{"meta":{"query_hash":"b15508754daf","filters":{"venue":"Computers and the Humanities"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"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/b15508754daf","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computers+and+the+Humanities"},"results":[{"id":"W1511980079","doi":"10.1023/a:1021855607270","title":"Categorisation Techniques in Computer-Assisted Reading and Analysis of Texts (CARAT) in the Humanities","year":2003,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"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 du Québec à Montréal","funders":"","keywords":"Computer science; Computational linguistics; Set (abstract data type); Process (computing); Reading (process); Natural language processing; Linguistics; Artificial intelligence; Programming language; Philosophy","score_opus":0.026891381403847812,"score_gpt":0.25621449946644526,"score_spread":0.22932311806259745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511980079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01698106,0.0026783973,0.9627343,0.0010716753,0.00036576774,0.0008209973,0.000814171,0.0044920044,0.0100417305],"genre_scores_gemma":[0.09037993,0.0012353386,0.89791083,0.00022689936,0.00016877623,0.00085953606,0.0013836324,0.0010957241,0.0067394734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98789537,0.0076893973,0.0009185111,0.0015507869,0.0016130168,0.00033292468],"domain_scores_gemma":[0.96139306,0.028935568,0.0012774603,0.0032390386,0.004769684,0.00038523824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072265556,0.0011297184,0.001209338,0.014109269,0.0029032573,0.0071135913,0.0023454465,0.0020487595,0.012229381],"category_scores_gemma":[0.027357323,0.00072713685,0.0017816816,0.0107309045,0.0036305182,0.00785522,0.0036189763,0.0037496984,0.0043290453],"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":[0.000251472,0.00017070418,0.0015044771,0.0013043765,0.00011817197,0.0002214719,0.016072625,0.0016628541,0.012168978,0.08546381,0.01205399,0.8690071],"study_design_scores_gemma":[0.0001757506,0.00038288592,0.01266422,0.0018435674,0.00039778164,0.0019189997,0.028874343,0.092935584,0.0579101,0.47130898,0.33118945,0.00039843086],"about_ca_topic_score_codex":0.0032649145,"about_ca_topic_score_gemma":0.0038568398,"teacher_disagreement_score":0.014109269,"about_ca_system_score_codex":0.0019039252,"about_ca_system_score_gemma":0.002437739,"threshold_uncertainty_score":0.040911376},"labels":[],"label_agreement":null},{"id":"W1963832348","doi":"10.1023/b:chum.0000031173.25446.37","title":"Intertextual Encoding in the Writing of Women's Literary History","year":2004,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":6,"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 Alberta","funders":"","keywords":"Intertextuality; SGML; Computer science; Literature; Relation (database); Linguistics; Sociology; Philosophy; Art; XML; World Wide Web","score_opus":0.045615571806744075,"score_gpt":0.1986165929571398,"score_spread":0.1530010211503957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963832348","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21779987,0.008645581,0.03544383,0.016090259,0.0012767079,0.000082278195,0.00027805514,0.00031050845,0.720073],"genre_scores_gemma":[0.97013503,0.0012293484,0.0026338664,0.00022715775,0.00023695033,0.000028977393,0.00007400991,0.00016947486,0.025265189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99556446,0.0032694112,0.00019149546,0.00027553842,0.00047682016,0.00022225705],"domain_scores_gemma":[0.9869197,0.010238028,0.0006571791,0.0012838028,0.00060388236,0.0002973893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030148206,0.00044229522,0.0003172752,0.0033323984,0.0049706646,0.01651221,0.00083422736,0.0013283943,0.009826079],"category_scores_gemma":[0.017477693,0.00036079634,0.00024533627,0.0034747948,0.02030858,0.012209875,0.0053115124,0.002463103,0.0009394143],"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":[0.00009620437,0.000019931358,0.00075745763,0.00020881719,0.000008676935,0.00029624245,0.22220358,0.00021428148,0.0008197986,0.7407094,0.0026548658,0.032010674],"study_design_scores_gemma":[0.00003210619,0.00007650871,0.0022689635,0.0014191602,0.000044248398,0.00085123745,0.18366073,0.0012669123,0.0047357064,0.303289,0.50231475,0.00004072479],"about_ca_topic_score_codex":0.0022971642,"about_ca_topic_score_gemma":0.0032203256,"teacher_disagreement_score":0.01651221,"about_ca_system_score_codex":0.00455548,"about_ca_system_score_gemma":0.0026480036,"threshold_uncertainty_score":0.033052444},"labels":[],"label_agreement":null},{"id":"W2048359833","doi":"10.1007/s10579-007-9017-9","title":"Automatically