{"meta":{"query_hash":"73698f1fbcfb","filters":{"venue":"North American Chapter of the Association for Computational Linguistics"},"cohort_total":13,"direct_labels_cover":0,"predictions_cover":13,"exported":13,"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/73698f1fbcfb","api":"https://metacan.xera.ac/api/v1/cohort?venue=North+American+Chapter+of+the+Association+for+Computational+Linguistics"},"results":[{"id":"W1548457881","doi":"","title":"Communication strategies for a computerized caregiver for individuals with Alzheimer’s disease","year":2012,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","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 Ottawa; University of Toronto","funders":"","keywords":"Task (project management); Vocabulary; Computer science; Preprocessor; Confusion; Disease; Noise (video); Human–computer interaction; Speech recognition; Cognitive psychology; Artificial intelligence; Natural language processing; Machine learning; Psychology; Medicine; Linguistics","score_opus":0.020782509783251652,"score_gpt":0.26590442363750444,"score_spread":0.24512191385425278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1548457881","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":[0.7176696,0.0016533086,0.22306518,0.008952122,0.00039325698,0.0009139349,0.0006402456,0.0069639026,0.039748505],"genre_scores_gemma":[0.8126693,0.0005618527,0.17144142,0.0008371808,0.0000740673,0.00025885948,0.0004626174,0.00022285842,0.013471848],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995165,0.00028898168,0.00003669245,0.00007756297,0.00004512121,0.000035063975],"domain_scores_gemma":[0.99895835,0.0005282649,0.000097335986,0.00013066374,0.0001980899,0.00008733641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010962695,0.00087422354,0.00027776312,0.0005016558,0.0012279032,0.0010527711,0.0007139011,0.0008345641,0.008433843],"category_scores_gemma":[0.005153134,0.00020367617,0.0003689011,0.0001846787,0.00044618009,0.0011778438,0.00096841366,0.00045561045,0.0030043856],"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":[0.0006247422,0.00093247753,0.045987893,0.0005418925,0.00005354832,0.0068379804,0.038491514,0.0029647008,0.04191914,0.01024564,0.049048375,0.8023522],"study_design_scores_gemma":[0.0008307477,0.0033798106,0.092969686,0.0016883232,0.0007879833,0.04103044,0.14544542,0.16219136,0.11246584,0.07832266,0.36001378,0.00087393896],"about_ca_topic_score_codex":0.0013620121,"about_ca_topic_score_gemma":0.0027175636,"teacher_disagreement_score":0.008433843,"about_ca_system_score_codex":0.0003463926,"about_ca_system_score_gemma":0.00077406986,"threshold_uncertainty_score":0.028214037},"labels":[],"label_agreement":null},{"id":"W1714170610","doi":"","title":"Grammaticality Judgement in a Word Completion Task","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital","funders":"","keywords":"Computer science; Grammaticality; Natural language processing; Syntax; Word (group theory); Judgement; Task (project management); Artificial intelligence; Usability; Grammar; Linguistics; Human–computer interaction","score_opus":0.01283611387327251,"score_gpt":0.25089103499739424,"score_spread":0.23805492112412172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1714170610","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":[0.9473209,0.00025207302,0.03981339,0.00017414858,0.00011883253,0.0005500945,0.000222705,0.00065532036,0.010892656],"genre_scores_gemma":[0.9675627,0.00010810917,0.02829005,0.00026719563,0.000063355605,0.0003266263,0.0005551292,0.00034629594,0.0024806063],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9870432,0.00681073,0.0007986624,0.0022444385,0.0026495843,0.00045331876],"domain_scores_gemma":[0.85949045,0.11383482,0.007182461,0.0060888953,0.011709256,0.0016940515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01274541,0.0011053944,0.0008467242,0.0012599828,0.00081147766,0.002587668,0.0011697776,0.0018456453,0.0055257