{"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/language-modelling/papers/3","list_of":"/task/language-modelling","task":"Language Modelling","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":3,"pages_in_order":177,"rows_per_page":100,"rows":[201,300],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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/language-modelling","prev":"/task/language-modelling/papers/2","next":"/task/language-modelling/papers/4","papers":[{"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/conditional-bert-contextual-augmentation","slug":"conditional-bert-contextual-augmentation","title":"Conditional BERT Contextual Augmentation","date":"2018-12-17","arxiv_id":"1812.06705","repositories_listed":5,"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":2,"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/conditional-bert-contextual-augmentation#ran","syntology_url":"https://syntology.ai/paper/1812.06705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.06705"}},"official":null}},{"url":"/paper/neural-abstractive-text-summarization-with","slug":"neural-abstractive-text-summarization-with","title":"Neural Abstractive Text Summarization with Sequence-to-Sequence Models","date":"2018-12-05","arxiv_id":"1812.02303","repositories_listed":5,"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/neural-abstractive-text-summarization-with#ran","syntology_url":"https://syntology.ai/paper/1812.02303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.02303"}},"official":{"repos":["tshi04/NATS"],"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/targeted-syntactic-evaluation-of-language","slug":"targeted-syntactic-evaluation-of-language","title":"Targeted Syntactic Evaluation of Language Models","date":"2018-08-27","arxiv_id":"1808.09031","repositories_listed":5,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/targeted-syntactic-evaluation-of-language#ran","syntology_url":"https://syntology.ai/paper/1808.09031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.09031"}},"official":{"repos":["BeckyMarvin/LM_syneval"],"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/neural-architecture-optimization","slug":"neural-architecture-optimization","title":"Neural Architecture Optimization","date":"2018-08-22","arxiv_id":"1808.07233","repositories_listed":5,"syntology":null},{"url":"/paper/online-spatial-concept-and-lexical","slug":"online-spatial-concept-and-lexical","title":"Online Spatial Concept and Lexical Acquisition with Simultaneous Localization and Mapping","date":"2017-04-15","arxiv_id":"1704.04664","repositories_listed":5,"syntology":null},{"url":"/paper/structured-sequence-modeling-with-graph","slug":"structured-sequence-modeling-with-graph","title":"Structured Sequence Modeling with Graph Convolutional Recurrent Networks","date":"2016-12-22","arxiv_id":"1612.07659","repositories_listed":5,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/structured-sequence-modeling-with-graph#ran","syntology_url":"https://syntology.ai/paper/1612.07659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.07659"}},"official":{"repos":["youngjoo-epfl/gconvRNN"],"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":["listed","official"]}}},{"url":"/paper/learning-python-code-suggestion-with-a-sparse","slug":"learning-python-code-suggestion-with-a-sparse","title":"Learning Python Code Suggestion with a Sparse Pointer Network","date":"2016-11-24","arxiv_id":"1611.08307","repositories_listed":5,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-python-code-suggestion-with-a-sparse#ran","syntology_url":"https://syntology.ai/paper/1611.08307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08307"}},"official":{"repos":["uclmr/pycodesuggest"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/assessing-the-ability-of-lstms-to-learn","slug":"assessing-the-ability-of-lstms-to-learn","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","date":"2016-11-04","arxiv_id":"1611.01368","repositories_listed":5,"syntology":null},{"url":"/paper/tying-word-vectors-and-word-classifiers-a","slug":"tying-word-vectors-and-word-classifiers-a","title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","date":"2016-11-04","arxiv_id":"1611.01462","repositories_listed":5,"syntology":null},{"url":"/paper/a-segmental-framework-for-fully-unsupervised","slug":"a-segmental-framework-for-fully-unsupervised","title":"A segmental framework for fully-unsupervised large-vocabulary speech recognition","date":"2016-06-22","arxiv_id":"1606.06950","repositories_listed":5,"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/a-segmental-framework-for-fully-unsupervised#ran","syntology_url":"https://syntology.ai/paper/1606.06950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.06950"}},"official":{"repos":["kamperh/bucktsong_segmentalist"],"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/gated-word-character-recurrent-language-model","slug":"gated-word-character-recurrent-language-model","title":"Gated Word-Character Recurrent Language