{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":13,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":13,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"73698f1fbcfb","filters":{"venue":"North American Chapter of the Association for Computational Linguistics"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Diman Ghazi","is_ca":true},{"name":"Diana Inkpen","is_ca":true},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02534671414079879,"gpt":0.288668501698871,"spread":0.2633217875580722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002664798,0.00007380701,0.0001736001,0.0001381407,0.00007758455,0.0000209075,0.00038031,0.00002904547,0.000002886509],"category_scores_gemma":[0.001580862,0.00006638785,0.0001302575,0.000471515,0.00007775667,0.00003244512,0.00006762129,0.0001341812,0.000002179648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000448473,"about_ca_system_score_gemma":0.00006767413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002405108,"about_ca_topic_score_gemma":0.0001903151,"domain_scores_codex":[0.9989487,0.00003278846,0.0003644934,0.0001634744,0.0003753347,0.0001152176],"domain_scores_gemma":[0.9976035,0.0007703701,0.000750345,0.0001975106,0.0006475846,0.00003065485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002930397,0.00009329328,0.3952119,0.000009054817,0.00008609692,9.51353e-8,0.0003667578,0.01832472,0.0001833418,0.5781938,0.0001220098,0.007379588],"study_design_scores_gemma":[0.000432101,0.00005251843,0.6953154,0.000005865254,0.00001939879,1.000061e-7,0.00001827478,0.2987667,0.00005972146,0.002987094,0.002265463,0.00007732736],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8555863,0.000005542408,0.1366052,0.00219821,0.002468443,0.0003244255,0.00008188705,0.00003644304,0.002693428],"genre_scores_gemma":[0.9622988,0.000001350326,0.0374526,0.00003612232,0.0001243035,0.000004542987,0.00003222334,0.000004982272,0.00004506378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5752068,"threshold_uncertainty_score":0.2707218,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"David Burkett","is_ca":false},{"name":"John Blitzer","is_ca":false},{"name":"Dan Klein","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007642669732457285,"gpt":0.2343343053735263,"spread":0.226691635641069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000226676,0.0001093787,0.0001741877,0.00005620256,0.0001585883,0.00007183977,0.0002992763,0.00002690999,4.846878e-7],"category_scores_gemma":[0.0008542419,0.00008109771,0.0000511225,0.0001828044,0.0001137956,0.00004240862,0.0001092002,0.0001491293,3.757055e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006801658,"about_ca_system_score_gemma":0.00007504804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004396408,"about_ca_topic_score_gemma":0.00007469571,"domain_scores_codex":[0.9990097,0.00002055376,0.0002294503,0.0001993628,0.0003878168,0.0001530623],"domain_scores_gemma":[0.998149,0.0002692064,0.0006523365,0.0001765346,0.0007073059,0.00004562457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005533053,0.0001258556,0.1206208,0.00008201815,0.0002102336,0.00000260196,0.000940157,0.004475425,0.0005842947,0.8296541,0.0003652113,0.04288399],"study_design_scores_gemma":[0.002628829,0.001099619,0.1464612,0.0002043828,0.0002786516,0.00003365638,0.00007671301,0.4090315,0.007942935,0.4141029,0.01664562,0.001493996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06499856,0.00005666547,0.9315124,0.001807817,0.0006285436,0.0004938603,0.0000545144,0.0001910552,0.0002565645],"genre_scores_gemma":[0.5894042,9.642708e-7,0.4103166,0.0001697437,0.00007315943,0.000005764095,0.000005794057,0.000006202843,0.00001756813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5244057,"threshold_uncertainty_score":0.3307069,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Florian Boudin","is_ca":true},{"name":"Jian‐Yun Nie","is_ca":true},{"name":"Martin