343],"category_scores_gemma":[0.15784132,0.00043124534,0.0005144214,0.00066065113,0.0013945252,0.0042836866,0.0018474488,0.0012265986,0.0017828362],"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":[0.005830944,0.0014676483,0.05185877,0.0026659854,0.00027190623,0.0013999665,0.086042464,0.0071014003,0.5108795,0.004433314,0.0073902407,0.32065785],"study_design_scores_gemma":[0.0013700888,0.017049443,0.5220127,0.0011230952,0.000618014,0.0060102,0.03473538,0.121696554,0.20546694,0.039016508,0.049063433,0.001837601],"about_ca_topic_score_codex":0.0017831936,"about_ca_topic_score_gemma":0.0012783641,"teacher_disagreement_score":0.01274541,"about_ca_system_score_codex":0.0005970861,"about_ca_system_score_gemma":0.0006667801,"threshold_uncertainty_score":0.067404985},"labels":[],"label_agreement":null},{"id":"W17659133","doi":"10.1017/s1481803500004127","title":"Joint Parsing and Alignment with Weakly Synchronized Grammars","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":62,"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":"Parsing; Computer science; Natural language processing; Artificial intelligence; Treebank; Word (group theory); Bottom-up parsing; Machine translation; Top-down parsing; Rule-based machine translation; Discriminative model; Speech recognition; Linguistics","score_opus":0.007642669732457285,"score_gpt":0.2343343053735263,"score_spread":0.22669163564106903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W17659133","genre_codex":"methods","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":[0.00924834,0.00035114956,0.9699931,0.00045893327,0.00013038573,0.000100419114,0.0011106922,0.009720474,0.00888657],"genre_scores_gemma":[0.20096622,0.0006552625,0.77303886,0.0002416966,0.00015204879,0.00017321463,0.0069744317,0.0046378076,0.013160364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963085,0.0015954772,0.0002378718,0.0007998294,0.0006823632,0.0003758777],"domain_scores_gemma":[0.9945398,0.00285449,0.000210426,0.0013606437,0.00090199924,0.00013268844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036321122,0.0012178981,0.001432959,0.0022436492,0.0022715773,0.004170787,0.0026073137,0.0015085111,0.008892339],"category_scores_gemma":[0.011504049,0.0015619404,0.0017667623,0.0040401206,0.0023841714,0.004769397,0.004125091,0.0023686276,0.0051763207],"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":[0.0005676992,0.00013774031,0.0024994924,0.0005544507,0.00021715063,0.00073766283,0.0016363682,0.10902376,0.013837941,0.3323434,0.044745494,0.4936989],"study_design_scores_gemma":[0.00008462347,0.000083751795,0.0014505632,0.0001008806,0.00015195676,0.00029267397,0.00036451645,0.4979049,0.018395716,0.4346687,0.046375565,0.00012613887],"about_ca_topic_score_codex":0.049614403,"about_ca_topic_score_gemma":0.089722276,"teacher_disagreement_score":0.049614403,"about_ca_system_score_codex":0.0021585175,"about_ca_system_score_gemma":0.00739217,"threshold_uncertainty_score":0.09865123},"labels":[],"label_agreement":null},{"id":"W1888011339","doi":"","title":"Clinical Information Retrieval using Document and PICO Structure","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"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; Université de Montréal","funders":"","keywords":"Information retrieval; Weighting; Computer science; Document Structure Description; Data mining; Medicine; XML; World Wide