{"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/load-vocabulary","entry":"load_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":5,"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":4,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":4},"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":"2609.03231","paper":"/paper/arxiv-2609-03231","title":"The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"neural-processing-lab/pnpl","path":"pnpl/competition/submission.py","file_url":"https://github.com/neural-processing-lab/pnpl/blob/HEAD/pnpl/competition/submission.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":"5a55c7cc4b984e7e","mcp_get_code":{"code_sha256":"5a55c7cc4b984e7e"}},{"arxiv_id":"2507.11818","paper":null,"title":"arXiv:2507.11818","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"andreirekesh/SynCoGen","path":"syncogen/constants/constants.py","file_url":"https://github.com/andreirekesh/SynCoGen/blob/HEAD/syncogen/constants/constants.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fbb30ba0a71b28f7","mcp_get_code":{"code_sha256":"fbb30ba0a71b28f7"}},{"arxiv_id":"2301.03416","paper":"/paper/ernie-3-0-tiny-frustratingly-simple-method-to","title":"ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization","date":"2023-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PaddlePaddle/PaddleNLP","path":"paddlenlp/experimental/model_utils.py","file_url":"https://github.com/PaddlePaddle/PaddleNLP/blob/HEAD/paddlenlp/experimental/model_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":"7667c4274e1b357d","mcp_get_code":{"code_sha256":"7667c4274e1b357d"}},{"arxiv_id":"2105.13626","paper":"/paper/byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yoreG123/Paddle-ByT5","path":"byt5/paddlenlp/experimental/model_utils.py","file_url":"https://github.com/yoreG123/Paddle-ByT5/blob/HEAD/byt5/paddlenlp/experimental/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7667c4274e1b357d","mcp_get_code":{"code_sha256":"7667c4274e1b357d"}},{"arxiv_id":"1805.06504","paper":"/paper/analogical-reasoning-on-chinese-morphological","title":"Analogical Reasoning on Chinese Morphological and Semantic Relations","date":"2018-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Embedding/Chinese-Word-Vectors","path":"evaluation/ana_eval_sparse.py","file_url":"https://github.com/Embedding/Chinese-Word-Vectors/blob/HEAD/evaluation/ana_eval_sparse.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":"0a442e6264a7c404","mcp_get_code":{"code_sha256":"0a442e6264a7c404"}}]}