{"meta":{"query_hash":"ce48bc7d526f","filters":{"venue":"Linguistics Vanguard"},"cohort_total":26,"direct_labels_cover":0,"predictions_cover":26,"exported":26,"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/ce48bc7d526f","api":"https://metacan.xera.ac/api/v1/cohort?venue=Linguistics+Vanguard"},"results":[{"id":"W2030992269","doi":"10.1515/lingvan-2014-1008","title":"Language structure and social agency: Confirming polar questions in conversation","year":2015,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":25,"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":"Semiotics; Linguistics; Conversation; Agency (philosophy); Repetition (rhetorical device); Function (biology); Conversation analysis; Selection (genetic algorithm); Computer science; Epistemology; Psychology; Artificial intelligence; Philosophy","score_opus":0.04871211242979754,"score_gpt":0.30793624629591115,"score_spread":0.2592241338661136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030992269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8740878,0.0020521018,0.000084735926,0.0008446592,0.0016223291,0.0003228534,0.00036625259,0.00022177682,0.12039751],"genre_scores_gemma":[0.99735546,0.0000075834864,0.00050644117,0.00018172667,0.0011637219,0.000005087605,0.0001379629,0.000018001168,0.00062402716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99920636,0.00010944339,0.0002104416,0.00014749536,0.00015710336,0.00016913972],"domain_scores_gemma":[0.99933857,0.000083311854,0.00009498847,0.0001940867,0.00023748685,0.000051575218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020969078,0.00012126223,0.00015636164,0.000104194245,0.00016551815,0.00018946594,0.00014080032,0.00006361209,0.00020143914],"category_scores_gemma":[0.0006681449,0.00012279037,0.000025089954,0.000037028432,0.00022526029,0.000067318004,0.000055530294,0.00020349064,0.000018556468],"study_design_candidate":"qualitative","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":[0.00001252819,0.000023292841,0.00094870216,0.000026192087,0.000016252754,0.00002154817,0.46422654,0.0000072548496,0.000060922725,0.5333145,0.0005940315,0.00074822194],"study_design_scores_gemma":[0.0027065687,0.00014023343,0.010373638,0.00013433957,0.00018842766,0.000013878165,0.58390486,0.00094970915,0.00030292413,0.07776256,0.32240015,0.0011226893],"about_ca_topic_score_codex":0.0016933726,"about_ca_topic_score_gemma":0.006245084,"teacher_disagreement_score":0.45555195,"about_ca_system_score_codex":0.000049421957,"about_ca_system_score_gemma":0.0000975889,"threshold_uncertainty_score":0.50072455},"labels":[],"label_agreement":null},{"id":"W2335647126","doi":"10.1515/lingvan-2015-0010","title":"An evaluation of noise on LPC-based vowel formant estimates: Implications for sociolinguistic data collection","year":2016,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Formant; Spurious relationship; Noise (video); Vowel; Computer science; Speech recognition; Data collection; SIGNAL (programming language); Interference (communication); Acoustics; Telecommunications; Artificial intelligence; Mathematics; Statistics; Physics; Machine learning","score_opus":0.15644486285609407,"score_gpt":0.44929474008707243,"score_spread":0.29284987723097833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335647126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02391722,0.00020066436,0.8575555,0.005517544,0.01555969,0.005975783,0.004135894,0.0007873171,0.08635037],"genre_scores_gemma":[0.9803358,0.000012515298,0.016908769,0.00024676922,0.0018229539,0.00010830618,0.0003935725,0.000025831716,0.00014552783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981651,0.00020515434,0.0004406635,0.0004193546,0.0004444587,0.0003253169],"domain_scores_gemma":[0.994322,0.0013830692,0.00034151308,0.00081133883,0.002999767,0.00014232591],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027545546,0.00014499761,0.00022114307,0.00015549132,0.00052952924,0.000035605623,0.00051893486,0.00016601763,0.00011968277],"category_scores_gemma":[0.07845806,0.00012273715,0.00006328375,0.00018929187,0.00021487134,0.000034485023,0.00003217714,0.00006594905,0.000020029976],"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":[0.00041518384,0.0012332888,0.009786829,0.0001152739,0.00015161985,0.0000024315293,0.010599193,0.0012799979,0.0023948755,0.92174274,0.016004845,0.036273703],"study_design_scores_gemma":[0.012129782,0.0019010084,0.036005452,0.00045322606,0.002426763,0.000002435535,0.0013453846,0.25151053,0.0033122862,0.44903857,0.24020092,0.0016736381],"about_ca_topic_score_codex":0.00037751417,"about_ca_topic_score_gemma":0.00066927006,"teacher_disagreement_score":0.9564185,"about_ca_system_score_codex":0.00027563464,"about_ca_system_score_gemma":0.0012251376,"threshold_uncertainty_score":0.9293045},"labels":[],"label_agreement":null},{"id":"W2565228806","doi":"10.1515/lingvan-2015-0012","title":"Extending ELAN into variationist sociolinguistics","year":2015,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":16,"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":"Computer science; Coding (social sciences); Transcription (linguistics); Linguistics; Natural language processing; Statistics; Mathematics","score_opus":0.056065576894293756,"score_gpt":0.3702220372922769,"score_spread":0.3141564603979831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565228806","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014556755,0.00026569655,0.034002233,0.0010782131,0.021958569,0.00035462613,0.00002517966,0.00059751654,0.9402623],"genre_scores_gemma":[0.94420654,0.000036548285,0.036910757,0.0008244087,0.013181974,0.000013274106,0.000059485283,0.000037071877,0.0047299345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778295,0.00027235725,0.00043926516,0.00035616494,0.00061942363,0.0005298223],"domain_scores_gemma":[0.9968484,0.00037694667,0.0002243497,0.0003256416,0.0017307849,0.00049389584],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017360753,0.00018950834,0.00026756155,0.0001359213,0.0008280791,0.00019043944,0.0003875233,0.00025409838,0.00020953132],"category_scores_gemma":[0.08496456,0.00021201787,0.00008526232,0.00028955378,0.00032277513,0.000022266,0.00009038387,0.00027242265,0.0004567648],"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":[0.000014428327,0.00008198884,0.0024814426,0.000008685107,0.000026452084,0.0000704267,0.030508965,0.000052123367,0.000006316073,0.95707697,0.009016959,0.0006552306],"study_design_scores_gemma":[0.00048646433,0.000056495213,0.00022149307,0.000012344416,0.000057403886,0.0000021341896,0.0035668823,0.00039921238,0.00001316692,0.16119123,0.83371603,0.00027716873],"about_ca_topic_score_codex":0.0044048955,"about_ca_topic_score_gemma":0.0010955213,"teacher_disagreement_score":0.9427509,"about_ca_system_score_codex":0.000412946,"about_ca_system_score_gemma":0.000983961,"threshold_uncertainty_score":0.9227432},"labels":[],"label_agreement":null},{"id":"W2590027471","doi":"10.1515/lingvan-2016-0025","title":"Individual differences in second language speech perception across tasks and contrasts: The case of English vowel contrasts by Korean learners","year":2017,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","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":"McGill University","funders":"Santé, Sciences Biologiques et Chimie du