{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":16,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":16,"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":"768c772dceab","filters":{"venue":"Synthesis lectures on human language technologies"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02076188500124745,"gpt":0.2760993430802039,"spread":0.2553374580789565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001885195,0.0002060703,0.000256541,0.0001988283,0.0002437618,0.0001553103,0.0005724548,0.0002065641,0.0000208065],"category_scores_gemma":[0.0006763894,0.0001738103,0.00009652957,0.0002052966,0.0001136468,0.0001314255,0.0001192607,0.0001988165,0.000002096408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003584091,"about_ca_system_score_gemma":0.00003222991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007015778,"about_ca_topic_score_gemma":0.0000572777,"domain_scores_codex":[0.9986782,0.00003388632,0.000191635,0.0005643268,0.0001870777,0.0003448566],"domain_scores_gemma":[0.9989268,0.0004144186,0.00005357841,0.00053715,0.00003968117,0.00002833674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001110915,0.00004346453,0.0000329175,0.00008529462,0.00006447042,0.00004525747,0.002746945,0.00002673637,0.05890688,0.07022757,0.0002686774,0.8675407],"study_design_scores_gemma":[0.0005238819,0.0001632003,0.0002085803,0.00009847185,0.00003822495,0.00004336768,0.003040518,0.003535236,0.9461379,0.04391542,0.001762768,0.0005324521],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3145986,0.005394342,0.6559633,0.01130738,0.0002018338,0.0007794431,0.00002221744,0.003860497,0.007872435],"genre_scores_gemma":[0.9650732,0.00003126814,0.03427654,0.0003055146,0.0000246799,0.0001133053,0.000002487438,0.0000177038,0.0001552532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.887231,"threshold_uncertainty_score":0.7087777,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01153816710099544,"gpt":0.2955057917965311,"spread":0.2839676246955357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0005953038,0.0009965712,0.000859984,0.001717575,0.0005259725,0.001425957,0.006088762,0.002723836,0.0002310791],"category_scores_gemma":[0.00322407,0.0008148248,0.0003566926,0.0004826126,0.0006375703,0.001165814,0.001318182,0.003559604,0.0002840651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004332947,"about_ca_system_score_gemma":0.0002735191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003205091,"about_ca_topic_score_gemma":0.00004056508,"domain_scores_codex":[0.9962649,0.00007207753,0.0007645385,0.001010739,0.001076068,0.0008116637],"domain_scores_gemma":[0.9949484,0.000553689,0.0008601259,0.003337729,0.000220935,0.00007914341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008057231,0.0001013814,0.000007229123,0.0007126076,0.0002077119,0.0005915603,0.004557199,0.00000465588,0.03172355,0.1960983,0.03620193,0.7297133],"study_design_scores_gemma":[0.0002989549,0.0003169197,0.00002015705,0.0008596716,0.0000776074,0.0001218984,0.0002671858,0.00005981298,0.8253755,0.1282203,0.04222594,0.002156095],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01181377,0.06198852,0.07567492,0.004599182,0.003422324,0.006337038,0.00084257,0.1679952,0.6673265],"genre_scores_gemma":[0.3834026,0.00028171,0.300399,0.002825044,0.001243791,0.0005833377,0.000676104,0.0005813743,0.3100071],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7936519,"threshold_uncertainty_score":0.9996107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05859163540961687,"gpt":0.3354402399822846,"spread":0.2768486045726677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003203245,0.0002205772,0.0002943723,0.0003770926,0.0003069683,0.0002705415,0.001155757,0.0001559792,0.00001377347],"category_scores_gemma":[0.001169602,0.0001689334,0.0001454637,0.0003754821,0.000110921,0.000197499,0.0001978948,0.0002011265,0.00001571293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000067755,"about_ca_system_score_gemma":0.00003379262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007557471,"about_ca_topic_score_gemma":0.00004255518,"domain_scores_codex":[0.9985822,0.00004231586,0.0002128599,0.0004440436,0.0003503982,0.0003681549],"domain_scores_gemma":[0.9990211,0.0003019625,0.000149697,0.0004240236,0.00006984056,0.00003338945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002200352,0.00007730637,0.00005157822,0.00003754577,0.00007610