{"meta":{"query_hash":"768c772dceab","filters":{"venue":"Synthesis lectures on human language technologies"},"cohort_total":16,"direct_labels_cover":0,"predictions_cover":16,"exported":16,"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/768c772dceab","api":"https://metacan.xera.ac/api/v1/cohort?venue=Synthesis+lectures+on+human+language+technologies"},"results":[{"id":"W2397944984","doi":"10.2200/s00659ed1v01y201508hlt030","title":"Natural Language Processing for Social Media","year":2015,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Ottawa; University of Toronto; University of Southern California","keywords":"Social media; Interpersonal communication; Natural (archaeology); Computer science; Internet privacy; Data science; Psychology; Sociology; Linguistics; World Wide Web; Communication; History","score_opus":0.05859163540961687,"score_gpt":0.3354402399822846,"score_spread":0.27684860457266774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397944984","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":[0.87720287,0.03234254,0.057995304,0.0099028945,0.0012318672,0.0011502333,0.000036401976,0.014104145,0.0060337256],"genre_scores_gemma":[0.9888109,0.0000022856009,0.010652127,0.00012679733,0.00016219054,0.00011518097,0.000009968336,0.000018717754,0.00010183206],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99858224,0.00004231586,0.00021285993,0.00044404357,0.00035039822,0.00036815487],"domain_scores_gemma":[0.9990211,0.0003019625,0.00014969698,0.00042402357,0.00006984056,0.00003338945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032032447,0.00022057725,0.00029437226,0.00037709257,0.00030696834,0.00027054152,0.001155757,0.00015597924,0.000013773474],"category_scores_gemma":[0.0011696023,0.00016893345,0.00014546374,0.00037548205,0.000110920984,0.00019749899,0.00019789483,0.00020112649,0.000015712934],"study_design_candidate":"design_other","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":[0.000022003522,0.00007730637,0.00005157822,0.000037545768,0.00007610423,0.000033213808,0.023756742,0.000016566259,0.012013788,0.01333741,0.008609584,0.94196814],"study_design_scores_gemma":[0.0018410527,0.00033243682,0.0010341817,0.00028983492,0.00018226348,0.000024697563,0.09663545,0.016774908,0.8585749,0.01634307,0.0057832315,0.0021839265],"about_ca_topic_score_codex":0.000007557471,"about_ca_topic_score_gemma":0.00004255518,"teacher_disagreement_score":0.9397842,"about_ca_system_score_codex":0.000067755,"about_ca_system_score_gemma":0.00003379262,"threshold_uncertainty_score":0.6888906},"labels":[],"label_agreement":null},{"id":"W2773853552","doi":"10.2200/s00809ed2v01y201710hlt038","title":"Natural Language Processing for Social Media, Second Edition","year":2017,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa; University of Toronto; University of Southern California","keywords":"Social media; Linguistics; Computer science; Natural language processing; World Wide Web; Philosophy","score_opus":0.035857188233221336,"score_gpt":0.3292590273087216,"score_spread":0.29340183907550027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773853552","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":[0.9460585,0.007614503,0.024803033,0.0077916128,0.0014089668,0.0008340177,0.000069606525,0.0056380006,0.0057817325],"genre_scores_gemma":[0.99476904,0.0000032061319,0.0044719144,0.00009308009,0.0003346945,0.00012782769,0.000013229744,0.000017255887,0.00016977203],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986998,0.000027019105,0.00019826411,0.00046444777,0.00026696417,0.00034350945],"domain_scores_gemma":[0.998622,0.00026315617,0.0003075091,0.00073824136,0.000049693732,0.000019372323],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00024691224,0.0002137812,0.00028217913,0.00028894385,0.0014709205,0.00074661407,0.0017061643,0.00017481213,0.000073291245],"category_scores_gemma":[0.0010321457,0.00017148982,0.0001697129,0.00009987739,0.00018378359,0.00039332206,0.0002508397,0.0002215155,0.000011681335],"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":[0.000013269396,0.00005619516,0.00005370958,0.000066534296,0.000075019845,0.000026893007,0.0075885146,0.0000020016255,0.036686644,0.009032653,0.005720583,0.940678],"study_design_scores_gemma":[0.0008890888,0.0001323479,0.0072294404,0.0002686632,0.00010356272,0.000010326601,0.0149433175,0.0047669164,0.95772964,0.010128368,0.002575361,0.0012229858],"about_ca_topic_score_codex":0.0000070172186,"about_ca_topic_score_gemma":0.00013838975,"teacher_disagreement_score":0.939455,"about_ca_system_score_codex":0.00004499787,"about_ca_system_score_gemma":0.000017717353,"threshold_uncertainty_score":0.99982905},"labels":[],"label_agreement":null},{"id":"W2985695201","doi":"10.2200/s00935ed1v02y201907hlt043","title":"Linguistic