{"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10394898,0.00025900896,0.8916015,0.0023669212,0.00027345025,0.0006304412,0.000029501245,0.00036384416,0.0005263444],"genre_scores_gemma":[0.79828507,0.0000050395815,0.20115258,0.0002080742,0.00006182688,0.00010574713,0.00013347366,0.000009335032,0.000038883965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985624,0.00006533774,0.00047551922,0.00024076716,0.0003864537,0.0002695495],"domain_scores_gemma":[0.99864346,0.00011710691,0.0003408743,0.00036900505,0.00041112708,0.00011845849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027656322,0.00017302246,0.00019073217,0.0003484587,0.00016074334,0.00028585127,0.00057221047,0.00008807747,0.000028890763],"category_scores_gemma":[0.00027274142,0.00015898289,0.000068290945,0.00070687087,0.000054640237,0.0046949005,0.0001376504,0.00016968275,0.0001961824],"study_design_candidate":"theoretical_or_conceptual","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":[0.00003944592,0.00026145205,0.0017186722,0.00013440276,0.000061670755,0.000011276343,0.03341771,0.007389153,0.034771346,0.39276218,0.01069289,0.51873976],"study_design_scores_gemma":[0.0038915835,0.0018416643,0.032137465,0.0028968963,0.00031253477,0.000101887854,0.009568351,0.4776159,0.1446264,0.3179081,0.004167668,0.004931541],"about_ca_topic_score_codex":0.00022490151,"about_ca_topic_score_gemma":0.000024133831,"teacher_disagreement_score":0.69433606,"about_ca_system_score_codex":0.000069788584,"about_ca_system_score_gemma":0.00010929597,"threshold_uncertainty_score":0.6483134},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17103073,0.00072806835,0.78345114,0.01568747,0.008089296,0.002048363,0.00023339629,0.0006387923,0.01809273],"genre_scores_gemma":[0.9948337,0.000020041629,0.00236007,0.0006402971,0.0013780239,0.00022233659,0.000038810336,0.000053714044,0.00045297263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964452,0.00024172089,0.00045640022,0.0010424823,0.00078824034,0.0010259824],"domain_scores_gemma":[0.995326,0.00031084276,0.00044590814,0.0033793754,0.00013575626,0.00040214072],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011171795,0.00047801784,0.0005832046,0.00014234704,0.0014045155,0.0016905284,0.004141407,0.00015456173,0.000010278697],"category_scores_gemma":[0.00024589538,0.00032039973,0.00015996028,0.00019555501,0.00047614437,0.0010324043,0.00076908845,0.00048605472,0.0002638794],"study_design_candidate":"theoretical_or_conceptual","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":[0.00018645567,0.0005406156,0.0074742646,0.00016110302,0.00058974494,0.0013924245,0.0734109,0.028110739,0.00174041,0.4742866,0.013630124,0.39847663],"study_design_scores_gemma":[0.020655936,0.0046011955,0.13754502,0.0038795732,0.001647622,0.0021887654,0.019117033,0.4039995,0.0031790147,0.026800588,0.3593859,0.01699985],"about_ca_topic_score_codex":0.0020612497,"about_ca_topic_score_gemma":0.0015561184,"teacher_disagreement_score":0.823803,"about_ca_system_score_codex":0.000091296184,"about_ca_system_score_gemma":0.00035023998,"threshold_uncertainty_score":0.9999248},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9293379,0.00021438544,0.0020271977,0.034782067,0.0035628225,0.0011086753,0.00025121952,0.000061509105,0.028654195],"genre_scores_gemma":[0.99874943,0.000023874165,0.00004667058,0.00005547039,0.0006096924,0.000034528053,0.000050030183,0.000014449774,0.00041582598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991661,0.000072441486,0.000261148,0.0001808556,0.0001661327,0.0001533276],"domain_scores_gemma":[0.99876696,0.00014735143,0.00043494516,0.00047221917,0.00014294544,0.000035580564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003417684,0.00012746242,0.00022342097,0.00003613194,0.00052006444,0.00036935497,0.00032741437,0.000031317126,0.00013803592