423,0.00003321381,0.02375674,0.00001656626,0.01201379,0.01333741,0.008609584,0.9419681],"study_design_scores_gemma":[0.001841053,0.0003324368,0.001034182,0.0002898349,0.0001822635,0.00002469756,0.09663545,0.01677491,0.8585749,0.01634307,0.005783231,0.002183927],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8772029,0.03234254,0.0579953,0.009902894,0.001231867,0.001150233,0.00003640198,0.01410414,0.006033726],"genre_scores_gemma":[0.9888109,0.000002285601,0.01065213,0.0001267973,0.0001621905,0.000115181,0.000009968336,0.00001871775,0.0001018321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9397842,"threshold_uncertainty_score":0.6888906,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01943691375922096,"gpt":0.2708791217803281,"spread":0.2514422080211071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003134755,0.000334458,0.0004241003,0.000517842,0.0002665263,0.0003572048,0.002124099,0.0003175897,0.0000116259],"category_scores_gemma":[0.000762635,0.0002556723,0.0001364351,0.0004706676,0.0001066522,0.000200734,0.0001439657,0.0003008877,0.0001880343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009375965,"about_ca_system_score_gemma":0.00002799979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001253702,"about_ca_topic_score_gemma":0.00003350016,"domain_scores_codex":[0.9979683,0.0001089577,0.000317766,0.0006360403,0.0003974207,0.0005714885],"domain_scores_gemma":[0.9978701,0.0002814985,0.0001532342,0.001596169,0.00004048508,0.00005850779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004533198,0.0003487605,0.0002425491,0.00008449372,0.0001165601,0.0008020937,0.002400376,0.0002728072,0.1007245,0.4783296,0.01830878,0.3983241],"study_design_scores_gemma":[0.0009159831,0.001662683,0.006775625,0.000574122,0.0000561811,0.0002418254,0.003660189,0.0007664098,0.9121972,0.06258272,0.008118405,0.002448694],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7331932,0.0224579,0.05864312,0.01047039,0.003139491,0.003272738,0.00008265128,0.05115875,0.1175818],"genre_scores_gemma":[0.9979921,0.00001678352,0.001361889,0.0002296387,0.0001340532,0.00007418898,0.000004639482,0.00001628679,0.0001704103],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8114727,"threshold_uncertainty_score":0.9999896,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04381029387077907,"gpt":0.3212424037328657,"spread":0.2774321098620867,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004218351,0.0005861135,0.0008093856,0.0008711084,0.0004605604,0.0004472225,0.002410326,0.0007074203,0.00004781796],"category_scores_gemma":[0.001030602,0.0004696834,0.000401198,0.000266011,0.0002265668,0.0001777857,0.00043508,0.0006722438,0.0000370097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002829928,"about_ca_system_score_gemma":0.0001894385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003609156,"about_ca_topic_score_gemma":0.0000618275,"domain_scores_codex":[0.9973576,0.00005176518,0.0004205463,0.0009141089,0.000694187,0.0005617619],"domain_scores_gemma":[0.9978765,0.0006022648,0.0004836637,0.0008545702,0.0001410983,0.00004195466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000190157,0.00005220421,0.000001202405,0.0001843749,0.000228765,0.00007236521,0.01085072,0.000004572201,0.001128707,0.01754653,0.1599284,0.8099831],"study_design_scores_gemma":[0.005348334,0.001365895,0.0001794452,0.006474128,0.00273063,0.0001179646,0.06228903,0.01268029,0.2556298,0.2282917,0.4076305,0.01726223],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01065023,0.348446,0.0351785,0.01246396,0.005957161,0.007045547,0.0008069647,0.05557499,0.5238766],"genre_scores_gemma":[0.8291681,0.00006145293,0.02279665,0.0005747472,0.002469081,0.0009572326,0.0005394488,0.0003288097,0.1431045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8185179,"threshold_uncertainty_score":0.9997755,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01440460455295874,"gpt":0.3076386150326261,"spread":0.2932340104796674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003131032,0.0004529157,0.0005593257,0.0004252079,0.0004671338,0.0005527144,0.001555796,0.0003261889,0.00002417264],"category_scores_gemma":[0.001828549,0.0003580387,0.0001134696,0.0003268968,0.0002017646,0.0002915675,0.0007141868,0.0004622649,0.000009624456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009231049,"about_ca_system_score_gemma":0.0000435295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