Vivant","keywords":"Psychology; Perception; Vowel; Formant; Weighting; Task (project management); Contrast (vision); Duration (music); Cognitive psychology; Speech perception; Natural (archaeology); Two-alternative forced choice; American English; Linguistics; Speech recognition; Computer science; Artificial intelligence","score_opus":0.028228791811886523,"score_gpt":0.35821914850801334,"score_spread":0.3299903566961268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590027471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9880775,0.0005912608,0.0000052954324,0.000051393865,0.001228164,0.0002518953,0.00091503275,0.000017203536,0.008862226],"genre_scores_gemma":[0.998409,0.000042294694,0.000055069802,0.000075223405,0.0005846138,0.000016353035,0.000041235788,0.000020748223,0.0007554974],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99851686,0.00019357182,0.00031268227,0.0003477122,0.00014819154,0.00048096554],"domain_scores_gemma":[0.99838895,0.00046712247,0.00020562237,0.0006022353,0.00023371479,0.000102372185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078314566,0.0001828764,0.00033266834,0.00005926545,0.00029918246,0.00015259186,0.0004711918,0.00023689076,0.0003820506],"category_scores_gemma":[0.0031854198,0.00014477076,0.000047345453,0.0000515942,0.00086602394,0.00001974492,0.00017755615,0.0006020233,0.000012373925],"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":[0.000454141,0.0005103272,0.2825139,0.00011240548,0.00042890524,0.0037877103,0.66369826,7.3524484e-7,0.0040129316,0.0021206134,0.006164393,0.0361957],"study_design_scores_gemma":[0.0042692744,0.00051051495,0.8796031,0.000066906374,0.00008213358,0.00021180067,0.11031287,0.00015648411,0.0008390786,0.0016664877,0.0017888233,0.000492533],"about_ca_topic_score_codex":0.0055658347,"about_ca_topic_score_gemma":0.009653666,"teacher_disagreement_score":0.59708923,"about_ca_system_score_codex":0.000018641373,"about_ca_system_score_gemma":0.000028524806,"threshold_uncertainty_score":0.84139144},"labels":[],"label_agreement":null},{"id":"W2609372572","doi":"10.1515/lingvan-2015-0032","title":"Is <i>like</i> like <i>like</i>?: Evaluating the same variant across multiple variables","year":2017,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":35,"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":"Salient; Meaning (existential); Variation (astronomy); Perception; Linguistics; Psychology; Variable (mathematics); Verb; Perspective (graphical); Transitive relation; Cognitive psychology; Social psychology; Mathematics; Computer science","score_opus":0.07200595367626476,"score_gpt":0.39841300019539977,"score_spread":0.326407046519135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609372572","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054984692,0.001374031,0.020113105,0.019301493,0.1460776,0.0041890536,0.0014024671,0.0015746914,0.7509829],"genre_scores_gemma":[0.9501131,0.0001271821,0.013125901,0.010579775,0.008888119,0.00005794592,0.000034718814,0.00006792948,0.017005282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99619704,0.000448696,0.00063074956,0.00069748645,0.0009446282,0.0010814066],"domain_scores_gemma":[0.9945827,0.0014831552,0.00073244935,0.0015947453,0.0013142091,0.00029274932],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.003966228,0.00034019494,0.00043804935,0.000045058347,0.0062964587,0.000991165,0.0017349819,0.0003591336,0.00048291485],"category_scores_gemma":[0.054701272,0.00028470205,0.00020944166,0.00016761845,0.00090280984,0.000073481184,0.00050145667,0.00052325526,0.00033396296],"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":[0.00039228253,0.00071673864,0.04324954,0.00015158871,0.0006790035,0.00064678636,0.3150577,0.00040332996,0.0008536417,0.46169525,0.16202569,0.014128459],"study_design_scores_gemma":[0.0012467841,0.00010466517,0.002241599,0.000052575015,0.00015860322,0.000009839844,0.004011905,0.0033100669,0.00005327383,0.013598553,0.9747027,0.00050944084],"about_ca_topic_score_codex":0.015554325,"about_ca_topic_score_gemma":0.004447624,"teacher_disagreement_score":0.8951284,"about_ca_system_score_codex":0.0001462582,"about_ca_system_score_gemma":0.00063312106,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W2800761643","doi":"10.1515/lingvan-2016-0081","title":"The syntax-prosody interface: current theoretical approaches and outstanding questions","year":2018,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Prosody; Syntax; Interface (matter); Linguistics; Computer science; Situated; Field (mathematics); Natural language processing; Recursion (computer science); Current (fluid); Artificial intelligence; Programming language; Physics; Mathematics; Speech recognition; Philosophy","score_opus":0.06771065085330953,"score_gpt":0.40110145685154186,"score_spread":0.33339080599823234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800761643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5508738,0.024334265,0.02440832,0.002694475,0.028997416,0.001402464,0.00019990005,0.0003995777,0.36668977],"genre_scores_gemma":[0.9971669,0.00010729158,0.00037291987,0.00002549537,0.0016428307,0.00003488968,0.000004169131,0.000023563518,0.00062194327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864745,0.0001841836,0.00022758599,0.00032730078,0.00015313528,0.00046031695],"domain_scores_gemma":[0.9985744,0.0006005972,0.00005376539,0.0004506165,0.00018986213,0.0001307949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006201073,0.00014905816,0.00015216571,0.00005888725,0.0004864408,0.00011065256,0.00028988987,0.00011552906,0.00023263348],"category_scores_gemma":[0.0023037249,0.00010463973,0.00004140141,0.00011782281,0.0018637852,0.0000060360276,0.00020278865,0.00047703926,0.00024998342],"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":[0.000107858476,0.000084743966,0.0022082157,0.000012119593,0.00007327605,0.000010954786,0.006543234,5.036981e-7,0.00006145829,0.97588587,0.0030133894,0.011998389],"study_design_scores_gemma":[0.001527747,0.0014014195,0.027375141,0.00019337199,0.00021962948,0.00012718485,0.0047809174,0.0048421538,0.0014994177,0.5580691,0.39900672,0.0009571689],"about_ca_topic_score_codex":0.000024585635,"about_ca_topic_score_gemma":0.00003113921,"teacher_disagreement_score":0.4462931,"about_ca_system_score_codex":0.000027461798,"about_ca_system_score_gemma":0.000035254383,"threshold_uncertainty_score":0.6867194},"labels":[],"label_agreement":null},{"id":"W2885411231","doi":"10.1515/lingvan-2017-0018","title":"Practice makes perfect: the consequences of lexical proficiency for articulation","year":2018,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":64,"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 Alberta","funders":"Deutsche Forschungsgemeinschaft","keywords":"Coarticulation; Articulation (sociology); Speech recognition; Linguistics; Psychology; Computer science; Speech production; Cognitive psychology; Constraint (computer-aided