Dawes","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01164874062539717,"gpt":0.3002182539384063,"spread":0.2885695133130092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001927905,0.00006574885,0.0001137792,0.00002041743,0.00008207496,0.00001522741,0.000095553,0.00007022386,0.000001187406],"category_scores_gemma":[0.003543131,0.0000523717,0.00006089644,0.00005518432,0.0001615165,0.000001864485,0.00005878281,0.0001074341,2.526832e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001106524,"about_ca_system_score_gemma":0.0000567186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001130685,"about_ca_topic_score_gemma":0.00002823209,"domain_scores_codex":[0.9993544,0.00002097786,0.00027228,0.00009479764,0.0001705684,0.00008700479],"domain_scores_gemma":[0.9988269,0.0001197321,0.0004771131,0.00008821514,0.0004522342,0.00003585251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001556641,0.00003137944,0.9717304,0.00002711116,0.0001744916,8.428127e-8,0.000111001,0.003273807,0.0009485829,0.004091118,0.0002650114,0.01919132],"study_design_scores_gemma":[0.001018534,0.0004261099,0.8537746,0.000009455826,0.00009880464,0.00000336081,0.00005514618,0.008628268,0.0009643257,0.003609486,0.1311687,0.0002431782],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994579,0.000008949969,0.004229115,0.0001350832,0.0007077272,0.0001098164,0.0001639805,0.00000625866,0.00006008282],"genre_scores_gemma":[0.9687084,0.000004394179,0.03052942,0.000252378,0.0003785478,4.436484e-7,0.0001026299,0.000004390262,0.00001939223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1309037,"threshold_uncertainty_score":0.4241714,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Computational linguistics; Linguistics; Natural language processing; Philosophy","authors":[{"name":"David K. Elson","is_ca":false},{"name":"Anna Kazantseva","is_ca":true},{"name":"Rada Mihalcea","is_ca":false},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01366432469359548,"gpt":0.2764200507866348,"spread":0.2627557260930394,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000463395,0.000205535,0.0002941418,0.0001105782,0.0002672459,0.00008283349,0.0009280883,0.00008194349,6.710204e-7],"category_scores_gemma":[0.008636238,0.0001473316,0.0002555181,0.000625773,0.0001263213,0.00008117593,0.000193514,0.0002446139,8.456037e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000159846,"about_ca_system_score_gemma":0.00009802931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004488386,"about_ca_topic_score_gemma":0.000003148601,"domain_scores_codex":[0.9981674,0.0000247476,0.0005105162,0.0002454461,0.0007444789,0.000307396],"domain_scores_gemma":[0.9922282,0.0013572,0.001644561,0.0001985105,0.004505231,0.00006627072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004919029,0.0001708266,0.03629952,0.0001205016,0.0001073754,5.536129e-8,0.0009849039,0.009080155,0.00001376398,0.9463452,0.003421109,0.003407386],"study_design_scores_gemma":[0.002242126,0.0006809236,0.1248556,0.001022727,0.0004131962,0.000007849371,0.0001086507,0.1609312,0.003449406,0.5838642,0.1208853,0.001538997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02322533,0.001130586,0.9542811,0.003885317,0.008195591,0.003615421,0.001844399,0.0004993456,0.003322911],"genre_scores_gemma":[0.66379,0.000002244415,0.3348355,0.0004662669,0.000660189,0.0000227435,0.00003621147,0.00001733321,0.0001694298],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6405647,"threshold_uncertainty_score":0.9997144,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Gabriel Murray","is_ca":true},{"name":"Giuseppe Carenini","is_ca":true},{"name":"Raymond