Web","score_opus":0.011648740625397166,"score_gpt":0.30021825393840634,"score_spread":0.2885695133130092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888011339","genre_codex":"methods","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":[0.09959158,0.008047386,0.86512655,0.0025978282,0.00042589995,0.0011134741,0.008850271,0.0063504893,0.007896395],"genre_scores_gemma":[0.43157056,0.002981223,0.5437069,0.00061109726,0.00067792006,0.0011779866,0.014505244,0.0004238821,0.004345237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957455,0.0013592246,0.0006999595,0.00078530255,0.0012528996,0.00015712013],"domain_scores_gemma":[0.9880932,0.0070016226,0.0013264068,0.0014231586,0.0018214962,0.00033406614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003358747,0.0009640335,0.0017973335,0.016395556,0.0011323818,0.0029326128,0.0010734331,0.0013351853,0.0026124376],"category_scores_gemma":[0.024944788,0.00062015717,0.0014417266,0.012329265,0.0008873081,0.007831783,0.0028730142,0.0010434838,0.0016897998],"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":[0.001067427,0.00033840025,0.011994122,0.0015615044,0.0003679744,0.0004783221,0.0013727028,0.028672004,0.018120792,0.036148224,0.022620823,0.87725776],"study_design_scores_gemma":[0.00036275154,0.0009802581,0.012623066,0.00043795136,0.00054618064,0.0019875797,0.0010121303,0.7502884,0.01876292,0.15061189,0.06213248,0.00025430674],"about_ca_topic_score_codex":0.0048958743,"about_ca_topic_score_gemma":0.004865097,"teacher_disagreement_score":0.016395556,"about_ca_system_score_codex":0.0017848689,"about_ca_system_score_gemma":0.0022586165,"threshold_uncertainty_score":0.017762959},"labels":[],"label_agreement":null},{"id":"W2113376122","doi":"","title":"Analysis of Summarization Evaluation Experiments","year":2007,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","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":"Université Laval","funders":"","keywords":"Automatic summarization; Computer science; Terminology; Presentation (obstetrics); Information retrieval; Focus (optics); Natural language processing; Multi-document summarization; Artificial intelligence; Data mining; Linguistics","score_opus":0.01988773488424193,"score_gpt":0.3238424057267155,"score_spread":0.3039546708424736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113376122","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":[0.9035753,0.0055488767,0.058416937,0.001237951,0.00072232843,0.0055715954,0.008591801,0.0026839525,0.013651322],"genre_scores_gemma":[0.9487934,0.0007594679,0.031649172,0.00040497942,0.00022345826,0.005344893,0.0091498615,0.000791805,0.0028829863],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8534503,0.09847936,0.015856704,0.0057684663,0.024676742,0.0017685331],"domain_scores_gemma":[0.44347715,0.44125932,0.02582361,0.021934252,0.06543244,0.0020732386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.061781432,0.0019325874,0.0019894862,0.004615422,0.0014315575,0.0028411774,0.0013103386,0.0013090151,0.0032324598],"category_scores_gemma":[0.32872027,0.0005187626,0.0013402125,0.0045381193,0.0011363697,0.0031533872,0.0016316879,0.0018365968,0.0010815241],"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":[0.033460792,0.00812998,0.07484902,0.015759567,0.0055181226,0.0007873436,0.010672129,0.03390468,0.08933765,0.009160733,0.042479377,0.6759406],"study_design_scores_gemma":[0.004653532,0.053626813,0.46463132,0.0036560334,0.007907915,0.0016996225,0.010378724,0.12220708,0.2367916,0.019008059,0.074002095,0.0014372391],"about_ca_topic_score_codex":0.0008541035,"about_ca_topic_score_gemma":0.00077109627,"teacher_disagreement_score":0.061781432,"about_ca_system_score_codex":0.0023365717,"about_ca_system_score_gemma":0.0013208418,"threshold_uncertainty_score":0.32673538},"labels":[],"label_agreement":null},{"id":"W2138392784","doi":"","title":"Using the Omega Index for Evaluating Abstractive Community Detection","year":2012,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":26,"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; University of the Fraser Valley","funders":"","keywords":"Automatic summarization; Computer science; Disjoint sets; Sentence; Artificial intelligence; Natural language processing; Cluster analysis; Metric (unit); Graph; Contrast (vision); Task (project management); Index (typography); Theoretical computer