006331192,"about_ca_topic_score_gemma":0.00004405049,"domain_scores_codex":[0.997766,0.00006122622,0.0004031104,0.0008354205,0.0003945184,0.0005397634],"domain_scores_gemma":[0.9977427,0.0007371866,0.000348219,0.001029327,0.0001000637,0.00004253393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005250846,0.0002161729,0.0002231686,0.0009454268,0.0001658484,0.0001106571,0.01698173,0.000008492547,0.4762042,0.0288487,0.0005708316,0.4756723],"study_design_scores_gemma":[0.0003810377,0.0002702795,0.00007927614,0.0008371912,0.00007844142,0.00002271768,0.002368232,0.004281038,0.9465845,0.04391992,0.0003465027,0.0008308325],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8892898,0.05798765,0.03856174,0.001739463,0.0004130136,0.001828758,0.00007820543,0.00965669,0.0004446967],"genre_scores_gemma":[0.8261658,0.00002009712,0.1731884,0.0002128229,0.00006138246,0.0001018206,0.00001773904,0.00004521217,0.0001867723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4748414,"threshold_uncertainty_score":0.9998872,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03585718823322134,"gpt":0.3292590273087216,"spread":0.2934018390755003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002469122,0.0002137812,0.0002821791,0.0002889438,0.001470921,0.0007466141,0.001706164,0.0001748121,0.00007329124],"category_scores_gemma":[0.001032146,0.0001714898,0.0001697129,0.00009987739,0.0001837836,0.0003933221,0.0002508397,0.0002215155,0.00001168134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004499787,"about_ca_system_score_gemma":0.00001771735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007017219,"about_ca_topic_score_gemma":0.0001383897,"domain_scores_codex":[0.9986998,0.0000270191,0.0001982641,0.0004644478,0.0002669642,0.0003435095],"domain_scores_gemma":[0.998622,0.0002631562,0.0003075091,0.0007382414,0.00004969373,0.00001937232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000132694,0.00005619516,0.00005370958,0.0000665343,0.00007501985,0.00002689301,0.007588515,0.000002001625,0.03668664,0.009032653,0.005720583,0.940678],"study_design_scores_gemma":[0.0008890888,0.0001323479,0.00722944,0.0002686632,0.0001035627,0.0000103266,0.01494332,0.004766916,0.9577296,0.01012837,0.002575361,0.001222986],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9460585,0.007614503,0.02480303,0.007791613,0.001408967,0.0008340177,0.00006960653,0.005638001,0.005781732],"genre_scores_gemma":[0.994769,0.000003206132,0.004471914,0.00009308009,0.0003346945,0.0001278277,0.00001322974,0.00001725589,0.000169772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.939455,"threshold_uncertainty_score":0.9998291,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03886129174228645,"gpt":0.3072510998608941,"spread":0.2683898081186076,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000154207,0.0002178468,0.0002937013,0.0002247703,0.0004257099,0.0002574567,0.001008426,0.0001596354,0.00003140987],"category_scores_gemma":[0.0009673967,0.0001742506,0.0001761216,0.0004000444,0.00009649553,0.0002215064,0.0001718071,0.0002507184,0.00001684656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003662306,"about_ca_system_score_gemma":0.0000182579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003393772,"about_ca_topic_score_gemma":0.00001534268,"domain_scores_codex":[0.9986086,0.00003843287,0.000222919,0.000492611,0.0003137677,0.0003236361],"domain_scores_gemma":[0.9991626,0.0003215301,0.0001642918,0.0002780206,0.00004459923,0.00002896064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003130539,0.00006718574,0.00002963645,0.0001152238,0.0001003203,0.00003718334,0.03163395,0.0000201787,0.07347572,0.01203945,0.01561424,0.8668356],"study_design_scores_gemma":[0.0008769468,0.0002704653,0.0007746438,0.0002029452,0.0001404946,0.000006694722,0.03906368,0.0220855,0.9278591,0.004546876,0.002819892,0.00135281],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.636974,0.02579425,0.230589,0.07264744,0.001470863,0.002022547,0.0001117522,0.02559616,0.004793962],"genre_scores_gemma":[0.9920188,0.000004691767,0.00684615,0.0005617151,0.0003987906,0.0001102909,0.00001912635,0.00001777453,0.00002261731],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8654828,"threshold_uncertainty_score":0.7105735,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Université de Montréal","funders":"","keywords":"Social media; Computer