T. Ng","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06175701061134741,"gpt":0.3600102047298923,"spread":0.2982531941185449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000736804,0.0001008189,0.0001734225,0.00004015039,0.0006044991,0.00002304451,0.0001845554,0.00001626744,0.000002491917],"category_scores_gemma":[0.0006078044,0.0000785099,0.0002024761,0.0001891704,0.00006652805,0.00002974021,0.00005819265,0.0001772409,3.51554e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384882,"about_ca_system_score_gemma":0.00003737565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004003035,"about_ca_topic_score_gemma":0.00007749328,"domain_scores_codex":[0.9990666,0.0001146982,0.0002991185,0.00007689577,0.000266165,0.0001765518],"domain_scores_gemma":[0.9959802,0.001634281,0.001132159,0.0001511056,0.001075565,0.00002668036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004287469,0.0001277212,0.777732,0.00001022068,0.0003943416,2.484604e-9,0.000667951,0.1892358,0.00004158723,0.01908234,0.00004698714,0.01261812],"study_design_scores_gemma":[0.0004038053,0.0001008653,0.3911234,0.00001376879,0.0003774377,1.507543e-7,0.0005071333,0.5722824,0.000445148,0.03207947,0.002455691,0.0002107567],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4984254,0.00000507042,0.5000515,0.00004182003,0.0002654323,0.0004856278,0.0001777597,0.00002015763,0.0005272261],"genre_scores_gemma":[0.9846835,1.105043e-7,0.01440193,0.00005115696,0.0007322536,0.00003644069,0.00005993414,0.00001484594,0.00001980472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4862581,"threshold_uncertainty_score":0.464938,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Information retrieval; Philosophy","authors":[{"name":"Iris Hendrickx","is_ca":false},{"name":"Su Nam Kim","is_ca":false},{"name":"Zornitsa Kozareva","is_ca":false},{"name":"Preslav Nakov","is_ca":false},{"name":"Diarmuid Ó Séaghdha","is_ca":false},{"name":"Sebastian PadÃ","is_ca":false},{"name":"Marco Pennacchiotti","is_ca":false},{"name":"Lorenza Romano","is_ca":false},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02596209898882572,"gpt":0.29546025094887,"spread":0.2694981519600443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003477318,0.0001012593,0.0002726073,0.0001301953,0.00008363871,0.0000142093,0.0005281413,0.00004192965,5.537793e-7],"category_scores_gemma":[0.002464917,0.00008902499,0.0001391237,0.0004448272,0.00008453073,0.00005273033,0.00005405291,0.0000978185,6.729628e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008482057,"about_ca_system_score_gemma":0.00007819538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002836024,"about_ca_topic_score_gemma":0.00001205852,"domain_scores_codex":[0.998664,0.00004998472,0.0005809071,0.0001721828,0.0004136857,0.0001192878],"domain_scores_gemma":[0.9954229,0.0006823486,0.001977256,0.0002377424,0.001650631,0.0000291338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002115957,0.0002386022,0.7143742,0.00008458379,0.0001489902,2.117778e-7,0.001028154,0.01018436,0.0006912181,0.2482469,0.0001952357,0.02478644],"study_design_scores_gemma":[0.0002445334,0.0001587891,0.8854781,0.00004824509,0.00006234533,2.543144e-7,0.00001442623,0.08230738,0.001626843,0.02976347,0.0001656807,0.000129964],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04621384,0.00006410139,0.9520179,0.0008048891,0.0001490604,0.0003356279,0.0001496824,0.00007497952,0.0001899049],"genre_scores_gemma":[0.6467366,9.125915e-7,0.3531222,0.00003741612,0.00004348227,0.000002434547,0.00002300227,0.000004381746,0.0000296063],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6005228,"threshold_uncertainty_score":0.3630334,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Ramanjot Singh Bhatia","is_ca":true},{"name":"Amber Graystone","is_ca":true},{"name":"Ross A. Davies","is_ca":true},{"name":"Susan McClinton","is_ca":true},{"name":"Jason Morín","is_ca":true},{"name":"Richard