{"meta":{"query_hash":"3a76d6254d98","filters":{"venue":"ACM Transactions on Speech and Language Processing"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/3a76d6254d98","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+Transactions+on+Speech+and+Language+Processing"},"results":[{"id":"W2052227241","doi":"10.1145/1289600.1289602","title":"Adaptive text correction with Web-crawled domain-dependent dictionaries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Trigram; Vocabulary; Natural language processing; Domain (mathematical analysis); Information retrieval; Word (group theory); Artificial intelligence; Web page; Crawling; Punctuation; Linguistics; World Wide Web","score_opus":0.008003122257323006,"score_gpt":0.25074320704803005,"score_spread":0.24274008479070705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052227241","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":[0.014912476,0.003459594,0.9790333,0.00040552806,0.00019168688,0.00021206489,0.0000035372282,0.00097098574,0.0008108602],"genre_scores_gemma":[0.6213723,0.000017600001,0.37786472,0.00021323007,0.000045922963,0.000014352247,0.0000018318275,0.000016692866,0.00045337822],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983808,0.000036486537,0.00023821573,0.0005334304,0.00042643806,0.00038465683],"domain_scores_gemma":[0.9990073,0.00014055349,0.00012940435,0.00043573653,0.00015145229,0.00013559469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039843575,0.0002576426,0.00019752869,0.00033692233,0.0006079961,0.00033178643,0.00047399284,0.00012818989,0.000025422516],"category_scores_gemma":[0.00003265876,0.0002031653,0.00004284939,0.0006823508,0.00012593964,0.00095174165,0.000025840862,0.0004818879,0.000007895179],"study_design_candidate":"design_other","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":[0.00016943757,0.00010097609,0.000059898735,0.00003005493,0.000022966091,0.00013312163,0.0034380523,0.0000124690405,0.004218705,0.0002229158,0.000023213704,0.9915682],"study_design_scores_gemma":[0.0060939672,0.0033077039,0.001577905,0.0021027564,0.00027347618,0.0063460404,0.031363957,0.031545937,0.88556325,0.025502414,0.0025796425,0.0037429307],"about_ca_topic_score_codex":0.00008871258,"about_ca_topic_score_gemma":0.00042794523,"teacher_disagreement_score":0.9878253,"about_ca_system_score_codex":0.00010474679,"about_ca_system_score_gemma":0.00011879173,"threshold_uncertainty_score":0.82848406},"labels":[],"label_agreement":null},{"id":"W2091014931","doi":"10.1145/1177055.1177057","title":"Confidence estimation for NLP applications","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Université de Montréal","funders":"","keywords":"Computer science; Machine translation; Artificial intelligence; Natural language processing; Estimation; Confidence interval; Natural language; Machine learning; Statistics; Mathematics","score_opus":0.00987436474930131,"score_gpt":0.28429790564261975,"score_spread":0.27442354089331844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091014931","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044438287,0.004913214,0.99265563,0.00075321033,0.000027779579,0.0003959314,0.000008731331,0.00064894103,0.00015215488],"genre_scores_gemma":[0.43112507,0.000006785866,0.5683165,0.00016235343,0.000032154643,0.00015249239,0.0000066791745,0.0000088447405,0.00018907557],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904203,0.000014177497,0.00019229032,0.00036988355,0.00016559644,0.00021603983],"domain_scores_gemma":[0.9992441,0.0001160421,0.00008975353,0.0003964272,0.00010348652,0.00005018498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016100312,0.0001446771,0.00012430544,0.00015195797,0.00038933376,0.00032320127,0.0004842912,0.00008075377,0.000006637809],"category_scores_gemma":[0.00003117941,0.0001327451,0.00004062188,0.00035123026,0.000052925767,0.0006400461,0.00001222096,0.00014809288,0.000004479958],"study_design_candidate":"design_other","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":[0.0000063284056,0.000048459362,0.0000025855866,0.00009134108,0.000002894358,0.000003011647,0.0002768657,0.000043340344,0.003744363,0.005423162,0.000031357344,0.9903263],"study_design_scores_gemma":[0.0009902022,0.0002115519,0.000058404432,0.00033079594,0.00007103309,0.00024788763,0.00040744274,0.16137384,0.43025294,0.40301982,0.0021350582,0.00090101484],"about_ca_topic_score_codex":0.00008095615,"about_ca_topic_score_gemma":0.000027501188,"teacher_disagreement_score":0.9894253,"about_ca_system_score_codex":0.000032071664,"about_ca_system_score_gemma":0.00005220659,"threshold_uncertainty_score":0.54131883},"labels":[],"label_agreement":null},{"id":"W2109163800","doi":"10.1145/1187415.1187417","title":"A