{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":22,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":22,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"5250998b0ea9","filters":{"venue":"Meeting of the Association for Computational Linguistics"}},"results":[{"id":"W2115791615","doi":"","title":"Deep Learning for NLP (without Magic)","year":2012,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":132,"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; Artificial intelligence; Feature engineering; Deep learning; Artificial neural network; Paraphrase; Machine learning; Sentiment analysis; Natural language processing; Feature (linguistics); Focus (optics); MAGIC (telescope); Language model","authors":[{"name":"Richard Socher","is_ca":false},{"name":"Christopher D. Manning","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02272081690193958,"gpt":0.2786095360606215,"spread":0.2558887191586819,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009801683,0.001194637,0.0005381608,0.0009186136,0.0004843916,0.002782588,0.001342165,0.001772676,0.02192656],"category_scores_gemma":[0.00407519,0.0006503332,0.0008742206,0.001236292,0.001296812,0.005107338,0.001938472,0.004227479,0.01001178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348258,"about_ca_system_score_gemma":0.001013568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001926594,"about_ca_topic_score_gemma":0.002126985,"domain_scores_codex":[0.9993895,0.0001621111,0.00004765554,0.0001184468,0.0002320071,0.00005023491],"domain_scores_gemma":[0.9993348,0.0003868128,0.00003873346,0.00008929199,0.000116871,0.00003351268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003994281,0.00004842774,0.0001487823,0.00100648,0.00004481854,0.0001376181,0.0001763287,0.01420739,0.002680979,0.3554519,0.1592353,0.4668221],"study_design_scores_gemma":[0.00001629913,0.00003427914,0.0001663144,0.0004706261,0.00001630281,0.0002067088,0.00004547854,0.05292655,0.002375172,0.5102068,0.4335012,0.00003428261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001161207,0.03242556,0.9131408,0.009356223,0.002405776,0.00009755156,0.0008143042,0.003620402,0.03697819],"genre_scores_gemma":[0.04670541,0.06686021,0.7792779,0.006987286,0.003943806,0.0008361096,0.002979167,0.002189487,0.0902207],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02192656,"threshold_uncertainty_score":0.07335162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120158336","doi":"","title":"Cross Lingual Adaptation: An Experiment on Sentiment Classifications","year":2010,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Task (project management); Artificial intelligence; Representation (politics); Adaptation (eye); Key (lock); Sentiment analysis; Natural language; Translation (biology); Parallel corpora; Noise (video); Machine learning","authors":[{"name":"Bin Wei","is_ca":false},{"name":"Christopher Pal","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03508279994780869,"gpt":0.3290336885755691,"spread":0.2939508886277604,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00595533,0.000912739,0.0008915361,0.0007898061,0.0007965169,0.0007827425,0.001010834,0.0009300165,0.002240641],"category_scores_gemma":[0.01893003,0.0003393421,0.0006384653,0.001244728,0.0005815856,0.001681308,0.001779207,0.001428399,0.001670661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000360226,"about_ca_system_score_gemma":0.0004425497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003807691,"about_ca_topic_score_gemma":0.003452775,"domain_scores_codex":[0.994584,0.002975204,0.0004172167,0.001114748,0.0007202533,0.0001885417],"domain_scores_gemma":[0.9878486,0.006238101,0.0003986068,0.003189987,0.001925685,0.0003989759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.007495727,0.007850026,0.05790671,0.001218176,0.001414888,0.001914567,0.003424327,0.02165677,0.1349742,0.000930304,0.03233209,0.7288823],"study_design_scores_gemma":[0.001898672,0.01182909,0.247016,0.0002457152,0.001957144,0.004014042,0.005611611,0.4795981,0.1789994,0.006074841,0.06212859,0.0006268296],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708086,0.0006540071,0.01599091,0.0003860897,0.0004494031,0.0005240993,0.001103231,0.002648217,0.007435437],"genre_scores_gemma":[0.9499751,0.0002993061,0.0347217,0.0007333878,0.000163637,0.0005578804,0.005980571,0.0006424595,0.006926008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00595533,"threshold_uncertainty_score":0.03149515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161427841","doi":"","title":"Summarizing Emails with Conversational Cohesion and Subjectivity","year":2008,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":66,"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":"Automatic summarization; Cohesion (chemistry); Computer science; PageRank; Cosine similarity; Natural language processing; Artificial intelligence; Graph; Sentence; Empirical research; Information retrieval; Subjectivity; Theoretical computer science; Pattern recognition (psychology); Mathematics","authors":[{"name":"Giuseppe Carenini","is_ca":true},{"name":"Raymond T. Ng","is_ca":true},{"name":"Xiaodong Zhou","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01336756495223629,"gpt":0.2436825173727591,"spread":0.2303149524205229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003324555,0.001226314,0.0009969994,0.004025226,0.0008412492,0.002490154,0.0007553663,0.001119899,0.0009375978],"category_scores_gemma":[0.02397137,0.0005320183,0.0007730604,0.002409586,0.0006215124,0.005029156,0.001353118,0.0006785095,0.0005331694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005924078,"about_ca_system_score_gemma":0.0006183968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001079974,"about_ca_topic_score_gemma":0.001503333,"domain_scores_codex":[0.9968136,0.001583424,0.0003205725,0.0005923277,0.0005747551,0.0001153062],"domain_scores_gemma":[0.9846705,0.01024063,0.00188392,0.001042944,0.001932597,0.0002294712],"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":[0.0009966069,0.0002481605,0.01733918,0.002727068,0.0006065104,0.0008823901,0.006635359,0.06530467,0.04592604,0.02422825,0.007312474,0.8277934],"study_design_scores_gemma":[0.00009275175,0.0007253079,0.0205816,0.0003130655,0.00109194,0.0009415674,0.004252906,0.7659903,0.04293973,0.1387453,0.02412135,0.0002041328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1160832,0.002279369,0.8766132,0.0006805406,0.000121476,0.0002138822,0.0004842319,0.001350205,0.002173785],"genre_scores_gemma":[0.5672662,0.001268927,0.4265423,0.0001388247,0.0004897352,0.0002102353,0.001941613,0.0002504736,0.001891817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004025226,"threshold_uncertainty_score":0.01758212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124618303","doi":"","title":"Substring-Based