design); Mathematics; Vowel","score_opus":0.06326567726277735,"score_gpt":0.43677603788864966,"score_spread":0.3735103606258723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885411231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75748473,0.0013306147,0.011854476,0.0043634064,0.0077175163,0.0017481701,0.00011259496,0.00009190885,0.2152966],"genre_scores_gemma":[0.9953833,0.000005605237,0.0024037398,0.00025931685,0.0011054376,0.000047799855,0.0000062530266,0.000010878313,0.00077765284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989881,0.00014650884,0.00023705482,0.00020078606,0.00015913033,0.00026843284],"domain_scores_gemma":[0.9973739,0.0012560082,0.0001241716,0.0003149718,0.0008907295,0.000040236733],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00072988897,0.000081991064,0.00012574212,0.000045317443,0.00017033907,0.000020052817,0.0002088969,0.00009770432,0.00021124272],"category_scores_gemma":[0.009058444,0.00005736864,0.0000515027,0.0001470248,0.0008969777,0.000008826358,0.000033765693,0.00014542935,0.000098021985],"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":[0.0014335578,0.0007937686,0.009155502,0.00009041991,0.000312492,0.000033894165,0.042726118,0.00002222657,0.024798678,0.8954041,0.017526792,0.007702479],"study_design_scores_gemma":[0.0032273433,0.008199631,0.10219823,0.000106435975,0.0006087114,0.00018092853,0.010565307,0.004956033,0.08708089,0.17894393,0.60300386,0.00092869194],"about_ca_topic_score_codex":0.00015199318,"about_ca_topic_score_gemma":0.000024842162,"teacher_disagreement_score":0.71646017,"about_ca_system_score_codex":0.000010905773,"about_ca_system_score_gemma":0.000082949075,"threshold_uncertainty_score":0.9992887},"labels":[],"label_agreement":null},{"id":"W2892039495","doi":"10.1515/lingvan-2017-0027","title":"The role of predictability in shaping phonological patterns","year":2018,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":108,"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":"Predictability; Context (archaeology); Computer science; Set (abstract data type); Comprehension; Reduction (mathematics); Cognitive psychology; Linguistics; Natural language processing; Psychology; Mathematics; Statistics; History","score_opus":0.04052652632450414,"score_gpt":0.3620769572044678,"score_spread":0.32155043087996366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892039495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9494593,0.00071728264,0.00008061403,0.000062980296,0.0015141442,0.00017301374,0.000037873197,0.000028208822,0.047926575],"genre_scores_gemma":[0.9988282,0.00002938172,0.00012846223,0.000043938286,0.00074412004,0.000020828888,0.000004279545,0.000011458885,0.00018937876],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99864405,0.0001766599,0.00033974042,0.00026610206,0.00014921305,0.0004242305],"domain_scores_gemma":[0.9985314,0.00055430864,0.00007805302,0.0005260561,0.00025198006,0.000058178477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006478362,0.00010189028,0.0001785149,0.00006167284,0.000101673795,0.000014466321,0.00042482038,0.00016472336,0.00053409376],"category_scores_gemma":[0.0024899074,0.00007483588,0.0000505432,0.00015826596,0.00052676676,0.0000039250217,0.00015616296,0.00035080328,0.00012268586],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033527997,0.00032211796,0.94088477,0.000014581236,0.00007159435,0.000028813183,0.011709452,0.0000018586726,0.0012395422,0.026210617,0.0005214901,0.018659854],"study_design_scores_gemma":[0.0005272108,0.0004890959,0.9227637,0.000024048448,0.000011040931,0.000004867123,0.0013548958,0.00049014814,0.0025674643,0.037230663,0.034392584,0.00014426389],"about_ca_topic_score_codex":0.000731262,"about_ca_topic_score_gemma":0.0007721783,"teacher_disagreement_score":0.049368843,"about_ca_system_score_codex":0.000025442872,"about_ca_system_score_gemma":0.000039955423,"threshold_uncertainty_score":0.58479524},"labels":[],"label_agreement":null},{"id":"W3092479361","doi":"10.1515/lingvan-2018-0068","title":"<i>I feel like</i> and <i>it feels like</i>: Two paths to the emergence of epistemic markers","year":2020,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":1,"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 Toronto","funders":"","keywords":"Complementizer; Preference; Variation (astronomy); Collocation (remote sensing); Vernacular; Persistence (discontinuity); Value (mathematics); Envelope (radar); Psychology; Epistemology; Linguistics; Philosophy; Computer science; Mathematics; Statistics; Syntax; Physics","score_opus":0.02804845608191886,"score_gpt":0.3099939949485337,"score_spread":0.28194553886661483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092479361","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031372525,0.0023005179,0.023028417,0.15957855,0.032980923,0.0036556213,0.0006060594,0.00065106805,0.7458263],"genre_scores_gemma":[0.9762957,0.00020746868,0.003948093,0.01597594,0.0023576024,0.000015096871,0.000008837073,0.000021322878,0.0011699547],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822134,0.00022630225,0.00042797194,0.00035742376,0.00039884332,0.0003681387],"domain_scores_gemma":[0.99830943,0.00040912972,0.00019004484,0.00027322816,0.00048522762,0.00033292925],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007638871,0.00016107954,0.000269659,0.00003969014,0.00034296556,0.000047965044,0.0004508207,0.00009922077,0.00026459983],"category_scores_gemma":[0.012444063,0.00013921797,0.00007709639,0.00038944968,0.00025711203,0.000014231644,0.00015869558,0.00019554478,0.000097896445],"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":[0.00029165376,0.0001407308,0.011618034,0.00018338392,0.00017958361,0.00013256793,0.1884433,0.00033805156,0.0012188465,0.38809738,0.40285355,0.006502924],"study_design_scores_gemma":[0.0003878697,0.00011714198,0.0003894764,0.00003178684,0.000075816904,0.0000018565862,0.0070762616,0.00026037465,0.000074961936,0.002310644,0.9890319,0.00024191955],"about_ca_topic_score_codex":0.0015910297,"about_ca_topic_score_gemma":0.0009081907,"teacher_disagreement_score":0.94492316,"about_ca_system_score_codex":0.000021564107,"about_ca_system_score_gemma":0.00021995981,"threshold_uncertainty_score":0.9958745},"labels":[],"label_agreement":null},{"id":"W4210262403","doi":"10.1515/lingvan-2020-0013","title":"A socially anchored approach to spatial language in Kalaallisut","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Categorization, perception, and language","field":"Psychology","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":"","keywords":"Sociocultural evolution; Affect (linguistics); Encoding (memory); Space (punctuation); Arctic; Geography; Sociology; Frame (networking); Linguistics; Psychology; Computer science; Communication; Ecology; Cognitive psychology; Anthropology; Philosophy","score_opus":0.015967087377721963,"score_gpt":0.3064200608114498,"score_spread":0.29045297343372783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210262403","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45517322,0.0005811626,0.013657614,0.00017510078,0.0072311354,0.0012802095,0.0004924398,0.00041063316,0.5209985],"genre_scores_gemma":[0.9856815,0.0000025507686,0.0018039513,0.0008529087,0.0026495128,0.0002109157,0.0005612986,0.0000601585,0.008177241],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99813294,0.00020736303,0.0003681352,0.000500656,0.00034708815,0.00044382463],"domain_scores_gemma":[0.9991899,0.00006051773,0.00009038088,0.0004405303,0.00009859149,0.00012005785],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040021184,0.00019552071,0.00026494154,0.00027581502,0.00021208466,0.000040562212,0.000351448,0.000094320436,0.0035269852],"category_scores_gemma":[0.0005434396,0.00023083735,0.00009138254,0.000533508,0.00003718103,0.000011501893,0.00014020049,0.00034993142,0.00018772081],"study_design_candidate":"qualitative","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":[0.0006477095,0.0028538965,0.042035848,0.000092611015,0.00016419866,0.0006779336,0.6891073,0.003439514,0.0018423522,0.1835666,0.0546731,0.020898914],"study_design_scores_gemma":[0.0060058027,0.0007836807,0.2526287,0.000025529238,0.00017238606,0.000072169845,0.12018412,0.0015987849,0.00007091754,0.003934887,0.6123113,0.0022117076],"about_ca_topic_score_codex":0.004173617,"about_ca_topic_score_gemma":0.0014991869,"teacher_disagreement_score":0.5689232,"about_ca_system_score_codex":0.0001911937,"about_ca_system_score_gemma":0.00011340151,"threshold_uncertainty_score":0.99738395},"labels":[],"label_agreement":null},{"id":"W4210791957","doi":"10.1515/lingvan-2020-0016","title":"Conflation