statistical model for near-synonym choice","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Synonym (taxonomy); Artificial intelligence; Natural language processing; Task (project management); Context (archaeology); Machine translation; Thesaurus; Mutual information; Information retrieval; Machine learning","score_opus":0.01971804255985616,"score_gpt":0.31857975632009145,"score_spread":0.2988617137602353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109163800","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003665246,0.0027266964,0.99218076,0.00043049347,0.00004811417,0.00023463013,0.000017776028,0.00057973934,0.000116560615],"genre_scores_gemma":[0.40694526,0.0000048428983,0.59223795,0.0004959788,0.000027361533,0.000017537566,0.0000031623779,0.000014287306,0.0002536242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986345,0.00001388799,0.00023543419,0.00045566575,0.0002415595,0.00041896262],"domain_scores_gemma":[0.9989464,0.0003163858,0.00007196594,0.00041113532,0.00010291799,0.0001511936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042536602,0.00019207405,0.00017612937,0.0001358429,0.0004433503,0.00038676543,0.0005717867,0.00011920869,0.000012583682],"category_scores_gemma":[0.00016760919,0.00016943265,0.00004658852,0.00031405894,0.000084642474,0.0005752994,0.000022147415,0.00029181407,0.0000028382308],"study_design_candidate":"design_other","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":[0.000030040112,0.000058808626,0.0000084538415,0.00009296165,0.000006819258,0.000020526864,0.0015493393,0.000031314285,0.0016022138,0.0005060942,0.000028958137,0.9960645],"study_design_scores_gemma":[0.0010248773,0.00024277027,0.00008452106,0.00020614575,0.00005419638,0.00017389693,0.00034814392,0.91281,0.061342157,0.02232167,0.0006835413,0.0007080326],"about_ca_topic_score_codex":0.000044332035,"about_ca_topic_score_gemma":0.000099708166,"teacher_disagreement_score":0.99535644,"about_ca_system_score_codex":0.00004174876,"about_ca_system_score_gemma":0.00010033998,"threshold_uncertainty_score":0.6909263},"labels":[],"label_agreement":null},{"id":"W2130998770","doi":"10.1145/1596517.1596518","title":"Extrinsic summarization evaluation","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Sixth Framework Programme","keywords":"Automatic summarization; Computer science; Task (project management); Information retrieval; Audit; Human–computer interaction; Natural language processing; Artificial intelligence","score_opus":0.024218930316466627,"score_gpt":0.29291025333555487,"score_spread":0.26869132301908827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130998770","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":[0.047257796,0.0008914804,0.9497743,0.0010210553,0.000060920072,0.00012245064,4.852222e-7,0.000150835,0.0007206403],"genre_scores_gemma":[0.88284624,0.000017710188,0.11658792,0.000399891,0.000033196655,0.000005434797,0.0000020888813,0.0000037897473,0.000103741266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918437,0.000031695854,0.00012661872,0.00026575912,0.00025239887,0.00013912847],"domain_scores_gemma":[0.9994972,0.000022646895,0.000040186776,0.00032340045,0.000066680535,0.000049920895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024076202,0.00008657066,0.0000743233,0.000119961405,0.00019050125,0.0001753455,0.00022644625,0.000046743924,0.000020946638],"category_scores_gemma":[0.0000343554,0.00008184119,0.000020805035,0.0002706592,0.000009944462,0.0005554298,0.0000043493496,0.00011156341,0.0000052981795],"study_design_candidate":"design_other","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":[0.0000027682693,0.000026537677,0.000008731467,0.00000650536,0.0000016740518,0.000003006769,0.0011368231,0.0003768467,0.0016918355,0.00011156916,0.0000019232048,0.9966318],"study_design_scores_gemma":[0.0010521711,0.00016511088,0.0015759778,0.00014184245,0.000048244565,0.00007983652,0.0007226022,0.9535074,0.031654015,0.010432492,0.00021474111,0.0004055425],"about_ca_topic_score_codex":0.00001322994,"about_ca_topic_score_gemma":0.000009614182,"teacher_disagreement_score":0.99622625,"about_ca_system_score_codex":0.000030502846,"about_ca_system_score_gemma":0.000051904288,"threshold_uncertainty_score":0.33373868},"labels":[],"label_agreement":null}]}