Fundamentals for Natural Language Processing II: 100 Essentials from Semantics and Pragmatics","year":2019,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pragmatics; Computer science; Linguistics; Semantics (computer science); Selection (genetic algorithm); Meaning (existential); Natural language processing; Natural language; Natural language understanding; Task (project management); Artificial intelligence; Deep linguistic processing; Computational linguistics; Natural (archaeology); Psychology; Philosophy","score_opus":0.014404604552958743,"score_gpt":0.3076386150326261,"score_spread":0.29323401047966735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985695201","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":[0.8892898,0.05798765,0.03856174,0.0017394634,0.00041301356,0.0018287578,0.000078205434,0.00965669,0.00044469672],"genre_scores_gemma":[0.8261658,0.000020097119,0.17318837,0.0002128229,0.00006138246,0.00010182057,0.00001773904,0.00004521217,0.0001867723],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99776596,0.00006122622,0.0004031104,0.0008354205,0.0003945184,0.0005397634],"domain_scores_gemma":[0.99774265,0.0007371866,0.00034821904,0.0010293267,0.00010006371,0.000042533928],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031310317,0.00045291573,0.00055932574,0.00042520792,0.00046713382,0.0005527144,0.0015557959,0.0003261889,0.000024172641],"category_scores_gemma":[0.0018285487,0.00035803867,0.00011346961,0.00032689678,0.00020176463,0.0002915675,0.00071418675,0.00046226487,0.000009624456],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052508458,0.00021617294,0.00022316864,0.00094542676,0.00016584844,0.000110657136,0.016981727,0.000008492547,0.47620422,0.028848697,0.00057083165,0.47567227],"study_design_scores_gemma":[0.00038103768,0.0002702795,0.00007927614,0.0008371912,0.00007844142,0.00002271768,0.0023682322,0.0042810384,0.9465845,0.043919917,0.00034650273,0.00083083246],"about_ca_topic_score_codex":0.00006331192,"about_ca_topic_score_gemma":0.000044050492,"teacher_disagreement_score":0.47484142,"about_ca_system_score_codex":0.00009231049,"about_ca_system_score_gemma":0.000043529504,"threshold_uncertainty_score":0.99988717},"labels":[],"label_agreement":null},{"id":"W3021520429","doi":"10.1007/978-3-031-02138-1","title":"Cross-Language Information Retrieval","year":2010,"lang":"en","type":"book","venue":"Synthesis lectures on human language technologies","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Cross-language information retrieval; Artificial intelligence; Natural language processing; Information retrieval; Linguistics; Machine translation; Philosophy","score_opus":0.011538167100995443,"score_gpt":0.2955057917965311,"score_spread":0.28396762469553566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021520429","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011813772,0.06198852,0.07567492,0.004599182,0.003422324,0.006337038,0.00084257004,0.16799515,0.6673265],"genre_scores_gemma":[0.3834026,0.00028171,0.300399,0.0028250439,0.0012437906,0.0005833377,0.00067610404,0.00058137433,0.31000707],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99626493,0.00007207753,0.00076453853,0.0010107385,0.0010760679,0.00081166375],"domain_scores_gemma":[0.9949484,0.000553689,0.0008601259,0.0033377295,0.00022093502,0.00007914341],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0005953038,0.0009965712,0.00085998396,0.0017175748,0.00052597246,0.001425957,0.006088762,0.0027238363,0.0002310791],"category_scores_gemma":[0.0032240697,0.0008148248,0.00035669262,0.00048261255,0.0006375703,0.0011658138,0.0013181815,0.0035596043,0.00028406514],"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":[0.00008057231,0.000101381374,0.000007229123,0.0007126076,0.00020771194,0.00059156027,0.004557199,0.0000046558803,0.031723548,0.19609833,0.03620193,0.72971326],"study_design_scores_gemma":[0.00029895492,0.00031691973,0.000020157055,0.0008596716,0.0000776074,0.00012189841,0.00026718577,0.00005981298,0.8253755,0.12822026,0.042225942,0.002156095],"about_ca_topic_score_codex":0.00003205091,"about_ca_topic_score_gemma":0.000040565083,"teacher_disagreement_score":0.79365194,"about_ca_system_score_codex":0.00043329474,"about_ca_system_score_gemma":0.00027351905,"threshold_uncertainty_score":0.99961066},"labels":[],"label_agreement":null},{"id":"W3086286810","doi":"10.1007/978-3-031-02178-7_5","title":"Semantic