{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":61,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":61,"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"},"query_hash":"66b9019c05d7","filters":{"venue":"Computational Linguistics"}},"results":[{"id":"W2084046180","doi":"10.1162/coli_a_00049","title":"Lexicon-Based Methods for Sentiment Analysis","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3255,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto; Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentiment analysis; Lexicon; Polarity (international relations); Natural language processing; Artificial intelligence; Negation; Consistency (knowledge bases); Orientation (vector space); Word (group theory); Process (computing); Reliability (semiconductor); Linguistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08804081832030412,"gpt":0.3846883079456333,"spread":0.2966474896253292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005435326,0.0001281036,0.0002334296,0.0003497213,0.0001557757,0.00009657346,0.0004309919,0.0000398345,0.00007039191],"category_scores_gemma":[0.0004182503,0.0001282136,0.0002982249,0.0007635624,0.0000316503,0.00003038454,0.00007314403,0.00004999691,0.00001840367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003017139,"about_ca_system_score_gemma":0.0001129049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007259322,"about_ca_topic_score_gemma":8.525061e-7,"domain_scores_codex":[0.9988253,0.00007441887,0.0003494935,0.0003562106,0.0002024434,0.0001922109],"domain_scores_gemma":[0.998261,0.0005680443,0.0001736824,0.000281478,0.0006269315,0.00008890196],"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":[0.00001170726,0.0002034996,0.005020113,0.00001532085,0.0009454419,0.000003127388,0.0005394056,0.09896165,0.00001214157,0.8818005,0.0007191829,0.01176785],"study_design_scores_gemma":[0.0002372295,0.00003840878,0.002166461,0.00000414228,0.0002717913,1.809339e-7,0.000009582795,0.9514331,0.0005974901,0.04001638,0.005070553,0.0001546358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001082206,0.00006017566,0.9967714,0.00005938243,0.0006082157,0.0001052908,0.000006410642,0.00008410008,0.002196791],"genre_scores_gemma":[0.1923297,3.781972e-7,0.8070714,0.0002817824,0.0001360475,0.00001255507,0.00006766232,0.000006427489,0.00009398293],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8524715,"threshold_uncertainty_score":0.52284,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136930489","doi":"10.1162/coli.2006.32.1.13","title":"Evaluating WordNet-based Measures of Lexical Semantic Relatedness","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1414,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"University of Toronto; University of Pennsylvania","keywords":"WordNet; Computer science; Semantic similarity; Natural language processing; Spelling; Artificial intelligence; Lexical database; Proxy (statistics); Similarity (geometry); Information retrieval; Measure (data warehouse); Linguistics; Machine learning; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.0587311279945921,"gpt":0.346960390515805,"spread":0.2882292625212128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004399797,0.0001279066,0.0001731069,0.000137932,0.0001045932,0.00007501498,0.0005196149,0.00007948533,0.000003718006],"category_scores_gemma":[0.001939885,0.0001230849,0.00005784373,0.0004018311,0.000084574,0.00003954266,0.00009851288,0.0001719385,0.000006008797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004478522,"about_ca_system_score_gemma":0.0002521246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003983629,"about_ca_topic_score_gemma":0.000002348397,"domain_scores_codex":[0.9984685,0.00007507822,0.0003981639,0.0002661726,0.0006191061,0.0001729418],"domain_scores_gemma":[0.9979158,0.0004566876,0.0002114476,0.0002274755,0.001149956,0.000038649],"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":[0.00001295665,0.0001373636,0.0007909734,0.00009430487,0.00001216839,0.0000272806,0.00006982309,0.1970885,0.0004811645,0.7902249,0.0006374067,0.01042317],"study_design_scores_gemma":[0.0001716767,0.00004543959,0.000435134,0.00008290158,0.00001011821,0.000003556346,0.000001052018,0.6532295,0.002272144,0.3434329,0.000193309,0.000122343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003044746,0.0008110262,0.9944451,0.0001129638,0.000358652,0.0000950504,0.000004088096,0.0003451139,0.0007832989],"genre_scores_gemma":[0.514506,1.704581e-7,0.4852756,0.00005659012,0.0001175206,0.000002163964,0.00001616254,0.000006224696,0.00001956101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5114613,"threshold_uncertainty_score":0.5019257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119168550","doi":"10.1162/0891201042544884","title":"The Alignment Template Approach to Statistical Machine Translation","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":933,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; NIST; Machine translation; Evaluation of machine translation; Natural language processing; Example-based machine translation; Artificial intelligence; Phrase; Machine translation software usability; Generalization; Transfer-based machine translation; Translation (biology); Task (project management); Context (archaeology); Feature (linguistics); Rule-based machine translation; Word (group theory); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02186480999394037,"gpt":0.2953628508639949,"spread":0.2734980408700545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002760893,0.0001209329,0.00009473804,0.00005579262,0.0003183471,0.0002380573,0.0005850637,0.00003925607,8.468202e-7],"category_scores_gemma":[0.0005605682,0.00009054558,0.00002685898,0.0002413265,0.00004955983,0.00003782843,0.0001030058,0.0001413132,0.00002181112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008865212,"about_ca_system_score_gemma":0.0001110723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001634068,"about_ca_topic_score_gemma":0.000002304735,"domain_scores_codex":[0.9988167,0.00003302265,0.0002493903,0.0002702501,0.0004276061,0.0002029738],"domain_scores_gemma":[0.9990401,0.0003185213,0.00006042736,0.000215184,0.0002676411,0.00009815669],"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":[0.000005691914,0.00004315557,0.000005760887,0.000008354309,0.000007212757,0.000005883958,0.0002410624,0.0401843,0.000009316496,0.9418948,0.0003566287,0.01723787],"study_design_scores_gemma":[0.0002169871,0.00005442309,0.0001234103,0.00001609617,0.000006033273,0.00001470499,0.000004850746,0.2367818,0.0001639628,0.751429,0.01102459,0.000164213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001964043,0.0006075578,0.9957199,0.0007919773,0.0003040493,0.0001933828,0.00001904406,0.0002665497,0.002077964],"genre_scores_gemma":[0.3559318,0.000001797003,0.6435779,0.0003137761,0.0001092379,0.00001079087,0.0000333517,0.000006764776,0.00001450781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3559122,"threshold_uncertainty_score":0.3692342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051593977","doi":"10.1162/coli_a_00002","title":"Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":302,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Paraphrase; Computer science; Natural language processing; Task (project management); Artificial intelligence; Parallel corpora; Field (mathematics); Linguistics; Machine translation","retraction":null,"screen_n_in":null,"score":{"opus":0.06410955906269462,"gpt":0.401568733933962,"spread":0.3374591748712674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009106915,0.0001117199,0.0001713811,0.00008992578,0.000100893,0.0001286425,0.0008560031,0.00006489684,0.000003132662],"category_scores_gemma":[0.005156851,0.0001068044,0.00001775721,0.0002381548,0.0001128469,0.0001109758,0.00068984,0.000231343,9.01996e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005324181,"about_ca_system_score_gemma":0.0001478878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001245521,"about_ca_topic_score_gemma":0.00004658329,"domain_scores_codex":[0.9988407,0.0001435012,0.0002994914,0.00035194,0.0002324453,0.0001319322],"domain_scores_gemma":[0.9975768,0.0009368802,0.0001897044,0.0004174549,0.0008149914,0.00006417209],"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":[0.00004246154,0.0003656923,0.02046316,0.0002783426,0.0001873026,0.0000777918,0.001038516,0.0102211,0.02072168,0.6539841,0.002883636,0.2897362],"study_design_scores_gemma":[0.0001219476,0.00002117768,0.002478539,0.00001437184,0.000009153549,0.00001527037,0.000002057794,0.9685342,0.0007929353,0.02763526,0.0002445883,0.0001305059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008246019,0.0003009305,0.9905028,0.00002681942,0.0005927841,0.00007031312,0.00008251968,0.0001313574,0.00004646146],"genre_scores_gemma":[0.377103,0.000001573377,0.6225455,0.00005735033,0.0001508638,0.000001034156,0.0001318797,0.000005648833,0.000003121746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9583131,"threshold_uncertainty_score":0.6173605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978620866","doi":"10.1162/coli.2008.34.2.145","title":"Semantic Role Labeling: An Introduction to the Special Issue","year":2008,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); Field (mathematics); Computational linguistics; Identification (biology); Computational model; Semantic role labeling; Artificial intelligence; Natural language processing; Data science; Key (lock); Semantics (computer science)","retraction":null,"screen_n_in":null,"score":{"opus":0.01392567728635698,"gpt":0.2788210233112759,"spread":0.2648953460249189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000217046,0.0001162558,0.0001043644,0.00009589627,0.0003822539,0.0001290599,0.0007736772,0.00004403409,0.0000186028],"category_scores_gemma":[0.001354275,0.00009377892,0.00002753405,0.0004030199,0.00005003763,0.00008391099,0.0001822402,0.0001779516,0.0001157377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004534355,"about_ca_system_score_gemma":0.0001056922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001175942,"about_ca_topic_score_gemma":0.000005355355,"domain_scores_codex":[0.9988614,0.00004927093,0.0002040722,0.0003334077,0.0003739664,0.0001778591],"domain_scores_gemma":[0.9987004,0.00009517739,0.0000714055,0.0003493384,0.0007008999,0.00008276167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001744407,0.0001612763,0.0002049295,0.00001815752,0.00001884791,0.00006771398,0.004287712,0.0540949,0.0001543782,0.7577237,0.1502345,0.03301639],"study_design_scores_gemma":[0.0001275605,0.0001353811,0.0003566821,0.00001222349,0.000008932961,0.0001145883,0.00002793166,0.2639326,0.001069882,0.209212,0.5247016,0.0003005831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001207295,0.0002320233,0.9876962,0.006540583,0.002707141,0.0001888848,0.000004820558,0.0005171378,0.0009058755],"genre_scores_gemma":[0.2151729,0.000002049423,0.7504694,0.0009916762,0.0330867,0.000005657058,0.00002452695,0.00001116526,0.0002358862],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5485117,"threshold_uncertainty_score":0.3824193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092527610","doi":"10.1162/089120102760173625","title":"Near-Synonymy and Lexical Choice","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":258,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Denotation (semiotics); Artificial intelligence; Context (archaeology); Lexicon; Lexical choice; Set (abstract data type); Selection (genetic algorithm); Lexical semantics; Ontology; Lexical item; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02487434097093336,"gpt":0.2844013043204678,"spread":0.2595269633495345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008147283,0.00009711654,0.00009454362,0.00004343636,0.0001660164,0.0002543552,0.000346433,0.00005284006,0.00001565882],"category_scores_gemma":[0.001388414,0.00009360576,0.00002055543,0.0001755878,0.00007182589,0.00006100869,0.0001816476,0.000152592,0.00003188372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001978699,"about_ca_system_score_gemma":0.00002290535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004117956,"about_ca_topic_score_gemma":7.84477e-7,"domain_scores_codex":[0.9992155,0.00002122591,0.0001491435,0.0002421996,0.0002251996,0.0001467707],"domain_scores_gemma":[0.9991345,0.000311794,0.00005344331,0.0001504496,0.0002694555,0.00008033056],"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":[0.000001260606,0.00006258654,0.0008228436,0.00003228877,0.00001010367,0.0000446527,0.0003137041,0.001115144,0.00001030719,0.9567891,0.006195815,0.03460224],"study_design_scores_gemma":[0.0001139283,0.00003095228,0.0004842757,0.00001872054,0.000003580005,0.00002436342,8.26975e-7,0.7646385,0.00004197348,0.203032,0.03146802,0.0001428124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001408552,0.002171738,0.9914245,0.0006884438,0.0003626679,0.00007377549,0.000005211758,0.0005450177,0.003320078],"genre_scores_gemma":[0.4591157,0.000003348942,0.5402219,0.0003835908,0.0001840797,0.000001611671,0.000002719659,0.000004560212,0.00008254185],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7635234,"threshold_uncertainty_score":0.3817132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164948578","doi":"10.1162/089120103321337458","title":"Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":257,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Word (group theory); Task (project management); Machine translation; Vocabulary; Beam search; Word error rate; Sentence; Translation (biology); Artificial intelligence; Natural language processing; Dynamic programming; Search algorithm; Speech recognition; Set (abstract data type); Algorithm; Linguistics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01830414375166094,"gpt":0.319656416215049,"spread":0.3013522724633881,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000360497,0.0001276742,0.0001313179,0.0001035874,0.0001934615,0.0001993635,0.0001915057,0.00005628932,0.000001686864],"category_scores_gemma":[0.0008416311,0.0001309318,0.00002459237,0.0002009559,0.00006134166,0.00005973696,0.00004471504,0.0001579332,9.862298e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004220701,"about_ca_system_score_gemma":0.000100681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005340537,"about_ca_topic_score_gemma":0.000002412773,"domain_scores_codex":[0.9989419,0.00003841783,0.0002255324,0.0003199161,0.0002463447,0.0002278759],"domain_scores_gemma":[0.9987721,0.0005896285,0.00005355659,0.0001143339,0.0003923052,0.00007808103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003461803,0.00003361582,0.00002913849,0.00006003354,0.000009739777,0.000008815572,0.0001904209,0.0008268346,0.00001230049,0.2049632,0.00001441733,0.793848],"study_design_scores_gemma":[0.0002379481,0.00005790232,0.00004165336,0.00002582101,0.000007742315,0.00001873348,0.000006095666,0.8301212,0.00009455298,0.166341,0.002902819,0.0001445283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000749093,0.001709541,0.9973238,0.0000645002,0.0001785199,0.0002943572,0.00003061732,0.0002550227,0.00006876071],"genre_scores_gemma":[0.1729416,0.00000444744,0.8268375,0.00004869045,0.00004941965,0.00001862648,0.00007178765,0.00001334771,0.00001456124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8292944,"threshold_uncertainty_score":0.5339246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046436395","doi":"10.1162/089120100561755","title":"The Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach","year":2000,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":221,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Rhetorical question; Computer science; Automatic summarization; Parsing; Natural language processing; Artificial intelligence; Linguistics; Context (archaeology); Natural language understanding; Natural language; Philosophy; History","retraction":null,"screen_n_in":null,"score":{"opus":0.02046125002567074,"gpt":0.2820272355339836,"spread":0.2615659855083128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002481046,0.0001172433,0.0001337122,0.00004436624,0.0002388302,0.0001347886,0.0007631826,0.00006212516,0.000004278945],"category_scores_gemma":[0.0009332905,0.00008804749,0.00005214831,0.0005499513,0.0001169018,0.00003411451,0.00006191197,0.0001793188,0.000005707053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005360713,"about_ca_system_score_gemma":0.0002281131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001083225,"about_ca_topic_score_gemma":2.32954e-7,"domain_scores_codex":[0.9987621,0.00007726541,0.000309685,0.0002304776,0.0004276507,0.0001928708],"domain_scores_gemma":[0.9981668,0.0008222381,0.0001206206,0.000278872,0.000555158,0.00005632362],"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":[0.000039271,0.0002425128,0.0003138606,0.00005607863,0.00002578673,0.00001619037,0.0002059412,0.2687278,0.00004154179,0.6673367,0.002226544,0.06076775],"study_design_scores_gemma":[0.0001640213,0.00003991852,0.0001714644,0.00002880459,0.000006412219,0.000004799259,0.000002372931,0.8793194,0.0003243699,0.1135528,0.006259916,0.0001256704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001183806,0.001262976,0.994296,0.0001619985,0.0002017042,0.0001159572,0.000006106678,0.0002914435,0.002480057],"genre_scores_gemma":[0.4812593,0.000003427416,0.5185337,0.00006390238,0.00007820348,0.000001632443,0.00001112887,0.000005488559,0.00004320317],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6105916,"threshold_uncertainty_score":0.3590472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123215530","doi":"10.1162/coli.08-010-r1-07-048","title":"Unsupervised Type and Token Identification of Idiomatic Expressions","year":2009,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Atomic Energy of Canada Limited; University of Toronto","keywords":"Linguistics; Identification (biology); Interpretation (philosophy); Computer science; Natural language processing; Literal (mathematical logic); Task (project management); Context (archaeology); Security token; Artificial intelligence; Semantic property; Expression (computer science); Psychology; History","retraction":null,"screen_n_in":null,"score":{"opus":0.01564023181424613,"gpt":0.2969218139515016,"spread":0.2812815821372555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001308024,0.00006790786,0.0000956415,0.00008631039,0.00006676902,0.00006101749,0.0002943111,0.00003605475,0.000001246592],"category_scores_gemma":[0.00137965,0.00006378917,0.00001392329,0.0002907392,0.00002588565,0.00006021193,0.00006178629,0.00005905602,0.00000275502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001177222,"about_ca_system_score_gemma":0.00005857098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001357859,"about_ca_topic_score_gemma":6.684039e-8,"domain_scores_codex":[0.9993083,0.0000233598,0.000249956,0.0001517497,0.000189736,0.00007682151],"domain_scores_gemma":[0.9988797,0.0001075694,0.0001202622,0.0001696792,0.0006842895,0.00003847907],"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":[0.000006065298,0.00008136348,0.0001398941,0.00006088792,0.000008423167,0.00000693512,0.000667673,0.001302814,0.01013905,0.9691526,0.0005407694,0.01789354],"study_design_scores_gemma":[0.000119594,0.00006118437,0.003332626,0.00007009749,0.000008154714,0.000006895634,0.000008525846,0.2276384,0.006827014,0.7616497,0.0001604881,0.000117324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007569154,0.001098612,0.9902043,0.0002482025,0.0002105895,0.00009606723,0.000004030861,0.0002055377,0.0003634446],"genre_scores_gemma":[0.6096856,0.000003748404,0.3901688,0.00007969642,0.0000393273,6.443012e-7,0.000008813236,0.000002045011,0.00001132167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6021165,"threshold_uncertainty_score":0.2601247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166391512","doi":"10.1162/089120101317066122","title":"Automatic Verb Classification Based on Statistical Distributions of Argument Structure","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":199,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; National Science Foundation","keywords":"Computer science; Natural language processing; Artificial intelligence; Verb; Sentence; Argument (complex analysis); Classifier (UML); Predicate (mathematical logic)","retraction":null,"screen_n_in":null,"score":{"opus":0.01714931419756963,"gpt":0.3015708389109142,"spread":0.2844215247133445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001173393,0.0001233298,0.0001405816,0.0001126922,0.0001095446,0.00006899241,0.000416345,0.00006321901,0.00003585215],"category_scores_gemma":[0.001627695,0.0001151874,0.00003282929,0.0003335315,0.00007641276,0.00003430615,0.00005619775,0.0001524901,0.000007979969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001069874,"about_ca_system_score_gemma":0.0001756481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000347467,"about_ca_topic_score_gemma":6.768471e-7,"domain_scores_codex":[0.9987867,0.00005111873,0.000313791,0.0002465443,0.0004515106,0.000150292],"domain_scores_gemma":[0.9984072,0.0005074773,0.0001698162,0.0002826753,0.0005654882,0.00006737462],"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":[0.000006401883,0.0001142166,0.0003383942,0.00003665547,0.000007050457,0.00001318237,0.00003385678,0.007837563,0.00006380514,0.9784966,0.0007667011,0.01228562],"study_design_scores_gemma":[0.000129581,0.00006304944,0.003439865,0.00004107792,0.000007808873,0.000003726035,0.000001665462,0.7440857,0.0002930028,0.2511464,0.0006926729,0.00009544264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001280471,0.00004791232,0.9972195,0.0002598085,0.0002660084,0.0001200916,0.0001487252,0.0002496978,0.0004077714],"genre_scores_gemma":[0.5333604,4.288027e-7,0.4663011,0.00009294384,0.0000551592,0.000003060586,0.0001786023,0.000004137556,0.000004236224],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7362481,"threshold_uncertainty_score":0.4697207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1894075015","doi":"10.1162/coli_a_00226","title":"CODRA: A Novel Discriminative Framework for Rhetorical Analysis","year":2015,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":186,"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","funders":"","keywords":"Parsing; Computer science; Natural language processing; Rhetorical question; Discriminative model; Artificial intelligence; Coherence (philosophical gambling strategy); Probabilistic logic; Parse tree; Classifier (UML); Linguistics; Margin (machine learning); Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07786810095225595,"gpt":0.3751987668656995,"spread":0.2973306659134436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0002850612,0.0001381977,0.0002210264,0.0002049582,0.0001098429,0.000144605,0.0005789624,0.0000909786,0.000001244056],"category_scores_gemma":[0.008746425,0.0001271432,0.0001098638,0.0009114628,0.00005659757,0.00006395414,0.0001903908,0.0001653347,0.000005118034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001238793,"about_ca_system_score_gemma":0.0002002412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000736619,"about_ca_topic_score_gemma":0.000001277063,"domain_scores_codex":[0.9987779,0.00002330813,0.0002482608,0.0003456343,0.0004059414,0.0001989892],"domain_scores_gemma":[0.9967791,0.0008913649,0.0001454367,0.0002352279,0.001802901,0.0001459143],"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":[0.000007216363,0.00006834111,0.00008543059,0.000009544587,0.00007421607,0.000003994111,0.000514692,0.006049588,0.000001596265,0.991304,0.0008261686,0.001055194],"study_design_scores_gemma":[0.0001197383,0.0000476049,0.00006812382,0.00001057938,0.00006435032,0.000001685819,0.00001256635,0.4018248,0.00005455965,0.5952826,0.002390289,0.0001230936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003288896,0.0002923463,0.9978364,0.0003609971,0.0006130231,0.0001363196,0.00003609671,0.0003235951,0.0003683946],"genre_scores_gemma":[0.3168893,3.070712e-7,0.6824469,0.0002218898,0.0003347905,0.00001536317,0.00004798208,0.000007174288,0.00003632507],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3960215,"threshold_uncertainty_score":0.9996033,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109830295","doi":"10.1162/coli.2006.32.3.379","title":"Similarity of Semantic Relations","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"University of Waterloo; Johns Hopkins University","keywords":"Analogy; Word (group theory); Similarity (geometry); Vector space model; Semantic similarity; Relation (database); Vector space; Latent semantic analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01936146345015635,"gpt":0.2584151920057683,"spread":0.239053728555612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001170968,0.00006170789,0.00009166336,0.00006771857,0.00007290688,0.00002767917,0.000259325,0.00003413301,0.000006251223],"category_scores_gemma":[0.0004556641,0.00006803928,0.00003694312,0.0001712493,0.00003157489,0.00002872937,0.00008314009,0.00007258612,0.00001816427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002134113,"about_ca_system_score_gemma":0.00009430503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003761067,"about_ca_topic_score_gemma":0.000004292006,"domain_scores_codex":[0.99922,0.00002018527,0.0002726721,0.0001592798,0.0002299639,0.0000979187],"domain_scores_gemma":[0.9989856,0.0002443583,0.00009540632,0.0001949319,0.0004549367,0.0000247534],"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":[2.720753e-7,0.00002411432,0.002143857,0.000006058282,0.000002339051,0.000002006169,0.0000241219,0.3621563,0.000004090001,0.6350518,0.0003859306,0.0001990446],"study_design_scores_gemma":[0.00007270811,0.000006050012,0.008318843,0.000007417024,0.000003431276,0.000001485183,0.000001046764,0.6573916,0.00002503819,0.3325623,0.001560165,0.00004994178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004410035,0.00004927071,0.9820879,0.0001592082,0.000427519,0.00004784648,0.00000536725,0.00007395278,0.01273896],"genre_scores_gemma":[0.6442087,1.965164e-7,0.3554773,0.00003567867,0.0001697142,6.95541e-7,0.00001128468,0.000002717086,0.00009369986],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6397987,"threshold_uncertainty_score":0.2774561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205635927","doi":"10.1162/coli_a_00426","title":"Deep