science; Mathematics; Combinatorics","score_opus":0.06175701061134741,"score_gpt":0.3600102047298923,"score_spread":0.2982531941185449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138392784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32747418,0.002780998,0.6474901,0.0006891683,0.00040954322,0.00088879,0.0031756586,0.0035188652,0.013572724],"genre_scores_gemma":[0.54874486,0.00062408077,0.44176888,0.00013823915,0.0001439685,0.0005757093,0.006019797,0.00045798146,0.0015264383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98279494,0.0055488204,0.0022597231,0.0017816416,0.007151089,0.0004637661],"domain_scores_gemma":[0.9050149,0.069121875,0.0074011395,0.0047908504,0.012001429,0.001669834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019157017,0.0017849326,0.0020268722,0.020341834,0.0019197854,0.0037222798,0.001991427,0.002832119,0.001743963],"category_scores_gemma":[0.08971703,0.00038761095,0.0012910911,0.009459052,0.0014909095,0.0079166675,0.002977448,0.0016473322,0.0008260077],"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":[0.0019906126,0.00088352157,0.092091456,0.0019425042,0.0018034593,0.00031094562,0.001844221,0.12709205,0.02315664,0.01991594,0.017611658,0.71135694],"study_design_scores_gemma":[0.00018050922,0.0018535617,0.034707326,0.0001835903,0.0003831762,0.00056913635,0.001263175,0.88263947,0.03630363,0.032464895,0.009229485,0.00022200789],"about_ca_topic_score_codex":0.00231731,"about_ca_topic_score_gemma":0.0030750379,"teacher_disagreement_score":0.020341834,"about_ca_system_score_codex":0.0017789613,"about_ca_system_score_gemma":0.0011131173,"threshold_uncertainty_score":0.10131323},"labels":[],"label_agreement":null},{"id":"W2151069987","doi":"","title":"Automatic Answer Typing for How-Questions","year":2007,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"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":"Typing; Computer science; Information retrieval; Natural language processing; World Wide Web; Artificial intelligence; Speech recognition","score_opus":0.018874629432145323,"score_gpt":0.27306325356320904,"score_spread":0.2541886241310637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151069987","genre_codex":"methods","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":[0.04636135,0.00047712625,0.8867611,0.0007287882,0.0002887681,0.0008169408,0.00785917,0.052235045,0.004471771],"genre_scores_gemma":[0.23963687,0.00029814508,0.71281034,0.00053685054,0.00029626393,0.001169139,0.031026958,0.006025112,0.008200328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99090695,0.0027055675,0.0010174768,0.0024562804,0.0023581574,0.00055556186],"domain_scores_gemma":[0.95922285,0.02327768,0.0025742117,0.006744175,0.007175687,0.0010054116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053799115,0.0017335056,0.0025430322,0.0060450835,0.0013452541,0.0038955738,0.0021722398,0.001965271,0.009997705],"category_scores_gemma":[0.041231066,0.0011131692,0.0014868262,0.0032364263,0.0009100765,0.0074116453,0.0046886196,0.0027643011,0.0071642743],"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":[0.0006932762,0.0005919515,0.037204616,0.0018172128,0.00025409862,0.0004892935,0.006998597,0.002434586,0.059408993,0.02934752,0.05858085,0.802179],"study_design_scores_gemma":[0.000242486,0.00046974336,0.03742491,0.00072972284,0.00033839763,0.0020206724,0.005355587,0.3838231,0.16976495,0.1531832,0.24612331,0.00052391266],"about_ca_topic_score_codex":0.002288708,"about_ca_topic_score_gemma":0.0037708643,"teacher_disagreement_score":0.009997705,"about_ca_system_score_codex":0.0007323854,"about_ca_system_score_gemma":0.0016771908,"threshold_uncertainty_score":0.033445597},"labels":[],"label_agreement":null},{"id":"W2251261672","doi":"","title":"Extracting Information for Generating A Diabetes Report Card from Free Text in Physicians Notes","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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":"National Research Council Canada; McMaster University; University of Ottawa","funders":"","keywords":"Text