{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":5,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":5,"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":"4cb97538a8a0","filters":{"venue":"Dialogue & Discourse"}},"results":[{"id":"W2810821963","doi":"10.5087/dad.2018.101","title":"A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version","year":2018,"lang":"en","type":"article","venue":"Dialogue & Discourse","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal; McGill University; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Samsung; Compute Canada; Samsung Advanced Institute of Technology; Canadian Institute for Advanced Research","keywords":"Computer science; Data science; Artificial intelligence; Transfer of learning; Data-driven; Machine learning","authors":[{"name":"Iulian Vlad Serban","is_ca":true},{"name":"Ryan Lowe","is_ca":true},{"name":"Peter Henderson","is_ca":true},{"name":"Laurent Charlin","is_ca":true},{"name":"Joëlle Pineau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0922818192006133,"gpt":0.3122704740781831,"spread":0.2199886548775699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01904847,0.001600518,0.00181157,0.01331458,0.002428056,0.005478545,0.004737551,0.002323529,0.0225133],"category_scores_gemma":[0.07938923,0.001766904,0.001252764,0.020189,0.002087669,0.008500996,0.004769988,0.003153273,0.01947124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002173811,"about_ca_system_score_gemma":0.005698648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004336862,"about_ca_topic_score_gemma":0.00698217,"domain_scores_codex":[0.9837266,0.006142931,0.002886008,0.00244566,0.004495636,0.0003031339],"domain_scores_gemma":[0.9107084,0.05425183,0.002561713,0.01602809,0.01496953,0.001480414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003436968,0.0003408582,0.005636648,0.01343121,0.0001785682,0.0002491913,0.001480244,0.004159671,0.005432594,0.01890762,0.28477,0.6650697],"study_design_scores_gemma":[0.00005931632,0.0001053178,0.008137676,0.003353654,0.0000783337,0.0004989677,0.000664529,0.004785548,0.008292857,0.0106902,0.963172,0.0001615235],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"review","genre_scores_codex":[0.02742877,0.0972506,0.3525999,0.009356732,0.00515734,0.002649438,0.3970071,0.03043065,0.07811948],"genre_scores_gemma":[0.04081134,0.02607972,0.3749047,0.001495632,0.0009167872,0.003671796,0.5349616,0.007889258,0.00926917],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.0225133,"threshold_uncertainty_score":0.1007391,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2593751037","doi":"10.5087/dad.2017.102","title":"Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus","year":2017,"lang":"en","type":"article","venue":"Dialogue & Discourse","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":"McGill University","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; Samsung Advanced Institute of Technology","keywords":"Utterance; Computer science; Conversation; Context (archaeology); Task (project management); Artificial intelligence; Construct (python library); Natural language processing; Feature engineering; End-to-end principle; Recall; Feature (linguistics); Precision and recall; Artificial neural network; Speech recognition; Machine learning; Deep learning; Linguistics","authors":[{"name":"Ryan Lowe","is_ca":true},{"name":"Nissan Pow","is_ca":true},{"name":"Iulian Vlad Serban","is_ca":false},{"name":"Laurent Charlin","is_ca":true},{"name":"Chia‐Wei Liu","is_ca":true},{"name":"Joëlle Pineau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04910393159180949,"gpt":0.2845377901034271,"spread":0.2354338585116176,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003414104,0.002785882,0.001183196,0.000911732,0.001030879,0.001691567,0.002644169,0.002213203,0.006716634],"category_scores_gemma":[0.01076533,0.0008683479,0.001143383,0.0006272497,0.000728379,0.002875923,0.002183222,0.003433058,0.005764708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001702836,"about_ca_system_score_gemma":0.001276737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01146266,"about_ca_topic_score_gemma":0.01610716,"domain_scores_codex":[0.9972655,0.001205978,0.0001251044,0.0009867853,0.000228228,0.0001884951],"domain_scores_gemma":[0.9962167,0.002160238,0.000109801,0.0005528635,0.0007625284,0.0001978241],"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":[0.002551694,0.002400896,0.00637616,0.001488684,0.0007249638,0.0007614478,0.002447007,0.3314799,0.02358606,0.003604995,0.07930416,0.5452741],"study_design_scores_gemma":[0.0001818157,0.0004252322,0.002023577,0.00008931271,0.00009030511,0.0001504169,0.0004735979,0.9620607,0.01693306,0.002981755,0.01450958,0.00008068801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3880969,0.004139055,0.47181,0.001303586,0.002074148,0.002080805,0.012063,0.09972835,0.01870414],"genre_scores_gemma":[0.5913557,0.0005424359,0.3553995,0.0008249721,0.0001891324,0.00226195,0.03220155,0.002263123,0.01496169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01146266,"threshold_uncertainty_score":0.02279186,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041917831","doi":"10.5087/dad.2013.211","title":"Annotation upon Annotation: Adding Signalling Information to a Corpus of Discourse Relations","year":2013,"lang":"en","type":"article","venue":"Dialogue & Discourse","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Annotation; Rhetorical question; Parsing; Computer science; Natural language processing; Artificial intelligence; Corpus linguistics; Linguistics; Information retrieval","authors":[{"name":"Maite Taboada","is_ca":true},{"name":"Debopam