{"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":"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":[0.014179462,0.00011217183,0.98160666,0.000558527,0.0007063977,0.0015326099,0.0009877022,0.00007090374,0.00024556307],"genre_scores_gemma":[0.7959328,0.0000013411652,0.20312087,0.00022007046,0.00029144515,0.0001500007,0.0002431123,0.000014073065,0.000026270458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99876904,0.000056216595,0.00034020498,0.00019062623,0.0003677609,0.0002761526],"domain_scores_gemma":[0.99586046,0.0013269365,0.0010000875,0.0003222635,0.0013826996,0.00010754473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036857213,0.00014791805,0.00026140295,0.000067766174,0.00026672683,0.00009505428,0.00057905633,0.000027980685,2.9757047e-7],"category_scores_gemma":[0.00064027024,0.0001194348,0.00016538911,0.00019112714,0.00008735109,0.00012654581,0.000086989065,0.000051368086,9.94603e-7],"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":[0.00025039635,0.00023987764,0.18016492,0.00011950225,0.0005772322,1.16323335e-7,0.0026162518,0.03537723,0.0000036497515,0.7752524,0.001635295,0.003763156],"study_design_scores_gemma":[0.007563221,0.0010154715,0.43599403,0.00013875497,0.00076132786,0.000003890589,0.00056696596,0.27325353,0.00011267258,0.08547691,0.19386102,0.0012521897],"about_ca_topic_score_codex":0.0000369482,"about_ca_topic_score_gemma":0.000030334759,"teacher_disagreement_score":0.78175336,"about_ca_system_score_codex":0.00008348758,"about_ca_system_score_gemma":0.00019407799,"threshold_uncertainty_score":0.48704097},"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":"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":[0.4517892,0.0000072653397,0.53624296,0.002256319,0.0048603276,0.0012257588,0.00024549974,0.00012625109,0.0032464263],"genre_scores_gemma":[0.9542439,3.7953797e-7,0.04523589,0.00022253774,0.00021013689,0.000018027547,0.000035610272,0.0000060260377,0.0000275092],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986594,0.000050016537,0.0004335835,0.00019424029,0.0004757794,0.00018702901],"domain_scores_gemma":[0.9978114,0.0005487399,0.0006395279,0.00023997686,0.0007089904,0.00005140094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004966114,0.00009774044,0.00021184573,0.00008145581,0.00008914777,0.000044001434,0.00045035893,0.000029849596,0.0000014112248],"category_scores_gemma":[0.0024233968,0.00008511194,0.00010378442,0.00034186468,0.00006686992,0.000029875982,0.00009364848,0.00014025456,0.0000070882493],"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":[0.000020503565,0.00013916467,0.5738457,0.000026147727,0.00004225856,4.677118e-7,0.0003267949,0.00972833,0.00003442204,0.4102695,0.00030593516,0.005260811],"study_design_scores_gemma":[0.00045341966,0.000052434694,0.8679803,0.000008520243,0.0000109966395,5.5706374e-7,0.0000105892095,0.09070626,0.000030399367,0.031893667,0.008714848,0.00013799623],"about_ca_topic_score_codex":0.00017630035,"about_ca_topic_score_gemma":0.00078676647,"teacher_disagreement_score":0.5024547,"about_ca_system_score_codex":0.00009390009,"about_ca_system_score_gemma":0.000072209274,"threshold_uncertainty_score":0.34707642},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06499856,0.00005666547,0.9315124,0.0018078174,0.0006285436,0.00049386034,0.0000545144,0.00019105522,0.0002565645],"genre_scores_gemma":[0.5894042,9.642708e-7,0.41031662,0.00016974373,0.000073159434,0.000005764095,0.000005794057,0.0000062028425,0.000017568125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990097,0.000020553758,0.00022945026,0.00019936281,0.00038781684,0.00015306233],"domain_scores_gemma":[0.998149,0.0002692064,0.0006523365,0.00017653457,0.00070730585,0.00004562457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022667604,0.00010937872,0.00017418772,0.000056202556,0.00015858833,0.00007183977,0.0002992763,0.000026909991,4.846878e-7],"category_scores_gemma":[0.0008542419,0.00008109771,0.0000511225,0.0001828044,0.00011379561,0.00004240862,0.00010920016,0.00014912926,3.7570547e-7],"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":[0.000055330525