Learning for Text Style Transfer: A Survey","year":2021,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Politeness; Style (visual arts); Task (project management); Variety (cybernetics); Natural language processing; Artificial intelligence; Transfer of learning; Field (mathematics); Natural language; Deep learning; Natural (archaeology); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04084954962181789,"gpt":0.2874410351691519,"spread":0.246591485547334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003378989,0.0001014844,0.00013952,0.00004514137,0.0001848054,0.0001443874,0.0002934175,0.00004848531,0.00001037007],"category_scores_gemma":[0.003394108,0.0001181685,0.00006302074,0.0002016657,0.00001826604,0.00003152327,0.00007832192,0.000131959,0.00001784065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003258877,"about_ca_system_score_gemma":0.0002051061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009119675,"about_ca_topic_score_gemma":0.00002222858,"domain_scores_codex":[0.9988807,0.00009399404,0.000248141,0.0003412392,0.0002357902,0.0002001706],"domain_scores_gemma":[0.9976185,0.0008819739,0.00003299944,0.0001829682,0.001210768,0.00007279617],"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":[0.000004223732,0.00004010415,0.001123633,0.00002477353,0.00001385584,0.00001344981,0.0003920356,0.6917797,0.000007944066,0.2926371,0.0001084862,0.0138547],"study_design_scores_gemma":[0.0002987031,0.00002569384,0.003556689,0.00001051861,0.000005282318,0.000006139757,0.00001227179,0.9616269,0.00003631285,0.02304009,0.01124338,0.0001380258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001491908,0.0001992897,0.9961666,0.00009710382,0.0008042656,0.00008313664,0.00000777606,0.0001066492,0.001043308],"genre_scores_gemma":[0.653213,0.000002948366,0.3460503,0.0001697967,0.0002750725,0.000005896417,0.00009707687,0.000009149267,0.0001768091],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6517211,"threshold_uncertainty_score":0.4818773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412158322","doi":"10.1162/coli.a.16","title":"🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Waterloo","funders":"","keywords":"Siren (mythology); Computer science; Natural language processing; Linguistics; Art; Literature; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02578220776824297,"gpt":0.3496665190830933,"spread":0.3238843113148503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001507917,0.0001122507,0.0001340782,0.0002948351,0.0001015674,0.0001073693,0.0006095241,0.000062545,0.000002706703],"category_scores_gemma":[0.003504268,0.00009994808,0.00002362512,0.000710151,0.00001629712,0.00004315704,0.0001171469,0.0004466688,0.00000884303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001313822,"about_ca_system_score_gemma":0.0002328763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005339435,"about_ca_topic_score_gemma":0.0008635564,"domain_scores_codex":[0.9983162,0.0005008184,0.0003116855,0.0002973137,0.0003517386,0.0002221866],"domain_scores_gemma":[0.9976754,0.001657096,0.00007107719,0.0002762325,0.000295567,0.00002460444],"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":[0.000006341449,0.00007106833,0.02528556,0.00001713034,0.000001773444,0.00002082613,0.001660036,0.481504,2.47307e-8,0.4898525,0.0004173033,0.001163463],"study_design_scores_gemma":[0.0002317293,0.00002311933,0.2538013,0.00005113423,7.537183e-7,5.616411e-7,0.0000240142,0.7033906,2.863912e-7,0.0420378,0.0003756339,0.00006307061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02804944,0.0002163912,0.9579679,0.003560403,0.001026439,0.0004052241,0.00004531341,0.0001153448,0.008613486],"genre_scores_gemma":[0.9845143,0.000001727642,0.01208354,0.003111054,0.00009151656,0.000006391571,0.0001134191,0.000006146959,0.00007190397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9564649,"threshold_uncertainty_score":0.4195189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170471032","doi":"10.1162/089120103322753365","title":"Disambiguating Nouns, Verbs, and Adjectives Using Automatically Acquired Selectional Preferences","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Atomic Energy of Canada Limited","keywords":"Computer science; Adjective; Noun; Natural language processing; Verb; Artificial intelligence; Word (group theory); Heuristic; Argument (complex analysis); Part of speech; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02433043378964063,"gpt":0.3023177727749802,"spread":0.2779873389853396,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002641315,0.0001512248,0.0001494238,0.0001030137,0.0003029068,0.0002689135,0.0002674358,0.00006521814,0.000006226759],"category_scores_gemma":[0.003470494,0.000145959,0.00002796024,0.0003103642,0.00009718001,0.0001318232,0.0001034111,0.0001166221,0.000002784954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006196801,"about_ca_system_score_gemma":0.0002645136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000850012,"about_ca_topic_score_gemma":0.000001428697,"domain_scores_codex":[0.9987483,0.0000955924,0.0002668155,0.0003364497,0.000351694,0.0002011608],"domain_scores_gemma":[0.9986271,0.0004731213,0.0001333999,0.0001263743,0.0005636302,0.00007635766],"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":[0.00000391169,0.00006473531,0.001593193,0.00005599161,0.00002802257,0.00001034269,0.0005710733,0.004009889,0.0002691076,0.9876966,0.00009310671,0.005603978],"study_design_scores_gemma":[0.0001176578,0.00004001143,0.0008666211,0.00004938451,0.000009978561,0.00004213292,0.00001437149,0.5108938,0.0004758117,0.4871502,0.000164158,0.0001758929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01328516,0.0007807509,0.9839089,0.00003326331,0.000364416,0.000102787,0.00000475086,0.0003885454,0.001131423],"genre_scores_gemma":[0.4772487,0.000001642219,0.5225801,0.00006909201,0.00007779127,0.000002342885,0.000004497317,0.000005811007,0.00001002776],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5068839,"threshold_uncertainty_score":0.5952037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151552691","doi":"10.1162/089120102762671963","title":"Generating Indicative-Informative Summaries with SumUM","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Université de Montréal; McGill University","keywords":"Automatic summarization; Computer science; Identification (biology); Information retrieval; Natural language processing; Process (computing); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02829016747849478,"gpt":0.2487386652571547,"spread":0.2204484977786599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001135132,0.0001274499,0.0001239117,0.0000877924,0.000253478,0.0001886457,0.0004075291,0.00003602537,0.00001933667],"category_scores_gemma":[0.000654533,0.0001132733,0.00002388224,0.0002267813,0.0000725369,0.0001199132,0.0001336591,0.0001462152,0.00006835842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004368013,"about_ca_system_score_gemma":0.00006430297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005254433,"about_ca_topic_score_gemma":0.00000242781,"domain_scores_codex":[0.998931,0.00002962266,0.0002562515,0.00022612,0.0003588329,0.0001982077],"domain_scores_gemma":[0.998735,0.0002656161,0.0002041632,0.0002167083,0.0005020234,0.00007647874],"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":[0.000001746735,0.00003379204,0.00125175,0.00001529008,0.00002550096,0.00001622082,0.003304446,0.4440913,0.000001146957,0.5429035,0.000948429,0.007406801],"study_design_scores_gemma":[0.0001987581,0.00004074923,0.0004301332,0.0000193807,0.000004171493,0.000008989932,0.00003656173,0.9840606,0.00002149255,0.009939238,0.005083399,0.0001564733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002850376,0.00009262795,0.9837396,0.000210948,0.0003023953,0.0000890099,0.000008083615,0.0001533783,0.01255365],"genre_scores_gemma":[0.5201121,0.000001819944,0.479193,0.0003360992,0.0002297053,0.000004783177,0.00001347604,0.000005446399,0.0001035348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5399693,"threshold_uncertainty_score":0.4619151,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111856253","doi":"10.1162/coli.2007.33.1.9","title":"Word-Level Confidence Estimation for Machine Translation","year":2007,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Research Council Canada; RWTH Aachen University; European Commission","keywords":"Computer science; Word (group theory); Phrase; Machine translation; Translation (biology); Natural language processing; Artificial intelligence; Example-based machine translation; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04620772119004527,"gpt":0.3427001006526349,"spread":0.2964923794625896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005494632,0.0001153809,0.0001075705,0.0001320301,0.0001523959,0.0001143301,0.0003929661,0.00006669373,0.000002449378],"category_scores_gemma":[0.001617474,0.0001182538,0.00004288153,0.0002469255,0.00003672504,0.000100047,0.00003854632,0.0001079287,0.000006190433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004910169,"about_ca_system_score_gemma":0.00008798507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000794121,"about_ca_topic_score_gemma":0.000006598346,"domain_scores_codex":[0.9989657,0.00001337215,0.0003022729,0.0002480218,0.0002833989,0.0001871712],"domain_scores_gemma":[0.9980484,0.0008718428,0.000133166,0.000155369,0.0007313395,0.00005987742],"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":[0.00001566753,0.00002816488,0.00003019,0.00003986647,0.000006456799,0.000005545327,0.0002244146,0.00780508,0.00005665724,0.7838953,0.0002586815,0.207634],"study_design_scores_gemma":[0.0001464974,0.00002286441,0.0001820774,0.00002225256,0.000004577546,0.000005333006,0.00000149025,0.5880851,0.0007840906,0.4094072,0.001235348,0.0001031629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004404034,0.0007700111,0.9974925,0.0002064104,0.0004745378,0.0002246124,0.00002186103,0.0003890236,0.0003770116],"genre_scores_gemma":[0.4207276,6.866873e-7,0.5788585,0.0001720817,0.0001391661,0.000004504883,0.00006659253,0.000006407751,0.00002448112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5802801,"threshold_uncertainty_score":0.4822249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168801328","doi":"10.1162/089120103322711587","title":"Embedding Web-Based Statistical Translation Models in Cross-Language Information Retrieval","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Cross-language information retrieval; Machine translation; Natural language processing; Information retrieval; Artificial intelligence; Process (computing); Translation (biology); Machine translation software usability; Language model; Embedding; Example-based machine translation; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01959166820152231,"gpt":0.3257819259314265,"spread":0.3061902577299042,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005225721,0.0001539222,0.0001512467,0.0002191649,0.0001083271,0.0003302728,0.0003347083,0.0001072752,0.00001110545],"category_scores_gemma":[0.002453764,0.0001640194,0.00003483359,0.0004855964,0.00005670328,0.0004436964,0.00003110208,0.0002552752,0.00001344085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001213119,"about_ca_system_score_gemma":0.0003620649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007054949,"about_ca_topic_score_gemma":0.000001702224,"domain_scores_codex":[0.9984801,0.00009080976,0.0004694044,0.0002339619,0.0004842656,0.0002414387],"domain_scores_gemma":[0.998595,0.0005175382,0.0001366653,0.000189264,0.0004883151,0.0000732082],"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":[0.00001755239,0.00003593525,0.0001187246,0.00004691873,0.000002969734,0.00002051147,0.0005240428,0.4167165,0.0000264962,0.5791559,0.00006382804,0.003270628],"study_design_scores_gemma":[0.0004634931,0.00002294461,0.00007013683,0.00003058062,0.000002655476,0.000004228568,0.000008282535,0.7859287,0.0003584665,0.212554,0.0004016501,0.0001548898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001831124,0.0002682963,0.9952231,0.0000373578,0.0003121331,0.0001602644,0.00003148464,0.0003290417,0.001807213],"genre_scores_gemma":[0.5022816,5.901915e-7,0.4974518,0.000151307,0.00002989678,0.000002706214,0.00007354189,0.000005278765,0.000003313211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5004505,"threshold_uncertainty_score":0.6688515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017292107","doi":"10.1162/coli_a_00143","title":"Computing Lexical Contrast","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; National Research Council Canada","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Contrast (vision); Computer science; Natural language processing; Artificial intelligence; Word (group theory); Meaning (existential); Focus (optics); Linguistics; Information