{"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-vocabulary","entry":"get_vocabulary","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":11,"n_papers_ran":7,"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":12,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":4,"unverified":5},"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":"2603.24150","paper":"/paper/arxiv-2603-24150","title":"A visual observation on the geometry of UMAP projections of the difference vectors of antonym and synonym word pair embeddings","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ramiluisto/CuriousSwirl","path":"semsim/data.py","file_url":"https://github.com/ramiluisto/CuriousSwirl/blob/HEAD/semsim/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f60cc27077f1980b","mcp_get_code":{"code_sha256":"f60cc27077f1980b"}},{"arxiv_id":"2405.04346","paper":"/paper/revisiting-character-level-adversarial","title":"Revisiting Character-level Adversarial Attacks for Language Models","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LIONS-EPFL/Charmer","path":"utils.py","file_url":"https://github.com/LIONS-EPFL/Charmer/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"593614c84d8b37c2","mcp_get_code":{"code_sha256":"593614c84d8b37c2"}},{"arxiv_id":"2402.10376","paper":"/paper/interpreting-clip-with-sparse-linear-concept","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI4LIFE-GROUP/SpLiCE","path":"splice/splice.py","file_url":"https://github.com/AI4LIFE-GROUP/SpLiCE/blob/HEAD/splice/splice.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"75d0d4017fcd11fd","mcp_get_code":{"code_sha256":"75d0d4017fcd11fd"}},{"arxiv_id":"2301.02195","paper":"/paper/towards-autoformalization-of-mathematics-and","title":"Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs","date":"2023-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gc974517/autoformalization","path":"src/load.py","file_url":"https://github.com/gc974517/autoformalization/blob/HEAD/src/load.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":"a4fbab6684b34cac","mcp_get_code":{"code_sha256":"a4fbab6684b34cac"}},{"arxiv_id":"2206.12088","paper":"/paper/classifying-unstructured-clinical-notes-via","title":"Classifying Unstructured Clinical Notes via Automatic Weak Supervision","date":"2022-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"autonlab/KeyClass","path":"keyclass/create_lfs.py","file_url":"https://github.com/autonlab/KeyClass/blob/HEAD/keyclass/create_lfs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e3d4b993b102216","mcp_get_code":{"code_sha256":"5e3d4b993b102216"}},{"arxiv_id":"2203.01976","paper":"/paper/overlap-based-vocabulary-generation-improves","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","date":"2022-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Vaidehi99/OBPE","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8ebaf21ef830e017","mcp_get_code":{"code_sha256":"8ebaf21ef830e017"}},{"arxiv_id":"1910.13267","paper":"/paper/191013267","title":"BPE-Dropout: Simple and Effective Subword Regularization","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rsennrich/subword-nmt","path":"subword_nmt/learn_bpe.py","file_url":"https://github.com/rsennrich/subword-nmt/blob/HEAD/subword_nmt/learn_bpe.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b83d785ca99bfc9f","mcp_get_code":{"code_sha256":"b83d785ca99bfc9f"}},{"arxiv_id":"1910.13267","paper":"/paper/191013267","title":"BPE-Dropout: Simple and Effective Subword Regularization","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mozilla/subword-nmt","path":"subword_nmt/learn_bpe.py","file_url":"https://github.com/mozilla/subword-nmt/blob/HEAD/subword_nmt/learn_bpe.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc7574327ea1f634","mcp_get_code":{"code_sha256":"bc7574327ea1f634"}},{"arxiv_id":"1910.13267","paper":"/paper/191013267","title":"BPE-Dropout: Simple and Effective Subword Regularization","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PatxiofromAlphensign/subword-nmt-mods","path":"subword_nmt/learn_bpe.py","file_url":"https://github.com/PatxiofromAlphensign/subword-nmt-mods/blob/HEAD/subword_nmt/learn_bpe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d923800aaefd70c","mcp_get_code":{"code_sha256":"7d923800aaefd70c"}},{"arxiv_id":"1910.02562","paper":"/paper/master-multi-aspect-non-local-network-for","title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","date":"2019-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiangxiluning/MASTER-TF","path":"src/dataset/utils.py","file_url":"https://github.com/jiangxiluning/MASTER-TF/blob/HEAD/src/dataset/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7852c913c2d2af2","mcp_get_code":{"code_sha256":"a7852c913c2d2af2"}},{"arxiv_id":"1909.00502","paper":"/paper/an-empirical-study-of-incorporating-pseudo","title":"An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction","date":"2019-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"butsugiri/gec-pseudodata","path":"generate_pseudo_samples.py","file_url":"https://github.com/butsugiri/gec-pseudodata/blob/HEAD/generate_pseudo_samples.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8644011efb17c983","mcp_get_code":{"code_sha256":"8644011efb17c983"}},{"arxiv_id":"1710.11041","paper":"/paper/unsupervised-neural-machine-translation","title":"Unsupervised Neural Machine Translation","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"b83d785ca99bfc9f","mcp_get_code":{"code_sha256":"b83d785ca99bfc9f"}},{"arxiv_id":"1508.07909","paper":"/paper/neural-machine-translation-of-rare-words-with","title":"Neural Machine Translation of Rare Words with Subword Units","date":"2015-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"b83d785ca99bfc9f","mcp_get_code":{"code_sha256":"b83d785ca99bfc9f"}},{"arxiv_id":"1508.07909","paper":"/paper/neural-machine-translation-of-rare-words-with","title":"Neural Machine Translation of Rare Words with Subword Units","date":"2015-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kh-mo/QA_wikisql","path":"learn_bpe.py","file_url":"https://github.com/kh-mo/QA_wikisql/blob/HEAD/learn_bpe.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":"9425aef3e44f6979","mcp_get_code":{"code_sha256":"9425aef3e44f6979"}},{"arxiv_id":"1508.07909","paper":"/paper/neural-machine-translation-of-rare-words-with","title":"Neural Machine Translation of Rare Words with Subword Units","date":"2015-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thinkwee/DPP_CNN_Summarization","path":"fairseq/raw_dataset/subword_nmt/learn_bpe.py","file_url":"https://github.com/thinkwee/DPP_CNN_Summarization/blob/HEAD/fairseq/raw_dataset/subword_nmt/learn_bpe.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc7574327ea1f634","mcp_get_code":{"code_sha256":"bc7574327ea1f634"}}]}