learning semantic knowledge about multiword predicates","year":2007,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Noun; Natural language processing; Linguistics; Artificial intelligence; Focus (optics); Verb","score_opus":0.012579192003722123,"score_gpt":0.2518575762560514,"score_spread":0.23927838425232925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048359833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31872794,0.0023401713,0.64254147,0.0032104095,0.00057071284,0.00026909966,0.0070211426,0.010201391,0.0151175475],"genre_scores_gemma":[0.7577632,0.0014023358,0.22144356,0.0005328339,0.00031498936,0.00013338239,0.014966596,0.00035392516,0.0030890708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991027,0.00016406598,0.00009082161,0.00038163934,0.0001794795,0.00008122855],"domain_scores_gemma":[0.99607986,0.002882479,0.00024921316,0.0003604561,0.00032549186,0.0001025091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070422306,0.0009707012,0.00091447076,0.002753978,0.00096407084,0.0020783343,0.001492165,0.0015401754,0.0053423536],"category_scores_gemma":[0.0059923492,0.00069759384,0.0013693066,0.002121081,0.00090883294,0.011037956,0.0019193197,0.0026199927,0.001389223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010024586,0.0011194048,0.011437666,0.0012505769,0.00031660846,0.0010939437,0.00086928066,0.017995123,0.030688617,0.07024643,0.03196274,0.8320171],"study_design_scores_gemma":[0.00018680787,0.00033550718,0.0073740873,0.00024714458,0.0003966995,0.00089342555,0.0011543718,0.5751946,0.029274127,0.3618402,0.023015358,0.00008772567],"about_ca_topic_score_codex":0.0028854485,"about_ca_topic_score_gemma":0.00499276,"teacher_disagreement_score":0.0053423536,"about_ca_system_score_codex":0.0009572328,"about_ca_system_score_gemma":0.0015155778,"threshold_uncertainty_score":0.017871976},"labels":[],"label_agreement":null},{"id":"W2057960659","doi":"10.1007/s10579-004-8682-1","title":"Article: Collating Texts Using Progressive Multiple Alignment","year":2004,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Universität Basel","keywords":"Collation; Witness; Computer science; Natural language processing; Phrase; Word (group theory); Base (topology); Point (geometry); Information retrieval; Linguistics; Artificial intelligence; Mathematics","score_opus":0.022612664260272315,"score_gpt":0.2515213186214391,"score_spread":0.2289086543611668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057960659","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041596305,0.004433667,0.8759482,0.0059657213,0.010502478,0.0018402117,0.01446919,0.020394605,0.024849547],"genre_scores_gemma":[0.04767074,0.0021859927,0.89838624,0.0005258347,0.0021103015,0.00053672615,0.023045007,0.004838636,0.020700516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99515283,0.0013885045,0.0007353519,0.0009913499,0.0015845716,0.00014735144],"domain_scores_gemma":[0.9779417,0.010631083,0.0015953903,0.002570864,0.0067194607,0.0005415593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003789288,0.0020207893,0.0019651495,0.009922904,0.0036730848,0.0047403877,0.002198759,0.0016574212,0.035863824],"category_scores_gemma":[0.031639248,0.0012716826,0.0012015096,0.009943134,0.001321067,0.0042561223,0.0031663687,0.0030519746,0.021675324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010620318,0.00027399708,0.0025482676,0.0044469535,0.0004091669,0.003746579,0.0033859222,0.0025875096,0.08633859,0.015150231,0.13578781,0.7442629],"study_design_scores_gemma":[0.00022965683,0.0004982461,0.0049822167,0.0010266311,0.00099723,0.004607878,0.00309049,0.045597646,0.14728145,0.034190927,0.757224,0.00027350092],"about_ca_topic_score_codex":0.0013039247,"about_ca_topic_score_gemma":0.0027330364,"teacher_disagreement_score":0.035863824,"about_ca_system_score_codex":0.00056927075,"about_ca_system_score_gemma":0.003320491,"threshold_uncertainty_score":0.1199764},"labels":[],"label_agreement":null},{"id":"W2147565428","doi":"10.1023/a:1025720518994","title":"Extending