,0.00012585559,0.12062081,0.00008201815,0.00021023359,0.0000026019604,0.000940157,0.004475425,0.0005842947,0.8296541,0.0003652113,0.042883992],"study_design_scores_gemma":[0.0026288286,0.0010996194,0.14646125,0.00020438278,0.0002786516,0.00003365638,0.00007671301,0.4090315,0.007942935,0.41410285,0.01664562,0.0014939957],"about_ca_topic_score_codex":0.00004396408,"about_ca_topic_score_gemma":0.00007469571,"teacher_disagreement_score":0.52440566,"about_ca_system_score_codex":0.00006801658,"about_ca_system_score_gemma":0.00007504804,"threshold_uncertainty_score":0.33070686},"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":"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":[0.99457896,0.000008949969,0.004229115,0.00013508317,0.0007077272,0.000109816385,0.00016398048,0.00000625866,0.000060082824],"genre_scores_gemma":[0.9687084,0.000004394179,0.030529425,0.000252378,0.00037854785,4.4364842e-7,0.0001026299,0.0000043902623,0.000019392228],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99935436,0.000020977865,0.00027227995,0.000094797644,0.00017056835,0.00008700479],"domain_scores_gemma":[0.99882686,0.00011973211,0.00047711312,0.000088215136,0.00045223424,0.000035852507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019279047,0.00006574885,0.0001137792,0.000020417427,0.00008207496,0.000015227408,0.000095553005,0.00007022386,0.0000011874064],"category_scores_gemma":[0.0035431308,0.0000523717,0.000060896436,0.000055184322,0.00016151647,0.0000018644854,0.00005878281,0.00010743411,2.5268324e-7],"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":[0.0001556641,0.000031379437,0.9717304,0.00002711116,0.00017449164,8.428127e-8,0.000111000954,0.0032738065,0.0009485829,0.004091118,0.00026501136,0.01919132],"study_design_scores_gemma":[0.0010185342,0.0004261099,0.8537746,0.000009455826,0.00009880464,0.00000336081,0.00005514618,0.008628268,0.0009643257,0.0036094864,0.13116872,0.00024317822],"about_ca_topic_score_codex":0.000011306848,"about_ca_topic_score_gemma":0.000028232093,"teacher_disagreement_score":0.13090372,"about_ca_system_score_codex":0.000011065236,"about_ca_system_score_gemma":0.000056718603,"threshold_uncertainty_score":0.42417145},"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":"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":[0.029207043,0.000055725894,0.96958566,0.00008836086,0.00029051444,0.00028438278,0.000052580894,0.000051233506,0.000384495],"genre_scores_gemma":[0.8030269,7.9427434e-7,0.19672965,0.00009717061,0.000045257653,0.000004892941,0.0000730097,0.0000048810452,0.00001742402],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845177,0.000039662773,0.00043515782,0.00017022488,0.0007798002,0.00012340132],"domain_scores_gemma":[0.99510396,0.0006372508,0.0013629046,0.00020072788,0.0026689738,0.000026190788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008919789,0.00008414971,0.00021168242,0.00027215146,0.00008093388,0.000020343196,0.00042378542,0.000029282843,0.000001376085],"category_scores_gemma":[0.0032270337,0.00007381995,0.00015036864,0.0012410276,0.000048643225,0.000046514222,0.00008159491,0.00005460589,2.5626576e-7],"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":[0.000037718433,0.00014366441,0.6425328,0.000025223231,0.00092900224,1.8824254e-7,0.0010586653,0.08612062,0.00015907937,0.23391981,0.000084985084,0.03498821],"study_design_scores_gemma":[0.00034229096,0.00009870698,0.34414545,0.000014927449,0.0005915285,1.4885143e-7,0.000025996982,0.6301433,0.004707769,0.019225242,0.00051091594,0.00019374788],"about_ca_topic_score_codex":0.000048436745,"about_ca_topic_score_gemma":0.000064076994,"teacher_disagreement_score":0.77381986,"about_ca_system_score_codex":0.00017508336,"about_ca_system_score_gemma":0.00006963658,"threshold_uncertainty_score":0.38632938},"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":"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":[0.49842542,0.00000507042,0.5000515,0.00004182003,0.00026543235,0.00048562777,0.00017775972,0.000020157631,0.00052722613],"genre_scores_gemma":[0.9846835,1.10504274e-7,0.014401929,0.000051156963,0.0007322536,