{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/question-answering/papers/2","list_of":"/task/question-answering","task":"Question Answering","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":109,"rows_per_page":100,"rows":[101,200],"of":10817,"counts":{"archive_papers_tagged":10817,"with_a_code_link":4171,"where_syntology_ran_a_sample":1274,"not_listed_spam_title":0,"listed":10817,"listed_where_code_ran":1274,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1073,"every_run_a_failure_of_syntologys_instrument":201,"listed_with_a_run_with_no_instrument_failure":1073,"listed_every_run_a_failure_of_syntologys_instrument":201,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/question-answering","prev":"/task/question-answering","next":"/task/question-answering/papers/3","papers":[{"url":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","repositories_listed":5,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/byt5-towards-a-token-free-future-with-pre#ran","syntology_url":"https://syntology.ai/paper/2105.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13626"}},"official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","repositories_listed":5,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mdetr-modulated-detection-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12763"}},"official":{"repos":["ashkamath/mdetr"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pangu-a-large-scale-autoregressive-pretrained","slug":"pangu-a-large-scale-autoregressive-pretrained","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","date":"2021-04-26","arxiv_id":"2104.12369","repositories_listed":5,"syntology":null},{"url":"/paper/few-shot-question-answering-by-pretraining","slug":"few-shot-question-answering-by-pretraining","title":"Few-Shot Question Answering by Pretraining Span Selection","date":"2021-01-02","arxiv_id":"2101.00438","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-question-answering-by-pretraining#ran","syntology_url":"https://syntology.ai/paper/2101.00438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00438"}},"official":{"repos":["oriram/splinter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/relevance-guided-supervision-for-openqa-with","slug":"relevance-guided-supervision-for-openqa-with","title":"Relevance-guided Supervision for OpenQA with ColBERT","date":"2020-07-01","arxiv_id":"2007.00814","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/relevance-guided-supervision-for-openqa-with#ran","syntology_url":"https://syntology.ai/paper/2007.00814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00814"}},"official":{"repos":["stanford-futuredata/ColBERT","stanfordnlp/ColBERT-QA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pathvqa-30000-questions-for-medical-visual","slug":"pathvqa-30000-questions-for-medical-visual","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","date":"2020-03-07","arxiv_id":"2003.10286","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pathvqa-30000-questions-for-medical-visual#ran","syntology_url":"https://syntology.ai/paper/2003.10286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10286"}},"official":null}},{"url":"/paper/predicting-subjective-features-from-questions","slug":"predicting-subjective-features-from-questions","title":"Predicting Subjective Features of Questions of QA Websites using BERT","date":"2020-02-24","arxiv_id":"2002.10107","repositories_listed":5,"syntology":null},{"url":"/paper/12-in-1-multi-task-vision-and-language","slug":"12-in-1-multi-task-vision-and-language","title":"12-in-1: Multi-Task Vision and Language Representation Learning","date":"2019-12-05","arxiv_id":"1912.02315","repositories_listed":5,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/12-in-1-multi-task-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/1912.02315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02315"}},"official":{"repos":["facebookresearch/vilbert-multi-task"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reducing-transformer-depth-on-demand-with-1","slug":"reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","arxiv_id":"1909.11556","repositories_listed":5,"syntology":null},{"url":"/paper/pubmedqa-a-dataset-for-biomedical-research","slug":"pubmedqa-a-dataset-for-biomedical-research","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","date":"2019-09-13","arxiv_id":"1909.06146","repositories_listed":5,"syntology":null},{"url":"/paper/towards-scalable-and-reliable-capsule","slug":"towards-scalable-and-reliable-capsule","title":"Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications","date":"2019-06-06","arxiv_id":"1906.02829","repositories_listed":5,"syntology":null},{"url":"/paper/document-expansion-by-query-prediction","slug":"document-expansion-by-query-prediction","title":"Document Expansion by Query