F. Davies","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009028242911674093,"gpt":0.255037806892002,"spread":0.2460095639803279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0002157832,0.00008329442,0.000149393,0.00003028148,0.00009028595,0.00001880651,0.0001549224,0.0000616957,4.005574e-7],"category_scores_gemma":[0.01372511,0.00007546988,0.00009852653,0.0000701847,0.00006937022,0.000003281229,0.00004947325,0.00009401276,2.882298e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000194662,"about_ca_system_score_gemma":0.00006551915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001152563,"about_ca_topic_score_gemma":0.0005821934,"domain_scores_codex":[0.9992209,0.00001452607,0.0003349217,0.0001282113,0.0001665242,0.0001349049],"domain_scores_gemma":[0.998082,0.0004985728,0.0007354848,0.000144775,0.0005197889,0.00001939668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004112443,0.00005511976,0.9343342,0.00002520196,0.0001296801,2.152343e-7,0.0003027995,0.01350182,0.006632323,0.0006727816,0.000465143,0.04383966],"study_design_scores_gemma":[0.002023245,0.0004740887,0.7969572,0.0000531345,0.0001386691,0.000001349498,0.0003507157,0.1019098,0.01565224,0.00514425,0.07668953,0.0006058112],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810464,0.00001087315,0.01713736,0.0003285475,0.0006218725,0.0002012088,0.0005273027,0.00001104822,0.0001154286],"genre_scores_gemma":[0.938439,0.000001208454,0.06006387,0.0002406996,0.0005781561,0.00002490005,0.000630106,0.000008148598,0.00001397585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.137377,"threshold_uncertainty_score":0.9945827,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Frank Rudzicz","is_ca":true},{"name":"Rozanne Wilson","is_ca":true},{"name":"Alex Mihailidis","is_ca":true},{"name":"Elizabeth Rochon","is_ca":true},{"name":"Carol Léonard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02078250978325165,"gpt":0.2659044236375044,"spread":0.2451219138542528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003685721,0.0001479181,0.000261403,0.00006776617,0.0002667268,0.00009505428,0.0005790563,0.00002798068,2.975705e-7],"category_scores_gemma":[0.0006402702,0.0001194348,0.0001653891,0.0001911271,0.00008735109,0.0001265458,0.00008698906,0.00005136809,9.946031e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008348758,"about_ca_system_score_gemma":0.000194078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000369482,"about_ca_topic_score_gemma":0.00003033476,"domain_scores_codex":[0.998769,0.0000562166,0.000340205,0.0001906262,0.0003677609,0.0002761526],"domain_scores_gemma":[0.9958605,0.001326937,0.001000087,0.0003222635,0.0013827,0.0001075447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002503963,0.0002398776,0.1801649,0.0001195022,0.0005772322,1.163233e-7,0.002616252,0.03537723,0.000003649752,0.7752524,0.001635295,0.003763156],"study_design_scores_gemma":[0.007563221,0.001015472,0.435994,0.000138755,0.0007613279,0.000003890589,0.000566966,0.2732535,0.0001126726,0.08547691,0.193861,0.00125219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01417946,0.0001121718,0.9816067,0.000558527,0.0007063977,0.00153261,0.0009877022,0.00007090374,0.0002455631],"genre_scores_gemma":[0.7959328,0.000001341165,0.2031209,0.0002200705,0.0002914451,0.0001500007,0.0002431123,0.00001407307,0.00002627046],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7817534,"threshold_uncertainty_score":0.487041,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Adaptation (eye); Search engine; Control (management); Information retrieval; Artificial intelligence; Psychology","authors":[{"name":"Ruiqiang Zhang","is_ca":false},{"name":"Yi Chang","is_ca":false},{"name":"Zhaohui Zheng","is_ca":false},{"name":"Donald Metzler","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01031049870942268,"gpt":0.239400819674497,"spread":0.2290903209650743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003345097,0.0001228849,0.0002521649,0.00007688611,0.0001543493,0.00004419843,0.0003288522,0.00002743368,7.499909e-7],"category_scores_gemma":[0.001131668,0.0001099649,0.0001706449,0.0002660253,0.00003800946,0.00004801069,0.00002998274,0.00007095211,0.000005019521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001353381,"about_ca_system_score_gemma":0.00008460398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003342112,"about_ca_topic_score_gemma":0.000007459516,"domain_