Relations and Deep Learning","year":2021,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on human language technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Permission; Relation (database); Computer science; Artificial intelligence; Deep learning; Natural language processing; Cognitive science; Psychology; Philosophy; Epistemology; Data mining","score_opus":0.020797629303994487,"score_gpt":0.2525003954038954,"score_spread":0.23170276609990093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086286810","genre_codex":"other","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":[0.008206013,0.07215932,0.16122404,0.005107906,0.0004609893,0.0010282517,0.000012554629,0.016594464,0.7352065],"genre_scores_gemma":[0.86654633,0.0005095218,0.016738694,0.00012431522,0.00008897091,0.00004837053,0.0000098989085,0.0000884613,0.11584543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983191,0.000036331356,0.00027299373,0.00079476065,0.0002894492,0.00028740242],"domain_scores_gemma":[0.99817884,0.00043397065,0.00018874789,0.0011265744,0.000042230902,0.000029661482],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001455909,0.0003804629,0.00042795666,0.00048117575,0.00036269173,0.00022409514,0.00087445683,0.00060579466,0.00014525803],"category_scores_gemma":[0.0006345036,0.00034531354,0.00012209137,0.00006873297,0.00015922509,0.00009409095,0.0006033744,0.0010177108,0.00004768422],"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":[0.0000010510877,0.000008535547,0.000014389175,0.000055860262,0.00008486901,0.000226406,0.00075305894,0.00018069941,0.0006334826,0.6448644,0.00009368175,0.35308358],"study_design_scores_gemma":[0.0008336873,0.0007229302,0.0004820919,0.00596612,0.0006954667,0.0005874517,0.0047566285,0.017567847,0.04845256,0.81654376,0.0962744,0.007117033],"about_ca_topic_score_codex":0.000012011832,"about_ca_topic_score_gemma":0.000082115024,"teacher_disagreement_score":0.8583403,"about_ca_system_score_codex":0.000077566496,"about_ca_system_score_gemma":0.00002594015,"threshold_uncertainty_score":0.99989986},"labels":[],"label_agreement":null},{"id":"W3152732297","doi":"10.2200/s01078ed2v01y202002hlt049","title":"Semantic Relations Between Nominals, Second Edition","year":2021,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Toronto","funders":"","keywords":"Curiosity; Mars Exploration Program; Automatic summarization; Computer science; Class (philosophy); Statement (logic); Recall; Semantics (computer science); Linguistics; Question answering; Natural language processing; Artificial intelligence; Psychology; Astrobiology; Programming language; Social psychology; Philosophy","score_opus":0.027629427682573822,"score_gpt":0.278961434224012,"score_spread":0.25133200654143817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152732297","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":[0.7309201,0.0019720432,0.24731061,0.0063294545,0.00025203486,0.00024312353,0.00002433677,0.004609201,0.0083391415],"genre_scores_gemma":[0.98420113,0.0000051295574,0.015021338,0.00011137012,0.00010332389,0.000040439256,0.00000759516,0.000014592634,0.00049505243],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986429,0.00007752274,0.00023845874,0.0005198221,0.00022975514,0.00029154855],"domain_scores_gemma":[0.9982665,0.00043720164,0.00009945165,0.001122152,0.000048591457,0.000026063966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001767878,0.00018266028,0.0002359187,0.0002721407,0.00028449483,0.00016092203,0.00081998116,0.00021710346,0.00022227435],"category_scores_gemma":[0.0007799416,0.00016709896,0.000092933886,0.0003255073,0.00007551934,0.00019408915,0.00028006124,0.0003396661,0.00009232753],"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":[0.000005992598,0.00025761212,0.004022649,0.00022127561,0.00032030695,0.0007752828,0.005058712,0.00062546943,0.13326557,0.25162545,0.01057415,0.59324753],"study_design_scores_gemma":[0.00019882384,0.00008023311,0.010107405,0.00022000063,0.00005262705,0.000039755734,0.0016809433,0.0010724372,0.9139288,0.06974351,0.0022315981,0.0006438396],"about_ca_topic_score_codex":0.000011833263,"about_ca_topic_score_gemma":0.000092603375,"teacher_disagreement_score":0.78066325,"about_ca_system_score_codex":0.00007531032,"about_ca_system_score_gemma":0.00004002494,"threshold_uncertainty_score":0.6814098},"labels":[],"label_agreement":null},{"id":"W3208821253","doi":"10.2200/s01123ed1v01y202108hlt053","title":"Pretrained