retrieval; Psychology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02047305350721997,"gpt":0.3092489102287959,"spread":0.288775856721576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002915573,0.0001225863,0.000129058,0.0000749032,0.0001601437,0.0001258515,0.0005054979,0.00006180983,0.000006494071],"category_scores_gemma":[0.001275478,0.0001176328,0.00004293554,0.0002182887,0.00005417071,0.0001052131,0.0002273031,0.0001926627,0.00005478769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004755133,"about_ca_system_score_gemma":0.00006681745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003340456,"about_ca_topic_score_gemma":1.448474e-7,"domain_scores_codex":[0.9989216,0.00003903943,0.0002274107,0.0001861995,0.0003034298,0.0003223119],"domain_scores_gemma":[0.9988371,0.0003594245,0.00009385264,0.0001760671,0.0003950808,0.0001384787],"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":[0.000001401425,0.00005334436,0.0009540607,0.00001079189,0.000006820171,0.000005637857,0.0002025842,0.0005454909,0.00001919839,0.9872227,0.001337099,0.009640886],"study_design_scores_gemma":[0.000339529,0.00004982559,0.002885003,0.00007638132,0.00001345821,0.00007185684,0.00001254647,0.5267381,0.001054163,0.4458925,0.02234588,0.0005207412],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004090774,0.00136019,0.9933465,0.0001286209,0.001055695,0.00006597034,0.000002969139,0.0006192405,0.003011792],"genre_scores_gemma":[0.5141332,5.096759e-7,0.4848037,0.0003661025,0.0006646885,7.992393e-7,0.000008497796,0.000005488976,0.0000169679],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5413302,"threshold_uncertainty_score":0.4796925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3201284223","doi":"10.1162/coli_a_00433","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":93,"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","funders":"","keywords":"Harm; Emotion recognition; Sentiment analysis; Key (lock); Computer science; Psychology; Social psychology; Artificial intelligence; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.0701563089762093,"gpt":0.3225153650597269,"spread":0.2523590560835176,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000761597,0.00009184471,0.0001620509,0.0003109789,0.000586083,0.000146256,0.0001864293,0.00002873281,0.00006349319],"category_scores_gemma":[0.0004895101,0.0001055787,0.0001154837,0.0006669898,0.00002082926,0.00003776584,0.0001850527,0.0001381428,0.000006641029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005812809,"about_ca_system_score_gemma":0.00006894302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000519262,"about_ca_topic_score_gemma":9.45907e-7,"domain_scores_codex":[0.9987316,0.0001144065,0.0002928482,0.0002992216,0.0004324024,0.0001295569],"domain_scores_gemma":[0.9985962,0.0006616344,0.0001702259,0.0001357295,0.0003837904,0.00005241583],"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":[0.00001077064,0.0002741012,0.003108358,0.0000836019,0.001129776,0.000007395909,0.004079225,0.8130454,0.00001185451,0.1459694,0.002379917,0.0299002],"study_design_scores_gemma":[0.0002220493,0.00005578115,0.002111688,0.00000482834,0.0002251929,0.000001990935,0.00009125397,0.9522966,0.000008036979,0.04239473,0.002463847,0.0001240739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01185826,0.00006776201,0.986604,0.000443522,0.0005533065,0.0001459434,0.00005123908,0.00008120747,0.0001947313],"genre_scores_gemma":[0.7174932,0.000002996142,0.2811179,0.0004617834,0.0001560097,0.00003235004,0.0006624685,0.000006669117,0.00006657585],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.705635,"threshold_uncertainty_score":0.4507736,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131526828","doi":"10.1162/coli.2006.32.2.223","title":"Building and Using a Lexical Knowledge Base of Near-Synonym Differences","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; University of Ottawa; University of Pennsylvania","keywords":"Computer science; Synonym (taxonomy); Natural language processing; Knowledge base; Artificial intelligence; Mistake; Natural language; Bilingual dictionary; Word (group theory); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02656855028045379,"gpt":0.3117453974176719,"spread":0.2851768471372181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001873533,0.0001051655,0.0001506744,0.00007838413,0.0001284155,0.0001265195,0.0002376,0.00005187832,0.000002014909],"category_scores_gemma":[0.0006222121,0.00009798116,0.00002836486,0.0002225359,0.0001388596,0.00004859341,0.0002032773,0.0001039154,7.415676e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002682572,"about_ca_system_score_gemma":0.0001421913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005455599,"about_ca_topic_score_gemma":0.00000353382,"domain_scores_codex":[0.999167,0.00004005439,0.0002383644,0.000221521,0.0001863025,0.000146779],"domain_scores_gemma":[0.9989266,0.0003831478,0.0001132436,0.0001136755,0.0004181362,0.00004516936],"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":[0.000002894054,0.00006380349,0.001814975,0.00006159167,0.000005387628,0.0000148616,0.00009996306,0.002691872,0.0004753615,0.9900975,0.00007070715,0.004601146],"study_design_scores_gemma":[0.00007910151,0.00001941639,0.001357748,0.00005886851,0.000005908827,0.00001274383,0.000001291492,0.6732213,0.0007140487,0.3242748,0.0001582387,0.00009650443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04440339,0.001545259,0.9533795,0.00003494023,0.000185562,0.00005135997,0.00000537647,0.0001328717,0.0002617146],"genre_scores_gemma":[0.4995616,4.482928e-7,0.5002994,0.00001714845,0.000108972,5.894105e-7,0.000001860443,0.000003449056,0.000006517294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6705295,"threshold_uncertainty_score":0.3995556,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137006453","doi":"10.1162/coli_a_00206","title":"Towards Topic-to-Question Generation","year":2015,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Predicate (mathematical logic); Natural language processing; Correctness; Artificial intelligence; Topic model; Similarity (geometry); Subsequence; Context (archaeology); String (physics); Information retrieval; Algorithm; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08126377489865644,"gpt":0.3230650423337741,"spread":0.2418012674351177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002713166,0.00008291971,0.00008223266,0.00007987137,0.00006386491,0.000125265,0.0003046051,0.00003920281,0.000002441442],"category_scores_gemma":[0.001590768,0.00008868984,0.0000212925,0.0001685498,0.000009745845,0.00005161215,0.0001283754,0.00006717601,0.0001007338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009341155,"about_ca_system_score_gemma":0.0002301341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001741577,"about_ca_topic_score_gemma":0.000002636399,"domain_scores_codex":[0.9990271,0.00003908638,0.0001997272,0.0002462654,0.0003578156,0.0001299462],"domain_scores_gemma":[0.9986648,0.00003707816,0.0000439904,0.0002110077,0.0008798916,0.0001632561],"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":[8.712155e-7,0.00001301451,0.00009540563,0.000002160425,0.000002493444,0.000004457097,0.0002606621,0.369571,0.000006966484,0.6165475,0.001943664,0.0115518],"study_design_scores_gemma":[0.0001273344,0.00003674771,0.0003845765,0.000005826154,0.000002258746,0.000004102227,0.000003873537,0.8794093,0.00006790484,0.09683399,0.02302152,0.0001025214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00301433,0.00003248185,0.9867741,0.0007762281,0.00247519,0.00008590688,0.000002015397,0.0001454002,0.006694352],"genre_scores_gemma":[0.4886471,2.903229e-7,0.5094382,0.0005696138,0.00122044,0.000003867628,0.00001671601,0.000003841761,0.00009996509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5197135,"threshold_uncertainty_score":0.3616667,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2562910494","doi":"10.1162/coli_a_00278","title":"Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications","year":2016,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computational linguistics; Perspective (graphical); Computer science; Linguistics; Field (mathematics); Sociocultural linguistics; Subjectivity; Multidisciplinary approach; Interpretation (philosophy); Sentiment analysis; Affect (linguistics); Artificial intelligence; Natural language processing; Sociology; Natural language; Epistemology; Social science; Comprehension approach","retraction":null,"screen_n_in":null,"score":{"opus":0.01678670568591051,"gpt":0.3042419730166649,"spread":0.2874552673307544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002184941,0.0001407309,0.0002118881,0.0002100481,0.0001405429,0.00005901343,0.0003131873,0.00004321562,0.00002442697],"category_scores_gemma":[0.0008776138,0.000111521,0.00006106366,0.0003532754,0.0001415465,0.00005236793,0.0001617394,0.00006060956,0.00002934995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003407844,"about_ca_system_score_gemma":0.0001382798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003428586,"about_ca_topic_score_gemma":0.00000136552,"domain_scores_codex":[0.9985452,0.00006384946,0.0004243321,0.0003530367,0.000469695,0.0001438726],"domain_scores_gemma":[0.9972406,0.001244598,0.0002515773,0.0002105898,0.0009589224,0.00009372526],"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":[0.000006211327,0.0000966646,0.001439531,0.00002470632,0.00009110937,0.000004795413,0.002459231,0.01290385,0.00008215947,0.9657454,0.00025741,0.01688894],"study_design_scores_gemma":[0.0009355851,0.00008587289,0.007106108,0.0001025273,0.00005979549,0.000005415013,0.0001209527,0.5485553,0.00019424,0.4361853,0.006318549,0.0003303893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00522464,0.0005433976,0.9899753,0.0001441241,0.0002531571,0.0001589988,0.00002548118,0.00005709563,0.003617782],"genre_scores_gemma":[0.7955231,0.000009312895,0.2039077,0.0001050598,0.0002817103,0.00001250522,0.00004512709,0.000007984817,0.0001074777],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7902985,"threshold_uncertainty_score":0.4547693,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105897558","doi":"10.1162/coli.2009.35.4.35402","title":"From Annotator Agreement to Noise Models","year":2009,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Benchmarking; Computer science; Noise (video); Agreement; Data set; Quality (philosophy); Set (abstract data type); Resource (disambiguation); Data quality; Data mining; Data science; Econometrics; Artificial intelligence; Mathematics; Linguistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02859109390663595,"gpt":0.2738249099219155,"spread":0.2452338160152796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008613839,0.0001228149,0.0001283765,0.00006792277,0.0001054261,0.0001519835,0.0005380135,0.00003482736,0.000009374538],"category_scores_gemma":[0.0002092068,0.0001183416,0.00004273839,0.000210982,0.00001240429,0.00004868642,0.000107752,0.00007384265,0.0001868959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004258307,"about_ca_system_score_gemma":0.00007465041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001622923,"about_ca_topic_score_gemma":6.454408e-7,"domain_scores_codex":[0.998859,0.00001966469,0.0002326232,0.0003303178,0.0003601741,0.0001982074],"domain_scores_gemma":[0.9990359,0.0001148479,0.0000549163,0.0002769359,0.000353943,0.000163478],"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":[0.000004885535,0.00008206347,0.00002095205,0.00000128802,0.000007538333,0.0000255658,0.0005491913,0.5370138,0.000005843559,0.4370436,0.00817441,0.01707087],"study_design_scores_gemma":[0.000107417,0.00006518699,0.001641256,0.000005818647,0.000002594358,6.481425e-7,0.000003760897,0.5630154,0.000006514489,0.4270432,0.007999836,0.0001083693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001496219,0.00006396708,0.9809409,0.001201159,0.0008395578,0.0001150369,0.00003174173,0.0001080678,0.01520328],"genre_scores_gemma":[0.5452018,0.000001004245,0.451488,0.002675169,0.0005741731,0.000001805182,0.00002782246,0.000002849207,0.00002739685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5437056,"threshold_uncertainty_score":0.4825832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220732108","doi":"10.1162/coli_a_00434","title":"Domain Adaptation with Pre-trained Transformers for Query-Focused Abstractive Text Summarization","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Automatic summarization; Computer science; Transformer; Domain adaptation; Natural language processing; Adaptation (eye); Artificial intelligence; Transfer of learning; Task (project management); Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.01946222096216806,"gpt":0.2497883595253038,"spread":0.2303261385631357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003034504,0.00013721,0.0001344385,0.0001265095,0.0004483581,0.00008611022,0.0002906624,0.00003385,0.000009495976],"category_scores_gemma":[0.0001647799,0.0001454561,0.00005070554,0.0002747664,0.00003222988,0.000094934,0.00004780973,0.0001528984,0.000001841392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001619794,"about_ca_system_score_gemma":0.0003769749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002341627,"about_ca_topic_score_gemma":0.00001480299,"domain_scores_codex":[0.9985887,0.00005708299,0.0002968483,0.0003637947,0.0004865697,0.0002070276],"domain_scores_gemma":[0.9987212,0.0004399255,0.0001618058,0.0001267107,0.0004848721,0.00006546019],"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":[0.00006026992,0.00005397799,0.00006555458,0.00001550114,0.00002165072,0.000003484262,0.00175946,0.7262504,0.00001239106,0.26296,0.00004886911,0.008748415],"study_design_scores_gemma":[0.0009113717,0.0002097872,0.001157175,0.000008447727,0.00001310151,0.000005756765,0.0002097049,0.9140549,0.00001743965,0.07437471,0.008849119,0.0001885323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003124626,0.00001831803,0.9940642,0.0003478159,0.0005187061,0.0005181237,0.00006763788,0.0001297226,0.001210911],"genre_scores_gemma":[0.5724633,3.916956e-7,0.4269343,0.0001406738,0.0001375649,0.00008047136,0.000176866,0.00001201625,0.00005436566],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5693387,"threshold_uncertainty_score":0.5931526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144719390","doi":"10.1162/coli_a_00077","title":"Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Automatic summarization; Computer science; Salience (neuroscience); Affect (linguistics); Context (archaeology); Information retrieval; Natural language processing; Artificial intelligence; Linguistics; History","retraction":null,"screen_n_in":null,"score":{"opus":0.09209636236490953,"gpt":0.3350728771866981,"spread":0.2429765148217886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014131,0.00008126213,0.0001292637,0.0001895111,0.00009654233,0.00006229727,0.0002154262,0.00002968264,0.000003585195],"category_scores_gemma":[0.001084485,0.00007873586,0.000008958368,0.0002536046,0.0000177103,0.0002163698,0.000213714,0.00008921577,0.000002246755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002583892,"about_ca_system_score_gemma":0.00009072454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000795785,"about_ca_topic_score_gemma":0.0009320165,"domain_scores_codex":[0.9990447,0.00005901064,0.0003854111,0.000157945,0.0002206366,0.0001322738],"domain_scores_gemma":[0.9991326,0.0001649712,0.00009478484,0.0001946436,0.0003138784,0.00009915228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003725066,0.0005678919,0.700582,0.00003536461,0.00001174606,0.000003154374,0.1206624,0.08985949,0.000002712751,0.07577664,0.00007601114,0.01238534],"study_design_scores_gemma":[0.0003294692,0.0002889006,0.693621,0.00003158781,0.000005397898,0.000001165612,0.004269131,0.2816797,0.000004352401,0.01897703,0.0006556744,0.0001365029],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6164947,0.000009350111,0.382322,0.00001620665,0.0002101331,0.0001369818,0.000006802722,0.00003527289,0.0007686004],"genre_scores_gemma":[0.840021,0.000001422821,0.1598575,0.00005540031,0.00003578394,0.00001092892,0.00001317182,0.000002421583,0.000002368032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2235264,"threshold_uncertainty_score":0.3210755,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129909699","doi":"10.1162/coli_a_00085","title":"Learning Entailment Relations by Global Graph Structure Optimization","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Haifa; Azrieli Foundation; Israel Science Foundation","keywords":"Logical consequence; Computer science; Textual entailment; Inference; Graph; Transitive relation; Artificial intelligence; Constraint (computer-aided design); Theoretical computer science; Natural language processing; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01091614832774298,"gpt":0.2556109568737796,"spread":0.2446948085460366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008022197,0.0001262415,0.00009294367,0.00006084517,0.0002169716,0.0001020288,0.0004229275,0.00007770752,0.00003540497],"category_scores_gemma":[0.0005576499,0.0001284343,0.0000342645,0.000375539,0.00004330838,0.00009876205,0.0001363652,0.0001834407,0.00001126413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009295539,"about_ca_system_score_gemma":0.00007746567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001327629,"about_ca_topic_score_gemma":9.622009e-7,"domain_scores_codex":[0.9990283,0.0000450446,0.0002190904,0.0002671885,0.0002824467,0.0001579526],"domain_scores_gemma":[0.9991003,0.00005870726,0.0001426376,0.000144732,0.0004851846,0.00006845385],"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":[0.000005611057,0.00006401337,0.002963841,0.0000123942,0.00002374672,0.00001181168,0.0005306072,0.2632276,0.00001526158,0.7263942,0.003558593,0.003192337],"study_design_scores_gemma":[0.0001424395,0.00006594973,0.0002837994,0.00001981221,0.00001150333,0.0000102896,0.00001187178,0.5154021,0.0002275106,0.4824274,0.001190462,0.0002068194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001691327,0.0003477907,0.9964669,0.00004963134,0.0003751002,0.00008812803,0.00002448549,0.0005023192,0.001976538],"genre_scores_gemma":[0.4112686,0.000001683765,0.5884038,0.00009671122,0.00005389092,0.000002049486,0.0001285707,0.000005054576,0.00003970273],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4110994,"threshold_uncertainty_score":0.5237399,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891212627","doi":"10.1162/coli_a_00333","title":"Introduction to the Special Issue on Language in Social Media: Exploiting Discourse and Other Contextual Information","year":2018,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Ottawa","funders":"","keywords":"Computer science; Social media; Context (archaeology); Perspective (graphical); Process (computing); Interpretation (philosophy); Task (project management); Linguistics; Artificial intelligence; Natural language processing; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02197099707484514,"gpt":0.2991216231871204,"spread":0.2771506261122753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002609091,0.00007205072,0.0000742284,0.00009400973,0.0001657892,0.0001172686,0.0001845959,0.00002940781,0.00001903865],"category_scores_gemma":[0.001499636,0.00006078698,0.00001193529,0.0001493547,0.00005422072,0.00008162871,0.00009101287,0.000100824,0.0001132099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003819706,"about_ca_system_score_gemma":0.00003341472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001063255,"about_ca_topic_score_gemma":0.00003345083,"domain_scores_codex":[0.9992651,0.00003642329,0.0001997677,0.0001469819,0.0002315338,0.0001201349],"domain_scores_gemma":[0.9994456,0.0001824716,0.00006190575,0.0001026476,0.0001761037,0.00003129422],"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":[0.00002321447,0.00002850443,0.0001617657,0.000007613151,0.000006439953,0.000002896713,0.07021653,0.01720747,0.000003149628,0.7422358,0.01824532,0.1518612],"study_design_scores_gemma":[0.0007232727,0.0001151976,0.004300438,0.00003943645,0.000007013365,0.000007888567,0.004582058,0.6048424,0.00007087886,0.02310983,0.3618858,0.0003157023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05903783,0.00001138211,0.9163428,0.009706011,0.005253867,0.0002698243,0.00002348927,0.00009070085,0.009264087],"genre_scores_gemma":[0.8916427,2.199398e-7,0.02292076,0.001542538,0.08384754,0.000005346335,0.00001153773,0.000005014557,0.0000242683],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8934221,"threshold_uncertainty_score":0.2478821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077818552","doi":"10.1162/coli.2010.36.1.36104","title":"Automatically Identifying the Source Words of Lexical Blends in English","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"University of Toronto","keywords":"Computer science; Natural language processing; Lexicon; Artificial intelligence; Task (project management); Set (abstract data type); Identification (biology); Word (group theory); Source text; Linguistics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01327449925434027,"gpt":0.2962019672436924,"spread":0.2829274679893521,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004871141,0.00009649496,0.0001304719,0.0001121288,0.00007790355,0.0001250218,0.0009260712,0.00007504258,0.000006998923],"category_scores_gemma":[0.005311776,0.00007530644,0.00004188326,0.0003932303,0.0001307066,0.0000561041,0.0002744924,0.000449149,0.000003536475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001662935,"about_ca_system_score_gemma":0.0001621159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009337953,"about_ca_topic_score_gemma":0.00001174583,"domain_scores_codex":[0.9988918,0.00004107706,0.0003363555,0.000194976,0.0003742205,0.0001615161],"domain_scores_gemma":[0.9982745,0.0007060957,0.0001239706,0.0002684813,0.0005848497,0.00004207216],"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":[0.000002720471,0.00004837625,0.0005829973,0.00003959086,0.000005846637,0.00001026458,0.001987469,0.001799811,0.0001514519,0.9835658,0.0003029417,0.0115027],"study_design_scores_gemma":[0.0001260753,0.00001869201,0.001018703,0.00006443867,0.000004470271,0.000007291747,0.00002584557,0.4641178,0.0008696741,0.531557,0.002062414,0.0001275376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006169973,0.0001405651,0.9907466,0.0002202696,0.0009849074,0.00008369939,0.000002164897,0.0003205939,0.001331203],"genre_scores_gemma":[0.5501709,3.935722e-7,0.4494991,0.00008350245,0.0002105615,0.000002706044,0.000002700707,0.000004697523,0.00002545321],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5440009,"threshold_uncertainty_score":0.6359076,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064296938","doi":"10.1162/coli_a_00064","title":"A Strategy for Information Presentation in Spoken Dialog Systems","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Ames Research Center; Atomic Energy of Canada Limited; National Aeronautics and Space Administration","keywords":"Dialog box; Computer science; Structuring; Dialog system; Process (computing); Presentation (obstetrics); User satisfaction; Human–computer interaction; Information retrieval; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.06398151558250546,"gpt":0.2799794875189091,"spread":0.2159979719364036,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002787302,0.00009396108,0.0001250976,0.0001889399,0.00005717458,0.0001413711,0.0002933839,0.00005911577,0.000001516087],"category_scores_gemma":[0.0007721965,0.00009753386,0.00003348181,0.0002211432,0.00001893223,0.0002349432,0.00004016435,0.00005486264,0.00004679652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004998031,"about_ca_system_score_gemma":0.0001588159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002136476,"about_ca_topic_score_gemma":0.00001227811,"domain_scores_codex":[0.9990227,0.00003934935,0.0004000777,0.0001479437,0.0002120259,0.0001779399],"domain_scores_gemma":[0.998872,0.000220593,0.000150548,0.0001448361,0.0005504499,0.00006154423],"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":[0.0000262685,0.00004668297,0.001708318,0.00007107492,0.000008677048,0.000004364913,0.001172134,0.07242908,0.000001340319,0.921679,0.0008809908,0.001972105],"study_design_scores_gemma":[0.0008459036,0.0001342091,0.02127647,0.00003318473,0.000004944307,0.000006535596,0.00008094942,0.8362836,0.00002863724,0.1368353,0.004274062,0.0001961837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001124746,0.00005051265,0.9731864,0.00001060062,0.002143967,0.0005327339,0.00003439791,0.00009326602,0.02282336],"genre_scores_gemma":[0.9394033,0.000001033187,0.05996976,0.00005108805,0.0003227779,0.00006050456,0.0001628105,0.000004809206,0.00002390945],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9382786,"threshold_uncertainty_score":0.3977315,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2884082915","doi":"10.1162/coli_a_00327","title":"Anaphora With Non-nominal Antecedents in Computational Linguistics: a Survey","year":2018,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Ruhr-Universität Bochum; Universität Hamburg","keywords":"Anaphora (linguistics); Antecedent (behavioral psychology); Computer science; Automatic summarization; Natural language processing; Linguistics; Sentence; Artificial intelligence; Machine translation; Computational linguistics; Field (mathematics); Resolution (logic); Psychology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01827161686791995,"gpt":0.3053307266107789,"spread":0.2870591097428589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000620689,0.0002803406,0.000295908,0.0003833673,0.0002171606,0.0002908494,0.0009829828,0.0001099173,0.00001009368],"category_scores_gemma":[0.004042829,0.0002669884,0.00003953522,0.0009632758,0.0002662696,0.00006998261,0.0002889108,0.0003238199,0.00005310675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000146567,"about_ca_system_score_gemma":0.000502973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002071671,"about_ca_topic_score_gemma":0.0002019616,"domain_scores_codex":[0.9977158,0.0001029893,0.0004965241,0.0006145286,0.0006714435,0.0003986924],"domain_scores_gemma":[0.99528,0.0006397661,0.0002438782,0.0003285971,0.003370695,0.00013708],"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":[0.0006150641,0.001302849,0.122268,0.0002942101,0.0002001662,0.001104534,0.003101811,0.1019985,0.00004942757,0.7462318,0.009933242,0.0129004],"study_design_scores_gemma":[0.0008079775,0.0003747997,0.05520325,0.0002157829,0.000009791947,0.00003330001,0.00001129305,0.7899166,0.0001511295,0.1514659,0.001276277,0.0005339265],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00748522,0.0001452673,0.9890861,0.00005903718,0.0009161118,0.0002211572,0.0000471458,0.000289392,0.001750565],"genre_scores_gemma":[0.5324219,6.291424e-7,0.4667625,0.0002109133,0.0004735674,0.000005311867,0.00008884546,0.0000152717,0.00002108054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.687918,"threshold_uncertainty_score":0.9999782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2602799059","doi":"10.1162/coli_a_00290","title":"Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease","year":2017,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"National