messaging; Computer science; Guideline; Diabetes mellitus; Population; Health records; Process (computing); Information retrieval; Medicine; Data mining; World Wide Web","score_opus":0.009028242911674093,"score_gpt":0.255037806892002,"score_spread":0.24600956398032792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2251261672","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19668855,0.0017342462,0.57461166,0.0036984796,0.00071177457,0.0046044127,0.16605113,0.04265761,0.009242099],"genre_scores_gemma":[0.11931767,0.00075103843,0.72792774,0.00036723402,0.00018160768,0.001056766,0.14746438,0.00043110663,0.002502471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789125,0.00043417737,0.0004339948,0.00048321608,0.0006474072,0.00011001619],"domain_scores_gemma":[0.9882108,0.007699793,0.0010785687,0.0010773316,0.00171291,0.00022067346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023044925,0.0012276412,0.0008690779,0.0071838065,0.00075960904,0.0020825537,0.0010652452,0.0014459436,0.004174344],"category_scores_gemma":[0.014562051,0.00047598657,0.0011125173,0.004019812,0.00036865677,0.002370662,0.0012264387,0.0010379906,0.0059876367],"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":[0.00082227075,0.0008147187,0.025630923,0.0016275125,0.00015307748,0.0016759452,0.0011940374,0.008630565,0.027515968,0.003515142,0.06753212,0.8608877],"study_design_scores_gemma":[0.0006826077,0.0008276475,0.07426293,0.0012860647,0.00072673534,0.003914998,0.0058106487,0.42584375,0.20952117,0.027969958,0.24874021,0.00041329858],"about_ca_topic_score_codex":0.004792041,"about_ca_topic_score_gemma":0.0053333184,"teacher_disagreement_score":0.0071838065,"about_ca_system_score_codex":0.000937253,"about_ca_system_score_gemma":0.0026357071,"threshold_uncertainty_score":0.013964593},"labels":[],"label_agreement":null},{"id":"W2792194291","doi":"","title":"Multi-way classification of semantic relations between pairs of nominals","year":2009,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Information retrieval; Philosophy","score_opus":0.025962098988825722,"score_gpt":0.29546025094887,"score_spread":0.2694981519600443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792194291","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7173652,0.002325051,0.24110505,0.001283687,0.00065659237,0.0003618425,0.009777943,0.0025874535,0.024537196],"genre_scores_gemma":[0.8806752,0.00033110922,0.10620113,0.000075080476,0.000081331535,0.00014228624,0.008176471,0.00014456538,0.00417287],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796766,0.00046024224,0.00028758228,0.00058942946,0.00049790705,0.00019727804],"domain_scores_gemma":[0.9942849,0.0024884585,0.00064647134,0.0007958736,0.0014001265,0.0003840893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017581349,0.00052011554,0.00055176823,0.005344762,0.0016304796,0.0026246782,0.0010068527,0.0012036286,0.006085287],"category_scores_gemma":[0.0070311744,0.00023782252,0.0013446682,0.002873498,0.0009417874,0.005089556,0.002098062,0.0012484405,0.0021865675],"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":[0.004125077,0.00064230204,0.13687682,0.0012360192,0.00040892628,0.0012798589,0.0043616723,0.0039723134,0.08478189,0.059603985,0.01590038,0.68681073],"study_design_scores_gemma":[0.00022087242,0.001165785,0.23310661,0.00093511457,0.001034435,0.0040039252,0.017154055,0.31689206,0.06904742,0.2690659,0.087013505,0.0003604827],"about_ca_topic_score_codex":0.0021031918,"about_ca_topic_score_gemma":0.0039110156,"teacher_disagreement_score":0.006085287,"about_ca_system_score_codex":0.0008489018,"about_ca_system_score_gemma":0.0010831269,"threshold_uncertainty_score":0.020357251},"labels":[],"label_agreement":null},{"id":"W2912796987","doi":"","title":"Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature","year":2012,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Computational linguistics; Linguistics; Natural language