0.00003644069,0.000059934137,0.000014845945,0.000019804724],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990666,0.00011469823,0.00029911855,0.00007689577,0.000266165,0.00017655177],"domain_scores_gemma":[0.9959802,0.0016342805,0.0011321595,0.0001511056,0.0010755651,0.000026680362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000736804,0.00010081892,0.00017342254,0.00004015039,0.00060449913,0.000023044506,0.00018455538,0.000016267444,0.000002491917],"category_scores_gemma":[0.0006078044,0.000078509904,0.00020247606,0.00018917039,0.00006652805,0.000029740213,0.000058192654,0.00017724095,3.5155395e-7],"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":[0.00004287469,0.00012772123,0.777732,0.000010220683,0.00039434162,2.4846036e-9,0.000667951,0.18923584,0.00004158723,0.019082341,0.00004698714,0.01261812],"study_design_scores_gemma":[0.0004038053,0.000100865305,0.39112338,0.00001376879,0.00037743765,1.5075433e-7,0.00050713326,0.5722824,0.00044514798,0.03207947,0.0024556913,0.00021075673],"about_ca_topic_score_codex":0.0004003035,"about_ca_topic_score_gemma":0.00007749328,"teacher_disagreement_score":0.4862581,"about_ca_system_score_codex":0.00013848822,"about_ca_system_score_gemma":0.00003737565,"threshold_uncertainty_score":0.46493798},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016637733,0.000008839805,0.98049426,0.0010453988,0.00099143,0.00035996188,0.000056257773,0.00007687048,0.00032925024],"genre_scores_gemma":[0.7054478,4.80775e-7,0.2938937,0.0002589945,0.00026957516,0.000010127986,0.000012917759,0.000008383549,0.000098014614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989284,0.000018687884,0.00033179202,0.00019940638,0.00030065386,0.00022101874],"domain_scores_gemma":[0.99663705,0.0011576855,0.0007023944,0.00021678253,0.0012379935,0.000048084246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005154131,0.00010175524,0.00017479208,0.00008559194,0.00020522476,0.000051199426,0.00042739732,0.000028948889,5.721005e-7],"category_scores_gemma":[0.0029972123,0.00009319215,0.00014122328,0.0002386532,0.000042466374,0.00004458523,0.00007092908,0.00007248263,0.0000012066413],"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":[0.00001312946,0.000080693746,0.074324965,0.00006223133,0.00014969986,2.814623e-7,0.00070094736,0.09911315,0.000010770486,0.77529806,0.00043272428,0.04981336],"study_design_scores_gemma":[0.0003218226,0.00006968174,0.07632068,0.000018737828,0.000035313762,7.0409226e-7,0.00002252029,0.88928723,0.000039769206,0.021500623,0.012222038,0.00016088982],"about_ca_topic_score_codex":0.000015141778,"about_ca_topic_score_gemma":0.00004880448,"teacher_disagreement_score":0.79017407,"about_ca_system_score_codex":0.00015041909,"about_ca_system_score_gemma":0.000081246166,"threshold_uncertainty_score":0.38002655},"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":"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":[0.9810464,0.00001087315,0.017137358,0.00032854747,0.00062187255,0.00020120876,0.0005273027,0.000011048215,0.000115428615],"genre_scores_gemma":[0.93843895,0.0000012084543,0.060063865,0.00024069959,0.00057815615,0.000024900053,0.00063010596,0.000008148598,0.000013975851],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992209,0.000014526067,0.00033492167,0.00012821132,0.00016652423,0.00013490488],"domain_scores_gemma":[0.998082,0.00049857283,0.00073548476,0.00014477497,0.0005197889,0.000019396684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00021578325,0.00008329442,0.00014939303,0.000030281477,0.00009028595,0.00001880651,0.00015492237,0.000061695704,4.005574e-7],"category_scores_gemma":[0.013725107,0.000075469885,0.00009852653,0.0000701847,0.00006937022,0.000003281229,0.000049473252,0.000094012765,2.882298e-7],"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":[0.000041124425,0.000055119755,0.93433416,0.000025201958,0.00012968013,2.152343e-7,0.00030279948,0.013501817,0.006632323,0.0006727816,0.00046514304,0.043839656],"study_design_scores_gemma":[0.0020232447,0.0004740887,0.7969572,0.000053134503,0.00013866906,0.000001349498,0.00035071568,0.10190979,0.015652245