Prediction","date":"2019-04-17","arxiv_id":"1904.08375","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/document-expansion-by-query-prediction#ran","syntology_url":"https://syntology.ai/paper/1904.08375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08375"}},"official":{"repos":["nyu-dl/dl4ir-doc2query"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gqa-a-new-dataset-for-compositional-question","slug":"gqa-a-new-dataset-for-compositional-question","title":"GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering","date":"2019-02-25","arxiv_id":"1902.09506","repositories_listed":5,"syntology":null},{"url":"/paper/stochastic-answer-networks-for-squad-20","slug":"stochastic-answer-networks-for-squad-20","title":"Stochastic Answer Networks for SQuAD 2.0","date":"2018-09-24","arxiv_id":"1809.09194","repositories_listed":5,"syntology":null},{"url":"/paper/multi-task-learning-for-machine-reading","slug":"multi-task-learning-for-machine-reading","title":"Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension","date":"2018-09-18","arxiv_id":"1809.06963","repositories_listed":5,"syntology":null},{"url":"/paper/scaling-neural-machine-translation","slug":"scaling-neural-machine-translation","title":"Scaling Neural Machine Translation","date":"2018-06-01","arxiv_id":"1806.00187","repositories_listed":5,"syntology":null},{"url":"/paper/learned-in-translation-contextualized-word","slug":"learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","date":"2017-08-01","arxiv_id":"1708.00107","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learned-in-translation-contextualized-word#ran","syntology_url":"https://syntology.ai/paper/1708.00107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00107"}},"official":{"repos":["salesforce/cove"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/clevr-a-diagnostic-dataset-for-compositional","slug":"clevr-a-diagnostic-dataset-for-compositional","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","date":"2016-12-20","arxiv_id":"1612.06890","repositories_listed":5,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/clevr-a-diagnostic-dataset-for-compositional#ran","syntology_url":"https://syntology.ai/paper/1612.06890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.06890"}},"official":null}},{"url":"/paper/tracking-the-world-state-with-recurrent","slug":"tracking-the-world-state-with-recurrent","title":"Tracking the World State with Recurrent Entity Networks","date":"2016-12-12","arxiv_id":"1612.03969","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/tracking-the-world-state-with-recurrent#ran","syntology_url":"https://syntology.ai/paper/1612.03969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.03969"}},"official":{"repos":["facebook/MemNN"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/machine-comprehension-using-match-lstm-and","slug":"machine-comprehension-using-match-lstm-and","title":"Machine Comprehension Using Match-LSTM and Answer Pointer","date":"2016-08-29","arxiv_id":"1608.07905","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/machine-comprehension-using-match-lstm-and#ran","syntology_url":"https://syntology.ai/paper/1608.07905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.07905"}},"official":{"repos":["shuohangwang/SeqMatchSeq"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/memory-networks","slug":"memory-networks","title":"Memory Networks","date":"2014-10-15","arxiv_id":"1410.3916","repositories_listed":5,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/memory-networks#ran","syntology_url":"https://syntology.ai/paper/1410.3916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1410.3916"}},"official":null}},{"url":"/paper/deepseek-r1-incentivizing-reasoning","slug":"deepseek-r1-incentivizing-reasoning","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","date":"2025-01-22","arxiv_id":"2501.12948","repositories_listed":4,"syntology":null},{"url":"/paper/regnlp-in-action-facilitating-compliance","slug":"regnlp-in-action-facilitating-compliance","title":"RIRAG: Regulatory Information Retrieval and Answer Generation","date":"2024-09-09","arxiv_id":"2409.05677","repositories_listed":4,"syntology":null},{"url":"/paper/i-srt-aligning-large-multimodal-models-for","slug":"i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","arxiv_id":"2406.11280","repositories_listed":4,"syntology":{"n":30,"n_ran":26,"n_constructed":0,"n_ran_checked":18,"n_instrument":8,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":16,"n_pointer_only":15,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 2 violated, 16 