scores_codex":[0.9987324,0.00005118544,0.0003306012,0.00024309,0.0004401232,0.0002025832],"domain_scores_gemma":[0.9968604,0.0009234332,0.000560779,0.0001807043,0.001420983,0.00005371868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001366858,0.000315572,0.006327548,0.00002439856,0.0006133899,4.511064e-7,0.001067519,0.832208,0.0001266938,0.04916653,0.008871918,0.1011413],"study_design_scores_gemma":[0.0006992773,0.0002664186,0.02093462,0.00001008822,0.00008400644,2.893856e-7,0.00002786342,0.9730777,0.0001506101,0.001306904,0.003293768,0.0001484311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006002708,0.00001951191,0.9903777,0.001668493,0.0002293943,0.0003783536,0.001093939,0.00004764923,0.0001822521],"genre_scores_gemma":[0.9240898,0.000002761937,0.07434479,0.0007176501,0.0002385676,0.000009939511,0.0003505881,0.000008080338,0.0002377629],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9180871,"threshold_uncertainty_score":0.448424,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Christopher Pinchak","is_ca":true},{"name":"Shane Bergsma","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01887462943214532,"gpt":0.273063253563209,"spread":0.2541886241310637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005154131,0.0001017552,0.0001747921,0.00008559194,0.0002052248,0.00005119943,0.0004273973,0.00002894889,5.721005e-7],"category_scores_gemma":[0.002997212,0.00009319215,0.0001412233,0.0002386532,0.00004246637,0.00004458523,0.00007092908,0.00007248263,0.000001206641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001504191,"about_ca_system_score_gemma":0.00008124617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001514178,"about_ca_topic_score_gemma":0.00004880448,"domain_scores_codex":[0.9989284,0.00001868788,0.000331792,0.0001994064,0.0003006539,0.0002210187],"domain_scores_gemma":[0.996637,0.001157686,0.0007023944,0.0002167825,0.001237993,0.00004808425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001312946,0.00008069375,0.07432497,0.00006223133,0.0001496999,2.814623e-7,0.0007009474,0.09911315,0.00001077049,0.7752981,0.0004327243,0.04981336],"study_design_scores_gemma":[0.0003218226,0.00006968174,0.07632068,0.00001873783,0.00003531376,7.040923e-7,0.00002252029,0.8892872,0.00003976921,0.02150062,0.01222204,0.0001608898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01663773,0.000008839805,0.9804943,0.001045399,0.00099143,0.0003599619,0.00005625777,0.00007687048,0.0003292502],"genre_scores_gemma":[0.7054478,4.80775e-7,0.2938937,0.0002589945,0.0002695752,0.00001012799,0.00001291776,0.000008383549,0.00009801461],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7901741,"threshold_uncertainty_score":0.3800265,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Alfred I. Renaud","is_ca":false},{"name":"Fraser Shein","is_ca":true},{"name":"Vivian Tsang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01283611387327251,"gpt":0.2508910349973942,"spread":0.2380549211241217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004966114,0.00009774044,0.0002118457,0.00008145581,0.00008914777,0.00004400143,0.0004503589,0.0000298496,0.000001411225],"category_scores_gemma":[0.002423397,0.00008511194,0.0001037844,0.0003418647,0.00006686992,0.00002987598,0.00009364848,0.0001402546,0.000007088249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009390009,"about_ca_system_score_gemma":0.00007220927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001763004,"about_ca_topic_score_gemma":0.0007867665,"domain_scores_codex":[0.9986594,0.00005001654,0.0004335835,0.0001942403,0.0004757794,0.000187029],"domain_scores_gemma":[0.9978114,0.0005487399,0.0006395279,0.0002399769,0.0007089904,0.00005140094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002050356,0.0001391647,0.5738457,0.00002614773,0.00004225856,4.677118e-7,0.0003267949,0.00972833,0.00003442204,0.4102695,0.0003059352,0.005260811],"study_design_scores_gemma":[0.0004534197,0.00005243469,0.8679803,0.000008520243,0.00001099664,5.570637e-7,0.00001058921,0.09070626,0.00003039937,0.03189367,0.008714848,0.0001379962],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4517892,0.00000726534,0.536243,0.002256319,0.004860328,0.001225759,0.0002454997,0.0001262511,0.003246426],"genre_scores_gemma":[0.9542439,3.79538e-7,0.04523589,0.0002225377,0.0002101369,0.00001802755,0.00003561027,0.000006026038,0.0000275092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5024547,"threshold_uncertainty_score":0.3470764,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Laura