],"category_scores_gemma":[0.0008789103,0.00008357045,0.00006367408,0.000007618207,0.0017401065,0.000293152,0.00009205736,0.00009625045,0.000023451516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016123486,0.00009448523,0.0030788062,0.000035695262,0.000079028454,0.0000021152384,0.099047944,0.000007782154,0.00002318923,0.8903395,0.00020684983,0.0069233514],"study_design_scores_gemma":[0.01199741,0.0004174984,0.10570543,0.0012410375,0.001786188,0.000010431521,0.12934065,0.03477601,0.00061148196,0.71080345,0.0019267241,0.0013836704],"about_ca_topic_score_codex":0.0029512679,"about_ca_topic_score_gemma":0.0041964995,"teacher_disagreement_score":0.17953606,"about_ca_system_score_codex":0.000012593005,"about_ca_system_score_gemma":0.000042473966,"threshold_uncertainty_score":0.6411495},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16061307,0.0032759765,0.80902517,0.0007000808,0.018611388,0.002399863,0.0034831816,0.0002316516,0.0016595965],"genre_scores_gemma":[0.9949079,0.00006972826,0.0030401745,0.00008340998,0.0012503306,0.000022335362,0.00046099516,0.000028719753,0.0001363677],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969236,0.0007038455,0.00066666724,0.0005346086,0.00056243833,0.00060884317],"domain_scores_gemma":[0.9954908,0.0009364714,0.0006883302,0.0019789818,0.00068637554,0.00021905656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046231984,0.00026120315,0.0004819451,0.00016195205,0.00054703554,0.00034167897,0.003608588,0.00013041156,0.000018812114],"category_scores_gemma":[0.00091384986,0.00018044097,0.00010736333,0.0005110091,0.00039255517,0.0009949551,0.00071888574,0.00020424776,0.00025717093],"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":[0.0005660157,0.00048743215,0.024449602,0.00019901486,0.0003847211,0.000040911014,0.0027823278,0.00067285355,0.0045999037,0.013904649,0.9467317,0.0051808776],"study_design_scores_gemma":[0.017201714,0.006876771,0.07971319,0.0021956393,0.0009924405,0.0010962553,0.0036589664,0.70744514,0.008149116,0.005855404,0.1621881,0.004627287],"about_ca_topic_score_codex":0.0041788667,"about_ca_topic_score_gemma":0.00096810283,"teacher_disagreement_score":0.83429486,"about_ca_system_score_codex":0.000069224334,"about_ca_system_score_gemma":0.0005447465,"threshold_uncertainty_score":0.73581696},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5141852,0.006133379,0.46240157,0.014603843,0.0011194814,0.0006222223,0.00009578601,0.00070714904,0.0001313912],"genre_scores_gemma":[0.8883089,0.000046131005,0.11049053,0.0005196214,0.00025543975,0.000040042287,0.00018669547,0.000025871213,0.00012680356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981285,0.00012308727,0.00026451645,0.0007153216,0.0004014202,0.0003671711],"domain_scores_gemma":[0.99844784,0.00013422238,0.0003374812,0.00075460796,0.00017196847,0.0001539129],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011889928,0.0003117325,0.00036222296,0.000250053,0.00023774867,0.0010277648,0.00077415333,0.00025652544,0.0000037003053],"category_scores_gemma":[0.000125537,0.00027165774,0.00007885779,0.00050843274,0.00009523653,0.00245102,0.00028766214,0.00059223734,0.00004806903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012972989,0.0017039949,0.095985025,0.0005848416,0.000602562,0.0005728592,0.08862957,0.00069083454,0.04658945,0.47384128,0.03383315,0.2568367],"study_design_scores_gemma":[0.0045284736,0.0005922993,0.13552304,0.0037794313,0.00030632273,0.00004807506,0.046484884,0.12985753,0.017455779,0.6509998,0.005140677,0.0052836863],"about_ca_topic_score_codex":0.00015439399,"about_ca_topic_score_gemma":0.00009599115,"teacher_disagreement_score":0.3741237,"about_ca_system_score_codex":0.000054538406,"about_ca_system_score_gemma":0.000077232165,"threshold_uncertainty_score":0.99997354},"labels":[],"label_agreement":null}]}