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/i-srt-aligning-large-multimodal-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.11280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11280"}},"official":{"repos":["snumprlab/SRT","snumprlab/isr-dpo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/babilong-testing-the-limits-of-llms-with-long","slug":"babilong-testing-the-limits-of-llms-with-long","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","date":"2024-06-14","arxiv_id":"2406.10149","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/babilong-testing-the-limits-of-llms-with-long#ran","syntology_url":"https://syntology.ai/paper/2406.10149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10149"}},"official":{"repos":["booydar/babilong"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/longlora-efficient-fine-tuning-of-long","slug":"longlora-efficient-fine-tuning-of-long","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","date":"2023-09-21","arxiv_id":"2309.12307","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/longlora-efficient-fine-tuning-of-long#ran","syntology_url":"https://syntology.ai/paper/2309.12307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12307"}},"official":{"repos":["dvlab-research/longlora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/med-flamingo-a-multimodal-medical-few-shot","slug":"med-flamingo-a-multimodal-medical-few-shot","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","date":"2023-07-27","arxiv_id":"2307.15189","repositories_listed":4,"syntology":null},{"url":"/paper/pythia-a-suite-for-analyzing-large-language","slug":"pythia-a-suite-for-analyzing-large-language","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","date":"2023-04-03","arxiv_id":"2304.01373","repositories_listed":4,"syntology":null},{"url":"/paper/mgtbench-benchmarking-machine-generated-text","slug":"mgtbench-benchmarking-machine-generated-text","title":"MGTBench: Benchmarking Machine-Generated Text Detection","date":"2023-03-26","arxiv_id":"2303.14822","repositories_listed":4,"syntology":{"n":26,"n_ran":19,"n_constructed":0,"n_ran_checked":18,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/mgtbench-benchmarking-machine-generated-text#ran","syntology_url":"https://syntology.ai/paper/2303.14822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14822"}},"official":{"repos":["xinleihe/mgtbench"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/video-text-as-game-players-hierarchical","slug":"video-text-as-game-players-hierarchical","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","date":"2023-03-25","arxiv_id":"2303.14369","repositories_listed":4,"syntology":{"n":16,"n_ran":12,"n_constructed":7,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/video-text-as-game-players-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2303.14369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14369"}},"official":{"repos":["jpthu17/HBI"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","repositories_listed":4,"syntology":null},{"url":"/paper/layoutlmv3-pre-training-for-document-ai-with","slug":"layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","repositories_listed":4,"syntology":null},{"url":"/paper/distilled-dual-encoder-model-for-vision","slug":"distilled-dual-encoder-model-for-vision","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","date":"2021-12-16","arxiv_id":"2112.08723","repositories_listed":4,"syntology":null},{"url":"/paper/longt5-efficient-text-to-text-transformer-for","slug":"longt5-efficient-text-to-text-transformer-for","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","date":"2021-12-15","arxiv_id":"2112.07916","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longt5-efficient-text-to-text-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.07916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07916"}},"official":{"repos":["google-research/longt5"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-much-can-clip-benefit-vision-and-language","slug":"how-much-can-clip-benefit-vision-and-language","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","date":"2021-07-13","arxiv_id":"2107.06383","repositories_listed":4,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/how-much-can-clip-benefit-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.06383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06383"}},"official":{"repos":["clip-vil/CLIP-ViL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/pondernet-learning-to-ponder","slug":"pondernet-learning-to-ponder","title":"PonderNet: Learning to Ponder","date":"2021-07-12","arxiv_id":"2107.05407","repositories_listed":4,"syntology":{"n":10,"n_ran":10,"n_constructed":5,"n_ran_checked":5,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pondernet-learning-to-ponder#ran","syntology_url":"https://syntology.ai/paper/2107.05407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05407"}},"official":null}},{"url":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","repositories_listed":4,"syntology":null},{"url":"/paper/logic-embeddings-for-complex-query-answering","slug":"logic-embeddings-for-complex-query-answering","title":"Logic Embeddings for Complex Query Answering","date":"2021-02-28","arxiv_id":"2103.00418","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/logic-embeddings-for-complex-query-answering#ran","syntology_url":"https://syntology.ai/paper/2103.00418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00418"}},"official":{"repos":["francoisluus/KGReasoning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/learning-dense-representations-of-phrases-at","slug":"learning-dense-representations-of-phrases-at","title":"Learning Dense