uncertainty_score":0.9260799,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marie‐Hélène Côté","is_ca":false},{"name":"Hugo Saint-Amant Lamy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1183089090307851,"gpt":0.3634778269242731,"spread":0.245168917893488,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005528369,0.0005129011,0.000274378,0.002605048,0.003142392,0.002603429,0.0004826066,0.0004474583,0.01557768],"category_scores_gemma":[0.001441712,0.0001834019,0.0001735259,0.005113605,0.001531277,0.0007773419,0.000491448,0.0007987616,0.001055193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02252145,"about_ca_system_score_gemma":0.01173717,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9680604,"about_ca_topic_score_gemma":0.972128,"domain_scores_codex":[0.9995627,0.00009734306,0.00001508875,0.0001085979,0.0001400147,0.00007623942],"domain_scores_gemma":[0.9994907,0.000138722,0.00003316041,0.00004374921,0.000253127,0.00004053544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000278625,0.00004991757,0.03322513,0.001068837,0.00008515365,0.0009320411,0.0488743,0.001778561,0.009506048,0.1833502,0.2804515,0.4403997],"study_design_scores_gemma":[0.000009711881,0.00001312088,0.08584839,0.0002124135,0.00001398526,0.0003539819,0.005577195,0.0004007523,0.001000347,0.00115954,0.9053744,0.00003612003],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.3325246,0.0606539,0.01430958,0.008183979,0.001157541,0.0002595689,0.0786933,0.0009161815,0.5033013],"genre_scores_gemma":[0.8371694,0.01044786,0.008568767,0.0007422601,0.0001760428,0.0001965177,0.01930153,0.000439251,0.1229584],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.03193963,"threshold_uncertainty_score":0.1634054,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Set (abstract data type); Language proficiency; Error analysis; Catalan; German; Language acquisition; Romance languages","authors":[{"name":"Nancy Gagné","is_ca":true},{"name":"Anna Joan Casademont","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09240474182370162,"gpt":0.3478189198680716,"spread":0.25541417804437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001418234,0.000323262,0.0003161896,0.0007878127,0.0005810479,0.001926926,0.0004392882,0.0003209919,0.003834918],"category_scores_gemma":[0.007941783,0.0001158345,0.0001329112,0.0007257949,0.0008951874,0.000417539,0.001270045,0.0006758854,0.0006073887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00131987,"about_ca_system_score_gemma":0.00106126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01008182,"about_ca_topic_score_gemma":0.0121647,"domain_scores_codex":[0.9979656,0.0007941585,0.0001090356,0.0003592278,0.000620785,0.0001511987],"domain_scores_gemma":[0.9877243,0.007671001,0.002015444,0.0006076577,0.001278507,0.0007031369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005175816,0.0008088433,0.681688,0.0002912377,0.00006683115,0.003413123,0.1100101,0.0006194801,0.03234327,0.002008534,0.0008818234,0.1673512],"study_design_scores_gemma":[0.00001627472,0.0003876206,0.9420906,0.0001234328,0.00004163857,0.001876032,0.03679355,0.0009111947,0.009472174,0.001068329,0.007185713,0.00003353429],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9951892,0.0001405869,0.000214436,0.0000477491,0.000004206874,0.000005728823,0.00003070274,0.00001242961,0.004354984],"genre_scores_gemma":[0.9982606,0.00006471935,0.0002165691,0.00002290861,0.000002208062,0.000006332063,0.00004169544,0.00001001175,0.001374922],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01008182,"threshold_uncertainty_score":0.02004629,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Laurel J. Brinton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05131447241279757,"gpt":0.3295214869649912,"spread":0.2782070145521937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002618549,0.0003512549,0.0004257957,0.001107966,0.001531159,0.004310885,0.001179742,0.001366985,0.01158199],"category_scores_gemma":[0.006960404,0.0005775085,0.0002703368,0.0006099205,0.004958656,0.00840972,0.003174362,0.002938842,0.00262234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001911995,"about_ca_system_score_gemma":0.001304219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00164283,"about_ca_topic_score_gemma":0.001886211,"domain_scores_codex":[0.9979431,0.0008925021,0.00008108748,0.0005062069,0.0004475789,0.0001295604],"domain_scores_gemma":[0.9946089,0.003199545,0.0003066995,0.0008817482,0.0007763293,0.0002267611],"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":[0.00009291238,0.00006110964,0.002762203,0.0001746759,0.00001152753,0.001022753,0.02473061,0.000171711,0.0239934,0.9065619,0.002147761,0.03826939],"study_design_scores_gemma":[0.00007023865,0.0003944981,0.02633189,0.0006942905,0.0001294933,0.007213337,0.02412099,0.01384794,0.0568127,0.4463113,0.4239064,0.0001668889],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2701729,0.001504151,0.1330205,0.003533688,0.0004836038,0.0001354639,0.0002804115,0.0007329335,0.5901364],"genre_scores_gemma":[0.9583995,0.0002544966,0.02129454,0.0002444592,0.00008992652,0.00004231396,0.0002231399,0.0006356082,0.01881603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01158199,"threshold_uncertainty_score":0.03874558,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Audit; Context (archaeology); Computer science; Focus (optics); Report writing; Management; History; Library science","authors":[{"name":"Cheryl Geisler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09666553958224774,"gpt":0.3430955398210389,"spread":0.2464300002387911,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01283012,0.0005389056,0.000471153,0.002568347,0.001451269,0.005258859,0.001446559,0.0007638911,0.01050687],"category_scores_gemma":[0.04154592,0.0003931082,0.0001983617,0.001379263,0.002119654,0.003069827,0.003620639,0.00180861,0.0038666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001296128,"about_ca_system_score_gemma":0.002996741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008312684,"about_ca_topic_score_gemma":0.002229281,"domain_scores_codex":[0.9891222,0.00592663,0.0004539879,0.0005940519,0.003610003,0.000293139],"domain_scores_gemma":[0.9420829,0.03651986,0.00203952,0.008182109,0.008409856,0.002765675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003435447,0.00028309,0.00452586,0.0003797455,0.000006787634,0.000364409,0.02031296,0.0008401977,0.0120822,0.02003992,0.07506987,0.8657513],"study_design_scores_gemma":[0.000183922,0.001181547,0.01390631,0.001217341,0.00003268797,0.001852356,0.0165822,0.01864428,0.04985346,0.02579858,0.8704964,0.0002509149],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.228552,0.001414284,0.4782678,0.01462064,0.00267,0.001894986,0.001506791,0.03433745,0.2367361],"genre_scores_gemma":[0.4179321,0.000542852,0.4468926,0.001202483,0.0003416448,0.001003424,0.0009888563,0.002768425,0.1283277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01283012,"threshold_uncertainty_score":0.06785297,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Variation (astronomy); Computer science; Linguistics; Astrophysics; Physics; Philosophy","authors":[{"name":"Filip Miletić","is_ca":false},{"name":"Anne Przewozny-Desriaux","is_ca":false},{"name":"Ludovic Tanguy","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05598935463493161,"gpt":0.3361349588186589,"spread":0.2801456041837273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007324419,0.0002898349,0.0002675234,0.001101648,0.000492536,0.001177925,0.0005789989,0.00032663,0.00233197],"category_scores_gemma":[0.004581069,0.0002172201,0.0002568989,0.001230131,0.0009451016,0.001010159,0.0006883708,0.0007475683,0.0003378739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001902902,"about_ca_system_score_gemma":0.001189189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1558919,"about_ca_topic_score_gemma":0.2614704,"domain_scores_codex":[0.999673,0.0001295397,0.000008943383,0.00009521322,0.00005854431,0.00003484916],"domain_scores_gemma":[0.9977036,0.001599529,0.0001719426,0.0002308325,0.0002388912,0.00005513331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002782689,0.0002337101,0.1538184,0.0005395514,0.0002590302,0.0009920141,0.007373995,0.5049837,0.04215569,0.1118931,0.01190018,0.1655723],"study_design_scores_gemma":[0.00000677169,0.00002223223,0.05026158,0.0000272581,0.00001280529,0.00004729866,0.0007810646,0.916795,0.001619891,0.02372525,0.006673152,0.00002776742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7573251,0.0004555604,0.2290324,0.0005382867,0.00004509842,0.0000856229,0.00371875,0.000646351,0.008152733],"genre_scores_gemma":[0.9693927,0.00008760555,0.02744446,0.00004546264,0.00001007352,0.00005831815,0.001587796,0.00009273202,0.001280749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1558919,"threshold_uncertainty_score":0.309969,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Complement (music); Dominance (genetics); Linguistics; Matching (statistics); Literature; History; Art; Philosophy; Mathematics; Chemistry","authors":[{"name":"Matthias