{"meta":{"query_hash":"709e4a003527","filters":{"venue":"Yearbook of Phraseology"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/709e4a003527","api":"https://metacan.xera.ac/api/v1/cohort?venue=Yearbook+of+Phraseology"},"results":[{"id":"W2610219444","doi":"10.1515/phras-2015-0005","title":"Clichés, an Understudied Subclass of Phrasemes","year":2015,"lang":"en","type":"article","venue":"Yearbook of Phraseology","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Phrase; Cliché; Section (typography); Referent; Meaning (existential); Linguistics; Typology; Dimension (graph theory); Subclass; Class (philosophy); Complementizer; History; Computer science; Mathematics; Sociology; Syntax; Pure mathematics; Artificial intelligence; Philosophy; Epistemology","score_opus":0.14303765866207765,"score_gpt":0.2831488872078733,"score_spread":0.14011122854579564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610219444","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22719336,0.0048531024,0.27412295,0.007908789,0.00076060736,0.00023253098,0.0019330468,0.0013342521,0.48166132],"genre_scores_gemma":[0.9621634,0.0008177872,0.019330215,0.0007351769,0.00022194289,0.00014161711,0.00068261696,0.00038888186,0.0155182695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997013,0.0013903951,0.0002341199,0.0005941272,0.0005471334,0.00022126573],"domain_scores_gemma":[0.9962548,0.0016762393,0.0003371578,0.0009995488,0.00054289977,0.00018941812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015874766,0.0005193967,0.000658367,0.0020358649,0.00378857,0.006237607,0.0009861012,0.0014769392,0.01049833],"category_scores_gemma":[0.00611854,0.0004108515,0.0005611144,0.0022620189,0.009801382,0.015491848,0.0048967614,0.0031256597,0.0015193823],"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":[0.00002746004,0.000007070376,0.00059255655,0.00008368935,0.0000053101376,0.0001353608,0.00558304,0.00009345273,0.0004265933,0.97851276,0.0023814747,0.012151266],"study_design_scores_gemma":[0.000018456787,0.00003548192,0.0022925604,0.00021983804,0.000013228288,0.0011220966,0.007927449,0.001377043,0.0005566755,0.79639065,0.18999548,0.00005101538],"about_ca_topic_score_codex":0.0011188607,"about_ca_topic_score_gemma":0.0011755035,"teacher_disagreement_score":0.01049833,"about_ca_system_score_codex":0.0016250577,"about_ca_system_score_gemma":0.0009221441,"threshold_uncertainty_score":0.035120368},"labels":[],"label_agreement":null},{"id":"W2610765827","doi":"10.1515/phras-2013-0003","title":"In support of multiword unit classifications: Corpus and human rating data validate phraseological classifications of three different multiword unit types","year":2013,"lang":"en","type":"article","venue":"Yearbook of Phraseology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"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":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Natural language processing; Linguistics; Artificial intelligence","score_opus":0.10055060976160914,"score_gpt":0.3419018279530505,"score_spread":0.2413512181914414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610765827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96357393,0.0008414236,0.013791215,0.0002845127,0.00009307463,0.00024027887,0.00072066544,0.000062230916,0.02039273],"genre_scores_gemma":[0.98844916,0.00020274712,0.008964125,0.00013503051,0.00003765149,0.0003343931,0.0009096415,0.00005907276,0.0009080861],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98763925,0.006457864,0.0014717871,0.0019584463,0.0022542276,0.00021839712],"domain_scores_gemma":[0.84870976,0.09178989,0.015682727,0.022740629,0.019885067,0.0011919618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013445177,0.00039697878,0.0004528923,0.0021087755,0.0012478699,0.0034952909,0.00092495553,0.00083211745,0.004108733],"category_scores_gemma":[0.094358325,0.0003019713,0.0002503834,0.0024629484,0.0029055055,0.0039948313,0.0023865951,0.0012185101,0.001212037],"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":[0.0022628047,0.0007001891,0.5300153,0.0020323712,0.00033447298,0.00063481205,0.14459342,0.0011103103,0.04789374,0.015556116,0.008370682,0.24649584],"study_design_scores_gemma":[0.00014247955,0.000745156,0.9067391,0.00063419103,0.00014466987,0.0015650565,0.039774813,0.00856002,0.011923344,0.010050095,0.019514322,0.00020672452],"about_ca_topic_score_codex":0.0029782818,"about_ca_topic_score_gemma":0.0044190916,"teacher_disagreement_score":0.013445177,"about_ca_system_score_codex":0.00047131968,"about_ca_system_score_gemma":0.00035826466,"threshold_uncertainty_score":0.07110578},"labels":[],"label_agreement":null},{"id":"W3216854874","doi":"10.1515/phras-2021-0004","title":"Morphemic