{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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","author_layer_release":"2026-06-26"},"query_hash":"b15508754daf","filters":{"venue":"Computers and the Humanities"}},"results":[{"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Steven Bird","is_ca":false},{"name":"Gary Simons","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0398088240749413,"gpt":0.2605981528609337,"spread":0.2207893287859924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005343618,0.00009584328,0.0001470489,0.0000716164,0.0002906409,0.001044352,0.0005169466,0.00001912384,0.000001439169],"category_scores_gemma":[0.00004736401,0.00005006407,0.0000272622,0.00009898462,0.0003052672,0.0007293458,0.0003579009,0.00008783895,3.005523e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007491564,"about_ca_system_score_gemma":0.00001179952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009026449,"about_ca_topic_score_gemma":0.00002669446,"domain_scores_codex":[0.9993474,0.00008938657,0.0001414883,0.0001692933,0.0001333445,0.0001191095],"domain_scores_gemma":[0.9993799,0.0001831677,0.00007962592,0.0003121344,0.00002959369,0.00001560174],"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":[0.0000105421,0.000007134649,0.00003375335,0.0000271042,0.00001447835,0.000005007731,0.01631833,0.000001149705,0.0003606961,0.9762457,0.0005128667,0.00646323],"study_design_scores_gemma":[0.005074997,0.001728446,0.00307833,0.001319292,0.0003241335,0.001143784,0.03377709,0.02114188,0.0383055,0.814691,0.0771773,0.002238235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.394622,0.01214563,0.5913869,0.0004794148,0.0002658948,0.0003038728,0.0000069856,0.0001414322,0.0006479376],"genre_scores_gemma":[0.9645044,0.00004193656,0.03403421,0.0006625314,0.00003339439,0.000007165126,0.000001413632,0.00000549142,0.0007095187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5698823,"threshold_uncertainty_score":0.9999927,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Matthew Spencer","is_ca":true},{"name":"Christopher J. Howe","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02261266426027232,"gpt":0.2515213186214391,"spread":0.2289086543611668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001794181,0.0001159359,0.0001314754,0.00004703184,0.000588276,0.0007224323,0.0004174934,0.00002650664,0.000001249474],"category_scores_gemma":[0.00002097971,0.00007564553,0.00003299369,0.00009804704,0.0003241173,0.0003246,0.0004146586,0.00009366513,0.000001287576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004782086,"about_ca_system_score_gemma":0.00003435951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000676944,"about_ca_topic_score_gemma":0.000006402882,"domain_scores_codex":[0.9992686,0.00004400912,0.0001459375,0.000194122,0.000157426,0.0001898912],"domain_scores_gemma":[0.9994949,0.0001099118,0.00009725391,0.0002211632,0.00005376917,0.00002304059],"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":[0.00001762352,0.00003691111,0.00009818012,0.00004103832,0.00003538126,0.00005027781,0.01602816,0.0004278021,0.0005323068,0.9581048,0.00007137281,0.0245561],"study_design_scores_gemma":[0.004351631,0.0001651414,0.0001859614,0.0006414168,0.00003456889,0.0003435186,0.0008085265,0.2804194,0.02302194,0.6884276,0.0009591896,0.0006411763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1641993,0.009016515,0.8246617,0.0006609757,0.0002895976,0.0004265558,0.000001077882,0.0004961603,0.0002481373],"genre_scores_gemma":[0.7442157,0.00000528096,0.2551077,0.0005668092,0.00006772465,0.000008624866,3.20995e-7,0.000005731743,0.0000221387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5800164,"threshold_uncertainty_score":0.6966431,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Afsaneh Fazly","is_ca":true},{"name":"Suzanne Stevenson","is_ca":true},{"name":"Ryan North","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01257919200372212,"gpt":0.2518575762560514,"spread":0.2392783842523293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000828934,0.0001448599,0.0001850682,0.0001072337,0.0005843299,0.0006511289,0.0007752857,0.00004753865,0.000003303371],"category_scores_gemma":[0.00006287135,0.00009233788,0.0000495679,0.0001223465,0.0005268346,0.0002666725,0.0005368313,0.0002568139,0.000009248053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001740321,"about_ca_system_score_gemma":0.00002248674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002438217,"about_ca_topic_score_gemma":0.0000154397,"domain_scores_codex":[0.9990626,0.00008214391,0.0002203316,0.0002220826,0.0001480972,0.0002647564],"domain_scores_gemma":[0.9989457,0.0006098007,0.00009042627,0.000242941,0.000074588,0.00003661721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001133472,0.0000252945,0.00009519665,0.00008919935,0.00002563338,0.00001657774,0.01381863,0.000004043723,0.00003919316,0.8761606,0.0004496223,0.1092647],"study_design_scores_gemma":[0.002291155,0.0002618595,0.003133907,0.000832236,0.00005264698,0.0002076434,0.0007269999,0.6557445,0.00214893,0.3106027,0.02313662,0.0008608369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007485312,0.009402706,0.9784904,0.0002872816,0.000264639,0.0001618519,1.851198e-7,0.001043558,0.002864035],"genre_scores_gemma":[0.8347608,0.00004512222,0.1637531,0.0004306211,0.0001377496,0.000006469691,0.000001020558,0.00001079778,0.0008542712],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8272755,"threshold_uncertainty_score":0.627885,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Cynthia