Transformers for Text Ranking: BERT and Beyond","year":2021,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Compute Canada","keywords":"Transformer; Computer science; Artificial intelligence; Natural language processing; Encoder; Ranking (information retrieval); Question answering; Information retrieval; Artificial neural network; Engineering","score_opus":0.020761885001247454,"score_gpt":0.2760993430802039,"score_spread":0.25533745807895647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208821253","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":[0.31459856,0.005394342,0.6559633,0.011307376,0.00020183375,0.0007794431,0.00002221744,0.0038604967,0.007872435],"genre_scores_gemma":[0.9650732,0.00003126814,0.03427654,0.0003055146,0.000024679905,0.0001133053,0.0000024874385,0.000017703804,0.00015525319],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986782,0.000033886317,0.000191635,0.00056432677,0.00018707769,0.00034485655],"domain_scores_gemma":[0.9989268,0.00041441864,0.000053578413,0.00053715,0.000039681174,0.000028336737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001885195,0.00020607034,0.000256541,0.00019882833,0.00024376182,0.00015531032,0.0005724548,0.00020656409,0.000020806503],"category_scores_gemma":[0.0006763894,0.00017381027,0.00009652957,0.00020529663,0.00011364682,0.00013142555,0.00011926067,0.00019881655,0.0000020964078],"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":[0.0000111091485,0.000043464534,0.0000329175,0.00008529462,0.00006447042,0.000045257475,0.0027469455,0.00002673637,0.058906876,0.07022757,0.00026867737,0.86754066],"study_design_scores_gemma":[0.0005238819,0.00016320027,0.00020858034,0.00009847185,0.00003822495,0.000043367676,0.003040518,0.0035352358,0.9461379,0.043915417,0.0017627685,0.00053245213],"about_ca_topic_score_codex":0.0000070157785,"about_ca_topic_score_gemma":0.000057277703,"teacher_disagreement_score":0.887231,"about_ca_system_score_codex":0.00003584091,"about_ca_system_score_gemma":0.00003222991,"threshold_uncertainty_score":0.7087777},"labels":[],"label_agreement":null},{"id":"W4211107845","doi":"10.2200/s00999ed3v01y202003hlt046","title":"Natural Language Processing for Social Media, Third Edition","year":2020,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Social media; Interpersonal communication; Natural (archaeology); Computer science; Psychology; Sociology; World Wide Web; Communication; History","score_opus":0.038861291742286454,"score_gpt":0.3072510998608941,"score_spread":0.26838980811860763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211107845","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":[0.636974,0.025794249,0.23058903,0.072647445,0.0014708631,0.0020225467,0.00011175222,0.025596164,0.0047939625],"genre_scores_gemma":[0.9920188,0.0000046917667,0.0068461504,0.0005617151,0.00039879064,0.00011029093,0.000019126352,0.000017774528,0.000022617309],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99860865,0.000038432867,0.00022291903,0.00049261097,0.00031376773,0.00032363614],"domain_scores_gemma":[0.9991626,0.0003215301,0.00016429182,0.00027802057,0.000044599234,0.00002896064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015420698,0.00021784678,0.0002937013,0.00022477032,0.00042570994,0.00025745668,0.0010084261,0.00015963537,0.00003140987],"category_scores_gemma":[0.0009673967,0.00017425063,0.00017612157,0.0004000444,0.00009649553,0.00022150636,0.00017180713,0.00025071844,0.000016846561],"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":[0.000031305386,0.00006718574,0.000029636452,0.00011522379,0.00010032034,0.000037183338,0.031633954,0.000020178699,0.07347572,0.012039448,0.015614242,0.8668356],"study_design_scores_gemma":[0.00087694684,0.0002704653,0.00077464385,0.00020294516,0.00014049464,0.000006694722,0.039063685,0.022085495,0.92785907,0.0045468756,0.0028198925,0.0013528096],"about_ca_topic_score_codex":0.0000033937724,"about_ca_topic_score_gemma":0.000015342684,"teacher_disagreement_score":0.8654828,"about_ca_system_score_codex":0.00003662306,"about_ca_system_score_gemma":0.0000182579,"threshold_uncertainty_score":0.7105735},"labels":[],"label_agreement":null},{"id":"W4211147687","doi":"10.2200/s00204ed1v01y200910hlt005","title":"Spoken