of spatial reference frames in deaf community sign languages","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Hearing Impairment and Communication","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":"Modality (human–computer interaction); Conflation; Affordance; Sign language; Modalities; Sign (mathematics); American Sign Language; Frame of reference; Frame (networking); Computer science; Linguistics; Manually coded language; Feature (linguistics); Sociolinguistics of sign languages; Psychology; Artificial intelligence; Sociology; Human–computer interaction; Mathematics","score_opus":0.0589559648813121,"score_gpt":0.3698895156348347,"score_spread":0.3109335507535226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210791957","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8785906,0.00019273581,0.00038561627,0.000056969537,0.0005948053,0.00018552202,0.000036960395,0.00005783618,0.11989898],"genre_scores_gemma":[0.99848163,0.0000045675406,0.00056204456,0.00009266484,0.00008509319,0.00003416324,0.00010748796,0.000012106272,0.00062026974],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99861115,0.000718658,0.00027078902,0.00009799404,0.00015438929,0.0001470378],"domain_scores_gemma":[0.99881256,0.00038628365,0.00012769416,0.0005659357,0.000081845086,0.00002568738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006548563,0.00007687213,0.00014535683,0.00010814136,0.00014643818,0.000008197885,0.00032793215,0.00005651806,0.00075009157],"category_scores_gemma":[0.0008163465,0.00009028758,0.000026963651,0.00013174136,0.000045287667,0.000007496276,0.00018055095,0.00060809497,0.000020951515],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066901784,0.002797573,0.5927911,0.00014106666,0.0001389782,0.00006960111,0.09903287,0.00119866,0.002230643,0.22865288,0.0034825082,0.06879513],"study_design_scores_gemma":[0.0018141107,0.0010438641,0.86983585,0.00005865721,0.000050976025,0.0000062775957,0.02376723,0.0010084942,0.00071250193,0.00792852,0.093330026,0.00044349753],"about_ca_topic_score_codex":0.009371114,"about_ca_topic_score_gemma":0.0005461115,"teacher_disagreement_score":0.27704477,"about_ca_system_score_codex":0.000051555748,"about_ca_system_score_gemma":0.00003357975,"threshold_uncertainty_score":0.9972256},"labels":[],"label_agreement":null},{"id":"W4214853268","doi":"10.1515/lingvan-2021-0057","title":"Disruptions due to COVID-19: using mixed methods to identify factors influencing language maintenance and shift","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":5,"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":"Context (archaeology); Social distance; Recreation; Language shift; Perception; Psychology; Distancing; Affect (linguistics); Coronavirus disease 2019 (COVID-19); Identity (music); Heritage language; Social psychology; Sociology; Pedagogy; Linguistics; Geography; Political science; Medicine; Communication","score_opus":0.10321131260074493,"score_gpt":0.5455870256524398,"score_spread":0.4423757130516949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214853268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97343653,0.000104694336,0.01569947,0.0013659096,0.003485306,0.0004687337,0.00019191949,0.00014838329,0.0050990772],"genre_scores_gemma":[0.95599514,0.0000029216385,0.03724935,0.004744507,0.00088469236,0.000030204177,0.000012986691,0.000023929395,0.0010562423],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980452,0.00054636004,0.000285787,0.00034015006,0.0003383489,0.0004441588],"domain_scores_gemma":[0.998056,0.00062376657,0.00010306806,0.00025899152,0.00013538181,0.0008227903],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.001389524,0.00014785634,0.00021313794,0.0002603147,0.0015131951,0.00015315932,0.00030820037,0.000054230346,0.00045475079],"category_scores_gemma":[0.034749243,0.00016497273,0.000061842926,0.00066907087,0.00009391699,0.000027110265,0.0002584173,0.00023086992,0.000014098148],"study_design_candidate":"qualitative","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":[0.000019958467,0.000066426466,0.0050552892,0.000043076583,0.000025310852,0.000049045564,0.94410414,0.0021230942,0.0011942991,0.0403217,0.0018961029,0.005101577],"study_design_scores_gemma":[0.00018368427,0.000038984937,0.012107672,0.000019389088,0.000044049706,0.0000042747483,0.21203159,0.00019915574,0.00018166032,0.0019178492,0.772859,0.00041270594],"about_ca_topic_score_codex":0.02866468,"about_ca_topic_score_gemma":0.003688114,"teacher_disagreement_score":0.7709629,"about_ca_system_score_codex":0.00051388016,"about_ca_system_score_gemma":0.00068829936,"threshold_uncertainty_score":0.9997867},"labels":[],"label_agreement":null},{"id":"W4285586648","doi":"10.1515/lingvan-2021-0048","title":"Cross-dialectal synchronic variation of a diachronic conditioned merger in Tlingit","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Variation (astronomy); Sound change; Perception; Linguistics; Indigenous; Set (abstract data type); History; Computer science; Psychology; Biology","score_opus":0.020944653249472533,"score_gpt":0.3604735833782272,"score_spread":0.3395289301287547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285586648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98374075,0.0008889957,0.0001680357,0.00003466164,0.0033097202,0.00026423432,0.00023288134,0.000036619742,0.011324097],"genre_scores_gemma":[0.9980419,0.000009425576,0.00012416732,0.00005437377,0.00040349166,0.000119931705,0.00010967784,0.000028591787,0.0011084023],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983071,0.00025081538,0.0004221812,0.00032705927,0.00027551406,0.00041730652],"domain_scores_gemma":[0.99893236,0.0002988208,0.00016233012,0.00038380598,0.0001669504,0.00005574102],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005818018,0.00012467988,0.0002492107,0.00027227725,0.00015414723,0.000015619913,0.0002912941,0.00010355964,0.0080881445],"category_scores_gemma":[0.0009811647,0.00014939265,0.00008476734,0.00043499214,0.00013691101,0.000009087147,0.00016548773,0.00052896986,0.00010263029],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039474084,0.00726965,0.34555197,0.00056315085,0.0020190077,0.0023102735,0.22664805,0.032456923,0.06329413,0.29927838,0.01133716,0.0053239013],"study_design_scores_gemma":[0.004492316,0.001195025,0.95670927,0.000023722048,0.000071051545,0.000031082815,0.0005617509,0.004177642,0.0007003571,0.01361966,0.017859705,0.0005584147],"about_ca_topic_score_codex":0.00062557694,"about_ca_topic_score_gemma":0.00008236059,"teacher_disagreement_score":0.6111573,"about_ca_system_score_codex":0.00019091161,"about_ca_system_score_gemma":0.00022366336,"threshold_uncertainty_score":0.9928186},"labels":[],"label_agreement":null},{"id":"W4294663728","doi":"10.1515/lingvan-2021-0109","title":"Exploring