Whissell","is_ca":true},{"name":"Lee Sigelman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01576704285015433,"gpt":0.2294682418826102,"spread":0.2137011990324559,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005157667,0.0001127413,0.0002241906,0.00004665474,0.0007819762,0.00035198,0.0002408107,0.00001322895,0.00003915009],"category_scores_gemma":[0.00003485483,0.00004288184,0.00005153237,0.00002572938,0.00466016,0.000131686,0.0001676594,0.00008189424,4.200807e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003122939,"about_ca_system_score_gemma":0.000006431479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001362218,"about_ca_topic_score_gemma":0.002193754,"domain_scores_codex":[0.9991636,0.000221608,0.0002239587,0.00009820441,0.0001787244,0.0001139052],"domain_scores_gemma":[0.9988635,0.0007535601,0.0001410483,0.0001818692,0.00005313349,0.000006911933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001228698,0.00002256896,0.0009946486,0.00003839398,0.000229685,0.000002028414,0.3186997,0.0000075,2.926274e-7,0.6762933,0.002030495,0.001558524],"study_design_scores_gemma":[0.004652322,0.0002976299,0.03551225,0.0003749926,0.0006519619,0.00003006385,0.8286935,0.001317254,0.0000177933,0.08562163,0.04254188,0.0002887348],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9516963,0.01341701,0.000004529163,0.001157145,0.0001565013,0.0002848467,0.000008146378,0.000009175863,0.03326628],"genre_scores_gemma":[0.9949087,0.002500467,0.000002073499,0.0002112525,0.0001801987,0.00001441753,0.00000207584,0.000005675023,0.002175141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5906717,"threshold_uncertainty_score":0.9980486,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Susan Brown","is_ca":true},{"name":"Isobel Grundy","is_ca":true},{"name":"Patricia Clements","is_ca":true},{"name":"Renée Elio","is_ca":true},{"name":"Sharon Balazs","is_ca":true},{"name":"Rebecca Cameron","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04561557180674407,"gpt":0.1986165929571398,"spread":0.1530010211503957,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006257055,0.0001466852,0.0002366164,0.0001075677,0.0003715609,0.0006568981,0.0003728594,0.00001905228,0.0001808441],"category_scores_gemma":[0.0000154056,0.00008299995,0.00008092284,0.00001665099,0.001614881,0.0004852659,0.0001116904,0.0002035235,0.000003860126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364935,"about_ca_system_score_gemma":0.00003113612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002535562,"about_ca_topic_score_gemma":0.0003522708,"domain_scores_codex":[0.9990561,0.00008698471,0.0003093255,0.0001297847,0.0001599576,0.0002578736],"domain_scores_gemma":[0.9993395,0.0003357788,0.00009667064,0.000168428,0.00004223658,0.00001745206],"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":[0.00002205606,0.0000228111,0.0000151516,0.00002971479,0.00001125435,0.000006126337,0.3740931,0.000001768835,4.170714e-7,0.6245603,0.0001918464,0.001045476],"study_design_scores_gemma":[0.002900031,0.0003273984,0.0004578951,0.0005018678,0.00002315148,0.00003657313,0.2830324,0.00007838438,0.000005202047,0.3116755,0.4005941,0.0003673563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8068123,0.002679402,0.00001484094,0.0002062154,0.0005043034,0.0001521119,0.000005628975,0.00002822525,0.189597],"genre_scores_gemma":[0.9956968,0.00003228693,0.00001019382,0.002479244,0.0003556536,0.00002335439,0.000003679495,0.00001100898,0.001387731],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4004023,"threshold_uncertainty_score":0.6334483,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jean-Frédéric de Pasquale","is_ca":true},{"name":"Jean-Guy Meunier","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02689138140384781,"gpt":0.2562144994664453,"spread":0.2293231180625974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001032652,0.0001849651,0.0004686904,0.0008025924,0.0002939784,0.0004800591,0.0005541028,0.00004982841,0.000001129417],"category_scores_gemma":[0.00001853167,0.0001216295,0.00009146371,0.0008463205,0.0006496895,0.0004101965,0.0001713422,0.0001681917,1.610371e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004154248,"about_ca_system_score_gemma":0.00002043265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003873609,"about_ca_topic_score_gemma":0.0007966632,"domain_scores_codex":[0.9984226,0.0004440607,0.0004349511,0.0002997653,0.0002039484,0.0001946539],"domain_scores_gemma":[0.9986882,0.0005810377,0.0002071128,0.0004466796,0.00006671535,0.00001029583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007973164,0.00005181447,0.002556195,0.0000248277,0.0001284309,0.000008596936,0.02260356,0.0001352445,0.00002823,0.9476224,0.00004300149,0.02678978],"study_design_scores_gemma":[0.003062339,0.0006224035,0.1298544,0.0004622247,0.0008958615,0.000106725,0.007635079,0.4362062,0.003322305,0.4090483,0.007208551,0.001575597],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1599532,0.001513445,0.8345889,0.000201756,0.00007665539,0.0005270656,0.000002554917,0.0001715656,0.002964827],"genre_scores_gemma":[0.9793939,0.000161316,0.01989945,0.0004437746,0.00001966425,0.00003616911,0.000004987995,0.000006898339,0.00003386685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8194407,"threshold_uncertainty_score":0.4959907,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}