Model","date":"2016-06-06","arxiv_id":"1606.01700","repositories_listed":5,"syntology":null},{"url":"/paper/adaptive-computation-time-for-recurrent","slug":"adaptive-computation-time-for-recurrent","title":"Adaptive Computation Time for Recurrent Neural Networks","date":"2016-03-29","arxiv_id":"1603.08983","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-computation-time-for-recurrent#ran","syntology_url":"https://syntology.ai/paper/1603.08983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.08983"}},"official":null}},{"url":"/paper/learning-longer-memory-in-recurrent-neural","slug":"learning-longer-memory-in-recurrent-neural","title":"Learning Longer Memory in Recurrent Neural Networks","date":"2014-12-24","arxiv_id":"1412.7753","repositories_listed":5,"syntology":null},{"url":"/paper/first-pass-large-vocabulary-continuous-speech","slug":"first-pass-large-vocabulary-continuous-speech","title":"First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs","date":"2014-08-12","arxiv_id":"1408.2873","repositories_listed":5,"syntology":null},{"url":"/paper/word2vec-explained-deriving-mikolov-et-als","slug":"word2vec-explained-deriving-mikolov-et-als","title":"word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method","date":"2014-02-15","arxiv_id":"1402.3722","repositories_listed":5,"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":2,"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/word2vec-explained-deriving-mikolov-et-als#ran","syntology_url":"https://syntology.ai/paper/1402.3722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1402.3722"}},"official":null}},{"url":"/paper/mamut-a-novel-framework-for-modifying","slug":"mamut-a-novel-framework-for-modifying","title":"MAMUT: A Novel Framework for Modifying Mathematical Formulas for the Generation of Specialized Datasets for Language Model Training","date":"2025-02-28","arxiv_id":"2502.20855","repositories_listed":4,"syntology":null},{"url":"/paper/deepseek-v3-technical-report","slug":"deepseek-v3-technical-report","title":"DeepSeek-V3 Technical Report","date":"2024-12-27","arxiv_id":"2412.19437","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/deepseek-v3-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.19437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.19437"}},"official":{"repos":["deepseek-ai/deepseek-v3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/gated-delta-networks-improving-mamba2-with","slug":"gated-delta-networks-improving-mamba2-with","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","date":"2024-12-09","arxiv_id":"2412.06464","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gated-delta-networks-improving-mamba2-with#ran","syntology_url":"https://syntology.ai/paper/2412.06464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06464"}},"official":{"repos":["NVlabs/GatedDeltaNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/the-ademamix-optimizer-better-faster-older","slug":"the-ademamix-optimizer-better-faster-older","title":"The AdEMAMix Optimizer: Better, Faster, Older","date":"2024-09-05","arxiv_id":"2409.03137","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-ademamix-optimizer-better-faster-older#ran","syntology_url":"https://syntology.ai/paper/2409.03137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03137"}},"official":{"repos":["apple/ml-ademamix"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llms-as-zero-shot-graph-learners-alignment-of","slug":"llms-as-zero-shot-graph-learners-alignment-of","title":"LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings","date":"2024-08-25","arxiv_id":"2408.14512","repositories_listed":4,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llms-as-zero-shot-graph-learners-alignment-of#ran","syntology_url":"https://syntology.ai/paper/2408.14512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14512"}},"official":{"repos":["w-rudder/tea-glm"],"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":["listed","official"]}}},{"url":"/paper/scaling-synthetic-data-creation-with","slug":"scaling-synthetic-data-creation-with","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","date":"2024-06-28","arxiv_id":"2406.20094","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-synthetic-data-creation-with#ran","syntology_url":"https://syntology.ai/paper/2406.20094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20094"}},"official":{"repos":["tencent-ailab/persona-hub"],"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":["listed","official"]}}},{"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/ranking-manipulation-for-conversational","slug":"ranking-manipulation-for-conversational","title":"Ranking Manipulation for Conversational Search