science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03845017820317961,"gpt":0.3030042455627232,"spread":0.2645540673595436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002839527,0.0003929788,0.0008943988,0.002031721,0.0001920844,0.00009679199,0.002034535,0.0005570484,0.0005740842],"category_scores_gemma":[0.0001990085,0.0003297845,0.0005874851,0.0005486798,0.0002867361,0.0000661335,0.0004115017,0.0003790628,0.00007569899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008598939,"about_ca_system_score_gemma":0.00004045054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008430779,"about_ca_topic_score_gemma":0.00008915966,"domain_scores_codex":[0.9978998,0.00003001061,0.0004831627,0.0006724067,0.0006609224,0.0002537186],"domain_scores_gemma":[0.9974762,0.000424515,0.000607043,0.001317978,0.0001401057,0.00003422467],"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":[0.000004021795,0.0000446306,0.000008755683,0.00002891002,0.001724295,0.00001245283,0.001677879,0.00002888112,0.0002702318,0.7266276,0.005702039,0.2638703],"study_design_scores_gemma":[0.0009222863,0.0004062763,0.000502183,0.0005627782,0.01088693,0.00001129742,0.008272163,0.001084855,0.07447322,0.482225,0.4147764,0.005876632],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0007623875,0.01852456,0.07254218,0.002053722,0.0002385475,0.001119354,0.0003007471,0.006159791,0.8982987],"genre_scores_gemma":[0.9545604,0.0001214308,0.006835389,0.00006536682,0.0002474567,0.0002756331,0.0001494955,0.00008482915,0.03765999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.953798,"threshold_uncertainty_score":0.9999154,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer; Computer science; Data science; History; Engineering; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01442307508105667,"gpt":0.274830912593896,"spread":0.2604078375128394,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004694288,0.000557532,0.0006302393,0.0005415889,0.001451619,0.0002144749,0.001130435,0.0005123883,0.02033349],"category_scores_gemma":[0.0006900123,0.0004564514,0.0001276685,0.00008292819,0.0008129706,0.00008826712,0.001086048,0.0009442632,0.0001783979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001585093,"about_ca_system_score_gemma":0.00004357745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007680724,"about_ca_topic_score_gemma":0.0001000596,"domain_scores_codex":[0.997576,0.0001048083,0.0003555844,0.0009729902,0.0005639293,0.000426662],"domain_scores_gemma":[0.9979653,0.000485563,0.0003547637,0.00110819,0.00003413801,0.00005202366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005213133,0.00006880188,0.00001506561,0.0002030436,0.0000755085,0.0003296966,0.002115768,0.0001117272,0.4511643,0.4762847,0.007621117,0.06195818],"study_design_scores_gemma":[0.0001593554,0.000387721,0.00009119426,0.0002806326,0.000156158,0.0001314635,0.001493482,0.00001151641,0.07884316,0.03136088,0.8856625,0.001421921],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.09805989,0.0238947,0.00004342751,0.0078771,0.003187799,0.001784302,0.001202732,0.01568024,0.8482698],"genre_scores_gemma":[0.7018093,0.003901806,0.007285302,0.001134946,0.00152015,0.001001641,0.0001316659,0.0006402947,0.2825748],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8780414,"threshold_uncertainty_score":0.9998484,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02079762930399449,"gpt":0.2525003954038954,"spread":0.2317027660999009,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001455909,0.0003804629,0.0004279567,0.0004811758,0.0003626917,0.0002240951,0.0008744568,0.0006057947,0.000145258],"category_scores_gemma":[0.0006345036,0.0003453135,0.0001220914,0.00006873297,0.0001592251,0.00009409095,0.0006033744,0.001017711,0.00004768422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000775665,"about_ca_system_score_gemma":0.00002594015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001201183,"about_ca_topic_score_gemma":0.00008211502,"domain_scores_codex":[0.9983191,0.00003633136,0.0002729937,0.0007947607,0.0002894492,0.0002874024],"domain_scores_gemma":[0.9981788,0.0004339707,0.0001887479,0.001126574,0.0000422309,0.00002966148],"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":[0.000001051088,0.000008535547,0.00001438917,0.00005586026,0.00008486901,0.000226406,0.0007530589,0.0001806994,0.0006334826,0.6448644,0.00009368175,0.3530836],"study_design_scores_gemma":[0.0008336873,0.0007229302,0.0004820919,0.00596612,0.0006954667,0.0005874517,0.004756629,0.01756785,0.04845256,0.8165438,0.0962744,0.007117033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.008206013,0.07215932,0.161224,0.005107906,0.0004609893,0.001028252,0.00001255463,0.01659446,0.7352065],"genre_scores_gemma":[0.8665463,0.0005095218,0.01673869,0.0001243152,0.00008897091,0.00004837053,0.000009898909,0.0000884613,0.1158454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8583403,"threshold_uncertainty_score":0.9998999,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Meaning (existential); Linguistics; Natural language processing; Artificial intelligence; Epistemology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.05269171406015205,"gpt":0.2754294053772743,"spread":0.2227376913171222,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008850307,0.0006200449,0.0007833382,0.0004281189,0.0008807045,0.0001853041,0.0005991912,0.0005922514,0.005740761],"category_scores_gemma":[0.0006746953,0.0004834339,0.000298438,0.00001191893,0.001343795,0.0000235941,0.0005012105,0.0007946067,0.0002374498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009073398,"about_ca_system_score_gemma":0.00003188826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004392458,"about_ca_topic_score_gemma":0.001007494,"domain_scores_codex":[0.9982792,0.0000196817,0.0003683185,0.0006563997,0.0002988492,0.000377599],"domain_scores_gemma":[0.998244,0.0004047061,0.0002739799,0.0009037458,0.0001488034,0.00002480687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007320327,0.00002524056,0.000001181089,0.000069647,0.0003061667,0.0005019892,0.003051109,2.557965e-7,0.00009629162,0.9554352,0.0133308,0.02717486],"study_design_scores_gemma":[0.0001167233,0.0001552508,0.000002829926,0.0005652225,0.0002389077,0.000009720548,0.00372395,5.206446e-7,0.005174147,0.09574045,0.8934767,0.0007955357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0009826963,0.01082817,0.000001210112,0.0007608066,0.0006190749,0.0002320411,0.0001906505,0.001903219,0.9844821],"genre_scores_gemma":[0.4217,0.0004333437,0.00004734823,0.0003416553,0.0008369288,0.00005691562,0.00006265427,0.000118434,0.5764027],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.880146,"threshold_uncertainty_score":0.9997618,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0727885303514739,"gpt":0.3277000594233558,"spread":0.254911529071882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007038076,0.001024239,0.00109194,0.001682248,0.0007696629,0.0002873275,0.005016326,0.0009854852,0.0003157684],"category_scores_gemma":[0.0008600648,0.0009095461,0.0006197828,0.0001457315,0.0003080962,0.00007599804,0.001140863,0.001538163,0.00002450235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004108711,"about_ca_system_score_gemma":0.00008067513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004315975,"about_ca_topic_score_gemma":0.0001140344,"domain_scores_codex":[0.9959924,0.0001149291,0.0007143473,0.00165409,0.0007669792,0.000757302],"domain_scores_gemma":[0.9945002,0.001330459,0.000725602,0.00331012,0.0000801663,0.00005344627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004088308,0.00008429433,0.000002637529,0.000527884,0.0003900208,0.0004205263,0.002032378,0.0001609403,0.01677359,0.7976869,0.005284154,0.1765958],"study_design_scores_gemma":[0.0008800547,0.001654848,0.00001358223,0.001787277,0.0002247069,0.0001516779,0.0006781874,0.0008919627,0.3984533,0.2772873,0.3129542,0.005022916],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.001458307,0.02851654,0.365402,0.003165564,0.001577917,0.01416587,0.001360011,0.09299479,0.491359],"genre_scores_gemma":[0.4507814,0.0001761897,0.2951677,0.0009771629,0.0004244637,0.005571097,0.00008940752,0.0008940356,0.2459185],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5203996,"threshold_uncertainty_score":0.9993355,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Social media; Computer