{"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/get-attn-key-pad-mask","entry":"get_attn_key_pad_mask","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":7,"n_papers_ran":4,"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":10,"n_samples_ran":7,"n_samples_fingerprinted":7,"n_places":12,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":6,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":3},"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":"2112.09174","paper":"/paper/learning-bounded-context-free-grammar-via","title":"Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations","date":"2021-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shihui2010/learn_cfg_with_neural_network","path":"models/transformer.py","file_url":"https://github.com/shihui2010/learn_cfg_with_neural_network/blob/HEAD/models/transformer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3a9b19c6089233c","mcp_get_code":{"code_sha256":"d3a9b19c6089233c"}},{"arxiv_id":"2006.09623","paper":"/paper/learning-visual-commonsense-for-robust-scene","title":"Learning Visual Commonsense for Robust Scene Graph Generation","date":"2020-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhecanJamesWang/GLAT_SGG","path":"lib/models_kern.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/models_kern.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f18f207a73aa64a","mcp_get_code":{"code_sha256":"6f18f207a73aa64a"}},{"arxiv_id":"1911.02613","paper":"/paper/hyper-sagnn-a-self-attention-based-graph-1","title":"Hyper-SAGNN: a self-attention based graph neural network for hypergraphs","date":"2019-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ma-compbio/Hyper-SAGNN","path":"Code/Modules.py","file_url":"https://github.com/ma-compbio/Hyper-SAGNN/blob/HEAD/Code/Modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0ba079bc599626f","mcp_get_code":{"code_sha256":"e0ba079bc599626f"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emanuele-progr/PSSP","path":"transformer.py","file_url":"https://github.com/emanuele-progr/PSSP/blob/HEAD/transformer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aebd1d5fbde8ed54","mcp_get_code":{"code_sha256":"aebd1d5fbde8ed54"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yueyongjiao/Transformer-Contextual","path":"transformer/Models.py","file_url":"https://github.com/yueyongjiao/Transformer-Contextual/blob/HEAD/transformer/Models.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f04747d4c95cdf6b","mcp_get_code":{"code_sha256":"f04747d4c95cdf6b"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"text-machine-lab/transformerpy","path":"transformer/Models.py","file_url":"https://github.com/text-machine-lab/transformerpy/blob/HEAD/transformer/Models.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2ca24065f182e91c","mcp_get_code":{"code_sha256":"2ca24065f182e91c"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MohamedAbdelsalam9/TT-Transformer","path":"transformer/Models.py","file_url":"https://github.com/MohamedAbdelsalam9/TT-Transformer/blob/HEAD/transformer/Models.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8558e623afb00642","mcp_get_code":{"code_sha256":"8558e623afb00642"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Fuchai/language","path":"deeplearning/modeltran.py","file_url":"https://github.com/Fuchai/language/blob/HEAD/deeplearning/modeltran.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0ba079bc599626f","mcp_get_code":{"code_sha256":"e0ba079bc599626f"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Matthewdowney18/Transformer_Dialogue","path":"src/transformer/Models.py","file_url":"https://github.com/Matthewdowney18/Transformer_Dialogue/blob/HEAD/src/transformer/Models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"79e1b19ea0f880a3","mcp_get_code":{"code_sha256":"79e1b19ea0f880a3"}},{"arxiv_id":"1603.08983","paper":"/paper/adaptive-computation-time-for-recurrent","title":"Adaptive Computation Time for Recurrent Neural Networks","date":"2016-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andreamad8/Universal-Transformer-Pytorch","path":"models/UTransformer.py","file_url":"https://github.com/andreamad8/Universal-Transformer-Pytorch/blob/HEAD/models/UTransformer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"095dea140acd99f6","mcp_get_code":{"code_sha256":"095dea140acd99f6"}},{"arxiv_id":"2023.findings-emnlp.672","paper":null,"title":"arXiv:2023.findings-emnlp.672","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guihuzhang/FactSpotter","path":"g2t_gen_code/code/modeling_kgpt.py","file_url":"https://github.com/guihuzhang/FactSpotter/blob/HEAD/g2t_gen_code/code/modeling_kgpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"01d7142796d717bd","mcp_get_code":{"code_sha256":"01d7142796d717bd"}},{"arxiv_id":"2020.emnlp-main.697","paper":null,"title":"arXiv:2020.emnlp-main.697","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wenhuchen/KGPT","path":"code/Model.py","file_url":"https://github.com/wenhuchen/KGPT/blob/HEAD/code/Model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"01d7142796d717bd","mcp_get_code":{"code_sha256":"01d7142796d717bd"}}]}