{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004623198,0.0002612032,0.0004819451,0.000161952,0.0005470355,0.000341679,0.003608588,0.0001304116,0.00001881211],"category_scores_gemma":[0.0009138499,0.000180441,0.0001073633,0.0005110091,0.0003925552,0.0009949551,0.0007188857,0.0002042478,0.0002571709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006922433,"about_ca_system_score_gemma":0.0005447465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004178867,"about_ca_topic_score_gemma":0.0009681028,"domain_scores_codex":[0.9969236,0.0007038455,0.0006666672,0.0005346086,0.0005624383,0.0006088432],"domain_scores_gemma":[0.9954908,0.0009364714,0.0006883302,0.001978982,0.0006863755,0.0002190566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005660157,0.0004874321,0.0244496,0.0001990149,0.0003847211,0.00004091101,0.002782328,0.0006728536,0.004599904,0.01390465,0.9467317,0.005180878],"study_design_scores_gemma":[0.01720171,0.006876771,0.07971319,0.002195639,0.0009924405,0.001096255,0.003658966,0.7074451,0.008149116,0.005855404,0.1621881,0.004627287],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1606131,0.003275977,0.8090252,0.0007000808,0.01861139,0.002399863,0.003483182,0.0002316516,0.001659596],"genre_scores_gemma":[0.9949079,0.00006972826,0.003040174,0.00008340998,0.001250331,0.00002233536,0.0004609952,0.00002871975,0.0001363677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8342949,"threshold_uncertainty_score":0.735817,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00111718,0.0004780178,0.0005832046,0.000142347,0.001404515,0.001690528,0.004141407,0.0001545617,0.0000102787],"category_scores_gemma":[0.0002458954,0.0003203997,0.0001599603,0.000195555,0.0004761444,0.001032404,0.0007690885,0.0004860547,0.0002638794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009129618,"about_ca_system_score_gemma":0.00035024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00206125,"about_ca_topic_score_gemma":0.001556118,"domain_scores_codex":[0.9964452,0.0002417209,0.0004564002,0.001042482,0.0007882403,0.001025982],"domain_scores_gemma":[0.995326,0.0003108428,0.0004459081,0.003379375,0.0001357563,0.0004021407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001864557,0.0005406156,0.007474265,0.000161103,0.0005897449,0.001392424,0.0734109,0.02811074,0.00174041,0.4742866,0.01363012,0.3984766],"study_design_scores_gemma":[0.02065594,0.004601195,0.137545,0.003879573,0.001647622,0.002188765,0.01911703,0.4039995,0.003179015,0.02680059,0.3593859,0.01699985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1710307,0.0007280683,0.7834511,0.01568747,0.008089296,0.002048363,0.0002333963,0.0006387923,0.01809273],"genre_scores_gemma":[0.9948337,0.00002004163,0.00236007,0.0006402971,0.001378024,0.0002223366,0.00003881034,0.00005371404,0.0004529726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.823803,"threshold_uncertainty_score":0.9999248,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002765632,0.0001730225,0.0001907322,0.0003484587,0.0001607433,0.0002858513,0.0005722105,0.00008807747,0.00002889076],"category_scores_gemma":[0.0002727414,0.0001589829,0.00006829094,0.0007068709,0.00005464024,0.0046949,0.0001376504,0.0001696828,0.0001961824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006978858,"about_ca_system_score_gemma":0.000109296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002249015,"about_ca_topic_score_gemma":0.00002413383,"domain_scores_codex":[0.9985624,0.00006533774,0.0004755192,0.0002407672,0.0003864537,0.0002695495],"domain_scores_gemma":[0.9986435,0.0001171069,0.0003408743,0.0003690051,0.0004111271,0.0001184585],"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":[0.00003944592,0.000261452,0.001718672,0.0001344028,0.00006167075,0.00001127634,0.03341771,0.007389153,0.03477135,0.3927622,0.01069289,0.5187398],"study_design_scores_gemma":[0.003891584,0.001841664,0.03213746,0.002896896,0.0003125348,0.0001018879,0.009568351,0.4776159,0.1446264,0.3179081,0.004167668,0.004931541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.103949,0.000259009,0.8916015,0.002366921,0.0002734502,0.0006304412,0.00002950125,0.0003638442,0.0005263444],"genre_scores_gemma":[0.7982851,0.000005039582,0.2011526,0.0002080742,0.00006182688,0.0001057471,0.0001334737,0.000009335032,0.00003888397],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6943361,"threshold_uncertainty_score":0.6483134,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001188993,0.0003117325,0.000362223,0.000250053,0.0002377487,0.001027765,0.0007741533,0.0002565254,0.000003700305],"category_scores_gemma":[0.000125537,0.0002716577,0.00007885779,0.0005084327,0.00009523653,0.00245102,0.0002876621,0.0005922373,0.00004806903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005453841,"about_ca_system_score_gemma":0.00007723217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000154394,"about_ca_topic_score_gemma":0.00009599115,"domain_scores_codex":[0.9981285,0.0001230873,0.0002645164,0.0007153216,0.0004014202,0.0003671711],"domain_scores_gemma":[0.9984478,0.0001342224,0.0003374812,0.000754608,0.0001719685,0.0001539129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001297299,0.001703995,0.09598503,0.0005848416,0.000602562,0.0005728592,0.08862957,0.0006908345,0.04658945,0.4738413,0.03383315,0.2568367],"study_design_scores_gemma":[0.004528474,0.0005922993,0.135523,0.003779431,0.0003063227,0.00004807506,0.04648488,0.1298575,0.01745578,0.6509998,0.005140677,0.005283686],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5141852,0.006133379,0.4624016,0.01460384,0.001119481,0.0006222223,0.00009578601,0.000707149,0.0001313912],"genre_scores_gemma":[0.8883089,0.000046131,0.1104905,0.0005196214,0.0002554398,0.00004004229,0.0001866955,0.00002587121,0.0001268036],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3741237,"threshold_uncertainty_score":0.9999735,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003417684,0.0001274624,0.000223421,0.00003613194,0.0005200644,0.000369355,0.0003274144,0.00003131713,0.0001380359],"category_scores_gemma":[0.0008789103,0.00008357045,0.00006367408,0.000007618207,0.001740106,0.000293152,0.00009205736,0.00009625045,0.00002345152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000012593,"about_ca_system_score_gemma":0.00004247397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002951268,"about_ca_topic_score_gemma":0.004196499,"domain_scores_codex":[0.9991661,0.00007244149,0.000261148,0.0001808556,0.0001661327,0.0001533276],"domain_scores_gemma":[0.998767,0.0001473514,0.0004349452,0.0004722192,0.0001429454,0.00003558056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001612349,0.00009448523,0.003078806,0.00003569526,0.00007902845,0.000002115238,0.09904794,0.000007782154,0.00002318923,0.8903395,0.0002068498,0.006923351],"study_design_scores_gemma":[0.01199741,0.0004174984,0.1057054,0.001241038,0.001786188,0.00001043152,0.1293406,0.03477601,0.000611482,0.7108034,0.001926724,0.00138367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9293379,0.0002143854,0.002027198,0.03478207,0.003562822,0.001108675,0.0002512195,0.0000615091,0.0286542],"genre_scores_gemma":[0.9987494,0.00002387416,0.00004667058,0.00005547039,0.0006096924,0.00003452805,0.00005003018,0.00001444977,0.000415826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1795361,"threshold_uncertainty_score":0.6411495,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}