{"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":"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":[0.1599532,0.0015134453,0.83458894,0.00020175605,0.00007665539,0.0005270656,0.000002554917,0.00017156557,0.0029648268],"genre_scores_gemma":[0.9793939,0.000161316,0.019899447,0.0004437746,0.000019664249,0.000036169113,0.000004987995,0.000006898339,0.000033866847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984226,0.0004440607,0.00043495113,0.00029976532,0.0002039484,0.00019465387],"domain_scores_gemma":[0.99868816,0.00058103766,0.0002071128,0.00044667962,0.00006671535,0.0000102958265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010326516,0.00018496509,0.00046869036,0.0008025924,0.00029397837,0.00048005907,0.00055410276,0.000049828406,0.000001129417],"category_scores_gemma":[0.000018531673,0.0001216295,0.000091463706,0.00084632053,0.00064968946,0.00041019646,0.00017134218,0.00016819168,1.6103711e-7],"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":[0.0000079731635,0.00005181447,0.0025561946,0.000024827703,0.00012843091,0.000008596936,0.02260356,0.00013524451,0.000028229999,0.94762236,0.00004300149,0.026789784],"study_design_scores_gemma":[0.0030623395,0.0006224035,0.12985444,0.00046222474,0.0008958615,0.000106725,0.007635079,0.43620616,0.0033223054,0.40904832,0.0072085513,0.0015755974],"about_ca_topic_score_codex":0.00038736087,"about_ca_topic_score_gemma":0.00079666317,"teacher_disagreement_score":0.81944066,"about_ca_system_score_codex":0.00004154248,"about_ca_system_score_gemma":0.000020432646,"threshold_uncertainty_score":0.4959907},"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":"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":[0.8068123,0.0026794015,0.000014840936,0.00020621537,0.0005043034,0.00015211194,0.0000056289746,0.000028225248,0.18959695],"genre_scores_gemma":[0.99569684,0.000032286935,0.000010193822,0.002479244,0.0003556536,0.000023354385,0.0000036794952,0.00001100898,0.0013877313],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990561,0.00008698471,0.0003093255,0.00012978473,0.0001599576,0.00025787362],"domain_scores_gemma":[0.99933946,0.0003357788,0.00009667064,0.00016842796,0.00004223658,0.00001745206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062570546,0.00014668518,0.00023661637,0.00010756768,0.00037156092,0.0006568981,0.00037285942,0.000019052284,0.00018084406],"category_scores_gemma":[0.000015405598,0.00008299995,0.000080922844,0.000016650985,0.0016148809,0.00048526586,0.000111690446,0.00020352345,0.0000038601256],"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":[0.000022056061,0.000022811098,0.000015151602,0.00002971479,0.000011254355,0.0000061263368,0.37409306,0.0000017688347,4.170714e-7,0.6245603,0.00019184637,0.0010454756],"study_design_scores_gemma":[0.0029000312,0.0003273984,0.00045789508,0.00050186785,0.00002315148,0.000036573132,0.28303245,0.00007838438,0.000005202047,0.31167555,0.40059415,0.0003673563],"about_ca_topic_score_codex":0.00025355624,"about_ca_topic_score_gemma":0.00035227078,"teacher_disagreement_score":0.4004023,"about_ca_system_score_codex":0.00013649349,"about_ca_system_score_gemma":0.000031136122,"threshold_uncertainty_score":0.6334483},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007485312,0.009402706,0.9784904,0.0002872816,0.00026463903,0.00016185186,1.851198e-7,0.001043558,0.002864035],"genre_scores_gemma":[0.83476084,0.000045122222,0.16375312,0.00043062106,0.00013774958,0.0000064696915,0.0000010205582,0.000010797785,0.00085427123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990626,0.00008214391,0.00022033164,0.00022208256,0.00014809716,0.00026475635],"domain_scores_gemma":[0.99894565,0.0006098007,0.00009042627,0.00024294098,0.000074587995,0.00003661721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000828934,0.00014485986,0.00018506816,0.0001072337,0.0005843299,0.0006511289,0.0007752857,0.000047538648,0.0000033033714],"category_scores_gemma":[0.00006287135,0.00009233788,0.000049567898,0.0001223465,0.0005268346,0.00026667252,0.0005368313,0.00025681392,0.000009248053],"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":[0.000011334719,0.000025294496,0.00009519665,0.00008919935,0.000025633382,0.000016577736,0.013818635,0.0000040437235,0.00003919316,0.87616056,0.00044962234,0.109264724],"study_design_scores_gemma":[0.0022911546,0.0002618595,0.0031339074,0.00083223596,0.000052646985,0.0002076434,0.0007269999,0.6557445,0.0021489298,0.3106027,0.023136618,0.00086083694],"about_ca_topic_score_codex":0.000024382169,"about_ca_topic_score_gemma":0.000015439698,"teacher_disagreement_score":0.8272755,"about_ca_system_score_codex":0.000017403212,"about_ca_system_score_gemma":0.000022486742,"threshold_uncertainty_score":0.62788504},