variation and change in a small-scale Indigenous society: the case of (s) in Pirahã","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","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":"Variation (astronomy); Sound change; Indigenous; Context (archaeology); Scale (ratio); Language change; Social change; Psychology; Demography; Geography; Social psychology; Sociology; Linguistics; Political science; Cartography; Ecology; Biology","score_opus":0.12170473993565635,"score_gpt":0.32382991997494676,"score_spread":0.20212518003929042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294663728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995123,0.00019010557,0.00010597475,0.00031543037,0.0013954488,0.00041013962,0.000023303764,0.000023037395,0.002413531],"genre_scores_gemma":[0.9979302,0.000093436305,0.0008378426,0.0003252612,0.000605705,0.00013865119,0.000004670121,0.000009005332,0.00005518328],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9989864,0.00025556755,0.00024471054,0.00016629316,0.00011974515,0.00022723251],"domain_scores_gemma":[0.9993369,0.0002957503,0.00011646132,0.00012336262,0.0000898956,0.000037618156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014166264,0.00006872105,0.00014015399,0.00009324172,0.0003673709,0.000017842158,0.00013009798,0.000044242577,0.00005138182],"category_scores_gemma":[0.0019084546,0.00006845085,0.000033593227,0.000378065,0.00008421523,0.000016418226,0.00011191274,0.0002214123,9.4311e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013213526,0.00009443733,0.019746702,0.00001845056,0.0000086668315,0.00036305617,0.92788094,0.00007629187,0.000017476552,0.048291087,0.000013314567,0.0034763843],"study_design_scores_gemma":[0.0052163117,0.0006386887,0.32172844,0.000109117216,0.00021000559,0.00022706481,0.47972742,0.008554881,0.00009903773,0.047295567,0.13486698,0.0013264942],"about_ca_topic_score_codex":0.07392507,"about_ca_topic_score_gemma":0.046883043,"teacher_disagreement_score":0.44815353,"about_ca_system_score_codex":0.00013891389,"about_ca_system_score_gemma":0.00012531602,"threshold_uncertainty_score":0.9705089},"labels":[],"label_agreement":null},{"id":"W4306249762","doi":"10.1515/lingvan-2021-0122","title":"Phonetic change over the career: a case study","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":14,"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":"European Commission","keywords":"Flexibility (engineering); Perspective (graphical); Psychology; Linguistics; Longitudinal study; Feature (linguistics); Computer science; Mathematics","score_opus":0.07789135288875891,"score_gpt":0.3521037197557527,"score_spread":0.2742123668669938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306249762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83625627,0.0006480202,0.0001530079,0.0016411504,0.030108988,0.003015409,0.00016472701,0.0004309623,0.12758148],"genre_scores_gemma":[0.9921755,0.000006309687,0.000113833456,0.0016394146,0.0041133426,0.00021349564,0.0000064700503,0.000018194787,0.0017134474],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980891,0.0005866437,0.00021420224,0.00024826752,0.00052287435,0.0003389161],"domain_scores_gemma":[0.9988839,0.00033386706,0.00010974002,0.00034423423,0.00022907919,0.00009919305],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011745847,0.000109069224,0.00014428198,0.00007038042,0.001930848,0.000063618776,0.00036094745,0.000040014813,0.0016386381],"category_scores_gemma":[0.004797682,0.00009522582,0.00006248751,0.00033723444,0.00012625332,0.000007894088,0.00023522422,0.0002973334,0.00003636017],"study_design_candidate":"qualitative","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":[0.00002990213,0.0007090044,0.035225283,0.000008751606,0.000102212456,0.015885206,0.8066575,0.00006155956,0.0000028819863,0.12457805,0.013792667,0.002946971],"study_design_scores_gemma":[0.00050660875,0.00017131488,0.0019903039,0.000001344562,0.000091947426,0.00011099587,0.13856865,0.00013481564,5.070017e-7,0.001145238,0.8571028,0.00017543929],"about_ca_topic_score_codex":0.040660173,"about_ca_topic_score_gemma":0.010428741,"teacher_disagreement_score":0.8433102,"about_ca_system_score_codex":0.00014604015,"about_ca_system_score_gemma":0.00017087384,"threshold_uncertainty_score":0.9993685},"labels":[],"label_agreement":null},{"id":"W4312200521","doi":"10.1515/lingvan-2022-0017","title":"The Red Hen Anonymizer and the Red Hen Protocol for de-identifying audiovisual recordings","year":2022,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":4,"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":"Fundación Séneca; Google; Alexander von Humboldt-Stiftung","keywords":"JSON; Computer science; Software; Protocol (science); Identification (biology); Face (sociological concept); Multimedia; Human–computer interaction; Speech recognition; World Wide Web; Programming language; Linguistics","score_opus":0.06178125760216429,"score_gpt":0.40706078183376426,"score_spread":0.34527952423159997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312200521","genre_codex":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07064747,0.00096768746,0.013164038,0.030931069,0.012955871,0.5364692,0.0001412069,0.0014496277,0.3332738],"genre_scores_gemma":[0.5990519,0.000010401337,0.004361557,0.00097499636,0.0015943195,0.37317815,0.000031830517,0.00009358528,0.020703234],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983411,0.0005294798,0.00034411103,0.00023836574,0.00018766569,0.0003593039],"domain_scores_gemma":[0.9978731,0.0010732154,0.00019512486,0.00067857886,0.00012728687,0.000052652864],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0023694052,0.00013090775,0.00017489935,0.000042937558,0.0013859847,0.00014097021,0.0005149454,0.000057554127,0.00015216124],"category_scores_gemma":[0.0022456911,0.000093633695,0.00009739187,0.00012500185,0.00013333399,0.000012788218,0.000336372,0.00035673808,0.000008914038],"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":[0.016846692,0.0008855751,0.0436768,0.0003462574,0.00110309,0.00005495935,0.07790195,0.00007520764,0.0006502143,0.2515112,0.5143948,0.09255324],"study_design_scores_gemma":[0.004225361,0.00023650138,0.003713012,0.000022760687,0.00006311396,0.000014773682,0.002878117,0.000866512,0.000024512236,0.020658134,0.96712244,0.0001747506],"about_ca_topic_score_codex":0.0001704237,"about_ca_topic_score_gemma":0.000017202081,"teacher_disagreement_score":0.5284045,"about_ca_system_score_codex":0.00008516163,"about_ca_system_score_gemma":0.000059050508,"threshold_uncertainty_score":0.99991405},"labels":[],"label_agreement":null},{"id":"W4377224620","doi":"10.1515/lingvan-2021-0143","title":"How did COVID-19 impact the use of Japanese complex words with <i>masuku</i> ‘mask’ in 2020?","year":2023,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Language, Metaphor, and Cognition","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":"York University","funders":"","keywords":"Newspaper; Compounding; Coronavirus