{"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/repackage-hidden","entry":"repackage_hidden","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":31,"n_papers_ran":17,"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":20,"n_samples_ran":6,"n_samples_fingerprinted":5,"n_places":34,"n_places_pointer_only":12,"by_status":{"ran_honours":4,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":14},"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":"2608.27035","paper":"/paper/arxiv-2608-27035","title":"Representing and Parsing Korean Constituency Structure at Different Levels of Granularity *","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"stanfordnlp/stanza","path":"stanza/models/charlm.py","file_url":"https://github.com/stanfordnlp/stanza/blob/HEAD/stanza/models/charlm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"arxiv_id":"2212.11851","paper":"/paper/storm-a-diffusion-based-stochastic","title":"StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation","date":"2022-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sp-uhh/storm","path":"sgmse/backbones/convtasnet.py","file_url":"https://github.com/sp-uhh/storm/blob/HEAD/sgmse/backbones/convtasnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3957da6e7bfb4ed6","mcp_get_code":{"code_sha256":"3957da6e7bfb4ed6"}},{"arxiv_id":"2212.11851","paper":"/paper/storm-a-diffusion-based-stochastic","title":"StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation","date":"2022-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sp-uhh/storm","path":"sgmse/backbones/convtasnet_utils/utils.py","file_url":"https://github.com/sp-uhh/storm/blob/HEAD/sgmse/backbones/convtasnet_utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa549fcbd479aad5","mcp_get_code":{"code_sha256":"fa549fcbd479aad5"}},{"arxiv_id":"2210.11222","paper":"/paper/private-algorithms-with-private-predictions","title":"Learning-Augmented Private Algorithms for Multiple Quantile Release","date":"2022-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anandsaha/nips.cocob.pytorch","path":"word_language_model/main.orig.py","file_url":"https://github.com/anandsaha/nips.cocob.pytorch/blob/HEAD/word_language_model/main.orig.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d98e69125467f2f0","mcp_get_code":{"code_sha256":"d98e69125467f2f0"}},{"arxiv_id":"2208.05924","paper":"/paper/regularizing-deep-neural-networks-with-1","title":"Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace","date":"2022-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"a81c5fb0b9535995","mcp_get_code":{"code_sha256":"a81c5fb0b9535995"}},{"arxiv_id":"2205.05040","paper":"/paper/a-communication-efficient-distributed-3","title":"A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks","date":"2022-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingruiliu-ml-lab/communication-efficient-local-gradient-clipping","path":"nlp/main_lstm.py","file_url":"https://github.com/mingruiliu-ml-lab/communication-efficient-local-gradient-clipping/blob/HEAD/nlp/main_lstm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"arxiv_id":"2201.07281","paper":"/paper/annotating-the-tweebank-corpus-on-named","title":"Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis","date":"2022-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"social-machines/tweebanknlp","path":"twitter-stanza/stanza/models/charlm.py","file_url":"https://github.com/social-machines/tweebanknlp/blob/HEAD/twitter-stanza/stanza/models/charlm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"arxiv_id":"2105.13937","paper":"/paper/polygonal-unadjusted-langevin-algorithms","title":"Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fin-young/THEO_POULA","path":"train_lstm.py","file_url":"https://github.com/fin-young/THEO_POULA/blob/HEAD/train_lstm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d007cafd2da71575","mcp_get_code":{"code_sha256":"d007cafd2da71575"}},{"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":"utils.py","file_url":"https://github.com/salesforce/awd-lstm-lm/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"arxiv_id":"2010.02519","paper":"/paper/improved-analysis-of-clipping-algorithms-for","title":"Improved Analysis of Clipping Algorithms for Non-convex