Engines","date":"2024-06-05","arxiv_id":"2406.03589","repositories_listed":4,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ranking-manipulation-for-conversational#ran","syntology_url":"https://syntology.ai/paper/2406.03589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03589"}},"official":{"repos":["spfrommer/ragdoll-data-pipeline","spfrommer/ranking_manipulation","spfrommer/ranking_manipulation_data_pipeline","spfrommer/cse-ranking-manipulation"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/xmodel-vlm-a-simple-baseline-for-multimodal","slug":"xmodel-vlm-a-simple-baseline-for-multimodal","title":"Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model","date":"2024-05-15","arxiv_id":"2405.09215","repositories_listed":4,"syntology":null},{"url":"/paper/qserve-w4a8kv4-quantization-and-system-co","slug":"qserve-w4a8kv4-quantization-and-system-co","title":"QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving","date":"2024-05-07","arxiv_id":"2405.04532","repositories_listed":4,"syntology":null},{"url":"/paper/openelm-an-efficient-language-model-family","slug":"openelm-an-efficient-language-model-family","title":"OpenELM: An Efficient Language Model Family with Open Training and Inference Framework","date":"2024-04-22","arxiv_id":"2404.14619","repositories_listed":4,"syntology":null},{"url":"/paper/hgrn2-gated-linear-rnns-with-state-expansion","slug":"hgrn2-gated-linear-rnns-with-state-expansion","title":"HGRN2: Gated Linear RNNs with State Expansion","date":"2024-04-11","arxiv_id":"2404.07904","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/hgrn2-gated-linear-rnns-with-state-expansion#ran","syntology_url":"https://syntology.ai/paper/2404.07904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07904"}},"official":{"repos":["sustcsonglin/flash-linear-attention","opennlplab/hgrn2"],"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/advancing-time-series-classification-with","slug":"advancing-time-series-classification-with","title":"Advancing Time Series Classification with Multimodal Language Modeling","date":"2024-03-19","arxiv_id":"2403.12371","repositories_listed":4,"syntology":null},{"url":"/paper/learning-transferable-time-series-classifier","slug":"learning-transferable-time-series-classifier","title":"Cross-Domain Pre-training with Language Models for Transferable Time Series Representations","date":"2024-03-19","arxiv_id":"2403.12372","repositories_listed":4,"syntology":null},{"url":"/paper/griffin-mixing-gated-linear-recurrences-with","slug":"griffin-mixing-gated-linear-recurrences-with","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","date":"2024-02-29","arxiv_id":"2402.19427","repositories_listed":4,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/griffin-mixing-gated-linear-recurrences-with#ran","syntology_url":"https://syntology.ai/paper/2402.19427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19427"}},"official":null}},{"url":"/paper/tower-an-open-multilingual-large-language","slug":"tower-an-open-multilingual-large-language","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","date":"2024-02-27","arxiv_id":"2402.17733","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"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) · 0 unverified","sample_list":"/paper/tower-an-open-multilingual-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.17733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17733"}},"official":{"repos":["deep-spin/tower-eval","epfllm/megatron-llm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/repetition-improves-language-model-embeddings","slug":"repetition-improves-language-model-embeddings","title":"Repetition Improves Language Model Embeddings","date":"2024-02-23","arxiv_id":"2402.15449","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 2 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) · 1 unverified","sample_list":"/paper/repetition-improves-language-model-embeddings#ran","syntology_url":"https://syntology.ai/paper/2402.15449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15449"}},"official":{"repos":["jakespringer/echo-embeddings"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/x-lora-mixture-of-low-rank-adapter-experts-a","slug":"x-lora-mixture-of-low-rank-adapter-experts-a","title":"X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design","date":"2024-02-11","arxiv_id":"2402.07148","repositories_listed":4,"syntology":null},{"url":"/paper/algorithm-evolution-using-large-language","slug":"algorithm-evolution-using-large-language","title":"Algorithm Evolution Using Large Language Model","date":"2023-11-26","arxiv_id":"2311.15249","repositories_listed":4,"syntology":null},{"url":"/paper/chat-univi-unified-visual-representation","slug":"chat-univi-unified-visual-representation","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","date":"2023-11-14","arxiv_id":"2311.08046","repositories_listed":4,"syntology":null},{"url":"/paper/cogvlm-visual-expert-for-pretrained-language","slug":"cogvlm-visual-expert-for-pretrained-language","title":"CogVLM: Visual Expert for Pretrained Language