processing; Philosophy","score_opus":0.013664324693595478,"score_gpt":0.27642005078663484,"score_spread":0.2627557260930394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912796987","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028322754,0.05597597,0.4548256,0.17703946,0.06921454,0.0020111161,0.029367816,0.01572698,0.1675158],"genre_scores_gemma":[0.12378785,0.03218349,0.35604775,0.018458208,0.01970271,0.002128405,0.1560612,0.010332932,0.28129748],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917237,0.00498149,0.0007596897,0.0010937778,0.0011147393,0.00032658083],"domain_scores_gemma":[0.97931033,0.009439401,0.0004965748,0.0034487452,0.0048262416,0.0024786438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013547912,0.0014548351,0.002865105,0.005133531,0.004271756,0.017126212,0.0030383782,0.0026361598,0.043578554],"category_scores_gemma":[0.02383636,0.0014027153,0.0017472593,0.0036664596,0.0027719594,0.018560365,0.01110659,0.007866414,0.020914562],"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":[0.00028342305,0.00037564093,0.00085798785,0.00080442545,0.000091377246,0.0002551888,0.0027970304,0.00045963295,0.0028612255,0.03666759,0.8084598,0.14608663],"study_design_scores_gemma":[0.000077881625,0.000028841745,0.0008468859,0.0005638821,0.0000752777,0.0002777825,0.0015952263,0.003305534,0.0018745528,0.044339344,0.9469571,0.000057826834],"about_ca_topic_score_codex":0.006851045,"about_ca_topic_score_gemma":0.019111255,"teacher_disagreement_score":0.043578554,"about_ca_system_score_codex":0.003540784,"about_ca_system_score_gemma":0.007946497,"threshold_uncertainty_score":0.1457848},"labels":[],"label_agreement":null},{"id":"W30283642","doi":"10.1002/evl3.9","title":"Hierarchical versus Flat Classification of Emotions in Text","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":69,"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 Ottawa","funders":"","keywords":"Computer science; Task (project management); Polarity (international relations); Artificial intelligence; Neutrality; Hierarchical database model; Machine learning; Pattern recognition (psychology); Data mining; Natural language processing; Engineering","score_opus":0.02534671414079879,"score_gpt":0.288668501698871,"score_spread":0.2633217875580722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30283642","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.695809,0.003976427,0.090496495,0.003414454,0.0009040656,0.0013503054,0.034948155,0.004255372,0.16484576],"genre_scores_gemma":[0.9561647,0.0004670082,0.026244812,0.00023294847,0.00025926632,0.00033302364,0.009479703,0.0001742246,0.0066441875],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896455,0.00025615958,0.00013881248,0.00019775024,0.00029321993,0.00014948013],"domain_scores_gemma":[0.9960199,0.0021384289,0.0004937918,0.00026782145,0.00078272074,0.00029733047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075858366,0.00052704196,0.00030120995,0.0037434371,0.00072214514,0.0019474206,0.00054845156,0.0006245879,0.017233366],"category_scores_gemma":[0.007433729,0.00009678444,0.00036499102,0.0026034962,0.0008373816,0.003708951,0.0012157562,0.0006932634,0.004993873],"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":[0.0029948067,0.00032687275,0.08776324,0.0023406905,0.00018601307,0.0014716185,0.010511006,0.003767943,0.042926,0.036833514,0.09067166,0.7202067],"study_design_scores_gemma":[0.0001335662,0.0007669736,0.4836673,0.0012804678,0.00026050652,0.002343067,0.022473047,0.19234423,0.015144279,0.13369347,0.14765589,0.00023715611],"about_ca_topic_score_codex":0.0019637155,"about_ca_topic_score_gemma":0.00253072,"teacher_disagreement_score":0.017233366,"about_ca_system_score_codex":0.0007893389,"about_ca_system_score_gemma":0.00029936736,"threshold_uncertainty_score":0.0576514},"labels":[],"label_agreement":null},{"id":"W30536900","doi":"10.1111/risa.13248","title":"Data-driven computational linguistics at