disease 2019 (COVID-19); Sentence; Computer science; Advertising; History; Artificial intelligence; Sociology; Media studies; Business","score_opus":0.08374675119605893,"score_gpt":0.3525271364932683,"score_spread":0.2687803852972094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377224620","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9715118,0.0004870901,0.00088158646,0.0016549446,0.0022157335,0.0010939519,0.0007637817,0.00038718278,0.02100394],"genre_scores_gemma":[0.99129725,0.00003199095,0.00034139358,0.0015332297,0.00074665266,0.000050220686,0.00026077597,0.00005361988,0.005684843],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981573,0.00027335435,0.0003286381,0.0003885968,0.00035912122,0.0004929906],"domain_scores_gemma":[0.99779177,0.000923968,0.00020657931,0.0007049465,0.00019758304,0.00017517473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042408923,0.00026372433,0.00038977782,0.00019213221,0.00009984563,0.0000966887,0.00030968848,0.00013365649,0.0005314802],"category_scores_gemma":[0.0037078024,0.00017030489,0.00014316305,0.0010496797,0.00021797896,0.000031202104,0.00006988362,0.0003150542,0.00010817749],"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":[0.0057008793,0.0018903713,0.13064723,0.0008534758,0.0020958213,0.008843275,0.423337,0.004210298,0.0026492742,0.018761039,0.38537136,0.015639974],"study_design_scores_gemma":[0.010789848,0.0020811895,0.13463154,0.00029124419,0.00091201224,0.0002685778,0.11083354,0.0024239519,0.0002672429,0.005456034,0.7297949,0.0022498632],"about_ca_topic_score_codex":0.0026505138,"about_ca_topic_score_gemma":0.0012374439,"teacher_disagreement_score":0.3444236,"about_ca_system_score_codex":0.00006775927,"about_ca_system_score_gemma":0.000101685786,"threshold_uncertainty_score":0.6944832},"labels":[],"label_agreement":null},{"id":"W4391967989","doi":"10.1515/lingvan-2023-0038","title":"Plains Cree Order as alternation","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Lexicography and 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":"University of Alberta","funders":"","keywords":"Alternation (linguistics); Phenomenon; Lexeme; Linguistics; Computer science; Mathematics; Epistemology; Philosophy","score_opus":0.019250155242884776,"score_gpt":0.2696289642022423,"score_spread":0.25037880895935755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391967989","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":[0.009732145,0.0036423937,0.00023967694,0.00022815616,0.0077077793,0.000116307594,0.000084820334,0.00046450016,0.9777842],"genre_scores_gemma":[0.964896,0.00008258088,0.0002860661,0.0005232405,0.009631821,0.000013140478,0.000039068484,0.000029769404,0.024498273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999245,0.000015220802,0.000159204,0.00020219227,0.00018322658,0.00019518644],"domain_scores_gemma":[0.99944454,0.00010358566,0.00002559631,0.00014290142,0.00024293188,0.000040426123],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008933042,0.0001346991,0.00011015113,0.00013312236,0.00024377649,0.00033705359,0.00010823321,0.000032734395,0.002142049],"category_scores_gemma":[0.00065853895,0.00011079105,0.0000898749,0.00006653988,0.00013190517,0.000033532528,0.000037797203,0.00015072088,0.0005650498],"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":[0.0000064467517,0.00002440416,0.000047604535,0.00007402873,0.00011920828,0.00016401621,0.055970922,0.0000050111817,0.0000045959628,0.92391413,0.016345479,0.0033241746],"study_design_scores_gemma":[0.000089698784,0.000056272038,0.000025407055,0.00007582787,0.000054843713,0.0000022618358,0.0028331082,0.00021848483,0.000044855766,0.016351422,0.9800824,0.00016542873],"about_ca_topic_score_codex":0.0004566753,"about_ca_topic_score_gemma":0.000889986,"teacher_disagreement_score":0.9637369,"about_ca_system_score_codex":0.0000173265,"about_ca_system_score_gemma":0.000029393183,"threshold_uncertainty_score":0.9987701},"labels":[],"label_agreement":null},{"id":"W4392656786","doi":"10.1515/lingvan-2023-0051","title":"The role of syntax in hashtag popularity","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","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":"University of Toronto","funders":"","keywords":"Popularity; Computer science; Syntax; Natural language processing; Semantics (computer science); CLARITY; Artificial intelligence; Linguistics; Information retrieval; Psychology; Programming language; Social psychology","score_opus":0.008434858255253173,"score_gpt":0.26520548807037014,"score_spread":0.25677062981511695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392656786","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16479994,0.13070598,0.3210594,0.0036942651,0.036942758,0.0012355956,0.000055585286,0.0014445547,0.34006193],"genre_scores_gemma":[0.9918298,0.000051536026,0.0075416295,0.000023732335,0.0002505164,0.000002422539,0.0000022427269,0.000005311922,0.00029278174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917215,0.0000340539,0.0002446618,0.00019014612,0.00020159798,0.00015738638],"domain_scores_gemma":[0.99933237,0.0001953415,0.000042325268,0.00033015502,0.00007146242,0.000028329243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038673266,0.000070131115,0.00011234328,0.00009329064,0.000061079394,0.0001695168,0.00045643788,0.000032578555,0.0000075443695],"category_scores_gemma":[0.00056116976,0.00005148026,0.00007898675,0.00038582785,0.000027035252,0.000024728939,0.00013396105,0.00011899007,0.000021652757],"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":[0.0000022676122,0.000028797389,0.0121547235,0.000018702696,0.000040329785,0.00003380275,0.0011063891,0.000077608405,0.0001732317,0.93902063,0.00047039328,0.04687311],"study_design_scores_gemma":[0.00011260346,0.0000407606,0.0023966138,0.00015775643,0.00002789021,0.000002452476,0.00034170508,0.53991586,0.0031881654,0.06999846,0.3836102,0.00020756439],"about_ca_topic_score_codex":0.000101408616,"about_ca_topic_score_gemma":0.000059637296,"teacher_disagreement_score":0.8690222,"about_ca_system_score_codex":0.000019174637,"about_ca_system_score_gemma":0.00003927709,"threshold_uncertainty_score":0.2099304},"labels":[],"label_agreement":null},{"id":"W4393936388","doi":"10.1515/lingvan-2023-0087","title":"A diachronic consequence of intransitivity: structural underspecification and processing biases in Old French","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Categorization, perception, and language","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":"University of Toronto","funders":"","keywords":"Underspecification; Linguistics; Verb; Grammar; Representation (politics); Object (grammar); Parsing; Corollary; Optimality theory; Computer science; History; Philosophy; Artificial intelligence; Phonology; Mathematics; Political