Models","date":"2023-11-06","arxiv_id":"2311.03079","repositories_listed":4,"syntology":null},{"url":"/paper/nlp-evaluation-in-trouble-on-the-need-to","slug":"nlp-evaluation-in-trouble-on-the-need-to","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","date":"2023-10-27","arxiv_id":"2310.18018","repositories_listed":4,"syntology":null},{"url":"/paper/discrete-diffusion-language-modeling-by","slug":"discrete-diffusion-language-modeling-by","title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","date":"2023-10-25","arxiv_id":"2310.16834","repositories_listed":4,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/discrete-diffusion-language-modeling-by#ran","syntology_url":"https://syntology.ai/paper/2310.16834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16834"}},"official":{"repos":["louaaron/score-entropy-discrete-diffusion"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llemma-an-open-language-model-for-mathematics","slug":"llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","date":"2023-10-16","arxiv_id":"2310.10631","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/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}},"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/neftune-noisy-embeddings-improve-instruction","slug":"neftune-noisy-embeddings-improve-instruction","title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning","date":"2023-10-09","arxiv_id":"2310.05914","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neftune-noisy-embeddings-improve-instruction#ran","syntology_url":"https://syntology.ai/paper/2310.05914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05914"}},"official":{"repos":["neelsjain/neftune"],"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/ultrafeedback-boosting-language-models-with","slug":"ultrafeedback-boosting-language-models-with","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","date":"2023-10-02","arxiv_id":"2310.01377","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/ultrafeedback-boosting-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2310.01377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01377"}},"official":{"repos":["thunlp/ultrafeedback"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/expertqa-expert-curated-questions-and","slug":"expertqa-expert-curated-questions-and","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","date":"2023-09-14","arxiv_id":"2309.07852","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/expertqa-expert-curated-questions-and#ran","syntology_url":"https://syntology.ai/paper/2309.07852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07852"}},"official":{"repos":["chaitanyamalaviya/expertqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"6 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-is-chatgpt-s-behavior-changing-over-time#ran","syntology_url":"https://syntology.ai/paper/2307.09009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09009"}},"official":{"repos":["lchen001/llmdrift"],"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":["listed","official"]}}},{"url":"/paper/provable-robust-watermarking-for-ai-generated","slug":"provable-robust-watermarking-for-ai-generated","title":"Provable Robust Watermarking for AI-Generated Text","date":"2023-06-30","arxiv_id":"2306.17439","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/provable-robust-watermarking-for-ai-generated#ran","syntology_url":"https://syntology.ai/paper/2306.17439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17439"}},"official":{"repos":["xuandongzhao/gptwatermark","xuandongzhao/unigram-watermark"],"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":["listed","official"]}}},{"url":"/paper/hyenadna-long-range-genomic-sequence-modeling","slug":"hyenadna-long-range-genomic-sequence-modeling","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","date":"2023-06-27","arxiv_id":"2306.15794","repositories_listed":4,"syntology":{"n":28,"n_ran":17,"n_constructed":11,"n_ran_checked":13,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":1,"phrase":"17 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/hyenadna-long-range-genomic-sequence-modeling#ran","syntology_url":"https://syntology.ai/paper/2306.15794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15794"}},"official":{"repos":["HazyResearch/hyena-dna"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mme-a-comprehensive-evaluation-benchmark-for","slug":"mme-a-comprehensive-evaluation-benchmark-for","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","date":"2023-06-23","arxiv_id":"2306.13394","repositories_listed":4,"syntology":null},{"url":"/paper/video-llama-an-instruction-tuned-audio-visual","slug":"video-llama-an-instruction-tuned-audio-visual","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","date":"2023-06-05","arxiv_id":"2306.02858","repositories_listed":4,"syntology":{"n":25,"n_ran":18,"n_constructed":7,"n_ran_checked":8,"n_instrument":10,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":9,"phrase":"18 