FaMAF-UNC, Argentina","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computational linguistics; Computer science; Applied linguistics; Linguistics; Language technology; Language and Communication Technologies; Natural language; Natural language processing; Data science; Philosophy","score_opus":0.02033526140629643,"score_gpt":0.28923574419932174,"score_spread":0.2689004827930253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30536900","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15314628,0.046915255,0.23508203,0.09323102,0.004262451,0.0008120768,0.08538916,0.017817825,0.36334383],"genre_scores_gemma":[0.5287258,0.019477123,0.23023011,0.0021630833,0.0010689422,0.0014509899,0.060651407,0.007401015,0.14883156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948338,0.0028256837,0.0002480086,0.0010758055,0.0007909596,0.00022571236],"domain_scores_gemma":[0.9887129,0.00753114,0.000402211,0.00091914367,0.001954317,0.0004803114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051890165,0.00067341834,0.00086794095,0.0022762485,0.002668364,0.0051373565,0.00084636884,0.0014601091,0.023013491],"category_scores_gemma":[0.015931094,0.0005345237,0.0007315933,0.0035628781,0.0016881162,0.0021104547,0.0023573348,0.0013912023,0.007413831],"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":[0.00062485976,0.00025381724,0.018244332,0.0015040992,0.00013876492,0.0013109107,0.007436552,0.01163536,0.0029849308,0.21660247,0.35053366,0.38873023],"study_design_scores_gemma":[0.00006935431,0.000040815958,0.012053675,0.0009571611,0.000027839214,0.0003126755,0.0018854038,0.026272207,0.0017803172,0.078235775,0.8783075,0.00005727051],"about_ca_topic_score_codex":0.055790715,"about_ca_topic_score_gemma":0.04460387,"teacher_disagreement_score":0.055790715,"about_ca_system_score_codex":0.006513893,"about_ca_system_score_gemma":0.007582611,"threshold_uncertainty_score":0.11093199},"labels":[],"label_agreement":null},{"id":"W99763915","doi":"","title":"Search Engine Adaptation by Feedback Control Adjustment for Time-sensitive Query","year":2009,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Adaptation (eye); Search engine; Control (management); Information retrieval; Artificial intelligence; Psychology","score_opus":0.010310498709422678,"score_gpt":0.239400819674497,"score_spread":0.2290903209650743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W99763915","genre_codex":"methods","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":[0.17270596,0.0017611545,0.79989755,0.00057153666,0.0006526272,0.00040162663,0.00031174216,0.018999329,0.0046984837],"genre_scores_gemma":[0.92518115,0.000152708,0.07098637,0.0002116561,0.00014257034,0.00010164508,0.00027534142,0.00040036353,0.0025482813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984547,0.00027840666,0.000119681834,0.0004846414,0.00046873555,0.00019381238],"domain_scores_gemma":[0.99597734,0.0017293958,0.00022095855,0.0006216256,0.0012938015,0.00015690543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020204326,0.0009272467,0.001330773,0.0011136375,0.00053460523,0.001245438,0.0018552302,0.0011194774,0.0034422886],"category_scores_gemma":[0.013864012,0.00040592847,0.0004914049,0.0010265122,0.00046145587,0.00183312,0.0009396269,0.0012660627,0.0010309485],"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":[0.0018725259,0.0013382096,0.0049124532,0.0002974466,0.00019936783,0.0002527951,0.00039209667,0.07376473,0.12476033,0.0031419045,0.012594447,0.7764737],"study_design_scores_gemma":[0.00009577196,0.00019298724,0.0024064193,0.000008428331,0.000088573746,0.00011077063,0.0000584281,0.96691185,0.026402334,0.0016809001,0.0020000713,0.000043571647],"about_ca_topic_score_codex":0.0077570155,"about_ca_topic_score_gemma":0.0059818467,"teacher_disagreement_score":0.0077570155,"about_ca_system_score_codex":0.0006733516,"about_ca_system_score_gemma":0.0011930895,"threshold_uncertainty_score":0.015423715},"labels":[],"label_agreement":null}]}