and Syntactic Phrasemes","year":2021,"lang":"en","type":"article","venue":"Yearbook of Phraseology","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Morpheme; Linguistics; Lexeme; Prosody; Computer science; Syntactic structure; Syntax; Morphophonology; Artificial intelligence; Natural language processing; Philosophy; Phonology","score_opus":0.014137400184230478,"score_gpt":0.2106917609973028,"score_spread":0.19655436081307232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216854874","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22070491,0.0067926035,0.055967186,0.002565051,0.0006224891,0.00009556053,0.0007784755,0.0003096659,0.7121641],"genre_scores_gemma":[0.95544016,0.0024962106,0.012048787,0.00042492294,0.00017601124,0.00006473418,0.0004544195,0.00013143805,0.028763369],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99949574,0.00027472855,0.000041871826,0.000061929895,0.00008127012,0.000044555374],"domain_scores_gemma":[0.99975353,0.000118070115,0.00002605673,0.00004027571,0.000049059472,0.000012905107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036897353,0.00026595045,0.00016807529,0.0007286907,0.00076566066,0.0017313829,0.00023922452,0.00038456364,0.008417131],"category_scores_gemma":[0.0007730707,0.00013613729,0.00011535082,0.0007155437,0.0022004293,0.0022348908,0.00111761,0.0010097509,0.0011123228],"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":[0.00006325699,0.000011100004,0.00055488304,0.00014762621,0.000005393483,0.0002981145,0.00479493,0.00012839181,0.0058696605,0.9438065,0.0034680523,0.040851954],"study_design_scores_gemma":[0.0000287872,0.00011337073,0.0075340346,0.00030633842,0.00003778604,0.0026563222,0.006485577,0.001423056,0.0087842075,0.3748362,0.5977507,0.000043487405],"about_ca_topic_score_codex":0.00052684377,"about_ca_topic_score_gemma":0.0006509878,"teacher_disagreement_score":0.008417131,"about_ca_system_score_codex":0.000630882,"about_ca_system_score_gemma":0.0003260417,"threshold_uncertainty_score":0.028158128},"labels":[],"label_agreement":null},{"id":"W4388575640","doi":"10.1515/phras-2023-0004","title":"Hidden in plain sound: overlooked repetition in <i>Just a Minute</i>","year":2023,"lang":"en","type":"article","venue":"Yearbook of Phraseology","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Repetition (rhetorical device); Word (group theory); Entertainment; Linguistics; Quarter (Canadian coin); Remainder; Psychology; Computer science; Arithmetic; History; Mathematics; Art; Visual arts; Philosophy","score_opus":0.054884305673758356,"score_gpt":0.29474221224951597,"score_spread":0.23985790657575762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388575640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.983951,0.00013264,0.0028377238,0.00031463642,0.000050126047,0.000023410474,0.000059421458,0.00008022107,0.012550962],"genre_scores_gemma":[0.9969779,0.00004549833,0.0008077665,0.00009881819,0.000018592746,0.000020050971,0.00005743624,0.00005331157,0.0019206101],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976162,0.0012291376,0.00010599806,0.00023210025,0.0005946539,0.00022201361],"domain_scores_gemma":[0.98672235,0.010360689,0.0011718695,0.0006003812,0.0006128971,0.0005317099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012009592,0.00033073584,0.000347038,0.00058803824,0.0012965557,0.0026163491,0.0006512266,0.0008378589,0.0038946485],"category_scores_gemma":[0.014100928,0.000323455,0.00016032613,0.0004743087,0.0015906995,0.0013277675,0.0016447862,0.00086724485,0.00074877363],"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":[0.0026066415,0.00043182517,0.09298699,0.0010838802,0.00017584147,0.008232334,0.651788,0.0010185492,0.07493075,0.011903329,0.014356884,0.14048499],"study_design_scores_gemma":[0.000078279794,0.0018442681,0.38998005,0.0007410029,0.00021873745,0.010416047,0.4605042,0.006702871,0.021276597,0.007167363,0.10075847,0.00031217982],"about_ca_topic_score_codex":0.0026261553,"about_ca_topic_score_gemma":0.0048143333,"teacher_disagreement_score":0.0038946485,"about_ca_system_score_codex":0.0005127933,"about_ca_system_score_gemma":0.00029034153,"threshold_uncertainty_score":0.01302892},"labels":[],"label_agreement":null}]}