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/video-llama-an-instruction-tuned-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2306.02858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02858"}},"official":{"repos":["damo-nlp-sg/video-llama"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/factscore-fine-grained-atomic-evaluation-of","slug":"factscore-fine-grained-atomic-evaluation-of","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","date":"2023-05-23","arxiv_id":"2305.14251","repositories_listed":4,"syntology":{"n":15,"n_ran":11,"n_constructed":1,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":6,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/factscore-fine-grained-atomic-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2305.14251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14251"}},"official":{"repos":["shmsw25/factscore"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/gqa-training-generalized-multi-query","slug":"gqa-training-generalized-multi-query","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","date":"2023-05-22","arxiv_id":"2305.13245","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gqa-training-generalized-multi-query#ran","syntology_url":"https://syntology.ai/paper/2305.13245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13245"}},"official":null}},{"url":"/paper/how-to-index-item-ids-for-recommendation","slug":"how-to-index-item-ids-for-recommendation","title":"How to Index Item IDs for Recommendation Foundation Models","date":"2023-05-11","arxiv_id":"2305.06569","repositories_listed":4,"syntology":null},{"url":"/paper/deeptextmark-deep-learning-based-text","slug":"deeptextmark-deep-learning-based-text","title":"DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text","date":"2023-05-09","arxiv_id":"2305.05773","repositories_listed":4,"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":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) · 0 unverified","sample_list":"/paper/deeptextmark-deep-learning-based-text#ran","syntology_url":"https://syntology.ai/paper/2305.05773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05773"}},"official":null}},{"url":"/paper/lamp-when-large-language-models-meet","slug":"lamp-when-large-language-models-meet","title":"LaMP: When Large Language Models Meet Personalization","date":"2023-04-22","arxiv_id":"2304.11406","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 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) · 1 unverified","sample_list":"/paper/lamp-when-large-language-models-meet#ran","syntology_url":"https://syntology.ai/paper/2304.11406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11406"}},"official":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/winclip-zero-few-shot-anomaly-classification","slug":"winclip-zero-few-shot-anomaly-classification","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","date":"2023-03-26","arxiv_id":"2303.14814","repositories_listed":4,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":3,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/winclip-zero-few-shot-anomaly-classification#ran","syntology_url":"https://syntology.ai/paper/2303.14814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14814"}},"official":null}},{"url":"/paper/detectgpt-zero-shot-machine-generated-text","slug":"detectgpt-zero-shot-machine-generated-text","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","date":"2023-01-26","arxiv_id":"2301.11305","repositories_listed":4,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/detectgpt-zero-shot-machine-generated-text#ran","syntology_url":"https://syntology.ai/paper/2301.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11305"}},"official":{"repos":["eric-mitchell/detect-gpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/text-only-training-for-image-captioning-using#ran","syntology_url":"https://syntology.ai/paper/2211.00575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00575"}},"official":{"repos":["davidhuji/capdec"],"state":"official (archive's flag): 2 ran","n_ran":2,"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/foundation-transformers","slug":"foundation-transformers","title":"Foundation Transformers","date":"2022-10-12","arxiv_id":"2210.06423","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/foundation-transformers#ran","syntology_url":"https://syntology.ai/paper/2210.06423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06423"}},"official":{"repos":["microsoft/unilm"],"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/pix2struct-screenshot-parsing-as-pretraining","slug":"pix2struct-screenshot-parsing-as-pretraining","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","date":"2022-10-07","arxiv_id":"2210.03347","repositories_listed":4,"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/pix2struct-screenshot-parsing-as-pretraining#ran","syntology_url":"https://syntology.ai/paper/2210.03347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03347"}},"official":{"repos":["google-research/pix2struct"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/binding-language-models-in-symbolic-languages","slug":"binding-language-models-in-symbolic-languages","title":"Binding Language Models in Symbolic Languages","date":"2022-10-06","arxiv_id":"2210.02875","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/binding-language-models-in-symbolic-languages#ran","syntology_url":"https://syntology.ai/paper/2210.02875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02875"}},"official":{"repos":["hkunlp/binder"],"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/emb-gam-an-interpretable-and-efficient","slug":"emb-gam-an-interpretable-and-efficient","title":"Augmenting