science","score_opus":0.03199731922509109,"score_gpt":0.3445328847187323,"score_spread":0.3125355654936412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393936388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98552495,0.00595664,0.003158437,0.00006921715,0.0008657805,0.00017099243,0.000052891948,0.00008737145,0.004113702],"genre_scores_gemma":[0.9987323,0.00008003675,0.00032529057,0.00003053706,0.0004281252,0.000008247602,0.000061962186,0.00001696968,0.00031651015],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99915946,0.000054691005,0.00024106816,0.00027305982,0.00010046354,0.00017126731],"domain_scores_gemma":[0.9994883,0.00017049766,0.000048687496,0.00015077699,0.000104695406,0.0000370741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001520218,0.00010723704,0.00014788951,0.00016366829,0.000039488223,0.000049760107,0.000058569716,0.000082789884,0.00027065008],"category_scores_gemma":[0.00040902736,0.00010645653,0.000025919358,0.00027821964,0.0001666656,0.00003083569,0.000010170321,0.00013390943,0.000009358833],"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":[0.00013610414,0.00032120576,0.05997428,0.0024486878,0.00019522417,0.0012565787,0.31311402,0.00051982456,0.018573295,0.4578576,0.0009877612,0.14461543],"study_design_scores_gemma":[0.0027018485,0.0005099822,0.86925465,0.0021528758,0.0004375334,0.0005033861,0.028679566,0.033030383,0.0021190597,0.04997373,0.008919956,0.001717008],"about_ca_topic_score_codex":0.0011482908,"about_ca_topic_score_gemma":0.0008297333,"teacher_disagreement_score":0.8092804,"about_ca_system_score_codex":0.00006269169,"about_ca_system_score_gemma":0.000092465496,"threshold_uncertainty_score":0.4341171},"labels":[],"label_agreement":null},{"id":"W4399982581","doi":"10.1515/lingvan-2023-0148","title":"The syntax of African American English borrowings in the Louisiana Creole tense-mood-aspect system","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Arts and Humanities Research Council; University of Oxford; Georgetown University; Louisiana State University; McGill University; University of Sussex; University of Pennsylvania","keywords":"Creole language; Linguistics; Syntax; English-based creole languages; History; Mood; American English; Psychology; Philosophy; Language assessment","score_opus":0.011343924825938927,"score_gpt":0.2920378295530314,"score_spread":0.2806939047270925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399982581","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015594029,0.0013472791,0.0007931207,0.004649816,0.014270815,0.0008289873,0.00010724878,0.00048515256,0.96192354],"genre_scores_gemma":[0.9952581,0.00005582561,0.00037988307,0.00024317799,0.0033894833,0.000022254422,0.000004487781,0.000020520769,0.0006262484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978747,0.00047501706,0.000432877,0.00027877564,0.0005065915,0.00043208024],"domain_scores_gemma":[0.99687284,0.0020492557,0.00015954941,0.00037970074,0.00045934226,0.00007928914],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022668792,0.00014310676,0.0002551332,0.00011136016,0.00040639643,0.00019078623,0.0006212485,0.00007982221,0.000022478027],"category_scores_gemma":[0.022322144,0.000094048206,0.00011959876,0.00082875806,0.0006162282,0.000017917446,0.00005170481,0.00028508558,0.000025297046],"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":[0.000012392471,0.000027292643,0.0007426064,0.00004033275,0.00003488473,0.00011633731,0.06954073,0.0000097788325,0.00000822583,0.9248581,0.0037891988,0.000820104],"study_design_scores_gemma":[0.00012582334,0.000074916716,0.0009144733,0.00010026927,0.00008101869,0.0000031069794,0.10291891,0.0004247799,0.000026304417,0.002544633,0.8926145,0.00017125429],"about_ca_topic_score_codex":0.008080106,"about_ca_topic_score_gemma":0.004151959,"teacher_disagreement_score":0.9796641,"about_ca_system_score_codex":0.0001685111,"about_ca_system_score_gemma":0.00034763038,"threshold_uncertainty_score":0.9985252},"labels":[],"label_agreement":null},{"id":"W4402422143","doi":"10.1515/lingvan-2023-0102","title":"Bibliographic bias and information-density sampling","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Advanced Text Analysis Techniques","field":"Computer Science","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 Alberta","funders":"Marcus och Amalia Wallenbergs minnesfond","keywords":"Sampling bias; Sampling (signal processing); Statistics; Information retrieval; Computer science; Geography; Mathematics; Sample size determination; Telecommunications","score_opus":0.025144856216042854,"score_gpt":0.29749520760234294,"score_spread":0.2723503513863001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402422143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003108893,0.0007748639,0.9896422,0.00012300727,0.00061276584,0.000077845005,0.000004662995,0.0011170815,0.004538704],"genre_scores_gemma":[0.70375216,0.0003451489,0.2953639,0.0002694214,0.00021931785,0.0000049302525,0.000006486187,0.00000769359,0.000030932566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990843,0.000018873945,0.0002474861,0.00023508239,0.00022405964,0.00019021814],"domain_scores_gemma":[0.9989987,0.00022755758,0.00005338088,0.00039341018,0.00024874782,0.00007820459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029587667,0.0001277588,0.00014180731,0.0016832018,0.00010680229,0.0006350323,0.00032194055,0.000060183535,0.0000038442345],"category_scores_gemma":[0.0011316742,0.00012013071,0.00007298486,0.002736359,0.000049879138,0.00047016793,0.00023398895,0.00017894877,0.00004269451],"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":[0.0000014158076,0.000009976211,0.0020879149,0.00008953161,0.000049730126,0.00003598423,0.0006902107,0.000049041737,0.000074796226,0.9393233,0.0016369332,0.05595113],"study_design_scores_gemma":[0.00012113676,0.00007187185,0.0035702435,0.00017808635,0.00007043198,0.000031933792,0.000044542303,0.09879767,0.0015598014,0.28517216,0.60980713,0.0005749663],"about_ca_topic_score_codex":0.000030919495,"about_ca_topic_score_gemma":0.000008130378,"teacher_disagreement_score":0.7006433,"about_ca_system_score_codex":0.000016796426,"about_ca_system_score_gemma":0.000033011213,"threshold_uncertainty_score":0.61236316},"labels":[],"label_agreement":null},{"id":"W4403221822","doi":"10.1515/lingvan-2024-0091","title":"Using constructed languages to introduce and teach linguistics","year":2024,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"EFL/ESL Teaching and Learning","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":"University of Alberta","funders":"","keywords":"Linguistics; Applied linguistics; Computer science; Quantitative linguistics; Media linguistics; Programming language; Sociology; Philosophy","score_opus":0.037804785940285766,"score_gpt":0.31828005229765444,"score_spread":0.2804752663573687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403221822","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28878453,0.008141188,0.0029708995,0.00038284628,0.024249325,0.00055715826,0.00028129117,0.0022340775,0.6723987],"genre_scores_gemma":[0.9658515,0.000011461313,0.011820629,0.00029013015,0.016732939,0.000003029898,0.000023953417,0.000063734886,0.005202632],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998753,0.00006878886,0.0002706344,0.0003881778,0.00019184692,0.00032755182],"domain_scores_gemma":[0.999052,0.00023097417,0.00004399645,0.00023011163,0.00030451253,0.00013839659],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00033355984,0.00021840102,0.00023555242,0.00021232136,0.00038671202,0.0006459425,0.00012791736,0.000065494554,0.0003479569],"category_scores_gemma":[0.008518349,0.00020468976,0.000053688756,0.00007100891,0.00017069475,0.000015352976,0.00009176387,0.000505003,0.00010369323],"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":[0.0000131517545,0.000026180787,0.000544761,0.00024735075,0.00009661172,0.00019342499,0.06168822,0.00014146359,0.00022959776,0.9194338,0.010231737,0.0071537225],"study_design_scores_gemma":[0.00010188681,0.00006545037,0.00002874467,0.0002634303,0.000108972614,0.000013155587,0.0061388444,0.0039550206,0.00007689555,0.0013948814,0.9875261,0.0003266148],"about_ca_topic_score_codex":0.00047759543,"about_ca_topic_score_gemma":0.00011525523,"teacher_disagreement_score":0.9772944,"about_ca_system_score_codex":0.000046563044,"about_ca_system_score_gemma":0.00006395435,"threshold_uncertainty_score":0.99983335},"labels":[],"label_agreement":null},{"id":"W4408918469","doi":"10.1515/lingvan-2024-0247","title":"Asymmetry