Transliteration","year":2007,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":61,"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":"Transliteration; Substring; Computer science; Margin (machine learning); Artificial intelligence; Word (group theory); Natural language processing; Machine translation; Speech recognition; Programming language; Machine learning; Data structure; Mathematics","authors":[{"name":"Tarek Sherif","is_ca":true},{"name":"Grzegorz Kondrak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01112075728909654,"gpt":0.2755006221297466,"spread":0.2643798648406501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008406619,0.0005936558,0.00077991,0.0005918657,0.0005640626,0.001258934,0.001513303,0.0009437546,0.009057875],"category_scores_gemma":[0.004397772,0.0003364872,0.0006686663,0.0009635891,0.0008478089,0.00238298,0.001229785,0.001486846,0.006192189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005366497,"about_ca_system_score_gemma":0.001023985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007096136,"about_ca_topic_score_gemma":0.0008742723,"domain_scores_codex":[0.998674,0.0003185599,0.0001155183,0.00042234,0.000377794,0.00009185897],"domain_scores_gemma":[0.9973017,0.001143154,0.0001532855,0.0007729901,0.0005809411,0.00004805107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002929316,0.0001809349,0.001156338,0.0008254529,0.0001060288,0.0004762609,0.000805666,0.0549937,0.1950909,0.1380057,0.01461815,0.593448],"study_design_scores_gemma":[0.00005306216,0.0002872222,0.0005512887,0.00006897838,0.00009866714,0.0008506349,0.0001749435,0.5019233,0.3041437,0.1008564,0.09090339,0.00008856576],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00989526,0.0002145862,0.9791346,0.0001927523,0.000113422,0.00006889374,0.0002115368,0.004056973,0.006111972],"genre_scores_gemma":[0.2925997,0.000480064,0.6900888,0.000310421,0.00009645263,0.0001696845,0.001151221,0.001358785,0.01374482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009057875,"threshold_uncertainty_score":0.03030163,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096565906","doi":"","title":"Alignment-Based Discriminative String Similarity","year":2007,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"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":"Discriminative model; Coreference; Artificial intelligence; Computer science; Substring; String metric; Similarity (geometry); Character (mathematics); Natural language processing; Longest common subsequence problem; String (physics); Word (group theory); Pattern recognition (psychology); Transliteration; Heuristic; String searching algorithm; Mathematics; Pattern matching; Resolution (logic); Algorithm; Set (abstract data type)","authors":[{"name":"Shane Bergsma","is_ca":true},{"name":"Grzegorz Kondrak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01628738332415331,"gpt":0.2953723765151392,"spread":0.2790849931909859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00154235,0.0006003175,0.001530709,0.003846962,0.0006893366,0.001102409,0.001571028,0.0007734903,0.00250752],"category_scores_gemma":[0.007312349,0.0002540779,0.0005424664,0.004968217,0.0008512837,0.002222912,0.001642399,0.000862533,0.001794837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005512426,"about_ca_system_score_gemma":0.000798322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008711013,"about_ca_topic_score_gemma":0.001519419,"domain_scores_codex":[0.9973628,0.0006219286,0.0001683611,0.0006997891,0.0009777171,0.0001694113],"domain_scores_gemma":[0.9960316,0.001126095,0.0005429389,0.001282823,0.000843252,0.0001732548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004615589,0.000388522,0.01324662,0.0004186064,0.0001552072,0.0001825583,0.000245671,0.0347811,0.08358547,0.0316047,0.007315861,0.8276141],"study_design_scores_gemma":[0.00007156301,0.0008021127,0.01997499,0.00003487004,0.0001034421,0.001716093,0.000194624,0.8387704,0.07313561,0.05217202,0.01290158,0.0001227065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07159048,0.0004947179,0.9210771,0.00008972681,0.00006303943,0.0001408528,0.0004943854,0.002436623,0.003612904],"genre_scores_gemma":[0.6587179,0.0002156448,0.3359312,0.0001368636,0.00009083121,0.0001661734,0.002211272,0.0002629427,0.002267076],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003846962,"threshold_uncertainty_score":0.00838846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097120204","doi":"","title":"Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain","year":2013,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":29,"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":"Automatic summarization; Centrality; Computer science; Redundancy (engineering); Sentence; Natural language processing; Information retrieval; Domain (mathematical analysis); Artificial intelligence; Abstraction; Multi-document summarization","authors":[{"name":"Jackie Chi Kit Cheung","is_ca":true},{"name":"Gerald