Interpretable Models with LLMs during Training","date":"2022-09-23","arxiv_id":"2209.11799","repositories_listed":4,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"8 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/emb-gam-an-interpretable-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2209.11799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.11799"}},"official":{"repos":["csinva/emb-gam","csinva/imodelsX","microsoft/augmented-interpretable-models"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-int8-8-bit-matrix-multiplication-for","slug":"llm-int8-8-bit-matrix-multiplication-for","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","date":"2022-08-15","arxiv_id":"2208.07339","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/llm-int8-8-bit-matrix-multiplication-for#ran","syntology_url":"https://syntology.ai/paper/2208.07339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07339"}},"official":{"repos":["timdettmers/bitsandbytes"],"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/protoformer-embedding-prototypes-for-1","slug":"protoformer-embedding-prototypes-for-1","title":"Protoformer: Embedding Prototypes for Transformers","date":"2022-06-25","arxiv_id":"2206.12710","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/open-vocabulary-detr-with-conditional","slug":"open-vocabulary-detr-with-conditional","title":"Open-Vocabulary DETR with Conditional Matching","date":"2022-03-22","arxiv_id":"2203.11876","repositories_listed":4,"syntology":{"n":8,"n_ran":6,"n_constructed":2,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-vocabulary-detr-with-conditional#ran","syntology_url":"https://syntology.ai/paper/2203.11876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11876"}},"official":{"repos":["yuhangzang/ov-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/memorizing-transformers-1","slug":"memorizing-transformers-1","title":"Memorizing Transformers","date":"2022-03-16","arxiv_id":"2203.08913","repositories_listed":4,"syntology":{"n":34,"n_ran":23,"n_constructed":6,"n_ran_checked":18,"n_instrument":5,"n_unverified":11,"n_honours":3,"n_violates":1,"n_no_contract":14,"n_pointer_only":2,"phrase":"23 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/memorizing-transformers-1#ran","syntology_url":"https://syntology.ai/paper/2203.08913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08913"}},"official":{"repos":["lucidrains/memorizing-transformers-pytorch"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","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":0,"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/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}},"official":{"repos":["ofa-sys/ofa"],"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/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clipcap-clip-prefix-for-image-captioning#ran","syntology_url":"https://syntology.ai/paper/2111.09734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09734"}},"official":{"repos":["rmokady/clip_prefix_caption"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/node-feature-extraction-by-self-supervised-1","slug":"node-feature-extraction-by-self-supervised-1","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","date":"2021-10-29","arxiv_id":"2111.00064","repositories_listed":4,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":15,"n_instrument":2,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/node-feature-extraction-by-self-supervised-1#ran","syntology_url":"https://syntology.ai/paper/2111.00064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00064"}},"official":{"repos":["amzn/pecos"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-empirical-survey-of-the-effectiveness-of","slug":"an-empirical-survey-of-the-effectiveness-of","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","date":"2021-10-16","arxiv_id":"2110.08527","repositories_listed":4,"syntology":null},{"url":"/paper/mluke-the-power-of-entity-representations-in","slug":"mluke-the-power-of-entity-representations-in","title":"mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08151","repositories_listed":4,"syntology":null},{"url":"/paper/primer-searching-for-efficient-transformers","slug":"primer-searching-for-efficient-transformers","title":"Primer: Searching for Efficient Transformers for Language Modeling","date":"2021-09-17","arxiv_id":"2109.08668","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":3,"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/primer-searching-for-efficient-transformers#ran","syntology_url":"https://syntology.ai/paper/2109.08668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08668"}},"official":{"repos":["google-research/google-research"],"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/vision-and-language-or-vision-for-language-on","slug":"vision-and-language-or-vision-for-language-on","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","date":"2021-09-09","arxiv_id":"2109.04448","repositories_listed":4,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/vision-and-language-or-vision-for-language-on#ran","syntology_url":"https://syntology.ai/paper/2109.04448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04448"}},"official":{"repos":["e-bug/cross-modal-ablation","e-bug/volta"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/differentiable-prompt-makes-pre-trained","slug":"differentiable-prompt-makes-pre-trained","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","date":"2021-08-30","arxiv_id":"2108.13161","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 