{"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":"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":[0.738528,0.0024196934,0.00002748095,0.00033042108,0.0005245908,0.0001588231,0.000044452612,0.00006587462,0.25790063],"genre_scores_gemma":[0.99809396,0.000026055499,0.00009849518,0.00017315763,0.00030386235,0.000006644745,0.000011232196,0.0000111838,0.001275405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992126,0.00007690524,0.0002474367,0.00014962805,0.00013396371,0.00017942161],"domain_scores_gemma":[0.9993738,0.00006794689,0.0001395375,0.00020665996,0.0001508029,0.000061282415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018470688,0.00011170808,0.0002968848,0.00012595694,0.0000553535,0.000006095245,0.00014673675,0.00004606081,0.0005820672],"category_scores_gemma":[0.000046330497,0.000092074086,0.00008488846,0.00003821533,0.0010068946,0.00009233489,0.00005864949,0.00007233952,0.000020667178],"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":[0.00021119302,0.0004321887,0.0068580615,0.00009054889,0.00040428917,0.000020019988,0.14918587,0.0000050886215,0.0006767716,0.82605547,0.014894457,0.0011660289],"study_design_scores_gemma":[0.009000548,0.0066638617,0.0073275757,0.00018907916,0.0007091197,0.000016902508,0.36155704,0.00010992082,0.015338035,0.11099632,0.48655486,0.00153674],"about_ca_topic_score_codex":0.0006943081,"about_ca_topic_score_gemma":0.0023803734,"teacher_disagreement_score":0.71505916,"about_ca_system_score_codex":0.000009450829,"about_ca_system_score_gemma":0.000042734006,"threshold_uncertainty_score":0.6373227},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9242422,0.00086849375,0.07149257,0.0017204919,0.00010667683,0.0008028269,0.00007082003,0.00017004441,0.00052586506],"genre_scores_gemma":[0.89289206,0.000028686585,0.10675518,0.000076428674,0.000017528706,0.00003656518,0.00006729953,0.000010273355,0.000115980205],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9982531,0.00017534535,0.00068766664,0.00045721716,0.00018951847,0.00023715573],"domain_scores_gemma":[0.9976514,0.00039635034,0.00052133907,0.0011539359,0.0002133955,0.000063560554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035415028,0.00017439216,0.0004298602,0.00029633238,0.000054810876,0.000019913858,0.0014366785,0.00017411585,0.00012522616],"category_scores_gemma":[0.00029896255,0.00014651201,0.000034352357,0.00033043633,0.0006061214,0.00039383877,0.0008335796,0.00026410472,0.000007911931],"study_design_candidate":"bench_or_experimental","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":[0.000031424996,0.0008030216,0.16008572,0.00025579016,0.00008321515,0.000016015336,0.0008207846,0.00000990937,0.5613127,0.2578139,0.0009975499,0.017769996],"study_design_scores_gemma":[0.0034152127,0.0011929161,0.38921267,0.0004241844,0.00016352156,0.00006669718,0.00030585864,0.05583028,0.3586789,0.18788512,0.0015783166,0.0012463153],"about_ca_topic_score_codex":0.0005497838,"about_ca_topic_score_gemma":0.0003792571,"teacher_disagreement_score":0.22912695,"about_ca_system_score_codex":0.000015140151,"about_ca_system_score_gemma":0.000074884076,"threshold_uncertainty_score":0.59745866},"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":"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":[0.8308259,0.008139698,0.000008517737,0.00052655203,0.0002701121,0.000054292388,0.000022519678,0.000039444098,0.16011293],"genre_scores_gemma":[0.9954021,0.00015568573,0.000094214,0.0003323769,0.00021065526,0.000005321895,0.000006021141,0.0000070751603,0.0037865383],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995374,0.00003256547,0.00011775616,0.00013267998,0.000055112698,0.00012445729],"domain_scores_gemma":[0.99966556,0.000093349976,0.00004622645,0.00011518159,0.00005452977,0.00002513504],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000043156455,0.00007436717,0.00015944235,0.000049634516,0.00007397167,0.000012017952,0.000042724972,0.000027574262,0.0037893744],"category_scores_gemma":[0.000042678013,0.00006532265,0.00004882033,0.000021352262,0.00044861715,0.000050860293,0.000053972217,0.00006534342,0.00002391207],"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":[0.000056625566,0.00021039482,0.008172155,0.0002600762,0.0004989189,0.0003052753,0.06838869,6.1163854e-7,0.012611516,0.89247954,0.011144156,0.00587201],"study_design_scores_gemma":[0.0031619817,0.0006038604,0.009690573,0.00030056783,0.0005963643,0.00024110837,0.0698442,0.000042849453,0.07285995,0.051759064,0.78971326,0.0011862098],"about_ca_topic_score_codex":0.000112196096,"about_ca_topic_score_gemma":0.00043724678,"teacher_disagreement_score":0.8407205,"about_ca_system_score_codex":0.0000032492308,"about_ca_system_score_gemma":0.000020116944,"threshold_uncertainty_score":0.9971213},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8504534,0.00022462763,0.0000020297207,0.00087357545,0.00015010954,0.00016842264,0.00002597249,0.00007700852,0.14802486],"genre_scores_gemma":[0.9938048,0.000059406542,0.000058401987,0.00016313214,0.000119793534,0.00004695024,0.00007623653,0.000015224908,0.005656026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990255,0.00014053703,0.0003236451,0.00017097672,0.000114900016,0.0002244036],"domain_scores_gemma":[0.99929774,0.00018867101,0.000104518775,0.00035491702,0.000031873024,0.000022291662],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030521138,0.00010080125,0.00022226118,0.00033835333,0.000039363324,0.000023348013,0.00023396802,0.00006893572,0.0015852809],"category_scores_gemma":[0.00005691781,0.00010027291,0.00004397486,0.000106138934,0.00035823145,0.0001381407,0.00009404424,0.00016096055,0.0002976331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007877062,0.00016248648,0.0057350774,0.000071707844,0.00002544933,0.00010875041,0.06831156,0.0000337079,0.0011629174,0.9164954,0.007141724,0.00067244377],"study_design_scores_gemma":[0.010017069,0.0007302107,0.07993023,0.0008070728,0.000101216116,0.00003948187,0.31664297,0.0010305927,0.0024817064,0.44976795,0.1366449,0.0018066113],"about_ca_topic_score_codex":0.0015168063,"about_ca_topic_score_gemma":0.026934166,"teacher_disagreement_score":0.46672747,"about_ca_system_score_codex":0.000039533435,"about_ca_system_score_gemma":0.00005863945,"threshold_uncertainty_score":0.9993274},"labels":[],"label_agreement":null}]}