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16419928,0.009016515,0.82466173,0.0006609757,0.0002895976,0.00042655584,0.0000010778815,0.0004961603,0.0002481373],"genre_scores_gemma":[0.74421567,0.00000528096,0.2551077,0.0005668092,0.00006772465,0.000008624866,3.2099496e-7,0.0000057317434,0.0000221387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992686,0.000044009117,0.00014593755,0.00019412197,0.00015742598,0.00018989122],"domain_scores_gemma":[0.99949485,0.00010991182,0.00009725391,0.0002211632,0.000053769167,0.000023040593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017941807,0.000115935894,0.00013147536,0.000047031837,0.000588276,0.0007224323,0.00041749337,0.000026506643,0.0000012494744],"category_scores_gemma":[0.00002097971,0.00007564553,0.000032993692,0.00009804704,0.0003241173,0.0003246,0.00041465863,0.00009366513,0.0000012875759],"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":[0.00001762352,0.000036911115,0.00009818012,0.00004103832,0.000035381265,0.00005027781,0.016028162,0.0004278021,0.00053230685,0.95810485,0.00007137281,0.024556099],"study_design_scores_gemma":[0.0043516313,0.00016514138,0.00018596138,0.0006414168,0.00003456889,0.00034351856,0.00080852647,0.28041938,0.023021936,0.68842757,0.0009591896,0.0006411763],"about_ca_topic_score_codex":0.0000676944,"about_ca_topic_score_gemma":0.000006402882,"teacher_disagreement_score":0.5800164,"about_ca_system_score_codex":0.000047820864,"about_ca_system_score_gemma":0.00003435951,"threshold_uncertainty_score":0.6966431},"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":"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":[0.39462197,0.012145629,0.59138685,0.0004794148,0.00026589484,0.00030387283,0.0000069856,0.00014143225,0.0006479376],"genre_scores_gemma":[0.96450436,0.00004193656,0.034034215,0.00066253135,0.000033394386,0.0000071651257,0.0000014136318,0.00000549142,0.00070951873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993474,0.000089386565,0.00014148829,0.00016929329,0.0001333445,0.000119109536],"domain_scores_gemma":[0.9993799,0.00018316774,0.00007962592,0.00031213445,0.000029593692,0.00001560174],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005343618,0.00009584328,0.0001470489,0.0000716164,0.0002906409,0.0010443522,0.0005169466,0.000019123841,0.0000014391688],"category_scores_gemma":[0.00004736401,0.00005006407,0.000027262196,0.000098984616,0.00030526723,0.0007293458,0.0003579009,0.000087838955,3.0055227e-7],"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":[0.000010542098,0.0000071346485,0.00003375335,0.000027104204,0.00001447835,0.0000050077306,0.016318327,0.0000011497049,0.00036069608,0.9762457,0.00051286665,0.00646323],"study_design_scores_gemma":[0.005074997,0.0017284461,0.0030783296,0.0013192921,0.0003241335,0.0011437841,0.03377709,0.021141877,0.038305502,0.814691,0.0771773,0.002238235],"about_ca_topic_score_codex":0.00009026449,"about_ca_topic_score_gemma":0.000026694455,"teacher_disagreement_score":0.56988233,"about_ca_system_score_codex":0.000007491564,"about_ca_system_score_gemma":0.000011799518,"threshold_uncertainty_score":0.99999267},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95169634,0.013417006,0.0000045291627,0.0011571455,0.00015650134,0.00028484673,0.000008146378,0.000009175863,0.033266284],"genre_scores_gemma":[0.9949087,0.0025004665,0.0000020734994,0.0002112525,0.00018019865,0.000014417535,0.0000020758396,0.000005675023,0.0021751414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9991636,0.00022160797,0.00022395872,0.00009820441,0.00017872443,0.00011390521],"domain_scores_gemma":[0.99886346,0.0007535601,0.00014104834,0.0001818692,0.00005313349,0.0000069119333],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00051576673,0.00011274133,0.00022419065,0.000046654743,0.00078197615,0.00035197995,0.00024081074,0.000013228949,0.00003915009],"category_scores_gemma":[0.00003485483,0.00004288184,0.000051532366,0.000025729383,0.00466016,0.00013168604,0.00016765935,0.00008189424,4.200807e-7],"study_design_candidate":"qualitative","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":[0.00012286982,0.000022568956,0.0009946486,0.00003839398,0.00022968497,0.0000020284137,0.3186997,0.0000075000003,2.926274e-7,0.6762933,0.0020304946,0.0015585241],"study_design_scores_gemma":[0.004652322,0.00029762986,0.035512254,0.00037499255,0.0006519619,0.000030063853,0.8286935,0.0013172542,0.000017793303,0.085621625,0.042541876,0.00028873482],"about_ca_topic_score_codex":0.0013622176,"about_ca_topic_score_gemma":0.002193754,"teacher_disagreement_score":0.59067166,"about_ca_system_score_codex":0.0000031229386,"about_ca_system_score_gemma":0.000006431479,"threshold_uncertainty_score":0.9980486},"labels":[],"label_agreement":null}]}