Meyer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0688148870694358,"gpt":0.3428270208740393,"spread":0.2740121338046035,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001357286,0.0005914583,0.0003372779,0.003264055,0.005112742,0.003189419,0.001035586,0.000568107,0.006786157],"category_scores_gemma":[0.002704961,0.0003913821,0.0002929812,0.003943217,0.006666231,0.002583215,0.001436089,0.001258193,0.0005972147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01952511,"about_ca_system_score_gemma":0.01619496,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7847671,"about_ca_topic_score_gemma":0.8785889,"domain_scores_codex":[0.9989201,0.0001635683,0.00006540189,0.000234188,0.0003695375,0.0002472916],"domain_scores_gemma":[0.998067,0.0007509604,0.0002125123,0.0001878497,0.0006681901,0.0001135367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002759134,0.00005297547,0.01884421,0.0007031847,0.00002768102,0.001137187,0.5001956,0.0002738338,0.02167296,0.3799916,0.006249783,0.07057504],"study_design_scores_gemma":[0.0000464411,0.00008696436,0.1695567,0.0005771291,0.0001375989,0.002855562,0.13347,0.001193196,0.01530895,0.01429261,0.6622251,0.0002497614],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7528069,0.003684324,0.006980701,0.0008345667,0.0001396061,0.0001312266,0.002043699,0.0001895366,0.2331894],"genre_scores_gemma":[0.9754219,0.001061757,0.002157795,0.00009383724,0.00002247614,0.00003653031,0.0008955238,0.0001370315,0.0201732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2152329,"threshold_uncertainty_score":0.4330009,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université TÉLUQ","funders":"","keywords":"Catalan; Cohesion (chemistry); Coherence (philosophical gambling strategy); Perception; Error analysis; Language proficiency","authors":[{"name":"Anna Joan Casademont","is_ca":true},{"name":"Carme Bach","is_ca":false},{"name":"Èric Viladrich Castellanas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06872773850521371,"gpt":0.3779615765626628,"spread":0.3092338380574491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00213305,0.000442041,0.0004577961,0.00207881,0.0006981625,0.001396393,0.0005098704,0.0004769799,0.001860897],"category_scores_gemma":[0.0143055,0.0001454971,0.0001181765,0.001534648,0.0008316562,0.0006372639,0.0009125367,0.0004391889,0.0002893244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009392841,"about_ca_system_score_gemma":0.0007557234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004585296,"about_ca_topic_score_gemma":0.00885658,"domain_scores_codex":[0.997579,0.001293005,0.0001742297,0.0002809426,0.0005761621,0.00009662542],"domain_scores_gemma":[0.9706303,0.02324102,0.002313472,0.0009303145,0.002608184,0.0002767703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0009087032,0.001317777,0.2519159,0.002176277,0.0001196905,0.005117238,0.2015712,0.00321668,0.07548843,0.001999594,0.006621563,0.4495468],"study_design_scores_gemma":[0.00004777113,0.0008956247,0.8447791,0.0004306107,0.00006881759,0.002851106,0.07772949,0.007183714,0.02830003,0.001250069,0.03637969,0.00008402649],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956893,0.0003044776,0.001439197,0.00007587123,0.00002374891,0.0000445643,0.0001234946,0.00003405039,0.002265126],"genre_scores_gemma":[0.9915249,0.000236325,0.004081837,0.00004051127,0.00001608468,0.00007451773,0.0004337423,0.00003996247,0.003552165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004585296,"threshold_uncertainty_score":0.01128083,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Belén Labrador","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1227946942209858,"gpt":0.3941716250231471,"spread":0.2713769308021614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000275108,0.0004724278,0.0002459189,0.0007366212,0.001698093,0.002272202,0.000394441,0.0006000172,0.1307648],"category_scores_gemma":[0.0007928631,0.0001219839,0.0003131781,0.0007042875,0.001009358,0.002412711,0.001398878,0.001438583,0.0610707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000741878,"about_ca_system_score_gemma":0.0006088711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004159219,"about_ca_topic_score_gemma":0.01163168,"domain_scores_codex":[0.9998127,0.00004918666,0.00000633541,0.00004478671,0.00005662128,0.00003040344],"domain_scores_gemma":[0.9998152,0.00005272561,0.00001091915,0.00002260163,0.00005947176,0.00003914376],"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":[0.00005108564,0.00002768431,0.0007068001,0.0003065416,0.000006135724,0.0002663093,0.01078996,0.00005085891,0.001036795,0.09728037,0.7335107,0.1559668],"study_design_scores_gemma":[0.000001873827,0.00000700752,0.0004112055,0.00003588543,0.000001107231,0.0001203664,0.0008984107,0.00001628623,0.00006915825,0.001281429,0.9971544,0.000002910166],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.005486526,0.004903826,0.004749823,0.008372913,0.004945996,0.00005306334,0.0008408406,0.0007439041,0.9699033],"genre_scores_gemma":[0.03654902,0.002954894,0.003198625,0.003087029,0.0009357416,0.000052393,0.0008149519,0.001096078,0.9513114],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8692352,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}