Institute on Deafness and Other Communication Disorders; National Institutes of Health; Alzheimer Society; AGE-WELL; Carnegie Mellon University; Natural Sciences and Engineering Research Council of Canada; University of Pittsburgh","keywords":"Computer science; Confusion; Dementia; Cognitive psychology; Vocabulary; Function (biology); Cognition; Process (computing); Parsing; Spoken language; Decision tree; Artificial intelligence; Natural language processing; Psychology; Disease; Linguistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03038340881292735,"gpt":0.2762257908780106,"spread":0.2458423820650832,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002178435,0.0001219325,0.0001518039,0.00008797803,0.0005081863,0.0005253215,0.0003649056,0.00002703976,0.000001035726],"category_scores_gemma":[0.0006443737,0.0001011603,0.00001440145,0.00008372544,0.00008240357,0.0001269923,0.0001777682,0.0001143293,0.000008118946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000018448,"about_ca_system_score_gemma":0.000166923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001842805,"about_ca_topic_score_gemma":0.0002669663,"domain_scores_codex":[0.9990162,0.00004148197,0.0001645777,0.0003129062,0.0002823907,0.0001824356],"domain_scores_gemma":[0.9989007,0.00022481,0.000159655,0.0003177616,0.0002416332,0.0001554702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001959286,0.0001384136,0.5498988,0.0001087502,0.00006842176,0.000587602,0.002732982,0.02188277,0.00001766019,0.4210097,0.0001860728,0.003172927],"study_design_scores_gemma":[0.001389742,0.000100628,0.7458422,0.0002816281,0.00003234345,0.00002744157,0.00005930679,0.2158453,0.00002920638,0.03563805,0.0003971661,0.0003570908],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2097752,0.0005087041,0.7844238,0.00033774,0.001229742,0.0004319428,0.00002443186,0.0001265857,0.003141897],"genre_scores_gemma":[0.9628205,0.000003976223,0.03682455,0.00005812491,0.0002407908,0.000008387057,0.00002483959,0.000009266337,0.000009627535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7530453,"threshold_uncertainty_score":0.5065687,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3193068792","doi":"10.1162/coli_a_00422","title":"Probing Classifiers: Promises, Shortcomings, and Advances","year":2021,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; Artificial intelligence; Variety (cybernetics); Classifier (UML); Machine learning; Property (philosophy); Artificial neural network; Deep neural networks; Natural language processing; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.03569677429684543,"gpt":0.2887908698049079,"spread":0.2530940955080625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002415431,0.0002736971,0.0003386974,0.0001119495,0.0001617901,0.000681244,0.0006678646,0.0001810798,0.000003448753],"category_scores_gemma":[0.001126551,0.0003054516,0.00007448009,0.0001146423,0.00006978245,0.00008416878,0.001789385,0.0005543225,0.00000236914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008920155,"about_ca_system_score_gemma":0.0006261425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008811446,"about_ca_topic_score_gemma":0.000003833994,"domain_scores_codex":[0.9979324,0.00006127217,0.0004656321,0.0008673725,0.0004219654,0.0002514019],"domain_scores_gemma":[0.9981336,0.0002827734,0.0002468131,0.0004676806,0.0007436311,0.0001255024],"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":[0.000005089625,0.00009434447,0.001114312,0.0009144395,0.00009535552,0.0001550596,0.002002074,0.5675159,0.000008241533,0.385594,0.0003102965,0.04219098],"study_design_scores_gemma":[0.0001427802,0.00001284882,0.000251031,0.0003267005,0.00002005197,0.00001640964,0.00003940128,0.8806025,0.00002245966,0.1106846,0.007538482,0.0003426272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003136722,0.003456555,0.9872974,0.0002413801,0.002736717,0.0002748164,0.00001163538,0.0002075238,0.002637291],"genre_scores_gemma":[0.4142305,0.00007310679,0.5847118,0.0001722496,0.0006440337,0.00002055756,0.00007635282,0.00001537944,0.0000559677],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4110938,"threshold_uncertainty_score":0.9999397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154889602","doi":"10.1162/coli.2010.36.1.36101","title":"A Graph-Theoretic Framework for Semantic Distance","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Semantic similarity; Natural language processing; Artificial intelligence; Coherence (philosophical gambling strategy); Information retrieval; Set (abstract data type); Semantic computing; Semantic Web; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01206336355466009,"gpt":0.3012501952456227,"spread":0.2891868316909626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000121887,0.00009680245,0.00009490502,0.00002348304,0.0001005786,0.00002160792,0.0001518649,0.0001625907,0.000009463297],"category_scores_gemma":[0.006009991,0.00009080475,0.0000670043,0.00005706305,0.0002439068,2.471651e-7,0.00003684827,0.000134147,0.00000621624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002629011,"about_ca_system_score_gemma":0.00006144204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.396849e-7,"about_ca_topic_score_gemma":0.000003993587,"domain_scores_codex":[0.9993603,0.00001152294,0.0001474408,0.0002172727,0.0001024871,0.0001609578],"domain_scores_gemma":[0.9992435,0.000217436,0.00005711381,0.0001561692,0.000259612,0.0000661581],"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":[0.000077827,0.00009179907,0.001626577,0.0000740722,0.00004722706,0.000003683657,0.00005383797,0.0007252026,0.001575549,0.9848264,0.005076896,0.005820945],"study_design_scores_gemma":[0.0003208071,0.0001770184,0.0013471,0.00002380237,0.00002362273,0.000007412606,0.00001858147,0.005926474,0.0009776072,0.7469691,0.2439949,0.0002135745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03195066,0.0002029458,0.9654597,0.0001616931,0.001441937,0.0001058956,0.00006028356,0.00003208904,0.0005847709],"genre_scores_gemma":[0.700623,0.000006194758,0.2979518,0.0002146649,0.0009579702,0.00001274653,0.0001506206,0.00001130404,0.00007163871],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6686724,"threshold_uncertainty_score":0.7194955,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008170323","doi":"10.1162/coli_a_00380","title":"The Limitations of Stylometry for Detecting Machine-Generated Fake News","year":2020,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Stylometry; Misinformation; Computer science; Artificial intelligence; Authorship attribution; Natural language processing; Machine learning; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.1728446409505819,"gpt":0.3757561247219955,"spread":0.2029114837714136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005680899,0.0001300425,0.0001871174,0.00008917998,0.0008673275,0.0002204032,0.0003275859,0.0001395365,0.00000750722],"category_scores_gemma":[0.05329722,0.000115857,0.000119844,0.0002716814,0.0001487149,0.00001897999,0.0001173297,0.0002722195,0.000008482636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000774161,"about_ca_system_score_gemma":0.001052556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001336405,"about_ca_topic_score_gemma":0.000293646,"domain_scores_codex":[0.9985673,0.0001092018,0.0005279487,0.0001532811,0.0004529956,0.0001893166],"domain_scores_gemma":[0.9941486,0.003269622,0.0005125175,0.0001263265,0.001815709,0.0001272173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004680807,0.0000466591,0.00009318096,0.0001469031,0.0001535077,7.251857e-7,0.02641992,0.291219,0.000007884362,0.6214941,0.01104962,0.04932171],"study_design_scores_gemma":[0.0003947165,0.00006016215,0.0006117737,0.00006572065,0.00008187872,2.813873e-7,0.005816284,0.4005699,0.00004925616,0.1584112,0.4336226,0.0003161525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008279372,0.0009793306,0.8614061,0.006623032,0.00960237,0.002392926,0.001719757,0.0003443576,0.1086527],"genre_scores_gemma":[0.9480206,0.0001774191,0.04916722,0.0004120571,0.001450832,0.000009214691,0.0005013081,0.00001774547,0.0002436051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9397413,"threshold_uncertainty_score":0.9546773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048760284","doi":"10.1162/089120104323093267","title":"Inferable Centers, Centering Transitions, and the Notion of Coherence","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"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","funders":"","keywords":"Cohesion (chemistry); Coherence (philosophical gambling strategy); Computer science; Indeterminacy (philosophy); Transition (genetics); Linguistics; Identity (music); Natural language processing; Epistemology; Mathematics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.0108289784077711,"gpt":0.2574355551626614,"spread":0.2466065767548903,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001553725,0.00006432726,0.00009054044,0.00004358241,0.0001134764,0.00006488444,0.0002431647,0.00002429186,7.611142e-7],"category_scores_gemma":[0.00033472,0.00004947824,0.00002349405,0.0001273592,0.0001195371,0.00005526081,0.00007289893,0.00008954571,9.635398e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002274594,"about_ca_system_score_gemma":0.00005487702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002658777,"about_ca_topic_score_gemma":0.00000186555,"domain_scores_codex":[0.999441,0.00002453397,0.0001703032,0.0001231859,0.0001598563,0.00008108261],"domain_scores_gemma":[0.9993883,0.0001109049,0.00008045042,0.0001085152,0.0002884651,0.00002335763],"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":[0.000009749515,0.00002627663,0.00004915146,0.00003299446,0.000006523474,0.000003961093,0.0004909012,0.009193419,0.00007699081,0.9882396,0.00001348839,0.001856886],"study_design_scores_gemma":[0.0009711998,0.00003848044,0.0004136492,0.0001516881,0.000009032536,0.00002254652,0.00001348403,0.0696674,0.001438536,0.9269553,0.0002144902,0.0001042333],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001757758,0.0005908473,0.9963555,0.0006138477,0.0001703268,0.00009525597,0.000005879674,0.00009546517,0.0003151479],"genre_scores_gemma":[0.6087928,0.000005294813,0.3910356,0.0001200006,0.00003402369,0.000002092732,0.000005415108,0.000002158497,0.000002674458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.607035,"threshold_uncertainty_score":0.2017664,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1502796908","doi":"10.1162/coli.2002.28.4.560","title":"<i>Patterns of Text: In Honour of Michael Hoey</i> Mike Scott and Geoff Thompson (editors) (University of Liverpool) Amsterdam: John Benjamins, 2001, vii+323 pp; hardbound, ISBN 90-272-2572-9 and 1-55619-792-6, $100.00, € 110.00","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Pennsylvania","keywords":"Honour; Sociology; Media studies; Political science; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.02927748883288635,"gpt":0.2119638490646402,"spread":0.1826863602317539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000219971,0.0002333944,0.0004535208,0.0002144949,0.0002340174,0.0001389016,0.0002301038,0.0001117416,0.0004723547],"category_scores_gemma":[0.0002252315,0.0002642073,0.00009291164,0.00006311639,0.0004850413,0.0001962414,0.0001751914,0.0002828966,0.000009978061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003765231,"about_ca_system_score_gemma":0.00004988693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008059738,"about_ca_topic_score_gemma":0.001064958,"domain_scores_codex":[0.9985255,0.00006183654,0.000475794,0.0002986176,0.0003723305,0.0002659258],"domain_scores_gemma":[0.9983026,0.0003953703,0.0003597593,0.0001593095,0.0006752522,0.0001076805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007433643,0.003769119,0.1149248,0.004989352,0.0007875517,0.0003904281,0.1432044,0.003551801,0.0001097541,0.6216832,0.09553123,0.01031499],"study_design_scores_gemma":[0.006613285,0.001788671,0.09589355,0.002493856,0.0003718073,0.00004456815,0.02710019,0.03362751,0.0001061285,0.02979153,0.8002272,0.001941647],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.961434,0.002812145,0.0002365718,0.0001200752,0.001615653,0.0003147198,0.001927657,0.00003599927,0.03150319],"genre_scores_gemma":[0.995257,0.0003084188,0.0006361342,0.00008889067,0.001159916,7.771935e-7,0.0001238416,0.00002466331,0.002400403],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.704696,"threshold_uncertainty_score":0.999981,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1521465908","doi":"10.1162/089120101300346831","title":"Book