Representations of Phrases at Scale","date":"2020-12-23","arxiv_id":"2012.12624","repositories_listed":4,"syntology":null},{"url":"/paper/distilling-knowledge-from-reader-to-retriever-1","slug":"distilling-knowledge-from-reader-to-retriever-1","title":"Distilling Knowledge from Reader to Retriever for Question Answering","date":"2020-12-08","arxiv_id":"2012.04584","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distilling-knowledge-from-reader-to-retriever-1#ran","syntology_url":"https://syntology.ai/paper/2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}},"official":{"repos":["facebookresearch/FiD"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multi-relational-embedding-for-knowledge","slug":"multi-relational-embedding-for-knowledge","title":"Multi-Relational Embedding for Knowledge Graph Representation and Analysis","date":"2020-09-28","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/beyond-accuracy-behavioral-testing-of-nlp","slug":"beyond-accuracy-behavioral-testing-of-nlp","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","date":"2020-05-08","arxiv_id":"2005.04118","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-accuracy-behavioral-testing-of-nlp#ran","syntology_url":"https://syntology.ai/paper/2005.04118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04118"}},"official":{"repos":["marcotcr/checklist"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ktrain-a-low-code-library-for-augmented","slug":"ktrain-a-low-code-library-for-augmented","title":"ktrain: A Low-Code Library for Augmented Machine Learning","date":"2020-04-19","arxiv_id":"2004.10703","repositories_listed":4,"syntology":{"n":16,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/ktrain-a-low-code-library-for-augmented#ran","syntology_url":"https://syntology.ai/paper/2004.10703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.10703"}},"official":{"repos":["amaiya/ktrain"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":10,"ran_from_kinds":["listed"]}}},{"url":"/paper/talking-heads-attention","slug":"talking-heads-attention","title":"Talking-Heads Attention","date":"2020-03-05","arxiv_id":"2003.02436","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/talking-heads-attention#ran","syntology_url":"https://syntology.ai/paper/2003.02436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02436"}},"official":{"repos":["zygmuntz/hyperband"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/arabert-transformer-based-model-for-arabic","slug":"arabert-transformer-based-model-for-arabic","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","date":"2020-02-28","arxiv_id":"2003.00104","repositories_listed":4,"syntology":null},{"url":"/paper/break-it-down-a-question-understanding","slug":"break-it-down-a-question-understanding","title":"Break It Down: A Question Understanding Benchmark","date":"2020-01-31","arxiv_id":"2001.11770","repositories_listed":4,"syntology":null},{"url":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","slug":"dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dice-loss-for-data-imbalanced-nlp-tasks#ran","syntology_url":"https://syntology.ai/paper/1911.02855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02855"}},"official":{"repos":["ShannonAI/dice_loss_for_NLP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mlqa-evaluating-cross-lingual-extractive","slug":"mlqa-evaluating-cross-lingual-extractive","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","date":"2019-10-16","arxiv_id":"1910.07475","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mlqa-evaluating-cross-lingual-extractive#ran","syntology_url":"https://syntology.ai/paper/1910.07475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07475"}},"official":{"repos":["facebookresearch/MLQA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tag-based-multi-span-extraction-in-reading","slug":"tag-based-multi-span-extraction-in-reading","title":"A Simple and Effective Model for Answering Multi-span Questions","date":"2019-09-29","arxiv_id":"1909.13375","repositories_listed":4,"syntology":null},{"url":"/paper/synthetic-qa-corpora-generation-with","slug":"synthetic-qa-corpora-generation-with","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","date":"2019-06-12","arxiv_id":"1906.05416","repositories_listed":4,"syntology":null},{"url":"/paper/scene-text-visual-question-answering","slug":"scene-text-visual-question-answering","title":"Scene Text Visual Question Answering","date":"2019-05-31","arxiv_id":"1905.13648","repositories_listed":4,"syntology":null},{"url":"/paper/190409380","slug":"190409380","title":"Repurposing Entailment for Multi-Hop Question Answering Tasks","date":"2019-04-20","arxiv_id":"1904.09380","repositories_listed":4,"syntology":null},{"url":"/paper/commonsenseqa-a-question-answering-challenge","slug":"commonsenseqa-a-question-answering-challenge","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","date":"2018-11-02","arxiv_id":"1811.00937","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/commonsenseqa-a-question-answering-challenge#ran","syntology_url":"https://syntology.ai/paper/1811.00937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00937"}},"official":{"repos":["jonathanherzig/commonsenseqa"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/zero-shot-user-intent-detection-via-capsule","slug":"zero-shot-user-intent-detection-via-capsule","title":"Zero-shot