Optimization","date":"2020-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zbh2047/clipping-algorithms","path":"main_lstm.py","file_url":"https://github.com/zbh2047/clipping-algorithms/blob/HEAD/main_lstm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ec9329606c156d1d","mcp_get_code":{"code_sha256":"ec9329606c156d1d"}},{"arxiv_id":"2010.00763","paper":"/paper/bongard-logo-a-new-benchmark-for-human-level","title":"Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning","date":"2020-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/Bongard-LOGO","path":"Bongard-LOGO_Baselines/models/recurrent_model.py","file_url":"https://github.com/NVlabs/Bongard-LOGO/blob/HEAD/Bongard-LOGO_Baselines/models/recurrent_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6aaf07ccda31ac5f","mcp_get_code":{"code_sha256":"6aaf07ccda31ac5f"}},{"arxiv_id":"2006.16981","paper":"/paper/learning-to-combine-top-down-and-bottom-up","title":"Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules","date":"2020-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sarthmit/BRIMs","path":"CIFAR10/train_cifar.py","file_url":"https://github.com/sarthmit/BRIMs/blob/HEAD/CIFAR10/train_cifar.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e50bd9c4161128d","mcp_get_code":{"code_sha256":"9e50bd9c4161128d"}},{"arxiv_id":"2006.16981","paper":"/paper/learning-to-combine-top-down-and-bottom-up","title":"Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules","date":"2020-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sarthmit/BRIMs","path":"MNIST/train_mnist.py","file_url":"https://github.com/sarthmit/BRIMs/blob/HEAD/MNIST/train_mnist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ed7de278461e386","mcp_get_code":{"code_sha256":"0ed7de278461e386"}},{"arxiv_id":"2003.04179","paper":"/paper/capacity-of-continuous-channels-with-memory","title":"Capacity of Continuous Channels with Memory via Directed Information Neural Estimator","date":"2020-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"omerlux/DINE","path":"dine/utils.py","file_url":"https://github.com/omerlux/DINE/blob/HEAD/dine/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d4b3cad9501696da","mcp_get_code":{"code_sha256":"d4b3cad9501696da"}},{"arxiv_id":"2001.00705","paper":"/paper/fractional-skipping-towards-finer-grained","title":"Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference","date":"2020-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Torment123/DFS","path":"models.py","file_url":"https://github.com/Torment123/DFS/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6f41456f1266f92","mcp_get_code":{"code_sha256":"b6f41456f1266f92"}},{"arxiv_id":"1910.13466","paper":"/paper/ordered-memory","title":"Ordered Memory","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yikangshen/Ordered-Memory","path":"utils/utils.py","file_url":"https://github.com/yikangshen/Ordered-Memory/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eee10a1cbab04d32","mcp_get_code":{"code_sha256":"eee10a1cbab04d32"}},{"arxiv_id":"1910.05923","paper":"/paper/code-generation-as-a-dual-task-of-code","title":"Code Generation as a Dual Task of Code Summarization","date":"2019-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"code-gen/cgcs","path":"language_model/lm_train.py","file_url":"https://github.com/code-gen/cgcs/blob/HEAD/language_model/lm_train.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6aaf07ccda31ac5f","mcp_get_code":{"code_sha256":"6aaf07ccda31ac5f"}},{"arxiv_id":"1909.10893","paper":"/paper/recurrent-independent-mechanisms","title":"Recurrent Independent Mechanisms","date":"2019-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anirudh9119/RIMs","path":"event_based/train_copying.py","file_url":"https://github.com/anirudh9119/RIMs/blob/HEAD/event_based/train_copying.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a81c5fb0b9535995","mcp_get_code":{"code_sha256":"a81c5fb0b9535995"}},{"arxiv_id":"1909.10893","paper":"/paper/recurrent-independent-mechanisms","title":"Recurrent Independent Mechanisms","date":"2019-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anirudh9119/RIMs","path":"event_based/train_adding.py","file_url":"https://github.com/anirudh9119/RIMs/blob/HEAD/event_based/train_adding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"70d200be038af543","mcp_get_code":{"code_sha256":"70d200be038af543"}},{"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":"utils.py","file_url":"https://github.com/JingzhaoZhang/why-clipping-accelerates/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"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":"utils.py","file_url":"https://github.com/IanTheColder/ONLSTM-analysis/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"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/word_PTB/utils.py","file_url":"https://github.com/locuslab/trellisnet/blob/HEAD/TrellisNet/word_PTB/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"arxiv_id":"1808.09357","paper":"/paper/rational-recurrences","title":"Rational