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) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/differentiable-prompt-makes-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2108.13161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13161"}},"official":{"repos":["zjunlp/DART"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-empirical-cybersecurity-evaluation-of","slug":"an-empirical-cybersecurity-evaluation-of","title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","date":"2021-08-20","arxiv_id":"2108.09293","repositories_listed":4,"syntology":null},{"url":"/paper/w2v-bert-combining-contrastive-learning-and","slug":"w2v-bert-combining-contrastive-learning-and","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","date":"2021-08-07","arxiv_id":"2108.06209","repositories_listed":4,"syntology":null},{"url":"/paper/tapex-table-pre-training-via-learning-a","slug":"tapex-table-pre-training-via-learning-a","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","date":"2021-07-16","arxiv_id":"2107.07653","repositories_listed":4,"syntology":null},{"url":"/paper/scene-transformer-a-unified-multi-task-model","slug":"scene-transformer-a-unified-multi-task-model","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","date":"2021-06-15","arxiv_id":"2106.08417","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/scene-transformer-a-unified-multi-task-model#ran","syntology_url":"https://syntology.ai/paper/2106.08417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08417"}},"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/read-like-humans-autonomous-bidirectional-and","slug":"read-like-humans-autonomous-bidirectional-and","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","date":"2021-03-11","arxiv_id":"2103.06495","repositories_listed":4,"syntology":{"n":28,"n_ran":18,"n_constructed":11,"n_ran_checked":13,"n_instrument":5,"n_unverified":10,"n_honours":0,"n_violates":1,"n_no_contract":12,"n_pointer_only":18,"phrase":"18 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/read-like-humans-autonomous-bidirectional-and#ran","syntology_url":"https://syntology.ai/paper/2103.06495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06495"}},"official":{"repos":["FangShancheng/ABINet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/proof-artifact-co-training-for-theorem","slug":"proof-artifact-co-training-for-theorem","title":"Proof Artifact Co-training for Theorem Proving with Language Models","date":"2021-02-11","arxiv_id":"2102.06203","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/proof-artifact-co-training-for-theorem#ran","syntology_url":"https://syntology.ai/paper/2102.06203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06203"}},"official":{"repos":["jasonrute/lean-proof-recording-public","jasonrute/lean_proof_recording","jesse-michael-han/lean-step-public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/argmax-flows-and-multinomial-diffusion","slug":"argmax-flows-and-multinomial-diffusion","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","date":"2021-02-10","arxiv_id":"2102.05379","repositories_listed":4,"syntology":{"n":20,"n_ran":14,"n_constructed":1,"n_ran_checked":9,"n_instrument":5,"n_unverified":6,"n_honours":7,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"14 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 7 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/argmax-flows-and-multinomial-diffusion#ran","syntology_url":"https://syntology.ai/paper/2102.05379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05379"}},"official":{"repos":["didriknielsen/argmax_flows","ehoogeboom/multinomial_diffusion"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/controlvae-tuning-analytical-properties-and","slug":"controlvae-tuning-analytical-properties-and","title":"ControlVAE: Tuning, Analytical Properties, and Performance Analysis","date":"2020-10-31","arxiv_id":"2011.01754","repositories_listed":4,"syntology":null},{"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/infoxlm-an-information-theoretic-framework","slug":"infoxlm-an-information-theoretic-framework","title":"InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training","date":"2020-07-15","arxiv_id":"2007.07834","repositories_listed":4,"syntology":null},{"url":"/paper/slowing-down-the-weight-norm-increase-in","slug":"slowing-down-the-weight-norm-increase-in","title":"AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights","date":"2020-06-15","arxiv_id":"2006.08217","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/slowing-down-the-weight-norm-increase-in#ran","syntology_url":"https://syntology.ai/paper/2006.08217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08217"}},"official":{"repos":["clovaai/AdamP"],"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":["named_in_paper"]}}},{"url":"/paper/transformer-based-end-to-end-question","slug":"transformer-based-end-to-end-question","title":"Simplifying