User Intent Detection via Capsule Neural Networks","date":"2018-09-02","arxiv_id":"1809.00385","repositories_listed":4,"syntology":null},{"url":"/paper/coqa-a-conversational-question-answering","slug":"coqa-a-conversational-question-answering","title":"CoQA: A Conversational Question Answering Challenge","date":"2018-08-21","arxiv_id":"1808.07042","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coqa-a-conversational-question-answering#ran","syntology_url":"https://syntology.ai/paper/1808.07042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.07042"}},"official":null}},{"url":"/paper/did-the-model-understand-the-question","slug":"did-the-model-understand-the-question","title":"Did the Model Understand the Question?","date":"2018-05-14","arxiv_id":"1805.05492","repositories_listed":4,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/did-the-model-understand-the-question#ran","syntology_url":"https://syntology.ai/paper/1805.05492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.05492"}},"official":{"repos":["pramodkaushik/acl18_results"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/embodied-question-answering","slug":"embodied-question-answering","title":"Embodied Question Answering","date":"2017-11-30","arxiv_id":"1711.11543","repositories_listed":4,"syntology":null},{"url":"/paper/machine-comprehension-by-text-to-text-neural","slug":"machine-comprehension-by-text-to-text-neural","title":"Machine Comprehension by Text-to-Text Neural Question Generation","date":"2017-05-04","arxiv_id":"1705.02012","repositories_listed":4,"syntology":null},{"url":"/paper/learning-to-skim-text","slug":"learning-to-skim-text","title":"Learning to Skim Text","date":"2017-04-23","arxiv_id":"1704.06877","repositories_listed":4,"syntology":null},{"url":"/paper/gated-attention-readers-for-text","slug":"gated-attention-readers-for-text","title":"Gated-Attention Readers for Text Comprehension","date":"2016-06-05","arxiv_id":"1606.01549","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gated-attention-readers-for-text#ran","syntology_url":"https://syntology.ai/paper/1606.01549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.01549"}},"official":{"repos":["bdhingra/ga-reader"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/adding-gradient-noise-improves-learning-for","slug":"adding-gradient-noise-improves-learning-for","title":"Adding Gradient Noise Improves Learning for Very Deep Networks","date":"2015-11-21","arxiv_id":"1511.06807","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adding-gradient-noise-improves-learning-for#ran","syntology_url":"https://syntology.ai/paper/1511.06807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06807"}},"official":null}},{"url":"/paper/compositional-semantic-parsing-on-semi","slug":"compositional-semantic-parsing-on-semi","title":"Compositional Semantic Parsing on Semi-Structured Tables","date":"2015-08-03","arxiv_id":"1508.00305","repositories_listed":4,"syntology":null},{"url":"/paper/glove-global-vectors-for-word-representation","slug":"glove-global-vectors-for-word-representation","title":"GloVe: Global Vectors for Word Representation","date":"2014-10-01","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/infochartqa-a-benchmark-for-multimodal","slug":"infochartqa-a-benchmark-for-multimodal","title":"InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts","date":"2025-05-25","arxiv_id":"2505.19028","repositories_listed":3,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":16,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":3,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/infochartqa-a-benchmark-for-multimodal#ran","syntology_url":"https://syntology.ai/paper/2505.19028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19028"}},"official":{"repos":["cooldawnant/infochartqa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/search-r1-training-llms-to-reason-and","slug":"search-r1-training-llms-to-reason-and","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","date":"2025-03-12","arxiv_id":"2503.09516","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/search-r1-training-llms-to-reason-and#ran","syntology_url":"https://syntology.ai/paper/2503.09516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09516"}},"official":{"repos":["petergriffinjin/search-r1"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/mapeval-a-map-based-evaluation-of-geo-spatial","slug":"mapeval-a-map-based-evaluation-of-geo-spatial","title":"MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models","date":"2024-12-31","arxiv_id":"2501.00316","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mapeval-a-map-based-evaluation-of-geo-spatial#ran","syntology