Recurrences","date":"2018-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Noahs-ARK/rational-recurrences","path":"language_model/train_lm.py","file_url":"https://github.com/Noahs-ARK/rational-recurrences/blob/HEAD/language_model/train_lm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25b388c0d2d1ecab","mcp_get_code":{"code_sha256":"25b388c0d2d1ecab"}},{"arxiv_id":"1808.09029","paper":"/paper/pyramidal-recurrent-unit-for-language","title":"Pyramidal Recurrent Unit for Language Modeling","date":"2018-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sacmehta/PRU","path":"utils.py","file_url":"https://github.com/sacmehta/PRU/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d98e69125467f2f0","mcp_get_code":{"code_sha256":"d98e69125467f2f0"}},{"arxiv_id":"1806.01822","paper":"/paper/relational-recurrent-neural-networks","title":"Relational recurrent neural networks","date":"2018-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"L0SG/relational-rnn-pytorch","path":"train_rnn.py","file_url":"https://github.com/L0SG/relational-rnn-pytorch/blob/HEAD/train_rnn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a81c5fb0b9535995","mcp_get_code":{"code_sha256":"a81c5fb0b9535995"}},{"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":"utils.py","file_url":"https://github.com/urvashik/lm-context-analysis/blob/HEAD/utils.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":"d98e69125467f2f0","mcp_get_code":{"code_sha256":"d98e69125467f2f0"}},{"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":"utils.py","file_url":"https://github.com/sjmielke/spell-once/blob/HEAD/utils.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":"626ebcbda1b6e336","mcp_get_code":{"code_sha256":"626ebcbda1b6e336"}},{"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":"SachinIchake/KALM","path":"utils.py","file_url":"https://github.com/SachinIchake/KALM/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"4372bb4533fd1936","mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"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":"dynamiceval.py","file_url":"https://github.com/zihangdai/mos/blob/HEAD/dynamiceval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8bd3cf7e6979e441","mcp_get_code":{"code_sha256":"8bd3cf7e6979e441"}},{"arxiv_id":"1711.02013","paper":"/paper/neural-language-modeling-by-jointly-learning","title":"Neural Language Modeling by Jointly Learning Syntax and Lexicon","date":"2017-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-mll/PRPN-Analysis","path":"main_LM.py","file_url":"https://github.com/nyu-mll/PRPN-Analysis/blob/HEAD/main_LM.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8bad1a018e52e629","mcp_get_code":{"code_sha256":"8bad1a018e52e629"}},{"arxiv_id":"1710.02224","paper":"/paper/dilated-recurrent-neural-networks","title":"Dilated Recurrent Neural Networks","date":"2017-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zalandoresearch/pytorch-dilated-rnn","path":"lm.py","file_url":"https://github.com/zalandoresearch/pytorch-dilated-rnn/blob/HEAD/lm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5b50d8b3f7aa6aa7","mcp_get_code":{"code_sha256":"5b50d8b3f7aa6aa7"}},{"arxiv_id":"1709.07432","paper":"/paper/dynamic-evaluation-of-neural-sequence-models","title":"Dynamic Evaluation of Neural Sequence Models","date":"2017-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benkrause/dynamic-evaluation","path":"dynamiceval.py","file_url":"https://github.com/benkrause/dynamic-evaluation/blob/HEAD/dynamiceval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"d98e69125467f2f0","mcp_get_code":{"code_sha256":"d98e69125467f2f0"}},{"arxiv_id":"1704.05119","paper":"/paper/exploring-sparsity-in-recurrent-neural","title":"Exploring Sparsity in Recurrent Neural Networks","date":"2017-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"puhsu/pruning","path":"model.py","file_url":"https://github.com/puhsu/pruning/blob/HEAD/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6aaf07ccda31ac5f","mcp_get_code":{"code_sha256":"6aaf07ccda31ac5f"}},{"arxiv_id":"1609.04309","paper":"/paper/efficient-softmax-approximation-for-gpus","title":"Efficient softmax approximation for GPUs","date":"2016-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rosinality/adaptive-softmax-pytorch","path":"text8.py","file_url":"https://github.com/rosinality/adaptive-softmax-pytorch/blob/HEAD/text8.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16460bb9b7b5d0a1","mcp_get_code":{"code_sha256":"16460bb9b7b5d0a1"}}]}