Penn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02083360009022558,"gpt":0.268047448719079,"spread":0.2472138486288535,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003596587,0.0007975454,0.0007488864,0.0049431,0.000990977,0.00254568,0.001139416,0.00109075,0.001204737],"category_scores_gemma":[0.02187389,0.0003962458,0.0008011211,0.003239747,0.001254385,0.004688827,0.001572798,0.001235899,0.0004541005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009827525,"about_ca_system_score_gemma":0.0008535385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002425658,"about_ca_topic_score_gemma":0.002492246,"domain_scores_codex":[0.997279,0.001310666,0.0001827861,0.0005679709,0.0005401155,0.0001194942],"domain_scores_gemma":[0.9850045,0.008888086,0.001572664,0.001831249,0.002447158,0.0002562491],"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":[0.0007882637,0.0002837,0.0116812,0.0009225829,0.0002885069,0.0008732777,0.004987933,0.1135502,0.04971266,0.1208144,0.00653863,0.6895588],"study_design_scores_gemma":[0.00004944402,0.0002126457,0.005276733,0.00008057498,0.0001790284,0.0003835017,0.001204182,0.8431345,0.02310065,0.1139408,0.01235994,0.00007798223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04076795,0.0007591442,0.9560688,0.0004578887,0.00002464358,0.00009406261,0.0001376439,0.0004161739,0.001273663],"genre_scores_gemma":[0.4565983,0.0005435189,0.5402343,0.00008955847,0.0001502451,0.00014029,0.0007705925,0.0002174846,0.001255674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0049431,"threshold_uncertainty_score":0.0190208,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110750141","doi":"","title":"Automatic detection of deception in child-produced speech using syntactic complexity features","year":2013,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":27,"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":"Utterance; Deception; Sentence; Support vector machine; Computer science; Set (abstract data type); Artificial intelligence; Random forest; Measure (data warehouse); Natural language processing; Speech recognition; Pattern recognition (psychology); Machine learning; Psychology; Data mining; Social psychology","authors":[{"name":"Maria Yancheva","is_ca":true},{"name":"Frank Rudzicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03243081732255438,"gpt":0.3234808616065863,"spread":0.291050044284032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002254048,0.0004236963,0.0003970269,0.001446149,0.0003073601,0.0009201335,0.0004216927,0.0005523149,0.000862898],"category_scores_gemma":[0.01101306,0.0001699024,0.0002695578,0.0004481603,0.0003571478,0.001046792,0.0006996521,0.0005656411,0.0004398132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003503609,"about_ca_system_score_gemma":0.0003649275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001131197,"about_ca_topic_score_gemma":0.001617203,"domain_scores_codex":[0.9987621,0.0005936299,0.00009358568,0.0001469975,0.0002868549,0.0001168272],"domain_scores_gemma":[0.9901175,0.006743263,0.001465218,0.0004677344,0.001033508,0.0001728331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001597983,0.0003424293,0.3092204,0.0004530899,0.0002303577,0.00100706,0.003243322,0.0273016,0.1758455,0.002816187,0.001749022,0.4761932],"study_design_scores_gemma":[0.00003321957,0.0004267638,0.4202918,0.0001105256,0.0001075413,0.001544672,0.001866495,0.4906867,0.08049854,0.002859818,0.001482109,0.00009188816],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9741248,0.0001733652,0.02442728,0.00007203029,0.00001159505,0.00003005362,0.0001994168,0.000159275,0.0008020561],"genre_scores_gemma":[0.9885106,0.00008027356,0.01086685,0.00000883317,0.000009491314,0.00001809223,0.0003266971,0.00001280609,0.0001663151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002254048,"threshold_uncertainty_score":0.01192069,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166202273","doi":"","title":"Bootstrapping a Stochastic Transducer for Arabic-English Transliteration Extraction","year":2007,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":24,"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":"Bootstrapping (finance); Computer science; Transducer; Scripting language; Artificial intelligence; Natural language processing; Metric (unit); Transliteration; Task (project management); Speech recognition; Similarity (geometry); Arabic; Pattern recognition (psychology); Programming language; Linguistics; Acoustics; Engineering; Mathematics","authors":[{"name":"Tarek Sherif","is_ca":true},{"name":"Grzegorz Kondrak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01409818308605324,"gpt":0.2948093699806726,"spread":0.2807111868946193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001306289,0.0006978076,0.00083025,0.0006630222,0.0004962951,0.000598632,0.00113502,0.001029932,0.002647689],"category_scores_gemma":[0.006989904,0.0004209183,0.0006879524,0.0005384317,0.0005704576,0.001294449,0.001257257,0.001568389,0.002431586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003981024,"about_ca_system_score_gemma":0.001077207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002232038,"about_ca_topic_score_gemma":0.003744778,"domain_scores_codex":[0.9989686,0.0003767161,0.00006543864,0.000287454,0.0002142595,0.00008745825],"domain_scores_gemma":[0.996691,0.002254731,0.0001374763,0.0002654483,0.0005512852,0.00009999697],"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":[0.0005887948,0.0002849486,0.00450803,0.0002080847,0.0001122045,0.0004998581,0.0005159595,0.1227352,0.1010199,0.008974833,0.006438963,0.7541133],"study_design_scores_gemma":[0.00001138652,0.00009159778,0.0005117472,0.00000664707,0.00001456573,0.0001096164,0.00003794138,0.9742848,0.01938737,0.004316766,0.001210439,0.00001699363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04707269,0.0001076748,0.9468288,0.0003035283,0.00006859448,0.0000640031,0.000211931,0.004396667,0.0009460948],"genre_scores_gemma":[0.6380522,0.0001186249,0.3563839,0.0003169891,0.00009324498,0.000271262,0.001546176,0.0003394151,0.002878192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002647689,"threshold_uncertainty_score":0.008857429,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4531093","doi":"","title":"Extraction of Disease-Treatment Semantic Relations from Biomedical