Dialogue Systems","year":2009,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Spoken language; Computer science; Multimodality; Adaptation (eye); Communicative competence; Competence (human resources); Human–computer interaction; Natural language processing; Artificial intelligence; Linguistics; Psychology; World Wide Web","score_opus":0.01943691375922096,"score_gpt":0.2708791217803281,"score_spread":0.2514422080211071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211147687","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":[0.7331932,0.022457901,0.05864312,0.010470387,0.0031394914,0.0032727376,0.000082651284,0.05115875,0.11758177],"genre_scores_gemma":[0.9979921,0.00001678352,0.0013618887,0.00022963867,0.00013405323,0.00007418898,0.000004639482,0.000016286795,0.00017041028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979683,0.00010895774,0.00031776598,0.00063604035,0.0003974207,0.00057148846],"domain_scores_gemma":[0.9978701,0.0002814985,0.00015323417,0.0015961692,0.000040485083,0.000058507794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031347547,0.00033445802,0.0004241003,0.000517842,0.0002665263,0.00035720484,0.002124099,0.00031758973,0.000011625902],"category_scores_gemma":[0.00076263497,0.00025567235,0.00013643512,0.00047066755,0.000106652216,0.000200734,0.00014396572,0.0003008877,0.00018803426],"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":[0.000045331977,0.00034876054,0.00024254907,0.00008449372,0.000116560135,0.0008020937,0.0024003764,0.00027280717,0.100724496,0.4783296,0.018308777,0.39832413],"study_design_scores_gemma":[0.0009159831,0.0016626829,0.0067756246,0.00057412195,0.000056181096,0.00024182536,0.0036601888,0.0007664098,0.9121972,0.062582724,0.008118405,0.0024486936],"about_ca_topic_score_codex":0.00012537018,"about_ca_topic_score_gemma":0.000033500157,"teacher_disagreement_score":0.81147265,"about_ca_system_score_codex":0.00009375965,"about_ca_system_score_gemma":0.000027999793,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W4285540724","doi":"10.1007/978-3-031-02178-7_6","title":"Conclusion","year":2021,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on human language technologies","topic":"linguistics and terminology studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Meaning (existential); Linguistics; Natural language processing; Artificial intelligence; Epistemology; Philosophy","score_opus":0.05269171406015205,"score_gpt":0.2754294053772743,"score_spread":0.22273769131712223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285540724","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009826963,0.01082817,0.0000012101119,0.0007608066,0.00061907485,0.00023204107,0.00019065052,0.0019032191,0.9844821],"genre_scores_gemma":[0.42170003,0.0004333437,0.000047348225,0.00034165528,0.00083692884,0.00005691562,0.00006265427,0.00011843403,0.57640266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827915,0.0000196817,0.00036831852,0.0006563997,0.0002988492,0.00037759903],"domain_scores_gemma":[0.998244,0.00040470605,0.0002739799,0.0009037458,0.00014880336,0.000024806866],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000088503075,0.00062004494,0.0007833382,0.00042811892,0.0008807045,0.00018530407,0.0005991912,0.0005922514,0.0057407613],"category_scores_gemma":[0.0006746953,0.00048343392,0.000298438,0.000011918929,0.0013437945,0.000023594097,0.0005012105,0.00079460675,0.00023744976],"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":[0.0000073203273,0.000025240559,0.0000011810895,0.000069647,0.0003061667,0.0005019892,0.0030511094,2.557965e-7,0.00009629162,0.95543516,0.013330796,0.027174857],"study_design_scores_gemma":[0.000116723335,0.0001552508,0.0000028299264,0.00056522246,0.00023890773,0.000009720548,0.0037239504,5.206446e-7,0.0051741474,0.09574045,0.8934767,0.0007955357],"about_ca_topic_score_codex":0.000043924578,"about_ca_topic_score_gemma":0.0010074939,"teacher_disagreement_score":0.88014597,"about_ca_system_score_codex":0.00009073398,"about_ca_system_score_gemma":0.00003188826,"threshold_uncertainty_score":0.99976176},"labels":[],"label_agreement":null},{"id":"W4293211116","doi":"10.1007/978-3-031-02181-7_3","title":"Multi-Stage