Das","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01066699860770908,"gpt":0.2763759844067075,"spread":0.2657089857989984,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01289671,0.001305528,0.001398505,0.007326151,0.004346363,0.005791855,0.003114906,0.00285996,0.01478037],"category_scores_gemma":[0.06210398,0.001689528,0.001010419,0.007613868,0.003234994,0.01035716,0.007970722,0.006314311,0.005955084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001821511,"about_ca_system_score_gemma":0.004069498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004996373,"about_ca_topic_score_gemma":0.008377949,"domain_scores_codex":[0.9871459,0.005729913,0.001239706,0.002371267,0.003095447,0.0004176614],"domain_scores_gemma":[0.9151309,0.05338061,0.002164873,0.01669,0.01157067,0.001063023],"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":[0.001222176,0.0006642023,0.005871384,0.002823058,0.0001421175,0.002272218,0.03286527,0.006373188,0.1838109,0.1237888,0.0898954,0.5502713],"study_design_scores_gemma":[0.0001867509,0.0002770613,0.01156066,0.0008625234,0.0002902702,0.001077003,0.006630833,0.08906416,0.09832444,0.1125792,0.6785998,0.0005472344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04606997,0.0006290029,0.8903099,0.003277148,0.001403603,0.001412436,0.01137686,0.009970801,0.03555042],"genre_scores_gemma":[0.1191748,0.0005032485,0.8303044,0.001047421,0.0005962828,0.002481036,0.02629457,0.003922916,0.01567531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01478037,"threshold_uncertainty_score":0.06820518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2949637934","doi":"10.5087/dad.2019.104","title":"How compatible are our discourse annotation frameworks? Insights from mapping RST-DT and PDTB annotations","year":2019,"lang":"en","type":"article","venue":"Dialogue & Discourse","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":"Simon Fraser University","funders":"","keywords":"Treebank; Annotation; Computer science; Rhetorical question; Relation (database); Natural language processing; Resource (disambiguation); Artificial intelligence; Linguistics; Data mining","authors":[{"name":"Vera Demberg","is_ca":false},{"name":"Merel Scholman","is_ca":false},{"name":"Fatemeh Torabi Asr","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0142119105583365,"gpt":0.2761876015369167,"spread":0.2619756909785802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04872491,0.001055138,0.001142186,0.007927607,0.004958651,0.0146046,0.00303171,0.002958879,0.00668972],"category_scores_gemma":[0.156378,0.001405438,0.0009851481,0.007651697,0.005577852,0.02027694,0.008133505,0.004760646,0.002010665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005067472,"about_ca_system_score_gemma":0.005730564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01568007,"about_ca_topic_score_gemma":0.01499428,"domain_scores_codex":[0.9409975,0.04287031,0.002790053,0.005304534,0.006510457,0.001527162],"domain_scores_gemma":[0.8758059,0.08424418,0.005309265,0.02157288,0.01150205,0.001565757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0008775321,0.0002268313,0.0240212,0.001169961,0.0002074431,0.0007145589,0.07549348,0.01242501,0.01853564,0.5607303,0.009149878,0.2964482],"study_design_scores_gemma":[0.0001172627,0.0001798649,0.02775147,0.001505803,0.0002448594,0.0008237995,0.04102046,0.1501431,0.0232222,0.6209368,0.1336604,0.0003940435],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1371805,0.002088589,0.7805164,0.01040743,0.0003319677,0.00045412,0.003212524,0.002419059,0.06338934],"genre_scores_gemma":[0.6407163,0.0009235807,0.3487906,0.0005578442,0.00008878385,0.0006479772,0.003239642,0.001376877,0.003658463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04872491,"threshold_uncertainty_score":0.257685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2773571156","doi":"10.5087/dad.2017.204","title":"Discourse coherence and the interpretation of accented pronouns","year":2017,"lang":"en","type":"article","venue":"Dialogue & Discourse","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Cancer Care Ontario","funders":"","keywords":"Pronoun; Interpretation (philosophy); Salience (neuroscience); Coherence (philosophical gambling strategy); Linguistics; Generalization; Comprehension; Psychology; Character (mathematics); Epistemology; Cognitive psychology; Philosophy; Mathematics","authors":[{"name":"Mindaugas Mozuraitis","is_ca":true},{"name":"Daphna Heller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02660946524494552,"gpt":0.2895059161127754,"spread":0.2628964508678299,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003115471,0.0003822471,0.0002875721,0.001041448,0.001263496,0.003741519,0.0005224705,0.0008140714,0.002736908],"category_scores_gemma":[0.01323821,0.0003520083,0.0002399674,0.0006075059,0.004490968,0.004285621,0.001864876,0.001171175,0.0002260567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063678,"about_ca_system_score_gemma":0.0005538057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001281246,"about_ca_topic_score_gemma":0.001136756,"domain_scores_codex":[0.9971159,0.001754129,0.0001271065,0.0004166989,0.000445523,0.0001407916],"domain_scores_gemma":[0.9928644,0.004440903,0.001193581,0.0007451689,0.000565454,0.0001906207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0008629248,0.0003094374,0.03241419,0.0008344593,0.0001751194,0.001550504,0.2529606,0.002334532,0.1779499,0.4521666,0.001336503,0.07710526],"study_design_scores_gemma":[0.0003757776,0.001152706,0.1667894,0.0004234162,0.0002722725,0.001960383,0.08558714,0.01501737,0.05950831,0.6294919,0.03908518,0.000336027],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9344808,0.000701752,0.02320438,0.0008551678,0.00005861834,0.00005493512,0.00008737522,0.0001357029,0.04042134],"genre_scores_gemma":[0.9973756,0.00007690915,0.001925236,0.00004057863,0.00001451561,0.000008424489,0.000031447,0.00002702344,0.00050035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003741519,"threshold_uncertainty_score":0.01647639,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}