Sentences","year":2010,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Relationship extraction; Relation (database); Semantic relation; Measure (data warehouse); Computer science; Natural language processing; Focus (optics); Artificial intelligence; Semantics (computer science); Information retrieval; Information extraction; Data mining; Medicine; Programming language","authors":[{"name":"Oana Frunza","is_ca":true},{"name":"Diana Inkpen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01283156771914793,"gpt":0.2901257257106199,"spread":0.2772941579914719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002777044,0.001859489,0.0009872274,0.007624525,0.001354645,0.001555713,0.0007805753,0.001448708,0.004522142],"category_scores_gemma":[0.01233124,0.0005195304,0.001780354,0.003762815,0.0005567627,0.002806606,0.001316085,0.001519204,0.002280975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009379207,"about_ca_system_score_gemma":0.002812756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001999721,"about_ca_topic_score_gemma":0.002263961,"domain_scores_codex":[0.9970175,0.001048125,0.0005859991,0.0006483123,0.0005976566,0.0001024062],"domain_scores_gemma":[0.9887217,0.007994466,0.001213963,0.0006097175,0.001276883,0.0001831773],"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":[0.001480084,0.001069118,0.033326,0.01049337,0.0007212496,0.005336471,0.004174273,0.009742117,0.1425313,0.0331117,0.04533693,0.7126773],"study_design_scores_gemma":[0.000577191,0.001261284,0.1126506,0.002509524,0.003137933,0.0133085,0.006601665,0.2140257,0.173768,0.1312646,0.3404145,0.0004804946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2316056,0.01289424,0.6067489,0.007939966,0.001553746,0.003058734,0.1017147,0.008703025,0.02578108],"genre_scores_gemma":[0.3063249,0.002589495,0.5997563,0.000817115,0.0006653175,0.0008578229,0.08667322,0.0002977442,0.002017991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007624525,"threshold_uncertainty_score":0.01512808,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099233844","doi":"","title":"Even the Abstract have Color: Consensus in Word-Colour Associations","year":2011,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Categorization, perception, and language","field":"Psychology","cited_by":16,"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":"Lexicon; Computer science; Word Association; Focus (optics); Component (thermodynamics); Crowdsourcing; Word (group theory); Resource (disambiguation); Key (lock); Product (mathematics); Association (psychology); Visualization; Semantics (computer science); Natural language processing; Coherence (philosophical gambling strategy); Quality (philosophy); Artificial intelligence; Linguistics; World Wide Web; Psychology; Mathematics","authors":[{"name":"Saif M. Mohammad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0455092320359143,"gpt":0.3172408818883953,"spread":0.271731649852481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009702478,0.000528488,0.0006516836,0.003312032,0.002947431,0.005346668,0.0009428904,0.00141868,0.004956287],"category_scores_gemma":[0.06898937,0.000628927,0.0007060119,0.003669478,0.0048128,0.009835933,0.00541306,0.002061763,0.001543832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00137942,"about_ca_system_score_gemma":0.001413768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002579988,"about_ca_topic_score_gemma":0.002739295,"domain_scores_codex":[0.9874769,0.005933498,0.001327618,0.00283377,0.002064252,0.0003638856],"domain_scores_gemma":[0.9456494,0.03346223,0.003898442,0.00726269,0.008807111,0.0009200985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001312679,0.0001897224,0.03460949,0.002853001,0.0003332115,0.001297228,0.09149832,0.005379013,0.06015683,0.3548822,0.02996218,0.4175261],"study_design_scores_gemma":[0.0001398197,0.0001655256,0.0439808,0.0005552818,0.0003569169,0.001099142,0.02392522,0.02694831,0.01739742,0.7300494,0.1550304,0.0003517838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3182967,0.002322055,0.6216662,0.005091772,0.0007447422,0.000388285,0.001358096,0.001808084,0.04832406],"genre_scores_gemma":[0.8941706,0.0004655419,0.09967756,0.0005927039,0.0001216429,0.0002993555,0.000988311,0.0005459836,0.003138359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009702478,"threshold_uncertainty_score":0.05131221,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096960653","doi":"","title":"Selecting Query Term Alternations for Web Search by Exploiting Query Contexts","year":2008,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"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":"Query expansion; Computer science; Bigram; Web query classification; Web search query; Information retrieval; Query optimization; Query language; Sargable; Selection (genetic algorithm); Term (time); RDF query language; Context (archaeology); Search engine; Word (group theory); Natural language processing; Artificial intelligence","authors":[{"name":"Guihong Cao","is_ca":true},{"name":"Stephen Robertson","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02470986278797762,"gpt":0.2848725438985707,"spread":0.2601626811105931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001251447,0.0010649,0.001451069,0.003892079,0.00070719,0.0009618033,0.0008228598,0.0006048866,0.001644363],"category_scores_gemma":[0.006710636,0.0004423538,0.0005431543,0.00280833,0.0005072027,0.002129662,0.001070679,0.0007898942,0.001021419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003947652,"about_ca_system_score_gemma":0.001027126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002234688,"about_ca_topic_score_gemma":0.00660232,"domain_scores_codex":[0.9988952,0.0003553624,0.0001331676,0.0002338978,0.0002846464,0.00009778423],"domain_scores_gemma":[0.9972243,0.001711835,0.0002252828,0.0002842196,0.0004192185,0.0001351521],"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":[0.002087845,0.0005831356,0.01152162,0.0005008046,0.0001228427,0.0004821444,0.0005999417,0.01110177,0.2168382,0.002701542,0.004274617,0.7491856],"study_design_scores_gemma":[0.0007564157,0.002103671,0.03038364,0.0001307989,0.001056067,0.002987985,0.001086037,0.7874183,0.1396038,0.01356262,0.02059419,0.000316362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6507546,0.005428444,0.3318554,0.0006286401,0.0001276106,0.0008941311,0.0005953457,0.00466634,0.005049529],"genre_scores_gemma":[0.7845204,0.001029904,0.2104533,0.0002108848,0.0002813711,0.0003259346,0.00110019,0.0004019221,0.001676085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003892079,"threshold_uncertainty_score":0.006618321,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099242427","doi":"","title":"Entity-Based