{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":2,"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":"b0048cd771bf","filters":{"venue":"D-Lib Magazine"}},"results":[{"id":"W2052918223","doi":"10.1045/march2006-choudhury","title":"Document Recognition for a Million Books","year":2006,"lang":"en","type":"article","venue":"D-Lib Magazine","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; World Wide Web; Information retrieval; Scalability; Process (computing); Digital library; Order (exchange); Database; Linguistics","authors":[{"name":"Sayeed Choudhury","is_ca":false},{"name":"Tim DiLauro","is_ca":false},{"name":"Robert Ferguson","is_ca":true},{"name":"Michael Droettboom","is_ca":false},{"name":"Ichiro Fujinaga","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01687287626591295,"gpt":0.2506368321123671,"spread":0.2337639558464542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003930145,0.0007892844,0.000620023,0.002936518,0.0007301989,0.002465823,0.0006924744,0.001063804,0.05507511],"category_scores_gemma":[0.001983046,0.000352726,0.0005419341,0.002987656,0.0002091946,0.002039299,0.0007117942,0.0009743213,0.06368405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006129558,"about_ca_system_score_gemma":0.0006089787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003685303,"about_ca_topic_score_gemma":0.005898812,"domain_scores_codex":[0.999426,0.00002853257,0.00005587738,0.0001491777,0.0002851433,0.00005538526],"domain_scores_gemma":[0.9992536,0.0001235529,0.00005033463,0.0001407388,0.0003826119,0.00004909277],"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":[0.0001517368,0.00003336406,0.0004769175,0.000199736,0.0000264255,0.0001383286,0.00005054921,0.00064521,0.01740587,0.002156992,0.1446718,0.8340431],"study_design_scores_gemma":[0.00004758794,0.0001662973,0.005950326,0.0002344318,0.0001104729,0.002164435,0.0003575078,0.0561197,0.07519846,0.006226885,0.8533356,0.00008828447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05548001,0.03967108,0.5258646,0.01012675,0.01197347,0.0006922904,0.03478638,0.08882148,0.232584],"genre_scores_gemma":[0.1305299,0.01087891,0.4113624,0.001651832,0.001274837,0.0002846364,0.03854067,0.002470157,0.4030067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05507511,"threshold_uncertainty_score":0.1842446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2521029362","doi":"10.1045/september2016-atanassova","title":"Temporal Properties of Recurring In-text References","year":2016,"lang":"en","type":"article","venue":"D-Lib Magazine","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Section (typography); Rhetorical question; Computer science; Linguistics; History; Philosophy","authors":[{"name":"Iana Atanassova","is_ca":false},{"name":"Marc Bertin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02887544086342106,"gpt":0.2564139090851951,"spread":0.227538468221774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003089886,0.0003334568,0.0005091674,0.006529007,0.001284941,0.00284047,0.001377032,0.0006981795,0.008318846],"category_scores_gemma":[0.0415314,0.0004253989,0.0004540382,0.005865396,0.0007592414,0.004602716,0.001031834,0.0008455612,0.001557136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038973,"about_ca_system_score_gemma":0.0009382148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002901404,"about_ca_topic_score_gemma":0.00314744,"domain_scores_codex":[0.996172,0.0005656037,0.0004480378,0.0006520425,0.00184342,0.0003189081],"domain_scores_gemma":[0.9448398,0.03288911,0.006142838,0.004707161,0.01027313,0.001148032],"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":[0.002306161,0.0003394761,0.06103284,0.001395508,0.0002769792,0.003650952,0.006467577,0.01563454,0.06995424,0.5073476,0.01673873,0.3148554],"study_design_scores_gemma":[0.0001559302,0.0005051002,0.06768698,0.0005418676,0.0006373694,0.004514474,0.003474082,0.3752889,0.06442834,0.4054512,0.07711241,0.0002033638],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5981218,0.00254637,0.3475647,0.0009305308,0.0003490167,0.0002295875,0.008178716,0.003479443,0.03859983],"genre_scores_gemma":[0.9564962,0.0004237807,0.02924388,0.00009904763,0.000253618,0.0001169018,0.004419144,0.0006384566,0.008308874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008318846,"threshold_uncertainty_score":0.02782929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}