,0.0051442496,0.076689534,0.0006058112],"about_ca_topic_score_codex":0.00011525626,"about_ca_topic_score_gemma":0.0005821934,"teacher_disagreement_score":0.13737696,"about_ca_system_score_codex":0.000019466199,"about_ca_system_score_gemma":0.000065519154,"threshold_uncertainty_score":0.9945827},"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":"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":[0.046213835,0.00006410139,0.9520179,0.0008048891,0.00014906036,0.0003356279,0.00014968238,0.00007497952,0.0001899049],"genre_scores_gemma":[0.6467366,9.125915e-7,0.35312217,0.000037416125,0.000043482272,0.0000024345466,0.000023002269,0.0000043817463,0.000029606304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99866396,0.000049984716,0.0005809071,0.00017218283,0.00041368572,0.00011928776],"domain_scores_gemma":[0.9954229,0.0006823486,0.001977256,0.00023774238,0.0016506312,0.000029133798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003477318,0.00010125927,0.00027260726,0.00013019535,0.00008363871,0.000014209302,0.00052814133,0.00004192965,5.5377933e-7],"category_scores_gemma":[0.0024649168,0.000089024994,0.00013912375,0.00044482722,0.00008453073,0.000052730335,0.000054052907,0.0000978185,6.7296276e-7],"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":[0.000021159572,0.0002386022,0.7143742,0.00008458379,0.00014899022,2.1177776e-7,0.0010281543,0.010184355,0.0006912181,0.24824688,0.0001952357,0.024786435],"study_design_scores_gemma":[0.00024453335,0.00015878909,0.8854781,0.000048245085,0.00006234533,2.5431436e-7,0.000014426234,0.08230738,0.0016268435,0.029763466,0.00016568073,0.00012996396],"about_ca_topic_score_codex":0.000028360244,"about_ca_topic_score_gemma":0.000012058523,"teacher_disagreement_score":0.60052276,"about_ca_system_score_codex":0.00008482057,"about_ca_system_score_gemma":0.00007819538,"threshold_uncertainty_score":0.36303338},"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":"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":[0.023225328,0.0011305863,0.9542811,0.0038853171,0.008195591,0.0036154205,0.0018443995,0.0004993456,0.0033229114],"genre_scores_gemma":[0.66379005,0.0000022444146,0.33483553,0.00046626688,0.00066018896,0.000022743503,0.000036211466,0.000017333214,0.00016942975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981674,0.000024747598,0.0005105162,0.00024544608,0.0007444789,0.00030739597],"domain_scores_gemma":[0.9922282,0.0013571997,0.0016445608,0.00019851049,0.004505231,0.000066270724],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00046339503,0.00020553496,0.0002941418,0.00011057822,0.0002672459,0.00008283349,0.00092808827,0.00008194349,6.7102036e-7],"category_scores_gemma":[0.008636238,0.00014733164,0.00025551807,0.000625773,0.00012632126,0.00008117593,0.00019351403,0.00024461394,8.4560367e-7],"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":[0.000049190287,0.00017082656,0.036299523,0.00012050164,0.00010737543,5.5361287e-8,0.0009849039,0.009080155,0.000013763983,0.9463452,0.0034211092,0.0034073857],"study_design_scores_gemma":[0.0022421263,0.0006809236,0.124855556,0.001022727,0.00041319616,0.000007849371,0.000108650675,0.16093117,0.003449406,0.58386415,0.12088526,0.0015389968],"about_ca_topic_score_codex":0.000004488386,"about_ca_topic_score_gemma":0.0000031486013,"teacher_disagreement_score":0.64056474,"about_ca_system_score_codex":0.00015984598,"about_ca_system_score_gemma":0.00009802931,"threshold_uncertainty_score":0.99971443},"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":"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":[0.85558635,0.0000055424075,0.13660525,0.0021982105,0.0024684428,0.00032442555,0.000081887054,0.000036443038,0.0026934282],"genre_scores_gemma":[0.9622988,0.0000013503255,0.0374526,0.000036122317,0.00012430354,0.0000045429865,0.000032223343,0.0000049822715,0.000045063778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9989487,0.00003278846,0.00036449343,0.00016347444,0.0003753347,0.00011521764],"domain_scores_gemma":[0.99760354,0.0007703701,0.000750345,0.00019751056,0.00064758456,0.00003065485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