Local Coherence Modelling Using Topological Fields","year":2010,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"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":"Coherence (philosophical gambling strategy); Computer science; Sentence; Component (thermodynamics); Topology (electrical circuits); Grid; Natural language; Natural language processing; Field (mathematics); Artificial intelligence; Language model; Theoretical computer science; Mathematics; Physics; Pure mathematics","authors":[{"name":"Jackie Chi Kit Cheung","is_ca":true},{"name":"Gerald Penn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02298369617306752,"gpt":0.2908722400383604,"spread":0.2678885438652929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001763998,0.0004992763,0.0004229429,0.001554907,0.0005133665,0.001453412,0.0009400075,0.0006329161,0.002955499],"category_scores_gemma":[0.006124229,0.0003993792,0.0008203092,0.001048249,0.0007518596,0.00425284,0.001051638,0.0007595457,0.0004696093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008459762,"about_ca_system_score_gemma":0.0007361128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004189375,"about_ca_topic_score_gemma":0.006154549,"domain_scores_codex":[0.9992089,0.0003734078,0.00005538167,0.00016704,0.0001513692,0.00004390847],"domain_scores_gemma":[0.9961398,0.002637373,0.0004034918,0.000400494,0.000333342,0.00008550796],"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":[0.0004624616,0.0001495098,0.00595338,0.0003332849,0.00009735518,0.0004476995,0.00129738,0.6181254,0.01299375,0.2349693,0.002845935,0.1223245],"study_design_scores_gemma":[0.0000309663,0.00005028101,0.0004502721,0.00001215,0.00002489979,0.00004371049,0.0000745316,0.9542117,0.003544328,0.03883588,0.002704647,0.00001678983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05698764,0.0001418149,0.9385676,0.0002056856,0.00002211611,0.00009298949,0.0003753708,0.001664238,0.001942639],"genre_scores_gemma":[0.7269127,0.0001337191,0.2702868,0.00004423334,0.00001951494,0.0001302259,0.0008343477,0.0002149886,0.001423597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004189375,"threshold_uncertainty_score":0.009887099,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146546639","doi":"","title":"Learning Bigrams from Unigrams","year":2008,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Bigram; Perplexity; Computer science; Language model; Natural language processing; Artificial intelligence; Word (group theory); Trigram; Oracle; Set (abstract data type); Speech recognition; Mathematics; Programming language","authors":[{"name":"Xiaojin Zhu","is_ca":false},{"name":"Andrew B. Goldberg","is_ca":false},{"name":"Michael Rabbat","is_ca":true},{"name":"Robert Nowak","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02239389677370867,"gpt":0.2445550466316511,"spread":0.2221611498579424,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001782699,0.001268043,0.001078867,0.003335209,0.000702576,0.001367571,0.001567557,0.00139422,0.00308919],"category_scores_gemma":[0.01007375,0.0007294053,0.001037871,0.001987878,0.0006651078,0.004932363,0.001828956,0.002323459,0.002976471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005470841,"about_ca_system_score_gemma":0.0009781776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001620828,"about_ca_topic_score_gemma":0.002692252,"domain_scores_codex":[0.9990152,0.0003846548,0.00007620572,0.0002700074,0.0001419139,0.0001119058],"domain_scores_gemma":[0.9955534,0.002937123,0.0002739089,0.0006914452,0.0004186366,0.0001255359],"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":[0.000644828,0.0002719231,0.005878229,0.0005095004,0.0002304733,0.0006778223,0.0009754828,0.06455686,0.01448223,0.02929886,0.01020996,0.8722639],"study_design_scores_gemma":[0.00005026698,0.0001642416,0.001247036,0.00008242302,0.00006265422,0.0003087123,0.0003400806,0.8785776,0.008991661,0.1054612,0.004651956,0.00006213361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1088765,0.001167862,0.881627,0.0004976408,0.0001578854,0.0000942168,0.0007399554,0.004354657,0.002484161],"genre_scores_gemma":[0.6478997,0.0009393764,0.339471,0.0003178644,0.000230418,0.0002246472,0.003431472,0.0006826097,0.006802874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003335209,"threshold_uncertainty_score":0.01033437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2250669704","doi":"","title":"Probabilistic Domain Modelling With Contextualized Distributional Semantic Vectors","year":2013,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"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":"Automatic summarization; Computer science; Distributional semantics; Artificial intelligence; Probabilistic logic; Natural language processing; Domain (mathematical analysis); Semantics (computer science); Generative grammar; Generative model; Hidden Markov model; Semantic space; Machine learning; Semantic similarity; Mathematics","authors":[{"name":"Jackie Chi Kit Cheung","is_ca":true},{"name":"Gerald