_url":"https://syntology.ai/paper/2501.00316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00316"}},"official":{"repos":["MapEval/MapEval-API","MapEval/MapEval-Textual","MapEval/MapEval-Visual"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/swift-a-scalable-lightweight-infrastructure","slug":"swift-a-scalable-lightweight-infrastructure","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","date":"2024-08-10","arxiv_id":"2408.05517","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/swift-a-scalable-lightweight-infrastructure#ran","syntology_url":"https://syntology.ai/paper/2408.05517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05517"}},"official":{"repos":["modelscope/ms-swift","modelscope/swift"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/vrsbench-a-versatile-vision-language","slug":"vrsbench-a-versatile-vision-language","title":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","date":"2024-06-18","arxiv_id":"2406.12384","repositories_listed":3,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vrsbench-a-versatile-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.12384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12384"}},"official":{"repos":["lx709/vrsbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/large-language-model-validity-via-enhanced","slug":"large-language-model-validity-via-enhanced","title":"Large language model validity via enhanced conformal prediction methods","date":"2024-06-14","arxiv_id":"2406.09714","repositories_listed":3,"syntology":{"n":32,"n_ran":23,"n_constructed":0,"n_ran_checked":22,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":22,"n_pointer_only":12,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/large-language-model-validity-via-enhanced#ran","syntology_url":"https://syntology.ai/paper/2406.09714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09714"}},"official":{"repos":["jjcherian/conformal-safety"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/videollama-2-advancing-spatial-temporal","slug":"videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","arxiv_id":"2406.07476","repositories_listed":3,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/videollama-2-advancing-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2406.07476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07476"}},"official":{"repos":["damo-nlp-sg/videollama2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/crafting-interpretable-embeddings-by-asking","slug":"crafting-interpretable-embeddings-by-asking","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","date":"2024-05-26","arxiv_id":"2405.16714","repositories_listed":3,"syntology":null},{"url":"/paper/chameleon-mixed-modal-early-fusion-foundation","slug":"chameleon-mixed-modal-early-fusion-foundation","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","date":"2024-05-16","arxiv_id":"2405.09818","repositories_listed":3,"syntology":null},{"url":"/paper/uqa-corpus-for-urdu-question-answering","slug":"uqa-corpus-for-urdu-question-answering","title":"UQA: Corpus for Urdu Question Answering","date":"2024-05-02","arxiv_id":"2405.01458","repositories_listed":3,"syntology":null},{"url":"/paper/from-local-to-global-a-graph-rag-approach-to","slug":"from-local-to-global-a-graph-rag-approach-to","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","date":"2024-04-24","arxiv_id":"2404.16130","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/from-local-to-global-a-graph-rag-approach-to#ran","syntology_url":"https://syntology.ai/paper/2404.16130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16130"}},"official":null}},{"url":"/paper/sailor-open-language-models-for-south-east","slug":"sailor-open-language-models-for-south-east","title":"Sailor: Open Language Models for South-East Asia","date":"2024-04-04","arxiv_id":"2404.03608","repositories_listed":3,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/sailor-open-language-models-for-south-east#ran","syntology_url":"https://syntology.ai/paper/2404.03608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03608"}},"official":{"repos":["epfllm/megatron-llm","sail-sg/sailor-llm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-text-to-visual-generation-with","slug":"evaluating-text-to-visual-generation-with","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","date":"2024-04-01","arxiv_id":"2404.01291","repositories_listed":3,"syntology":null},{"url":"/paper/the-unreasonable-ineffectiveness-of-the","slug":"the-unreasonable-ineffectiveness-of-the","title":"The Unreasonable Ineffectiveness of the Deeper