Reviews","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04113790453060918,"gpt":0.34483954249689,"spread":0.3037016379662808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001595785,0.00009583127,0.0001375123,0.00005422498,0.00007715976,0.00002018201,0.00009207495,0.00005272818,0.004121761],"category_scores_gemma":[0.0006834097,0.00009015554,0.00006485583,0.000117699,0.0000368969,0.00001071479,0.00001531955,0.0001009419,0.002967534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001746279,"about_ca_system_score_gemma":0.0000218789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008885443,"about_ca_topic_score_gemma":0.000001313986,"domain_scores_codex":[0.9992099,0.00007349574,0.0002517518,0.0001807219,0.0001324828,0.0001516124],"domain_scores_gemma":[0.9993283,0.0001488576,0.00008618462,0.0001351056,0.0002414881,0.0000601102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005215468,0.0002495851,0.0008835691,0.0000253492,0.00006049858,0.0001884376,0.001159164,0.0003656599,0.000004038284,0.2985641,0.6706462,0.0278012],"study_design_scores_gemma":[0.0002705777,0.00003125216,0.002561275,0.00001651714,0.00003035717,0.00002743066,0.00004122362,0.0005083779,0.000001673595,0.02590644,0.9704892,0.0001156513],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.001694599,0.04858866,0.1247797,0.0002313141,0.005725112,0.0004189104,0.00003794697,0.0002034022,0.8183204],"genre_scores_gemma":[0.7692511,0.001515662,0.03768928,0.04936048,0.01707035,0.0001649796,0.001531325,0.0001224837,0.1232943],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7675565,"threshold_uncertainty_score":0.9978088,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2986265153","doi":"10.1162/coli_a_00367","title":"On the Linguistic Representational Power of Neural Machine Translation Models","year":2020,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Natural language processing; Machine translation; Artificial intelligence; Interpretability; Semantics (computer science); Rule-based machine translation; Word (group theory); Contrast (vision); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05564198337220849,"gpt":0.3233539129337652,"spread":0.2677119295615567,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003001909,0.0003100345,0.0003304252,0.0001545815,0.0001377982,0.0001842342,0.001512714,0.0001703825,0.00001398744],"category_scores_gemma":[0.004135843,0.000250916,0.0001763704,0.0002837665,0.0001195653,0.00003883559,0.0006349058,0.0008967537,0.00000622685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005547177,"about_ca_system_score_gemma":0.0003201678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002154437,"about_ca_topic_score_gemma":8.647553e-7,"domain_scores_codex":[0.9974905,0.0001463559,0.0006356502,0.0006228272,0.0009199234,0.0001847907],"domain_scores_gemma":[0.9957255,0.001815159,0.0005253474,0.0005789181,0.001275722,0.00007938723],"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":[0.000018869,0.00004321612,0.000006423096,0.00007339352,0.00003149264,0.00001653547,0.0008325799,0.2820479,0.000005472172,0.7153385,0.0005710868,0.001014534],"study_design_scores_gemma":[0.00006608821,0.0000311585,0.000018494,0.00006640128,0.0000122864,0.000001933191,0.000001863029,0.507749,0.00005230776,0.4918212,0.00005604725,0.0001232411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001439908,0.001924183,0.9909416,0.002125944,0.00124505,0.000388814,0.0001667696,0.0003468943,0.002716798],"genre_scores_gemma":[0.6159871,0.000003126723,0.3829848,0.0005540061,0.0002477619,0.00001313806,0.0001835144,0.0000182976,0.000008316805],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6158431,"threshold_uncertainty_score":0.9999943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391017630","doi":"10.1162/coli_a_00510","title":"Context-aware Transliteration of Romanized South Asian Languages","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Transliteration; Computer science; Romanization; Natural language processing; Context (archaeology); Artificial intelligence; Sentence; Word (group theory); Linguistics; History","retraction":null,"screen_n_in":null,"score":{"opus":0.01638905617639773,"gpt":0.2955521738544959,"spread":0.2791631176780982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001822414,0.0001072844,0.0001515844,0.0001861834,0.00008181569,0.00008417305,0.0004261225,0.00006021512,0.000005606549],"category_scores_gemma":[0.0006728086,0.0001044454,0.00005173793,0.0005242029,0.00004296631,0.000060973,0.00007797809,0.0001051529,0.00002366907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001892657,"about_ca_system_score_gemma":0.00008573226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005438433,"about_ca_topic_score_gemma":0.000002558329,"domain_scores_codex":[0.9990222,0.00004061929,0.0002682708,0.0002195209,0.0003052021,0.0001441372],"domain_scores_gemma":[0.9989225,0.0001683295,0.0001253149,0.0001848515,0.0005553298,0.00004372722],"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":[0.00001068874,0.00003803947,0.0003837764,0.0001194365,0.00002585746,0.00006306955,0.005425244,0.001840634,0.000202788,0.9711305,0.001620704,0.01913924],"study_design_scores_gemma":[0.0007829254,0.0001264275,0.002233902,0.0002047125,0.00002292748,0.00001279803,0.0003498165,0.5554255,0.004640022,0.4329648,0.002783504,0.0004527495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001575789,0.0002906228,0.9956532,0.0003075687,0.0002912522,0.000122298,0.00003795369,0.0008908935,0.0008304857],"genre_scores_gemma":[0.755289,9.464952e-7,0.2442854,0.0001259693,0.0001272373,0.000004186276,0.00009643649,0.000008684204,0.00006214235],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7537133,"threshold_uncertainty_score":0.4259161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416872671","doi":"10.1162/coli.a.583","title":"LLMs and Cultural Values: The Impact of Prompt Language and Explicit Cultural Framing","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Canada First Research Excellence Fund","keywords":"Framing (construction); Cultural diversity; Cultural values; Cultural bias; Hofstede's cultural dimensions theory; Perspective (graphical); Set (abstract data type); Cultural issues; Cultural psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03104474476676788,"gpt":0.4318547238264057,"spread":0.4008099790596378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004024454,0.00008326643,0.0001422692,0.00005551491,0.0004167238,0.00009812474,0.0001032922,0.00003770181,0.00001392014],"category_scores_gemma":[0.00239773,0.00005372548,0.00006705699,0.0002688256,0.0002761184,0.00003202524,0.00004826257,0.00008722962,8.936158e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003534205,"about_ca_system_score_gemma":0.0001334909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001106062,"about_ca_topic_score_gemma":0.0000324171,"domain_scores_codex":[0.9992124,0.0001418587,0.0001880487,0.0001355176,0.0002100066,0.0001121155],"domain_scores_gemma":[0.998255,0.001036329,0.00008711043,0.00005016571,0.000527157,0.00004429514],"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":[0.00002982253,0.00009440942,0.03414664,0.00006631383,0.0003587259,0.00000491444,0.0751088,0.0353794,0.0001268491,0.8259392,0.001538897,0.02720597],"study_design_scores_gemma":[0.000684448,0.00009004586,0.320834,0.0001501032,0.0002162762,0.000003869476,0.02524151,0.2513372,0.00005008224,0.396633,0.004390483,0.0003690619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9730208,0.00123338,0.01214193,0.0003276948,0.000215742,0.0001698071,0.00001849625,0.00003314657,0.01283901],"genre_scores_gemma":[0.9884768,0.00002379628,0.01076517,0.00005151771,0.0002866309,0.000002944365,0.00002091017,0.000002859458,0.0003693498],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4293063,"threshold_uncertainty_score":0.3205145,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404534114","doi":"10.1162/coli_a_00545","title":"The Emergence of Chunking Structures with Hierarchical RNN","year":2024,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates; University of Alberta; DeepMind; Canadian Institute for Advanced Research","keywords":"Chunking (psychology); Computer science; Natural language processing; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01130154070976787,"gpt":0.251264422587314,"spread":0.2399628818775461,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001678004,0.0000788805,0.00009099914,0.0000482155,0.0002174122,0.0001880703,0.0003944099,0.0000188749,0.00001049401],"category_scores_gemma":[0.0003264382,0.00004828427,0.00004875451,0.0003813104,0.0001107454,0.00003016182,0.000114007,0.0001201104,0.000003857863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007466908,"about_ca_system_score_gemma":0.0001154006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005723778,"about_ca_topic_score_gemma":0.000003805985,"domain_scores_codex":[0.99912,0.00002115561,0.0002195962,0.0001853782,0.0003176824,0.0001361884],"domain_scores_gemma":[0.9989621,0.0004836874,0.00006028387,0.0001587932,0.0002975742,0.00003758186],"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":[0.000002709276,0.000003861086,0.00008765836,0.00001626134,0.00003531303,0.000009479655,0.0002006968,0.08482827,0.000004001419,0.8986862,0.0003083733,0.01581717],"study_design_scores_gemma":[0.00002706726,0.00003813114,0.0009174006,0.00003175663,0.00001103367,0.000008448487,0.00001831552,0.8261019,0.00002419598,0.159623,0.01313167,0.00006708065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001396883,0.0007963637,0.9927365,0.0002498869,0.000688829,0.00004097315,0.000005390971,0.00007100234,0.004014161],"genre_scores_gemma":[0.8728279,0.000007605451,0.1267795,0.0000234585,0.0002900488,0.000001187219,0.000005342521,0.000005648674,0.00005925868],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8714311,"threshold_uncertainty_score":0.1968976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401117478","doi":"10.1162/coli_a_00533","title":"Exploring Temporal Sensitivity in the Brain Using Multi-timescale Language Models: An EEG Decoding Study","year":2024,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Cognitive Science and Mapping","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":"Electroencephalography; Decoding methods; Sensitivity (control systems); Computer science; Language model; Speech recognition; Artificial intelligence; Psychology; Neuroscience; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.2609003131987414,"gpt":0.3765898453257158,"spread":0.1156895321269744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001558318,0.0001310456,0.0001221014,0.0002086736,0.0002215291,0.0004974689,0.0003524976,0.00002058243,9.810519e-7],"category_scores_gemma":[0.0005869239,0.000111992,0.00004154367,0.0006651922,0.00003725103,0.0004976903,0.0001865282,0.0002080383,0.000008399255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006418323,"about_ca_system_score_gemma":0.0001561817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001821493,"about_ca_topic_score_gemma":0.0001370644,"domain_scores_codex":[0.9984906,0.0002109002,0.0002324497,0.0004333919,0.0003940427,0.0002386055],"domain_scores_gemma":[0.9987596,0.0007568168,0.00003743283,0.0002039396,0.0001863206,0.00005591478],"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":[0.000005483317,0.0005595091,0.003769222,0.00004701953,0.00002544693,0.001680857,0.08335877,0.8052892,0.000224833,0.07120082,0.00003425705,0.03380456],"study_design_scores_gemma":[0.0001449513,0.00003799885,0.004564207,0.00006215052,0.000005809692,0.00002005044,0.003209465,0.9859132,0.000007798115,0.005824511,0.00006142759,0.0001484269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3244538,0.00004982806,0.6744866,0.00008207034,0.0005009052,0.0001635423,0.000004340143,0.00009904806,0.0001598462],"genre_scores_gemma":[0.9103304,5.771388e-7,0.08916347,0.0002228979,0.00024882,0.000008812525,0.000008276937,0.000008365857,0.000008453252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5858765,"threshold_uncertainty_score":0.4797105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389613952","doi":"10.1162/coli_a_00501","title":"Stance Detection with Explanations","year":2023,"lang":"en","type":"article","venue":"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 British Columbia","funders":"","keywords":"Computer science; Automatic summarization; Artificial intelligence; Parsing; Benchmark (surveying); Machine learning; Focus (optics); Grammaticality; Natural language