Architectures for Reranking","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on human language technologies","topic":"Embedded Systems Design Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"sort; Computer science; Class (philosophy); Ranking (information retrieval); Relevance (law); Task (project management); Information retrieval; Artificial intelligence; Section (typography); Natural language processing; Machine learning; Engineering","score_opus":0.0727885303514739,"score_gpt":0.32770005942335584,"score_spread":0.25491152907188197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293211116","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014583068,0.028516542,0.36540198,0.0031655645,0.0015779171,0.014165874,0.0013600112,0.09299479,0.49135903],"genre_scores_gemma":[0.4507814,0.0001761897,0.2951677,0.0009771629,0.0004244637,0.0055710967,0.00008940752,0.00089403556,0.24591854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99599236,0.000114929055,0.00071434735,0.0016540904,0.00076697924,0.00075730204],"domain_scores_gemma":[0.9945002,0.0013304586,0.000725602,0.0033101202,0.000080166305,0.000053446267],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070380763,0.0010242395,0.0010919396,0.0016822484,0.0007696629,0.00028732748,0.0050163255,0.0009854852,0.00031576838],"category_scores_gemma":[0.00086006476,0.0009095461,0.0006197828,0.00014573151,0.00030809618,0.00007599804,0.0011408626,0.0015381626,0.00002450235],"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":[0.00004088308,0.000084294334,0.0000026375287,0.000527884,0.00039002075,0.00042052625,0.0020323782,0.00016094028,0.016773587,0.79768693,0.005284154,0.17659576],"study_design_scores_gemma":[0.00088005466,0.0016548479,0.000013582235,0.0017872769,0.00022470689,0.00015167793,0.0006781874,0.0008919627,0.39845327,0.27728727,0.31295425,0.0050229155],"about_ca_topic_score_codex":0.000043159755,"about_ca_topic_score_gemma":0.00011403444,"teacher_disagreement_score":0.52039963,"about_ca_system_score_codex":0.00041087106,"about_ca_system_score_gemma":0.00008067513,"threshold_uncertainty_score":0.9993355},"labels":[],"label_agreement":null},{"id":"W4293212745","doi":"10.1007/978-3-031-02181-7_4","title":"Refining Query and Document Representations","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on human language technologies","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Computer science; Vocabulary; Matching (statistics); Information retrieval; Section (typography); Artificial intelligence; Core (optical fiber); Natural language processing; Semantic matching; Linguistics; Mathematics","score_opus":0.02776359311982873,"score_gpt":0.290113440396588,"score_spread":0.26234984727675925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293212745","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027323929,0.025963109,0.0018116822,0.007034308,0.00055773515,0.0006745829,0.00004864506,0.011429442,0.9497481],"genre_scores_gemma":[0.7447021,0.0016725332,0.031295612,0.0011182411,0.00020410887,0.0007757049,0.00004286603,0.00023544989,0.21995336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978645,0.00004905906,0.00034541215,0.00094127,0.0004448384,0.00035493588],"domain_scores_gemma":[0.99720675,0.000785753,0.00027957585,0.0016706799,0.000026037727,0.00003119686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022875749,0.00045328648,0.0005165475,0.0006945865,0.0005320919,0.00024337957,0.0015833215,0.00037844974,0.00035871132],"category_scores_gemma":[0.00054254243,0.0003868887,0.00015085738,0.000086099615,0.00031546288,0.0001602155,0.0012676674,0.00075495645,0.000029057428],"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":[0.0000050590775,0.000009832774,0.000013309474,0.000036833433,0.00010106469,0.0002772889,0.0006047718,0.000010891279,0.00034894055,0.87193954,0.0024342574,0.12421818],"study_design_scores_gemma":[0.0004495384,0.00074254326,0.0005793533,0.0007120956,0.00025191304,0.000255221,0.003721247,0.000035241694,0.028550863,0.7951288,0.166864,0.0027091643],"about_ca_topic_score_codex":0.00012289915,"about_ca_topic_score_gemma":0.00016170162,"teacher_disagreement_score":0.74196976,"about_ca_system_score_codex":0.00012581672,"about_ca_system_score_gemma":0.000038397357,"threshold_uncertainty_score":0.9998583},"labels":[],"label_agreement":null},{"id":"W4293213317","doi":"10.1007/978-3-031-02181-7_6","title":"Future