026647976,0.00007380701,0.00017360006,0.00013814069,0.000077584555,0.000020907495,0.00038031003,0.000029045468,0.000002886509],"category_scores_gemma":[0.0015808615,0.00006638785,0.00013025745,0.00047151497,0.00007775667,0.000032445118,0.000067621295,0.00013418117,0.0000021796482],"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":[0.000029303967,0.00009329328,0.3952119,0.000009054817,0.000086096916,9.51353e-8,0.00036675783,0.018324716,0.0001833418,0.57819384,0.00012200984,0.0073795877],"study_design_scores_gemma":[0.000432101,0.000052518433,0.6953154,0.000005865254,0.00001939879,1.0000608e-7,0.000018274784,0.29876673,0.000059721457,0.0029870935,0.002265463,0.000077327364],"about_ca_topic_score_codex":0.000024051084,"about_ca_topic_score_gemma":0.00019031507,"teacher_disagreement_score":0.57520676,"about_ca_system_score_codex":0.0000448473,"about_ca_system_score_gemma":0.00006767413,"threshold_uncertainty_score":0.27072182},"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":"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":[0.02108917,0.00009612379,0.96285874,0.0015588133,0.006666676,0.0010684803,0.0033207438,0.0006910738,0.0026502053],"genre_scores_gemma":[0.54447407,0.0000010450032,0.4542126,0.00029809072,0.0004749627,0.000006448403,0.0003773663,0.000016181628,0.0001392681],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766153,0.0000477047,0.0005895323,0.0004887671,0.0009054918,0.00030695283],"domain_scores_gemma":[0.99372816,0.0010670447,0.0015066855,0.0006899869,0.0029119523,0.00009619926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00043834714,0.00022319754,0.0003161988,0.000122033365,0.0003907385,0.0001114894,0.0020094714,0.00007511907,0.00000509904],"category_scores_gemma":[0.010032679,0.00019831608,0.00014531905,0.00042505047,0.00017693076,0.000056121135,0.0009255185,0.00034245866,0.00001073799],"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":[0.00002461073,0.00013507306,0.08163271,0.00004816809,0.00015016095,0.0000022167346,0.00021126258,0.028974496,0.000041106257,0.8810764,0.004381099,0.0033227245],"study_design_scores_gemma":[0.0005571619,0.00011066472,0.033266593,0.000027346161,0.000099950994,0.0000055920405,0.0000070643273,0.7153351,0.00022359754,0.1393388,0.11050145,0.0005266661],"about_ca_topic_score_codex":0.000037004742,"about_ca_topic_score_gemma":0.00019996337,"teacher_disagreement_score":0.74173754,"about_ca_system_score_codex":0.0001566906,"about_ca_system_score_gemma":0.00020484258,"threshold_uncertainty_score":0.9983062},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006002708,0.000019511914,0.9903777,0.0016684935,0.00022939425,0.00037835358,0.0010939391,0.000047649228,0.00018225213],"genre_scores_gemma":[0.92408985,0.000002761937,0.07434479,0.00071765005,0.00023856756,0.000009939511,0.00035058815,0.000008080338,0.00023776291],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987324,0.000051185438,0.00033060124,0.00024308999,0.0004401232,0.00020258321],"domain_scores_gemma":[0.9968604,0.0009234332,0.000560779,0.00018070426,0.0014209832,0.00005371868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003345097,0.00012288487,0.0002521649,0.00007688611,0.00015434927,0.000044198427,0.0003288522,0.000027433683,7.4999093e-7],"category_scores_gemma":[0.001131668,0.00010996493,0.00017064493,0.00026602525,0.000038009457,0.000048010686,0.000029982739,0.00007095211,0.0000050195213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013668583,0.00031557202,0.006327548,0.000024398558,0.00061338994,4.5110644e-7,0.0010675194,0.83220804,0.00012669382,0.04916653,0.008871918,0.10114127],"study_design_scores_gemma":[0.00069927727,0.00026641856,0.020934625,0.000010088217,0.00008400644,2.8938555e-7,0.000027863416,0.9730777,0.00015061011,0.0013069039,0.003293768,0.00014843112],"about_ca_topic_score_codex":0.00003342112,"about_ca_topic_score_gemma":0.0000074595164,"teacher_disagreement_score":0.9180871,"about_ca_system_score_codex":0.00013533811,"about_ca_system_score_gemma":0.00008460398,"threshold_uncertainty_score":0.44842398},"labels":[],"label_agreement":null}]}