Layers","date":"2024-03-26","arxiv_id":"2403.17887","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-unreasonable-ineffectiveness-of-the#ran","syntology_url":"https://syntology.ai/paper/2403.17887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17887"}},"official":null}},{"url":"/paper/prismatic-vlms-investigating-the-design-space","slug":"prismatic-vlms-investigating-the-design-space","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","date":"2024-02-12","arxiv_id":"2402.07865","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prismatic-vlms-investigating-the-design-space#ran","syntology_url":"https://syntology.ai/paper/2402.07865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07865"}},"official":{"repos":["tri-ml/prismatic-vlms","tri-ml/vlm-evaluation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/raptor-recursive-abstractive-processing-for","slug":"raptor-recursive-abstractive-processing-for","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","date":"2024-01-31","arxiv_id":"2401.18059","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/raptor-recursive-abstractive-processing-for#ran","syntology_url":"https://syntology.ai/paper/2401.18059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.18059"}},"official":{"repos":["parthsarthi03/RAPTOR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-fusion-of-large-language-models","slug":"knowledge-fusion-of-large-language-models","title":"Knowledge Fusion of Large Language Models","date":"2024-01-19","arxiv_id":"2401.10491","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/knowledge-fusion-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2401.10491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10491"}},"official":{"repos":["fanqiwan/fusellm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/drivelm-driving-with-graph-visual-question","slug":"drivelm-driving-with-graph-visual-question","title":"DriveLM: Driving with Graph Visual Question Answering","date":"2023-12-21","arxiv_id":"2312.14150","repositories_listed":3,"syntology":null},{"url":"/paper/medgen-a-python-natural-language-processing","slug":"medgen-a-python-natural-language-processing","title":"Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation","date":"2023-11-28","arxiv_id":"2311.16588","repositories_listed":3,"syntology":null},{"url":"/paper/ehrxqa-a-multi-modal-question-answering-1","slug":"ehrxqa-a-multi-modal-question-answering-1","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","date":"2023-10-28","arxiv_id":"2310.18652","repositories_listed":3,"syntology":{"n":20,"n_ran":20,"n_constructed":0,"n_ran_checked":17,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ehrxqa-a-multi-modal-question-answering-1#ran","syntology_url":"https://syntology.ai/paper/2310.18652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18652"}},"official":{"repos":["baeseongsu/ehrxqa","baeseongsu/mimic-cxr-vqa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dspy-compiling-declarative-language-model","slug":"dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","arxiv_id":"2310.03714","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dspy-compiling-declarative-language-model#ran","syntology_url":"https://syntology.ai/paper/2310.03714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03714"}},"official":{"repos":["stanfordnlp/dspy"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/evaluating-hallucinations-in-chinese-large","slug":"evaluating-hallucinations-in-chinese-large","title":"Evaluating Hallucinations in Chinese Large Language Models","date":"2023-10-05","arxiv_id":"2310.03368","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-hallucinations-in-chinese-large#ran","syntology_url":"https://syntology.ai/paper/2310.03368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03368"}},"official":{"repos":["xiami2019/halluqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structchart-perception-structuring-reasoning","slug":"structchart-perception-structuring-reasoning","title":"StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding","date":"2023-09-20","arxiv_id":"2309.11268","repositories_listed":3,"syntology":null},{"url":"/paper/instructiongpt-4-a-200-instruction-paradigm","slug":"instructiongpt-4-a-200-instruction-paradigm","title":"InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4","date":"2023-08-23","arxiv_id":"2308.12067","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/instructiongpt-4-a-200-instruction-paradigm#ran","syntology_url":"https://syntology.ai/paper/2308.12067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12067"}},"official":{"repos":["waltonfuture/InstructionGPT-4"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/beam-retrieval-general-end-to-end-retrieval","slug":"beam-retrieval-general-end-to-end-retrieval","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","date":"2023-08-17","arxiv_id":"2308.08973","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/beam-retrieval-general-end-to-end-retrieval#ran","syntology_url":"https://syntology.ai/paper/2308.08973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08973"}},"official":{"repos":["Alab-NII/2wikimultihop","canghongjian/beam_retriever"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/autogen-enabling-next-gen-llm-applications","slug":"autogen-enabling-next-gen-llm-applications","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","date":"2023-08-16","arxiv_id":"2308.08155","repositories_listed":3,"syntology":{"n":8,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/autogen-enabling-next-gen-llm-applications#ran","syntology_url":"https://syntology.ai/paper/2308.