Directions and Conclusions","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on human language technologies","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer; Computer science; Data science; History; Engineering; Electrical engineering","score_opus":0.014423075081056667,"score_gpt":0.274830912593896,"score_spread":0.26040783751283936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293213317","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09805989,0.023894703,0.000043427506,0.0078771,0.0031877994,0.0017843021,0.0012027321,0.01568024,0.8482698],"genre_scores_gemma":[0.70180935,0.0039018057,0.007285302,0.001134946,0.0015201499,0.0010016406,0.00013166589,0.00064029475,0.28257483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997576,0.00010480826,0.00035558437,0.00097299024,0.00056392926,0.000426662],"domain_scores_gemma":[0.99796534,0.00048556304,0.00035476367,0.00110819,0.000034138007,0.000052023657],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046942878,0.000557532,0.00063023926,0.0005415889,0.0014516185,0.00021447489,0.001130435,0.0005123883,0.02033349],"category_scores_gemma":[0.0006900123,0.0004564514,0.00012766848,0.00008292819,0.00081297057,0.00008826712,0.0010860477,0.0009442632,0.00017839794],"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":[0.000052131334,0.00006880188,0.000015065608,0.00020304363,0.0000755085,0.00032969663,0.0021157681,0.000111727175,0.45116428,0.4762847,0.0076211174,0.06195818],"study_design_scores_gemma":[0.00015935543,0.000387721,0.00009119426,0.00028063258,0.00015615804,0.00013146353,0.0014934817,0.000011516415,0.07884316,0.031360883,0.8856625,0.001421921],"about_ca_topic_score_codex":0.000076807235,"about_ca_topic_score_gemma":0.000100059624,"teacher_disagreement_score":0.8780414,"about_ca_system_score_codex":0.00015850928,"about_ca_system_score_gemma":0.000043577453,"threshold_uncertainty_score":0.99984837},"labels":[],"label_agreement":null},{"id":"W4300927300","doi":"10.1007/978-3-031-02167-1_4","title":"Applications of Social Media Text Analysis","year":2018,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on human language technologies","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Social media; Computer science; World Wide Web","score_opus":0.023506218752693507,"score_gpt":0.28690396626457326,"score_spread":0.2633977475118798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300927300","genre_codex":"other","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":[0.003030053,0.009773085,0.11976428,0.0020898064,0.00034067075,0.0014247283,0.00034447148,0.007947568,0.85528535],"genre_scores_gemma":[0.94955105,0.00014112279,0.009361442,0.00010479648,0.00040904174,0.0002848199,0.00012567111,0.00009258656,0.0399295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979551,0.00002737483,0.00048786885,0.00072685484,0.0005381166,0.00026470106],"domain_scores_gemma":[0.997361,0.0004796412,0.00062653504,0.0013943245,0.00011297174,0.000025512492],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021847505,0.00039614554,0.0008397811,0.0020562818,0.00026717366,0.00010734051,0.0021110873,0.00056600984,0.0018006181],"category_scores_gemma":[0.00015544097,0.00033256976,0.0006585728,0.0005438016,0.0004349955,0.00006252457,0.00041492083,0.0003282293,0.00013199543],"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":[0.000006458452,0.000070164664,0.000015575828,0.000052841995,0.0031662888,0.000014521879,0.0038565083,0.0000090074545,0.0007718209,0.689882,0.0075092944,0.29464558],"study_design_scores_gemma":[0.00080025394,0.0005509122,0.0009412359,0.0007621203,0.011784159,0.000010882843,0.008541207,0.00097308645,0.24496724,0.41108707,0.313174,0.006407857],"about_ca_topic_score_codex":0.0000059140666,"about_ca_topic_score_gemma":0.000098665645,"teacher_disagreement_score":0.946521,"about_ca_system_score_codex":0.00006006694,"about_ca_system_score_gemma":0.000025620548,"threshold_uncertainty_score":0.9999126},"labels":[],"label_agreement":null},{"id":"W4312634722","doi":"10.1007/978-3-031-02157-2_4","title":"Applications