in French speech-in-noise perception: the effects of native dialect and cross-dialectal exposure","year":2025,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Phonetics and Phonology Research","field":"Psychology","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":"","keywords":"Asymmetry; Speech perception; Perception; Linguistics; Noise (video); Psychology; Speech recognition; Acoustics; Audiology; Computer science; Physics; Artificial intelligence; Philosophy; Medicine","score_opus":0.009096022296645455,"score_gpt":0.34880863823580566,"score_spread":0.3397126159391602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408918469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9539638,0.0024981587,0.000036041223,0.000066892666,0.002099889,0.00035163632,0.000017571896,0.000012728319,0.040953238],"genre_scores_gemma":[0.9975464,0.00009746466,0.00014169308,0.00010532579,0.0002788032,0.000038534617,0.000006094407,0.0000119798915,0.001773714],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986416,0.000272538,0.00030190728,0.00031322843,0.00014109552,0.00032962637],"domain_scores_gemma":[0.99790967,0.0014990403,0.00006052223,0.00032931878,0.00016171018,0.000039772734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043966962,0.00014462971,0.00027552794,0.00030465447,0.00006516255,0.000026519132,0.00025091445,0.00021259265,0.000104980856],"category_scores_gemma":[0.004277814,0.00012177661,0.00005139774,0.0005435413,0.000365095,0.0000075701723,0.00011910292,0.00056560256,0.000016121341],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000277572,0.0004941331,0.9382898,0.0003207528,0.00015555769,0.00053003,0.028666232,0.000011747344,0.0044462495,0.00815368,0.0023315514,0.016322695],"study_design_scores_gemma":[0.0013426914,0.0002657104,0.98935,0.0000893138,0.000017394665,0.000005848236,0.00023716158,0.0000618954,0.0010556522,0.0066919904,0.0007669915,0.000115320654],"about_ca_topic_score_codex":0.0010377592,"about_ca_topic_score_gemma":0.0008221577,"teacher_disagreement_score":0.05106023,"about_ca_system_score_codex":0.000047391026,"about_ca_system_score_gemma":0.00008354442,"threshold_uncertainty_score":0.5121252},"labels":[],"label_agreement":null},{"id":"W4413796994","doi":"10.1515/lingvan-2024-0201","title":"Instance memory models as a general computational framework for exploring language processing: bringing the lexicon to life","year":2025,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicon; Computer science; Cognitive science; Natural language processing; Linguistics; Artificial intelligence; Psychology; Cognitive psychology; Philosophy","score_opus":0.057039101299999395,"score_gpt":0.32504685551013524,"score_spread":0.26800775421013584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413796994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0130016925,0.00074040995,0.9774246,0.0013705603,0.0016323738,0.00038401142,0.0000047004005,0.00025198676,0.0051896195],"genre_scores_gemma":[0.5199715,0.0000022060485,0.47579125,0.0030965076,0.00071910076,0.000089991176,0.0000020722441,0.000013346215,0.00031405932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844843,0.000030277302,0.0003380709,0.0004948474,0.0003045675,0.00038380479],"domain_scores_gemma":[0.9985638,0.00036389203,0.00009311986,0.00053195015,0.00033649,0.00011071567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031886224,0.00018439077,0.00020343043,0.00014008695,0.0003373503,0.00031741243,0.0009266119,0.000067682515,0.0000020239434],"category_scores_gemma":[0.0027045845,0.00016810831,0.00007824817,0.00040176726,0.000028380173,0.000110680834,0.00031714674,0.0002391138,0.000007619726],"study_design_candidate":"simulation_or_modeling","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":[0.000009468894,0.000014748787,0.000015518197,0.000056615725,0.000014862508,0.000006726599,0.0062415977,0.3567054,0.000016389786,0.61322606,0.00018344325,0.023509197],"study_design_scores_gemma":[0.00016831292,0.00001614248,0.00001813674,0.00018614161,0.000010767019,0.0000013000586,0.00034680587,0.7930908,0.00027071266,0.20339741,0.0023290047,0.00016443648],"about_ca_topic_score_codex":0.0000334105,"about_ca_topic_score_gemma":0.000008530047,"teacher_disagreement_score":0.50696975,"about_ca_system_score_codex":0.00008102937,"about_ca_system_score_gemma":0.00038593094,"threshold_uncertainty_score":0.6855258},"labels":[],"label_agreement":null},{"id":"W4415076690","doi":"10.1515/lingvan-2025-0160","title":"Linguistic approaches to fake news research are growing and maturing: commentary on a special issue","year":2025,"lang":"en","type":"article","venue":"Linguistics Vanguard","topic":"Misinformation and Its Impacts","field":"Social Sciences","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":"Interpretation (philosophy); Sophistication; Context (archaeology); Fake news; Flourishing; Corpus linguistics; Social media; Natural (archaeology)","score_opus":0.17335017976923545,"score_gpt":0.3979844354813963,"score_spread":0.22463425571216084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415076690","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":[0.015455092,0.000083778286,0.00012075602,0.01546881,0.0032308246,0.0005749637,0.000023447523,0.00010280778,0.96493953],"genre_scores_gemma":[0.94137156,0.00007828943,0.0026703312,0.01596939,0.027772343,0.000010190002,0.000018679495,0.000024643296,0.012084586],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99820364,0.0001905382,0.0002759234,0.0002542699,0.00057114306,0.0005045187],"domain_scores_gemma":[0.9986715,0.00049445254,0.000059501068,0.00025377455,0.0002404172,0.00028035612],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011249861,0.00014173576,0.00020342112,0.00036990957,0.00089945394,0.0003384449,0.00028220657,0.00011696499,0.00014085446],"category_scores_gemma":[0.017620852,0.00014465806,0.00004113287,0.00052617415,0.00017096235,0.00004165611,0.00015105259,0.00038574747,0.00012973984],"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":[0.000120674995,0.00012088944,0.0012266871,0.00013913671,0.00003880336,0.000034727265,0.13521846,0.00007235836,0.0000035998935,0.30921397,0.5311844,0.022626355],"study_design_scores_gemma":[0.00022717303,0.00005355745,0.0008448716,0.00018937037,0.000012346057,1.9145203e-7,0.025766809,0.0000770524,0.000080048136,0.004333822,0.96826446,0.00015027013],"about_ca_topic_score_codex":0.0008938341,"about_ca_topic_score_gemma":0.0010289357,"teacher_disagreement_score":0.95285493,"about_ca_system_score_codex":0.00018227955,"about_ca_system_score_gemma":0.00013124963,"threshold_uncertainty_score":0.9906542},"labels":[],"label_agreement":null}]}