{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/embedded-dropout","entry":"embedded_dropout","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":16,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":9,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":18,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":9},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2602.03024","paper":"/paper/arxiv-2602-03024","title":"Consistency Deep Equilibrium Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"landrarwolf/CDEQ","path":"CDEQ-src/lib/optimizations.py","file_url":"https://github.com/landrarwolf/CDEQ/blob/HEAD/CDEQ-src/lib/optimizations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df1c4e8a21c5f2ef","mcp_get_code":{"code_sha256":"df1c4e8a21c5f2ef"}},{"arxiv_id":"2411.00899","paper":"/paper/certified-robustness-for-deep-equilibrium-1","title":"Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeizhiGao/Serialized-Randomized-Smoothing","path":"DEQ/lib/optimizations.py","file_url":"https://github.com/WeizhiGao/Serialized-Randomized-Smoothing/blob/HEAD/DEQ/lib/optimizations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df1c4e8a21c5f2ef","mcp_get_code":{"code_sha256":"df1c4e8a21c5f2ef"}},{"arxiv_id":"2311.01766","paper":"/paper/support-or-refute-analyzing-the-stance-of","title":"Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation","date":"2023-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yx3266/SEN","path":"training_and_evaluation/sent_emb/model.py","file_url":"https://github.com/yx3266/SEN/blob/HEAD/training_and_evaluation/sent_emb/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62d148258bdd054f","mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"arxiv_id":"2203.10256","paper":"/paper/dependency-based-mixture-language-models","title":"Dependency-based Mixture Language Models","date":"2022-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fadedcosine/dependency-guided-neural-text-generation","path":"DPLM-LSTM/embed_regularize.py","file_url":"https://github.com/fadedcosine/dependency-guided-neural-text-generation/blob/HEAD/DPLM-LSTM/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"62d148258bdd054f","mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"arxiv_id":"2010.02986","paper":"/paper/compositional-demographic-word-embeddings","title":"Compositional Demographic Word Embeddings","date":"2020-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/awd-lstm-lm","path":"embed_regularize.py","file_url":"https://github.com/salesforce/awd-lstm-lm/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"62d148258bdd054f","mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"arxiv_id":"2006.07116","paper":"/paper/nas-bench-nlp-neural-architecture-search","title":"NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing","date":"2020-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fmsnew/nas-bench-nlp-release","path":"embed_regularize.py","file_url":"https://github.com/fmsnew/nas-bench-nlp-release/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"62d148258bdd054f","mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"arxiv_id":"1905.11881","paper":"/paper/analysis-of-gradient-clipping-and-adaptive","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","date":"2019-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JingzhaoZhang/why-clipping-accelerates","path":"embed_regularize.py","file_url":"https://github.com/JingzhaoZhang/why-clipping-accelerates/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"62d148258bdd054f","mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"arxiv_id":"1810.10999","paper":"/paper/reversible-recurrent-neural-networks","title":"Reversible Recurrent Neural Networks","date":"2018-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matthewjmackay/reversible-rnn","path":"language_modelling/embed_regularize.py","file_url":"https://github.com/matthewjmackay/reversible-rnn/blob/HEAD/language_modelling/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4ed5e00e94ee3740","mcp_get_code":{"code_sha256":"4ed5e00e94ee3740"}},{"arxiv_id":"1810.09536","paper":"/paper/ordered-neurons-integrating-tree-structures","title":"Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks","date":"2018-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IanTheColder/ONLSTM-analysis","path":"embed_regularize.py","file_url":"https://github.com/IanTheColder/ONLSTM-analysis/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"62d148258bdd054f","mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"arxiv_id":"1810.06682","paper":"/paper/trellis-networks-for-sequence-modeling","title":"Trellis Networks for Sequence Modeling","date":"2018-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"locuslab/trellisnet","path":"TrellisNet/optimizations.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/optimizations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad3308380ac371b2","mcp_get_code":{"code_sha256":"ad3308380ac371b2"}},{"arxiv_id":"1805.04836","paper":"/paper/building-language-models-for-text-with-named","title":"Building Language Models for Text with Named Entities","date":"2018-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uclanlp/NamedEntityLanguageModel","path":"embed_regularize.py","file_url":"https://github.com/uclanlp/NamedEntityLanguageModel/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"3c2fe307e011be7d","mcp_get_code":{"code_sha256":"3c2fe307e011be7d"}},{"arxiv_id":"1805.04623","paper":"/paper/sharp-nearby-fuzzy-far-away-how-neural","title":"Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context","date":"2018-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"urvashik/lm-context-analysis","path":"embed_regularize.py","file_url":"https://github.com/urvashik/lm-context-analysis/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3c2fe307e011be7d","mcp_get_code":{"code_sha256":"3c2fe307e011be7d"}},{"arxiv_id":"1804.08205","paper":"/paper/spell-once-summon-anywhere-a-two-level-open","title":"Spell Once, Summon Anywhere: A Two-Level Open-Vocabulary Language Model","date":"2018-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjmielke/spell-once","path":"embed_regularize.py","file_url":"https://github.com/sjmielke/spell-once/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"85281b50c86cffc8","mcp_get_code":{"code_sha256":"85281b50c86cffc8"}},{"arxiv_id":"1803.08240","paper":"/paper/an-analysis-of-neural-language-modeling-at","title":"An Analysis of Neural Language Modeling at Multiple Scales","date":"2018-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AtheMathmo/lookahead-lstm","path":"embed_regularize.py","file_url":"https://github.com/AtheMathmo/lookahead-lstm/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"62d148258bdd054f","mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"arxiv_id":"1711.03953","paper":"/paper/breaking-the-softmax-bottleneck-a-high-rank","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","date":"2017-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yfreedomliTHU/mos-pytorch1.1","path":"embed_regularize.py","file_url":"https://github.com/yfreedomliTHU/mos-pytorch1.1/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61247fd8db2741cf","mcp_get_code":{"code_sha256":"61247fd8db2741cf"}},{"arxiv_id":"1711.03953","paper":"/paper/breaking-the-softmax-bottleneck-a-high-rank","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","date":"2017-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zihangdai/mos","path":"embed_regularize.py","file_url":"https://github.com/zihangdai/mos/blob/HEAD/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"612788fb8fc53b62","mcp_get_code":{"code_sha256":"612788fb8fc53b62"}},{"arxiv_id":"1711.03953","paper":"/paper/breaking-the-softmax-bottleneck-a-high-rank","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","date":"2017-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nkcr/overlap-ml","path":"awd/embed_regularize.py","file_url":"https://github.com/nkcr/overlap-ml/blob/HEAD/awd/embed_regularize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"6a3d8df0b754bb01","mcp_get_code":{"code_sha256":"6a3d8df0b754bb01"}},{"arxiv_id":"2025.naacl-long.61","paper":null,"title":"arXiv:2025.naacl-long.61","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"vonfeng/DPLink","path":"codes/models.py","file_url":"https://github.com/vonfeng/DPLink/blob/HEAD/codes/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61247fd8db2741cf","mcp_get_code":{"code_sha256":"61247fd8db2741cf"}}]}