of Social Media Text Analysis","year":2015,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on human language technologies","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Montréal","funders":"","keywords":"Social media; Computer science; World Wide Web","score_opus":0.038450178203179614,"score_gpt":0.30300424556272315,"score_spread":0.26455406735954357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312634722","genre_codex":"other","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":[0.0007623875,0.018524565,0.072542176,0.0020537218,0.00023854754,0.0011193542,0.00030074714,0.0061597913,0.8982987],"genre_scores_gemma":[0.9545604,0.00012143082,0.006835389,0.00006536682,0.00024745672,0.00027563312,0.00014949546,0.00008482915,0.03765999],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978998,0.000030010608,0.00048316273,0.0006724067,0.0006609224,0.0002537186],"domain_scores_gemma":[0.99747616,0.00042451496,0.00060704304,0.0013179778,0.00014010567,0.000034224675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028395266,0.00039297884,0.0008943988,0.0020317214,0.00019208441,0.00009679199,0.0020345347,0.00055704836,0.00057408423],"category_scores_gemma":[0.00019900854,0.00032978453,0.0005874851,0.00054867985,0.00028673615,0.0000661335,0.0004115017,0.00037906275,0.00007569899],"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":[0.000004021795,0.000044630597,0.000008755683,0.000028910015,0.001724295,0.000012452834,0.0016778795,0.000028881117,0.00027023177,0.7266276,0.0057020388,0.26387033],"study_design_scores_gemma":[0.0009222863,0.00040627626,0.00050218304,0.0005627782,0.010886934,0.0000112974185,0.008272163,0.0010848551,0.07447322,0.48222503,0.41477636,0.0058766324],"about_ca_topic_score_codex":0.000008430779,"about_ca_topic_score_gemma":0.000089159665,"teacher_disagreement_score":0.953798,"about_ca_system_score_codex":0.00008598939,"about_ca_system_score_gemma":0.000040450537,"threshold_uncertainty_score":0.9999154},"labels":[],"label_agreement":null},{"id":"W4313155193","doi":"10.1007/978-3-031-02157-2","title":"Natural Language Processing for Social Media","year":2015,"lang":"en","type":"book","venue":"Synthesis lectures on human language technologies","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Montréal","funders":"","keywords":"Social media; Interpersonal communication; Natural (archaeology); Computer science; Psychology; Sociology; Internet privacy; World Wide Web; Communication; History","score_opus":0.043810293870779074,"score_gpt":0.3212424037328657,"score_spread":0.27743210986208666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313155193","genre_codex":"other","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":[0.010650227,0.34844604,0.035178505,0.012463961,0.005957161,0.0070455475,0.0008069647,0.055574987,0.5238766],"genre_scores_gemma":[0.8291681,0.00006145293,0.02279665,0.0005747472,0.0024690814,0.00095723255,0.0005394488,0.00032880966,0.14310448],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973576,0.000051765182,0.00042054628,0.0009141089,0.00069418695,0.0005617619],"domain_scores_gemma":[0.99787647,0.00060226483,0.00048366372,0.0008545702,0.0001410983,0.00004195466],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042183514,0.0005861135,0.0008093856,0.0008711084,0.00046056043,0.00044722253,0.002410326,0.00070742035,0.000047817965],"category_scores_gemma":[0.0010306018,0.0004696834,0.00040119802,0.00026601105,0.00022656683,0.00017778573,0.00043508003,0.00067224377,0.0000370097],"study_design_candidate":"design_other","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":[0.000019015702,0.000052204206,0.0000012024047,0.0001843749,0.00022876498,0.00007236521,0.01085072,0.000004572201,0.0011287068,0.017546527,0.15992841,0.80998313],"study_design_scores_gemma":[0.0053483336,0.0013658946,0.0001794452,0.0064741275,0.0027306296,0.000117964606,0.06228903,0.012680288,0.25562984,0.22829172,0.4076305,0.017262232],"about_ca_topic_score_codex":0.0000036091562,"about_ca_topic_score_gemma":0.0000618275,"teacher_disagreement_score":0.81851786,"about_ca_system_score_codex":0.00028299278,"about_ca_system_score_gemma":0.00018943855,"threshold_uncertainty_score":0.99977547},"labels":[],"label_agreement":null}]}