Alonso Alemany","is_ca":false},{"name":"Gabriel Infante-López","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02033526140629643,"gpt":0.2892357441993217,"spread":0.2689004827930253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004383471,0.0002231975,0.0003161988,0.0001220334,0.0003907385,0.0001114894,0.002009471,0.00007511907,0.00000509904],"category_scores_gemma":[0.01003268,0.0001983161,0.000145319,0.0004250505,0.0001769308,0.00005612113,0.0009255185,0.0003424587,0.00001073799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001566906,"about_ca_system_score_gemma":0.0002048426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003700474,"about_ca_topic_score_gemma":0.0001999634,"domain_scores_codex":[0.9976615,0.0000477047,0.0005895323,0.0004887671,0.0009054918,0.0003069528],"domain_scores_gemma":[0.9937282,0.001067045,0.001506686,0.0006899869,0.002911952,0.00009619926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002461073,0.0001350731,0.08163271,0.00004816809,0.000150161,0.000002216735,0.0002112626,0.0289745,0.00004110626,0.8810764,0.004381099,0.003322724],"study_design_scores_gemma":[0.0005571619,0.0001106647,0.03326659,0.00002734616,0.00009995099,0.00000559204,0.000007064327,0.7153351,0.0002235975,0.1393388,0.1105015,0.0005266661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02108917,0.00009612379,0.9628587,0.001558813,0.006666676,0.00106848,0.003320744,0.0006910738,0.002650205],"genre_scores_gemma":[0.5444741,0.000001045003,0.4542126,0.0002980907,0.0004749627,0.000006448403,0.0003773663,0.00001618163,0.0001392681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7417375,"threshold_uncertainty_score":0.9983062,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marie-Josée Goulet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01988773488424193,"gpt":0.3238424057267155,"spread":0.3039546708424736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008919789,0.00008414971,0.0002116824,0.0002721515,0.00008093388,0.0000203432,0.0004237854,0.00002928284,0.000001376085],"category_scores_gemma":[0.003227034,0.00007381995,0.0001503686,0.001241028,0.00004864323,0.00004651422,0.00008159491,0.00005460589,2.562658e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001750834,"about_ca_system_score_gemma":0.00006963658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004843674,"about_ca_topic_score_gemma":0.00006407699,"domain_scores_codex":[0.9984518,0.00003966277,0.0004351578,0.0001702249,0.0007798002,0.0001234013],"domain_scores_gemma":[0.995104,0.0006372508,0.001362905,0.0002007279,0.002668974,0.00002619079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003771843,0.0001436644,0.6425328,0.00002522323,0.0009290022,1.882425e-7,0.001058665,0.08612062,0.0001590794,0.2339198,0.00008498508,0.03498821],"study_design_scores_gemma":[0.000342291,0.00009870698,0.3441454,0.00001492745,0.0005915285,1.488514e-7,0.00002599698,0.6301433,0.004707769,0.01922524,0.0005109159,0.0001937479],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02920704,0.00005572589,0.9695857,0.00008836086,0.0002905144,0.0002843828,0.00005258089,0.00005123351,0.000384495],"genre_scores_gemma":[0.8030269,7.942743e-7,0.1967296,0.00009717061,0.00004525765,0.000004892941,0.0000730097,0.000004881045,0.00001742402],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7738199,"threshold_uncertainty_score":0.3863294,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}