Penn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01520811403659151,"gpt":0.2314686742057899,"spread":0.2162605601691984,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001773755,0.0007036367,0.0006232508,0.001563247,0.000508959,0.001604181,0.001884488,0.001047923,0.003282818],"category_scores_gemma":[0.006248565,0.0005850699,0.001426221,0.001868036,0.0007194322,0.003314435,0.00163123,0.001909851,0.001515553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008596629,"about_ca_system_score_gemma":0.001058986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002665747,"about_ca_topic_score_gemma":0.005944633,"domain_scores_codex":[0.9986442,0.000603499,0.00008442056,0.000385546,0.0001993376,0.00008312689],"domain_scores_gemma":[0.9969458,0.001975573,0.0002077147,0.0004711563,0.0003207572,0.00007901756],"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":[0.000192734,0.0001505667,0.002973209,0.0002646536,0.0001448724,0.0002920739,0.0007145492,0.5781695,0.005690348,0.2160835,0.00749423,0.1878298],"study_design_scores_gemma":[0.00001147721,0.00001806801,0.0002342877,0.00001482022,0.00001584543,0.00005885648,0.00004622166,0.9174191,0.001250223,0.07764734,0.003268302,0.000015398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007571125,0.0001284522,0.9898398,0.0001706321,0.00002902011,0.00004482492,0.0003145929,0.0006781381,0.001223415],"genre_scores_gemma":[0.444993,0.0005714953,0.5437826,0.0002174987,0.0001460398,0.000423745,0.003763547,0.0004956953,0.005606429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003282818,"threshold_uncertainty_score":0.0109821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2250341893","doi":"","title":"Mapping Source to Target Strings without Alignment by Analogical Learning: A Case Study with Transliteration","year":2013,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"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":"Transliteration; Computer science; Natural language processing; Phrase; Analogy; Artificial intelligence; Machine translation; Task (project management); Translation (biology); Rule-based machine translation; Machine learning; Linguistics; Engineering","authors":[{"name":"Phillippe Langlais","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01025360225145763,"gpt":0.2590147617676204,"spread":0.2487611595161628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003982951,0.0008306911,0.0009803104,0.001027784,0.001577722,0.00181968,0.002014724,0.003441906,0.004013176],"category_scores_gemma":[0.02879564,0.0004288512,0.0007947137,0.002504324,0.001608558,0.004666582,0.001912792,0.002096742,0.001483626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007223265,"about_ca_system_score_gemma":0.0005428339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003737371,"about_ca_topic_score_gemma":0.005392193,"domain_scores_codex":[0.995472,0.003084724,0.0003358724,0.0004429277,0.0004989469,0.0001655719],"domain_scores_gemma":[0.9732549,0.02103142,0.0007209156,0.0035806,0.001193732,0.0002184013],"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":[0.002663039,0.005512726,0.03565233,0.003649383,0.000409331,0.03716484,0.03544879,0.09575075,0.03850665,0.03072159,0.015833,0.6986876],"study_design_scores_gemma":[0.00175651,0.004361705,0.02558405,0.0004131159,0.0005218175,0.02971308,0.0238256,0.5814965,0.1568883,0.08422687,0.09088419,0.000328216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9000833,0.0009240702,0.08197398,0.001698929,0.00006223762,0.0003767437,0.0006325123,0.00112852,0.01311973],"genre_scores_gemma":[0.9013769,0.0003512922,0.09303746,0.0002861659,0.00004821015,0.0001655457,0.0005800484,0.0003292841,0.003825058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004013176,"threshold_uncertainty_score":0.0210641,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W172656279","doi":"","title":"RALI: Automatic Weighting of Text Window Distances","year":2010,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"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":"Window (computing); Weighting; Word (group theory); Computer science; SemEval; Artificial intelligence; Task (project management); Word-sense disambiguation; Natural language processing; Limit (mathematics); Pattern recognition (psychology); Mathematics","authors":[{"name":"Bernard Brosseau-Villeneuve","is_ca":true},{"name":"Noriko Kando","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007342829639935821,"gpt":0.2629071066691153,"spread":0.2555642770291795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00285331,0.002290788,0.001523916,0.004078322,0.0006956268,0.001561743,0.00317861,0.001225994,0.004682442],"category_scores_gemma":[0.01174875,0.0009359595,0.001122352,0.002279689,0.0004621179,0.00434531,0.002195255,0.001860302,0.004192217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006977015,"about_ca_system_score_gemma":0.0008316221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001749362,"about_ca_topic_score_gemma":0.003596843,"domain_scores_codex":[0.9977822,0.0005263804,0.0002233024,0.0009287618,0.0004278393,0.0001116019],"domain_scores_gemma":[0.9955242,0.002052429,0.0005056604,0.001025451,0.0007245814,0.0001676806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001012106,0.0002411664,0.002900532,0.000771912,0.000287291,0.0001361316,0.0004516668,0.011573,0.05880722,0.005057437,0.02420236,0.8945593],"study_design_scores_gemma":[0.0002498229,0.0003893123,0.004641346,0.00007726997,0.000200696,0.0003964477,0.0002249348,0.8376523,0.1116906,0.01405215,0.03025047,0.0001747013],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02665626,0.001214009,0.906124,0.000138596,0.0003089411,0.0004341748,0.002171597,0.06173523,0.001217101],"genre_scores_gemma":[0.1156323,0.0003528465,0.8737032,0.00008963068,0.0001185557,0.0005541122,0.003967041,0.002876499,0.002705873],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004682442,"threshold_uncertainty_score":0.01566434,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1458921027","doi":"","title":"Ontology-Based Extraction and Summarization of Protein Mutation Impact Information","year":2010,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Automatic summarization; Computer science; Ontology; Information retrieval; Information extraction; Mutation; Pace; Data mining; Geography; Biology; Genetics","authors":[{"name":"Nona Naderi","is_ca":true},{"name":"René