science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02350621875269351,"gpt":0.2869039662645733,"spread":0.2633977475118798,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000218475,0.0003961455,0.0008397811,0.002056282,0.0002671737,0.0001073405,0.002111087,0.0005660098,0.001800618],"category_scores_gemma":[0.000155441,0.0003325698,0.0006585728,0.0005438016,0.0004349955,0.00006252457,0.0004149208,0.0003282293,0.0001319954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006006694,"about_ca_system_score_gemma":0.00002562055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005914067,"about_ca_topic_score_gemma":0.00009866565,"domain_scores_codex":[0.9979551,0.00002737483,0.0004878688,0.0007268548,0.0005381166,0.0002647011],"domain_scores_gemma":[0.997361,0.0004796412,0.000626535,0.001394324,0.0001129717,0.00002551249],"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":[0.000006458452,0.00007016466,0.00001557583,0.000052842,0.003166289,0.00001452188,0.003856508,0.000009007455,0.0007718209,0.689882,0.007509294,0.2946456],"study_design_scores_gemma":[0.0008002539,0.0005509122,0.0009412359,0.0007621203,0.01178416,0.00001088284,0.008541207,0.0009730865,0.2449672,0.4110871,0.313174,0.006407857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.003030053,0.009773085,0.1197643,0.002089806,0.0003406708,0.001424728,0.0003444715,0.007947568,0.8552853],"genre_scores_gemma":[0.949551,0.0001411228,0.009361442,0.0001047965,0.0004090417,0.0002848199,0.0001256711,0.00009258656,0.0399295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.946521,"threshold_uncertainty_score":0.9999126,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02762942768257382,"gpt":0.278961434224012,"spread":0.2513320065414382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001767878,0.0001826603,0.0002359187,0.0002721407,0.0002844948,0.000160922,0.0008199812,0.0002171035,0.0002222743],"category_scores_gemma":[0.0007799416,0.000167099,0.00009293389,0.0003255073,0.00007551934,0.0001940892,0.0002800612,0.0003396661,0.00009232753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007531032,"about_ca_system_score_gemma":0.00004002494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001183326,"about_ca_topic_score_gemma":0.00009260338,"domain_scores_codex":[0.9986429,0.00007752274,0.0002384587,0.0005198221,0.0002297551,0.0002915486],"domain_scores_gemma":[0.9982665,0.0004372016,0.00009945165,0.001122152,0.00004859146,0.00002606397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005992598,0.0002576121,0.004022649,0.0002212756,0.000320307,0.0007752828,0.005058712,0.0006254694,0.1332656,0.2516254,0.01057415,0.5932475],"study_design_scores_gemma":[0.0001988238,0.00008023311,0.0101074,0.0002200006,0.00005262705,0.00003975573,0.001680943,0.001072437,0.9139288,0.06974351,0.002231598,0.0006438396],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7309201,0.001972043,0.2473106,0.006329454,0.0002520349,0.0002431235,0.00002433677,0.004609201,0.008339141],"genre_scores_gemma":[0.9842011,0.000005129557,0.01502134,0.0001113701,0.0001033239,0.00004043926,0.00000759516,0.00001459263,0.0004950524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7806633,"threshold_uncertainty_score":0.6814098,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02776359311982873,"gpt":0.290113440396588,"spread":0.2623498472767593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002287575,0.0004532865,0.0005165475,0.0006945865,0.0005320919,0.0002433796,0.001583321,0.0003784497,0.0003587113],"category_scores_gemma":[0.0005425424,0.0003868887,0.0001508574,0.00008609962,0.0003154629,0.0001602155,0.001267667,0.0007549564,0.00002905743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001258167,"about_ca_system_score_gemma":0.00003839736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001228991,"about_ca_topic_score_gemma":0.0001617016,"domain_scores_codex":[0.9978645,0.00004905906,0.0003454121,0.00094127,0.0004448384,0.0003549359],"domain_scores_gemma":[0.9972067,0.000785753,0.0002795758,0.00167068,0.00002603773,0.00003119686],"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":[0.000005059077,0.000009832774,0.00001330947,0.00003683343,0.0001010647,0.0002772889,0.0006047718,0.00001089128,0.0003489405,0.8719395,0.002434257,0.1242182],"study_design_scores_gemma":[0.0004495384,0.0007425433,0.0005793533,0.0007120956,0.000251913,0.000255221,0.003721247,0.00003524169,0.02855086,0.7951288,0.166864,0.002709164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.002732393,0.02596311,0.001811682,0.007034308,0.0005577352,0.0006745829,0.00004864506,0.01142944,0.9497481],"genre_scores_gemma":[0.7447021,0.001672533,0.03129561,0.001118241,0.0002041089,0.0007757049,0.00004286603,0.0002354499,0.2199534],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7419698,"threshold_uncertainty_score":0.9998583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}