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08155"}},"official":null}},{"url":"/paper/think-on-graph-deep-and-responsible-reasoning","slug":"think-on-graph-deep-and-responsible-reasoning","title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","date":"2023-07-15","arxiv_id":"2307.07697","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/think-on-graph-deep-and-responsible-reasoning#ran","syntology_url":"https://syntology.ai/paper/2307.07697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07697"}},"official":{"repos":["gasolsun36/tog","idea-finai/tog"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"url":"/paper/shifting-attention-to-relevance-towards-the","slug":"shifting-attention-to-relevance-towards-the","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","date":"2023-07-03","arxiv_id":"2307.01379","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shifting-attention-to-relevance-towards-the#ran","syntology_url":"https://syntology.ai/paper/2307.01379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01379"}},"official":{"repos":["jinhaoduan/sar","jinhaoduan/shifting-attention-to-relevance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-in-context-learning-with-answer","slug":"enhancing-in-context-learning-with-answer","title":"Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering","date":"2023-06-07","arxiv_id":"2306.04508","repositories_listed":3,"syntology":null},{"url":"/paper/layout-and-task-aware-instruction-prompt-for","slug":"layout-and-task-aware-instruction-prompt-for","title":"Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering","date":"2023-06-01","arxiv_id":"2306.00526","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/layout-and-task-aware-instruction-prompt-for#ran","syntology_url":"https://syntology.ai/paper/2306.00526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00526"}},"official":{"repos":["wenjinw/latin-prompt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/averitec-a-dataset-for-real-world-claim-1","slug":"averitec-a-dataset-for-real-world-claim-1","title":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","date":"2023-05-22","arxiv_id":"2305.13117","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/averitec-a-dataset-for-real-world-claim-1#ran","syntology_url":"https://syntology.ai/paper/2305.13117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13117"}},"official":{"repos":["michschli/averitec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-models-in-remote-sensing","slug":"vision-language-models-in-remote-sensing","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","date":"2023-05-09","arxiv_id":"2305.05726","repositories_listed":3,"syntology":null},{"url":"/paper/creating-custom-event-data-without","slug":"creating-custom-event-data-without","title":"Creating Custom Event Data Without Dictionaries: A Bag-of-Tricks","date":"2023-04-03","arxiv_id":"2304.01331","repositories_listed":3,"syntology":null},{"url":"/paper/semantic-uncertainty-linguistic-invariances","slug":"semantic-uncertainty-linguistic-invariances","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","date":"2023-02-19","arxiv_id":"2302.09664","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semantic-uncertainty-linguistic-invariances#ran","syntology_url":"https://syntology.ai/paper/2302.09664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.09664"}},"official":{"repos":["lorenzkuhn/semantic_uncertainty"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/replug-retrieval-augmented-black-box-language","slug":"replug-retrieval-augmented-black-box-language","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","date":"2023-01-30","arxiv_id":"2301.12652","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/replug-retrieval-augmented-black-box-language#ran","syntology_url":"https://syntology.ai/paper/2301.12652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12652"}},"official":null}},{"url":"/paper/xlm-v-overcoming-the-vocabulary-bottleneck-in","slug":"xlm-v-overcoming-the-vocabulary-bottleneck-in","title":"XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models","date":"2023-01-25","arxiv_id":"2301.10472","repositories_listed":3,"syntology":null},{"url":"/paper/climabench-a-benchmark-dataset-for-climate","slug":"climabench-a-benchmark-dataset-for-climate","title":"Towards Answering Climate Questionnaires from Unstructured Climate Reports","date":"2023-01-11","arxiv_id":"2301.04253","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/climabench-a-benchmark-dataset-for-climate#ran","syntology_url":"https://syntology.ai/paper/2301.04253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.04253"}},"official":{"repos":["climabench/climabench"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}}],"record_sha256":"560f360a8e57772c8648af3c5a05acefeb0d6e1c0de72e972084bdee41f61285","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}