Witte","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006578853222055952,"gpt":0.277147336279809,"spread":0.2705684830577531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001794854,0.0009014318,0.001016966,0.01545508,0.0007697084,0.001888508,0.0008968039,0.0006517634,0.001442259],"category_scores_gemma":[0.008268399,0.0003222896,0.001285783,0.009566513,0.0003587117,0.003041138,0.001263565,0.001005108,0.0008836957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009955373,"about_ca_system_score_gemma":0.002398213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004207161,"about_ca_topic_score_gemma":0.005334178,"domain_scores_codex":[0.9982942,0.0002196838,0.0004274254,0.0003042652,0.0006598185,0.00009469991],"domain_scores_gemma":[0.9960394,0.001394742,0.0007469567,0.0004837691,0.001206969,0.0001281604],"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":[0.0004045807,0.0004010905,0.01317062,0.002405945,0.0004870095,0.001489817,0.002433458,0.009942805,0.08232056,0.01669832,0.03312489,0.837121],"study_design_scores_gemma":[0.0002562245,0.0005688039,0.06573948,0.001126444,0.002958806,0.003380472,0.005222474,0.2797298,0.1709707,0.1230427,0.3464722,0.0005319024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1244864,0.002692535,0.7964002,0.002377236,0.0004486966,0.001218142,0.05168657,0.01128498,0.009405237],"genre_scores_gemma":[0.1923563,0.002622599,0.7355883,0.0002419203,0.0002557873,0.0005384114,0.06499907,0.0006327732,0.002764812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01545508,"threshold_uncertainty_score":0.009492218,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3036997889","doi":"","title":"Using Attention-based Bidirectional LSTM to Identify Different Categories of Offensive Language Directed Toward Female Celebrities","year":2019,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Offensive; Harassment; Perspective (graphical); Margin (machine learning); Computer science; Social media; Artificial intelligence; Natural language processing; Psychology; Machine learning; Social psychology; World Wide Web; Mathematics","authors":[{"name":"Sima Sharifirad","is_ca":true},{"name":"Stan Matwin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02115456455403126,"gpt":0.2868773790427908,"spread":0.2657228144887596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004785695,0.001218884,0.0004863312,0.0007437851,0.0003105848,0.000676792,0.0008773964,0.0008600107,0.00188658],"category_scores_gemma":[0.001452094,0.0002845584,0.0005351119,0.0007133122,0.0002979443,0.001028295,0.0008469349,0.00127627,0.001144023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006924915,"about_ca_system_score_gemma":0.0006997238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01307019,"about_ca_topic_score_gemma":0.01773437,"domain_scores_codex":[0.9997776,0.00004038022,0.00001282432,0.00008381894,0.00002889702,0.00005647019],"domain_scores_gemma":[0.9995844,0.000190284,0.00003918088,0.00003207134,0.0001278714,0.00002621962],"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":[0.001029445,0.0008021776,0.01772607,0.0005069505,0.0003402297,0.0006340016,0.0007334998,0.1532401,0.06715653,0.002254691,0.01916972,0.7364066],"study_design_scores_gemma":[0.00001762234,0.0001139484,0.003433658,0.00004312772,0.00006967279,0.000078103,0.0001337494,0.9839684,0.008584346,0.001889362,0.001643815,0.00002424517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6844278,0.003562476,0.2764618,0.002144705,0.001198644,0.0002592402,0.005373108,0.01003416,0.01653807],"genre_scores_gemma":[0.947746,0.00048988,0.03787467,0.0004057686,0.00011961,0.0001563551,0.004284828,0.0001125266,0.008810393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01307019,"threshold_uncertainty_score":0.02598822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037566932","doi":"","title":"Augmenting Named Entity Recognition with Commonsense Knowledge","year":2019,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; Université du Québec","funders":"","keywords":"Commonsense knowledge; Computer science; Natural language processing; Artificial intelligence; Named-entity recognition; Ambiguity; Knowledge base; Natural language understanding; Natural language; Word embedding; Question answering; Embedding; Task (project management)","authors":[{"name":"Ghaith Dekhili","is_ca":true},{"name":"Ngoc Tan Le","is_ca":true},{"name":"Fatiha Sadat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01943582013185866,"gpt":0.2500863071328213,"spread":0.2306504870009626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002108996,0.0008928347,0.0009279219,0.003015332,0.0006717056,0.001509112,0.00167844,0.001348666,0.003663935],"category_scores_gemma":[0.005756081,0.0004773476,0.001060418,0.002045815,0.0008017191,0.01058436,0.003299816,0.001870265,0.002892255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000436266,"about_ca_system_score_gemma":0.0007159939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002746448,"about_ca_topic_score_gemma":0.006445686,"domain_scores_codex":[0.9987594,0.0003097872,0.00009004692,0.0004868206,0.0002489571,0.000104989],"domain_scores_gemma":[0.9962058,0.00163594,0.0002321816,0.001355427,0.0004864068,0.00008420384],"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":[0.0002353407,0.0003139329,0.004541595,0.0004171685,0.0002236986,0.0006411477,0.0005600667,0.04692139,0.02495666,0.01174426,0.01148415,0.8979607],"study_design_scores_gemma":[0.00001983238,0.0001264048,0.004603847,0.0001018836,0.0001619898,0.0007415318,0.0003309118,0.8833186,0.0398658,0.04520322,0.02543075,0.00009519204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06969673,0.001158828,0.9050866,0.0006894777,0.0002322993,0.0001312904,0.001360722,0.01475094,0.006893104],"genre_scores_gemma":[0.6793693,0.0006678288,0.3078799,0.0003303069,0.0001227098,0.00008289336,0.006306773,0.0003832106,0.004857155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003663935,"threshold_uncertainty_score":0.01225704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3088355435","doi":"","title":"PACTE: A colloaborative