Paragraph-level Question Generation via Transformer Language Models","date":"2020-05-03","arxiv_id":"2005.01107","repositories_listed":4,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/transformer-based-end-to-end-question#ran","syntology_url":"https://syntology.ai/paper/2005.01107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.01107"}},"official":null}},{"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/data-augmentation-using-pre-trained","slug":"data-augmentation-using-pre-trained","title":"Data Augmentation using Pre-trained Transformer Models","date":"2020-03-04","arxiv_id":"2003.02245","repositories_listed":4,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/data-augmentation-using-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2003.02245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02245"}},"official":{"repos":["varinf/TransformersDataAugmentation"],"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/accessing-higher-level-representations-in","slug":"accessing-higher-level-representations-in","title":"Addressing Some Limitations of Transformers with Feedback Memory","date":"2020-02-21","arxiv_id":"2002.09402","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"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; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/accessing-higher-level-representations-in#ran","syntology_url":"https://syntology.ai/paper/2002.09402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09402"}},"official":{"repos":["facebookresearch/transformer-sequential"],"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/adversarial-training-for-aspect-based","slug":"adversarial-training-for-aspect-based","title":"Adversarial Training for Aspect-Based Sentiment Analysis with BERT","date":"2020-01-30","arxiv_id":"2001.11316","repositories_listed":4,"syntology":null},{"url":"/paper/recurrent-highway-networks-with-grouped","slug":"recurrent-highway-networks-with-grouped","title":"Recurrent Highway Networks with Grouped Auxiliary Memory","date":"2019-12-13","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/fast-transformer-decoding-one-write-head-is","slug":"fast-transformer-decoding-one-write-head-is","title":"Fast Transformer Decoding: One Write-Head is All You Need","date":"2019-11-06","arxiv_id":"1911.02150","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/fast-transformer-decoding-one-write-head-is#ran","syntology_url":"https://syntology.ai/paper/1911.02150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02150"}},"official":null}},{"url":"/paper/multifit-efficient-multi-lingual-language","slug":"multifit-efficient-multi-lingual-language","title":"MultiFiT: Efficient Multi-lingual Language Model Fine-tuning","date":"2019-09-10","arxiv_id":"1909.04761","repositories_listed":4,"syntology":null},{"url":"/paper/using-text-embeddings-for-causal-inference","slug":"using-text-embeddings-for-causal-inference","title":"Adapting Text Embeddings for Causal Inference","date":"2019-05-29","arxiv_id":"1905.12741","repositories_listed":4,"syntology":null},{"url":"/paper/memory-efficient-adaptive-optimization-for","slug":"memory-efficient-adaptive-optimization-for","title":"Memory-Efficient Adaptive Optimization","date":"2019-01-30","arxiv_id":"1901.11150","repositories_listed":4,"syntology":null},{"url":"/paper/learning-private-neural-language-modeling","slug":"learning-private-neural-language-modeling","title":"Learning Private Neural Language Modeling with Attentive Aggregation","date":"2018-12-17","arxiv_id":"1812.07108","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-private-neural-language-modeling#ran","syntology_url":"https://syntology.ai/paper/1812.07108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.07108"}},"official":{"repos":["shaoxiongji/fed-att"],"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":["listed","official"]}}},{"url":"/paper/fast-neural-architecture-search-of-compact","slug":"fast-neural-architecture-search-of-compact","title":"Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells","date":"2018-10-25","arxiv_id":"1810.10804","repositories_listed":4,"syntology":null},{"url":"/paper/personalized-language-model-for-query-auto","slug":"personalized-language-model-for-query-auto","title":"Personalized Language Model for Query Auto-Completion","date":"2018-04-25","arxiv_id":"1804.09661","repositories_listed":4,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/personalized-language-model-for-query-auto#ran","syntology_url":"https://syntology.ai/paper/1804.09661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09661"}},"official":{"repos":["ajaech/query_completion"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}}],"record_sha256":"60fa847dc4c8881fa6c397b42b2331e29dbe50115f5f0e5f9fcb9f0eb14459ee","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}