processing; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02863169177005188,"gpt":0.2680939184902881,"spread":0.2394622267202363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001188059,0.00006515751,0.00006063707,0.0001163142,0.0001483064,0.00007315924,0.0002257357,0.00002173963,0.000002140459],"category_scores_gemma":[0.0004017585,0.00006342355,0.000014759,0.0005091421,0.00001758777,0.00004526701,0.00005485295,0.00007018746,0.00009409137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003445926,"about_ca_system_score_gemma":0.00007647699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003792707,"about_ca_topic_score_gemma":0.000008828702,"domain_scores_codex":[0.9992245,0.00001678594,0.0001375587,0.0002030043,0.0002872794,0.0001309081],"domain_scores_gemma":[0.9991518,0.0002140784,0.00005077747,0.0001693712,0.0003705145,0.00004351525],"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":[0.000001729713,0.000008714783,0.0002169646,0.000007440302,0.000007133829,0.0000165908,0.0001725326,0.6302264,0.000009512262,0.3635958,0.0003149924,0.005422154],"study_design_scores_gemma":[0.0001168265,0.00002064862,0.002077898,0.00001073773,0.000002169162,0.000004493182,0.00001304576,0.9265939,0.00004973546,0.06571292,0.005312558,0.0000850709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00316686,0.00001187742,0.9931639,0.0001586259,0.0005878059,0.00005629398,0.000004169715,0.0004338521,0.002416568],"genre_scores_gemma":[0.8074511,0.000001444203,0.1920456,0.0001106782,0.0002373663,0.000007375744,0.00001529892,0.000005736133,0.0001253778],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8042842,"threshold_uncertainty_score":0.2586337,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1538392035","doi":"10.1162/coli.2003.29.3.507","title":"Book Review","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"","field":"","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02411177161073708,"gpt":0.3140361472330895,"spread":0.2899243756223524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000261235,0.0001142947,0.0001559447,0.00004574867,0.00008618375,0.00001810244,0.00009979733,0.00002637284,0.001603332],"category_scores_gemma":[0.01055303,0.0001210817,0.0000553104,0.0002064492,0.00005345988,0.00001223572,0.0000154947,0.0001025548,0.006514065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005824283,"about_ca_system_score_gemma":0.0001666856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.639015e-7,"about_ca_topic_score_gemma":9.749134e-8,"domain_scores_codex":[0.9989709,0.00008063263,0.0002742335,0.0001784495,0.0003298654,0.0001659375],"domain_scores_gemma":[0.9985578,0.0002538672,0.00009908722,0.0001507202,0.0008484296,0.00009008721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001160341,0.0000339939,0.00005761788,0.000128007,0.00001075851,0.00001035486,0.000006387043,0.005316038,8.160292e-7,0.1792075,0.8151867,0.00004065442],"study_design_scores_gemma":[0.000151332,0.00001174761,0.0001350032,0.0002590562,0.00003352739,0.00001319041,7.596091e-7,0.002268718,0.00001015247,0.01640602,0.9805701,0.0001403583],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.00001243299,0.6600555,0.02485835,0.0002428783,0.001589073,0.0004581926,0.0001199005,0.0003774323,0.3122863],"genre_scores_gemma":[0.09390998,0.01254717,0.4898674,0.3637465,0.004869902,0.0001261575,0.002099936,0.0007081577,0.03212481],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.6475083,"threshold_uncertainty_score":0.9993094,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4233779307","doi":"10.1162/coli.2000.27.1.140","title":"<i>Construing Experience through Meaning: A Language-based Approach to Cognition</i> M. A. K. Halliday and Christian M. I. M. Matthiessen London: Cassell (Open linguistics series, edited by Robin Fawcett), 1999, xiii+657 pp; paperback, ISBN 0-304-70490-3, $102.00, £65.00","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Meaning (existential); Philosophy; Linguistics; Cognitive linguistics; Cognitive science; Cognition; Series (stratigraphy); Psychology; Epistemology; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.02494040335504384,"gpt":0.2963689442215807,"spread":0.2714285408665368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004482059,0.0006920403,0.0007297127,0.0001276341,0.0006505843,0.0005763496,0.0007096275,0.0003806118,0.0005516226],"category_scores_gemma":[0.003024117,0.0007487727,0.000123765,0.0009196451,0.0004205544,0.0001155033,0.00025814,0.0005978848,0.0002241005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216139,"about_ca_system_score_gemma":0.0002744478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008351832,"about_ca_topic_score_gemma":0.00004185496,"domain_scores_codex":[0.9958392,0.0002946582,0.001004005,0.001268586,0.0007572837,0.0008363168],"domain_scores_gemma":[0.9959971,0.0007269563,0.0004523028,0.0005838641,0.001808658,0.0004310744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001812223,0.003714095,0.002853497,0.0007382085,0.001008861,0.001605705,0.07969505,0.005364264,0.0009092508,0.1907939,0.7059448,0.005560145],"study_design_scores_gemma":[0.005238368,0.0005836587,0.0002554424,0.0004449411,0.0004345809,0.0004463878,0.01446846,0.007862926,0.001242855,0.0138105,0.9529945,0.002217341],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03627457,0.02264507,0.1799554,0.001648718,0.01296407,0.005436542,0.005312914,0.001461036,0.7343017],"genre_scores_gemma":[0.8911629,0.0002288314,0.08809224,0.00906942,0.003909149,0.000298488,0.005010006,0.0001916183,0.002037345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8548883,"threshold_uncertainty_score":0.9994963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392367355","doi":"10.1162/coli_a_00512","title":"A Novel Alignment-based Approach for PARSEVAL Measuress","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","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":"University of British Columbia","funders":"","keywords":"Computer science; Parsing; Sentence; Natural language processing; Artificial intelligence; Lexical analysis; Parseval's theorem; Machine translation; Word (group theory); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05511895696161671,"gpt":0.3166822825463177,"spread":0.261563325584701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000414872,0.0001364662,0.0001375059,0.0001574425,0.0001727696,0.0001564469,0.0006695569,0.00006674378,7.695515e-7],"category_scores_gemma":[0.001685288,0.0001340532,0.00006936133,0.0004732,0.0000430566,0.00003697828,0.0001261409,0.00009703215,0.000009307281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005304455,"about_ca_system_score_gemma":0.0001914315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003005405,"about_ca_topic_score_gemma":2.206609e-7,"domain_scores_codex":[0.9986968,0.0000202308,0.0002198167,0.0003561539,0.0004524512,0.0002545154],"domain_scores_gemma":[0.9984713,0.0004116724,0.0001003527,0.0002290198,0.0007172892,0.00007033479],"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":[0.00001534569,0.0001426484,0.00004954293,0.0001393208,0.00002484944,0.000008890592,0.0001464044,0.2022635,0.0004073539,0.7852108,0.006959952,0.004631341],"study_design_scores_gemma":[0.0003320258,0.00003182984,0.00003046138,0.00001832394,0.000007575174,0.000002778633,0.000003936443,0.89245,0.0009464008,0.1032599,0.002751252,0.0001655137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002482071,0.0001144454,0.9975126,0.0001660243,0.0004263354,0.0002561352,0.0000433665,0.001083693,0.0003725977],"genre_scores_gemma":[0.223503,2.894184e-7,0.7755782,0.0003372966,0.0002722031,0.00005546618,0.0001842056,0.00001435987,0.00005496935],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6901864,"threshold_uncertainty_score":0.5466533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2895279374","doi":"10.1162/coli_a_00363","title":"Scalable Micro-planned Generation of Discourse from Structured Data","year":2019,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Interpretability; Natural language processing; Scalability; Artificial intelligence; Natural language generation; Sentence; Pipeline (software); Paragraph; Fluency; Text simplification; Natural language understanding; Robustness (evolution); Natural language; Programming language; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.08137583821686917,"gpt":0.3230469773943666,"spread":0.2416711391774974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002178523,0.0002417251,0.0003726125,0.0001080911,0.00006570738,0.0001972598,0.002402661,0.0002104508,0.0000233821],"category_scores_gemma":[0.000739759,0.0002580584,0.00005902607,0.00008883825,0.00005067787,0.00006184082,0.002822452,0.0003621982,0.00003367002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005689555,"about_ca_system_score_gemma":0.000662004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009122794,"about_ca_topic_score_gemma":0.00001528566,"domain_scores_codex":[0.9977296,0.00007251936,0.0005932561,0.0008983238,0.0005228986,0.0001834158],"domain_scores_gemma":[0.9965972,0.000258888,0.0004734462,0.001884762,0.0007183728,0.00006736271],"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":[0.000004704902,0.00003440602,0.0004453851,0.00006534631,0.00006237205,0.000004791981,0.0001902297,0.9778287,0.00009925945,0.01699262,0.00290631,0.001365807],"study_design_scores_gemma":[0.0002037295,0.00001281247,0.0005458228,0.00008791415,0.00003442899,0.000001006738,0.000005837819,0.9305215,0.0001954982,0.06729671,0.0008638701,0.0002308339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01553711,0.0003972509,0.9752601,0.0001339299,0.006250766,0.0002477713,0.001729466,0.00007259264,0.0003710483],"genre_scores_gemma":[0.4768005,0.000005353434,0.5156596,0.00006916194,0.00139164,0.000001830312,0.006009672,0.00001302083,0.00004919215],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4612634,"threshold_uncertainty_score":0.9999872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4235980152","doi":"10.4018/978-1-4666-6042-7.ch012","title":"Demystifying Domain Specific Languages","year":2014,"lang":"en","type":"book-chapter","venue":"Computational Linguistics","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Vagueness; Digital subscriber line; Domain-specific language; Computer science; Domain (mathematical analysis); Software engineering; Programming language; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02048454424811195,"gpt":0.2533815354641975,"spread":0.2328969912160855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000243578,0.0003926393,0.0003834153,0.0002547802,0.000111492,0.0001487833,0.0009927882,0.000273358,0.00003191256],"category_scores_gemma":[0.00004847688,0.0004464426,0.0001381035,0.00005047657,0.00008021882,0.00002197002,0.0003621525,0.0004535864,0.0002170002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001387655,"about_ca_system_score_gemma":0.00009954895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000114711,"about_ca_topic_score_gemma":3.631408e-7,"domain_scores_codex":[0.9981413,0.00001932114,0.0004457938,0.0005789958,0.0005638245,0.0002507515],"domain_scores_gemma":[0.9981408,0.0003331983,0.0002393773,0.0006214464,0.0005407525,0.000124494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001048273,0.000004854376,0.000003373626,0.00004414153,0.00002343709,0.00008519114,0.00005578843,0.01398825,6.50715e-7,0.9695546,0.00525823,0.01098041],"study_design_scores_gemma":[0.00006094846,0.00001862045,0.00001026009,0.0001343617,0.000006299406,0.00001760438,1.161789e-7,0.01975177,0.00000293733,0.3494222,0.6302682,0.0003066538],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[6.919389e-7,0.0004268821,0.8806438,0.00006664284,0.0008832307,0.0001436885,0.00002895628,0.001026205,0.1167799],"genre_scores_gemma":[0.002067801,0.00003296671,0.9743351,0.000160622,0.001707263,0.000007384313,0.000149852,0.00008112383,0.02145786],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.62501,"threshold_uncertainty_score":0.9997987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4250326346","doi":"10.1162/coli_r_00106","title":"Briefly Noted","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02806631387154629,"gpt":0.2845006114861258,"spread":0.2564342976145795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001238305,0.00007763308,0.00007096436,0.00008111972,0.0001047057,0.00008385441,0.0004294763,0.00004505741,0.00001860109],"category_scores_gemma":[0.0009910046,0.00007730468,0.0000287003,0.0002414149,0.00004577619,0.00009963723,0.0001403885,0.00008060355,0.0002761482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003054714,"about_ca_system_score_gemma":0.00004307582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001662806,"about_ca_topic_score_gemma":9.911793e-8,"domain_scores_codex":[0.9992785,0.0000148623,0.0001630129,0.0001340548,0.0002139881,0.0001956138],"domain_scores_gemma":[0.9992053,0.0001772858,0.00007121139,0.0002300432,0.0002474416,0.00006873436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[5.973178e-7,0.00004264635,0.001831982,0.000002724883,0.000004608234,7.017047e-7,0.00008463753,0.0005714396,0.000008972668,0.9854346,0.004348788,0.007668334],"study_design_scores_gemma":[0.0003183346,0.00003770011,0.0484162,0.00001009749,0.000008220517,0.000009945164,0.00002441749,0.137531,0.0006711889,0.3207998,0.4918182,0.000354863],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008992796,0.0001523125,0.9846731,0.0005809663,0.001156842,0.00005606172,0.000003071678,0.0006235207,0.01185484],"genre_scores_gemma":[0.7512671,0.000001803383,0.2480071,0.0002810372,0.0002622572,0.000003891686,0.00001346652,0.000003963615,0.0001594117],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7503678,"threshold_uncertainty_score":0.3549418,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}