platform for textual annotation","year":2017,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; École de Technologie Supérieure","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web","authors":[{"name":"Pierre André Ménard","is_ca":true},{"name":"Caroline Barrière","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02131663514572495,"gpt":0.3138673364363536,"spread":0.2925507012906286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004145683,0.002620617,0.001335849,0.005602381,0.003037119,0.004033516,0.00358814,0.002585862,0.07197965],"category_scores_gemma":[0.01711976,0.001669865,0.001412854,0.004223833,0.001462979,0.01091528,0.01170651,0.003449132,0.05544557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009724924,"about_ca_system_score_gemma":0.003559273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005808033,"about_ca_topic_score_gemma":0.008825713,"domain_scores_codex":[0.9959992,0.001212822,0.0004816477,0.0009134742,0.001166366,0.0002265088],"domain_scores_gemma":[0.9863936,0.005316324,0.000699389,0.004159786,0.002570935,0.000859965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00179328,0.0003818393,0.001709738,0.002552224,0.0001917762,0.001626947,0.004328013,0.00276745,0.04999525,0.08283079,0.6072373,0.2445854],"study_design_scores_gemma":[0.0001719643,0.0001294413,0.001226023,0.0002688835,0.00009754003,0.0006603738,0.001059511,0.05040878,0.03232136,0.05400842,0.8594098,0.0002378443],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004116265,0.0003063716,0.7559756,0.001019079,0.0009929384,0.000888647,0.03713576,0.1768253,0.02274003],"genre_scores_gemma":[0.06187897,0.0005305351,0.6996862,0.00117256,0.0006458779,0.003073969,0.1465233,0.03994776,0.0465408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07197965,"threshold_uncertainty_score":0.2407959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3197573382","doi":"","title":"Proceedings of the ACL-IJCNLP 2021 Student Research Workshop.","year":2021,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Dental Research and COVID-19","field":"Dentistry","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Mathematics education; Data science; Psychology","authors":[{"name":"Jad Kabbara","is_ca":true},{"name":"Haitao Lin","is_ca":false},{"name":"Amandalynne Paullada","is_ca":false},{"name":"Jannis Vamvas","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07961984896349812,"gpt":0.418582325272663,"spread":0.3389624763091649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01235222,0.002411402,0.003038754,0.002971838,0.003661916,0.01218072,0.004553352,0.004866916,0.1682924],"category_scores_gemma":[0.02253159,0.001703931,0.001895152,0.002576815,0.001789963,0.01348507,0.007221777,0.006280842,0.1405028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003054442,"about_ca_system_score_gemma":0.004882525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0187659,"about_ca_topic_score_gemma":0.03657106,"domain_scores_codex":[0.9921849,0.004252728,0.0005716434,0.001064142,0.001432854,0.0004937687],"domain_scores_gemma":[0.9786004,0.00781996,0.0003738291,0.002796857,0.007498982,0.002909885],"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":[0.0001066227,0.00008959221,0.0001384821,0.0001299863,0.00001912592,0.00005403465,0.0001131792,0.00008587656,0.0002343537,0.001460479,0.9781418,0.01942636],"study_design_scores_gemma":[0.0001019632,0.00004143687,0.0008452629,0.000395124,0.00005779158,0.000247732,0.0007672828,0.002030469,0.001024729,0.008379363,0.9860596,0.0000492135],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01402758,0.04551449,0.1785391,0.179806,0.174863,0.001535698,0.09900144,0.03389325,0.2728195],"genre_scores_gemma":[0.03473219,0.01664625,0.0846919,0.01703571,0.02070054,0.00222908,0.2930169,0.01117715,0.5197702],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1682924,"threshold_uncertainty_score":0.5629944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3177369674","doi":"","title":"AdElectra - Effective Adversarial Electra","year":2021,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Classical Philosophy and Thought","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Adversarial system; Computer science; Artificial intelligence","authors":[{"name":"Makesh Narsimhan Sreedhar","is_ca":false},{"name":"Alessandro Sordoni","is_ca":false},{"name":"Siva Reddy","is_ca":false},{"name":"Aaron Courville","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01477190681740678,"gpt":0.2364592103238264,"spread":0.2216873035064197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001610748,0.001106189,0.0009357152,0.0007435356,0.0008411671,0.001532112,0.001589618,0.001748239,0.01938988],"category_scores_gemma":[0.005482165,0.0004891922,0.0006663745,0.0005785575,0.001758845,0.002623097,0.004255781,0.002791852,0.002718556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061332,"about_ca_system_score_gemma":0.00100859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001058805,"about_ca_topic_score_gemma":0.001784108,"domain_scores_codex":[0.9992195,0.0003008534,0.00003100256,0.0001648443,0.0001876662,0.00009612643],"domain_scores_gemma":[0.9979854,0.001311761,0.0000600424,0.0002962702,0.0002435895,0.0001028375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001355363,0.00008225199,0.0002869616,0.0001223248,0.00004923632,0.0001489239,0.00007825236,0.3140082,0.001930446,0.5868081,0.01408067,0.08226915],"study_design_scores_gemma":[0.00001274213,0.00003446703,0.00005732134,0.00001896849,0.000008056448,0.00006777734,0.00001570894,0.6987817,0.0008179473,0.2956849,0.004491941,0.000008458431],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0109896,0.0004658417,0.9519984,0.001385678,0.000309904,0.00005988777,0.0002342712,0.0004678835,0.03408861],"genre_scores_gemma":[0.6876865,0.0009643004,0.195692,0.001194252,0.0004854153,0.0002714229,0.0007770152,0.0005269053,0.1124022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01938988,"threshold_uncertainty_score":0.06486559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}