{"meta":{"query_hash":"4cb97538a8a0","filters":{"venue":"Dialogue & Discourse"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/4cb97538a8a0","api":"https://metacan.xera.ac/api/v1/cohort?venue=Dialogue+%26+Discourse"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.010666998607709078,"score_gpt":0.27637598440670746,"score_spread":0.2657089857989984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041917831","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046069972,0.00062900287,0.8903099,0.0032771477,0.001403603,0.0014124365,0.011376858,0.009970801,0.03555042],"genre_scores_gemma":[0.11917479,0.0005032485,0.83030444,0.0010474205,0.0005962828,0.0024810361,0.026294572,0.003922916,0.015675314],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9871459,0.005729913,0.0012397064,0.0023712667,0.003095447,0.00041766142],"domain_scores_gemma":[0.9151309,0.05338061,0.0021648733,0.01669,0.011570665,0.001063023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01289671,0.0013055276,0.0013985052,0.0073261512,0.004346363,0.005791855,0.0031149061,0.0028599603,0.014780366],"category_scores_gemma":[0.06210398,0.001689528,0.0010104188,0.0076138675,0.0032349941,0.010357164,0.007970722,0.006314311,0.005955084],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001222176,0.0006642023,0.005871384,0.0028230578,0.00014211745,0.0022722178,0.032865267,0.0063731875,0.1838109,0.12378882,0.089895405,0.5502713],"study_design_scores_gemma":[0.00018675085,0.00027706134,0.011560656,0.00086252345,0.00029027017,0.0010770028,0.006630833,0.08906416,0.09832444,0.112579204,0.67859983,0.00054723443],"about_ca_topic_score_codex":0.0049963733,"about_ca_topic_score_gemma":0.008377949,"teacher_disagreement_score":0.014780366,"about_ca_system_score_codex":0.0018215108,"about_ca_system_score_gemma":0.004069498,"threshold_uncertainty_score":0.06820518},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.049103931591809494,"score_gpt":0.28453779010342706,"score_spread":0.23543385851161758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593751037","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38809693,0.004139055,0.47180998,0.0013035857,0.0020741478,0.002080805,0.012063,0.099728346,0.018704139],"genre_scores_gemma":[0.59135574,0.0005424359,0.35539946,0.0008249721,0.00018913239,0.0022619504,0.032201547,0.0022631232,0.014961687],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726546,0.0012059776,0.00012510442,0.0009867853,0.00022822796,0.00018849515],"domain_scores_gemma":[0.9962167,0.0021602383,0.000109800996,0.0005528635,0.0007625284,0.00019782412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034141045,0.0027858817,0.0011831959,0.00091173203,0.0010308787,0.0016915674,0.0026441691,0.002213203,0.0067166337],"category_scores_gemma":[0.010765325,0.0008683479,0.0011433831,0.00062724965,0.000728379,0.0028759227,0.0021832222,0.0034330576,0.005764708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025516942,0.002400896,0.0063761603,0.0014886844,0.00072496384,0.0007614478,0.0024470075,0.33147994,0.023586055,0.003604995,0.07930416,0.5452741],"study_design_scores_gemma":[0.0001818157,0.0004252322,0.0020235768,0.000089312714,0.00009030511,0.0001504169,0.0004735979,0.96206075,0.01693306,0.0029817547,0.014509575,0.000080688005],"about_ca_topic_score_codex":0.011462662,"about_ca_topic_score_gemma":0.016107159,"teacher_disagreement_score":0.011462662,"about_ca_system_score_codex":0.001702836,"about_ca_system_score_gemma":0.0012767372,"threshold_uncertainty_score":0.022791862},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.026609465244945524,"score_gpt":0.28950591611277543,"score_spread":0.2628964508678299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773571156","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9344808,0.000701752,0.023204377,0.0008551678,0.000058618338,0.000054935124,0.00008737522,0.00013570288,0.04042134],"genre_scores_gemma":[0.9973756,0.00007690915,0.0019252362,0.00004057863,0.000014515608,0.000008424489,0.000031446998,0.000027023438,0.00050035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99711585,0.0017541287,0.00012710647,0.00041669892,0.00044552304,0.00014079163],"domain_scores_gemma":[0.9928644,0.004440903,0.0011935814,0.0007451689,0.000565454,0.00019062073