Dublin Core Metadata to Support the Description and Discovery of Language Resources","year":2003,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"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":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Metadata; Computer science; World Wide Web; Reuse; Computational linguistics; Information retrieval; Natural language processing; Engineering","score_opus":0.039808824074941296,"score_gpt":0.26059815286093374,"score_spread":0.22078932878599244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147565428","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005074587,0.00031754444,0.98126894,0.0010573806,0.00014760204,0.0003105339,0.0021222073,0.004647688,0.005053642],"genre_scores_gemma":[0.0563843,0.00066857133,0.92405903,0.00062649784,0.000115696974,0.00039257426,0.010527727,0.0011096847,0.0061158924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943605,0.0017482876,0.0011064829,0.00073145557,0.0016528643,0.00040047546],"domain_scores_gemma":[0.9788615,0.008428821,0.0012676368,0.006549256,0.0040843715,0.00080849923],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.013139128,0.00069176365,0.0011173019,0.010554732,0.0024510731,0.007454319,0.0032989192,0.001559183,0.003715116],"category_scores_gemma":[0.025464054,0.0013284588,0.0019160734,0.0081276875,0.0023618473,0.01819097,0.0078585325,0.003280865,0.0024903978],"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":[0.0002302436,0.00030126178,0.0031510966,0.00095327216,0.00014203516,0.00057296205,0.0036121898,0.004795642,0.010922,0.5883151,0.029837111,0.35716692],"study_design_scores_gemma":[0.000098728815,0.00007446332,0.0010272005,0.00062968716,0.00020653282,0.0008429271,0.0012381762,0.09235163,0.027805198,0.550624,0.3248862,0.00021528592],"about_ca_topic_score_codex":0.018277463,"about_ca_topic_score_gemma":0.022152914,"teacher_disagreement_score":0.99254566,"about_ca_system_score_codex":0.0025100089,"about_ca_system_score_gemma":0.007820893,"threshold_uncertainty_score":0.069487214},"labels":[],"label_agreement":null},{"id":"W325310379","doi":"10.1023/a:1017569003556","title":"The Times and the Man as Predictors of Emotion and Style in the Inaugural Addresses of U.S. Presidents","year":2001,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Presidential system; Personality; Psychology; Variance (accounting); Predictive power; Linguistics; Computational linguistics; Power (physics); Simple (philosophy); Social psychology; Computer science; Natural language processing; Political science; Epistemology; Law","score_opus":0.01576704285015433,"score_gpt":0.22946824188261022,"score_spread":0.21370119903245588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W325310379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99438596,0.0003501687,0.00004347507,0.0010569828,0.0000808268,0.0000030565068,0.00008963579,0.0000028348059,0.0039871326],"genre_scores_gemma":[0.99781513,0.0003145448,0.000062382736,0.00016549836,0.000095378746,0.000006873901,0.00010832852,0.000008337766,0.0014234214],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992495,0.00045132934,0.000037945534,0.000035403074,0.00010618234,0.000119561526],"domain_scores_gemma":[0.9927577,0.0021371034,0.0026261301,0.00016733327,0.0008788984,0.001432869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017680001,0.00018245027,0.00018585271,0.000701292,0.0011019553,0.0023996423,0.00018965738,0.00050828827,0.0031058341],"category_scores_gemma":[0.011778204,0.00011895345,0.00013202008,0.0009352477,0.0006130525,0.0009983872,0.0011068702,0.001252931,0.00074482244],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026078362,0.00011226888,0.9463849,0.000028450113,0.00005283231,0.00015233747,0.032048207,0.00012613715,0.00027422523,0.0008704821,0.0049577346,0.014731642],"study_design_scores_gemma":[0.0000042001334,0.000053621094,0.9440812,0.000046122113,0.000016205879,0.00005536533,0.050033227,0.0003112033,0.0000916994,0.00029536808,0.004998889,0.000012928539],"about_ca_topic_score_codex":0.009055195,"about_ca_topic_score_gemma":0.027067067,"teacher_disagreement_score":0.009055195,"about_ca_system_score_codex":0.0003906882,"about_ca_system_score_gemma":0.00035628065,"threshold_uncertainty_score":0.018004954},"labels":[],"label_agreement":null}]}