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031154708,0.0003822471,0.00028757207,0.001041448,0.0012634961,0.0037415186,0.0005224705,0.00081407145,0.0027369082],"category_scores_gemma":[0.013238212,0.0003520083,0.00023996744,0.0006075059,0.004490968,0.004285621,0.0018648756,0.0011711753,0.00022605665],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008629248,0.00030943737,0.032414194,0.00083445926,0.00017511938,0.0015505044,0.25296056,0.002334532,0.17794994,0.45216662,0.0013365028,0.07710526],"study_design_scores_gemma":[0.0003757776,0.0011527055,0.16678943,0.00042341618,0.00027227247,0.0019603826,0.085587144,0.015017371,0.059508305,0.6294919,0.03908518,0.000336027],"about_ca_topic_score_codex":0.0012812463,"about_ca_topic_score_gemma":0.0011367563,"teacher_disagreement_score":0.0037415186,"about_ca_system_score_codex":0.001063678,"about_ca_system_score_gemma":0.0005538057,"threshold_uncertainty_score":0.016476393},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0922818192006133,"score_gpt":0.31227047407818315,"score_spread":0.21998865487756986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810821963","genre_codex":"dataset","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027428767,0.0972506,0.35259995,0.0093567325,0.0051573403,0.0026494383,0.39700708,0.030430652,0.07811948],"genre_scores_gemma":[0.040811338,0.026079722,0.3749047,0.0014956318,0.00091678725,0.003671796,0.53496164,0.007889258,0.00926917],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9837266,0.0061429306,0.0028860078,0.0024456596,0.004495636,0.00030313394],"domain_scores_gemma":[0.9107084,0.054251827,0.0025617129,0.01602809,0.014969531,0.0014804143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019048471,0.0016005185,0.0018115704,0.013314576,0.002428056,0.0054785446,0.0047375513,0.0023235295,0.022513304],"category_scores_gemma":[0.07938923,0.0017669037,0.0012527639,0.020189002,0.0020876692,0.008500996,0.004769988,0.0031532731,0.019471241],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034369677,0.0003408582,0.005636648,0.01343121,0.00017856824,0.00024919127,0.0014802443,0.004159671,0.005432594,0.018907623,0.28477,0.6650697],"study_design_scores_gemma":[0.000059316317,0.00010531777,0.008137676,0.0033536537,0.0000783337,0.0004989677,0.000664529,0.0047855484,0.008292857,0.010690205,0.963172,0.00016152351],"about_ca_topic_score_codex":0.0043368624,"about_ca_topic_score_gemma":0.0069821696,"teacher_disagreement_score":0.022513304,"about_ca_system_score_codex":0.0021738114,"about_ca_system_score_gemma":0.0056986483,"threshold_uncertainty_score":0.10073912},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014211910558336502,"score_gpt":0.2761876015369167,"score_spread":0.2619756909785802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949637934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13718052,0.0020885887,0.78051645,0.010407435,0.0003319677,0.00045412005,0.0032125236,0.0024190592,0.06338934],"genre_scores_gemma":[0.64071625,0.00092358066,0.3487906,0.0005578442,0.00008878385,0.0006479772,0.0032396424,0.0013768767,0.0036584628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.94099754,0.042870305,0.0027900527,0.0053045335,0.006510457,0.0015271623],"domain_scores_gemma":[0.87580585,0.08424418,0.005309265,0.021572884,0.011502049,0.0015657567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04872491,0.0010551382,0.0011421856,0.007927607,0.004958651,0.014604604,0.0030317097,0.002958879,0.00668972],"category_scores_gemma":[0.156378,0.0014054384,0.0009851481,0.0076516974,0.0055778516,0.020276941,0.0081335055,0.004760646,0.0020106654],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008775321,0.00022683134,0.024021203,0.0011699607,0.0002074431,0.0007145589,0.07549348,0.012425014,0.018535644,0.56073034,0.009149878,0.29644817],"study_design_scores_gemma":[0.00011726269,0.00017986495,0.027751474,0.0015058027,0.0002448594,0.0008237995,0.041020457,0.15014313,0.023222199,0.62093675,0.1336604,0.00039404354],"about_ca_topic_score_codex":0.015680067,"about_ca_topic_score_gemma":0.014994276,"teacher_disagreement_score":0.04872491,"about_ca_system_score_codex":0.005067472,"about_ca_system_score_gemma":0.0057305642,"threshold_uncertainty_score":0.257685},"labels":[],"label_agreement":null}]}