{"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/create-tokenizer","entry":"create_tokenizer","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":8,"n_papers_ran":2,"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":8,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":6},"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":"2506.12687","paper":null,"title":"arXiv:2506.12687","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"Yuzt-zju/CoCorrRec","path":"module/config.py","file_url":"https://github.com/Yuzt-zju/CoCorrRec/blob/HEAD/module/config.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":"1cc6752574c0d00f","mcp_get_code":{"code_sha256":"1cc6752574c0d00f"}},{"arxiv_id":"2310.17230","paper":"/paper/codebook-features-sparse-and-discrete","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taufeeque9/codebook-features","path":"codebook_features/train_fsm_model.py","file_url":"https://github.com/taufeeque9/codebook-features/blob/HEAD/codebook_features/train_fsm_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7a3a433b5807b51","mcp_get_code":{"code_sha256":"e7a3a433b5807b51"}},{"arxiv_id":"2310.15047","paper":"/paper/meta-out-of-context-learning-in-neural","title":"Implicit meta-learning may lead language models to trust more reliable sources","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krasheninnikov/internalization","path":"src/lm_training_utils.py","file_url":"https://github.com/krasheninnikov/internalization/blob/HEAD/src/lm_training_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7441b30297b1a30","mcp_get_code":{"code_sha256":"a7441b30297b1a30"}},{"arxiv_id":"2307.14743","paper":"/paper/turning-whisper-into-real-time-transcription","title":"Turning Whisper into Real-Time Transcription System","date":"2023-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ufal/whisper_streaming","path":"whisper_online.py","file_url":"https://github.com/ufal/whisper_streaming/blob/HEAD/whisper_online.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a85d88eab9f432fd","mcp_get_code":{"code_sha256":"a85d88eab9f432fd"}},{"arxiv_id":"2305.07759","paper":"/paper/tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"danbraunai/simple_stories_train","path":"simple_stories_train/tokenizer.py","file_url":"https://github.com/danbraunai/simple_stories_train/blob/HEAD/simple_stories_train/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea33e0525958ca7b","mcp_get_code":{"code_sha256":"ea33e0525958ca7b"}},{"arxiv_id":"2205.09357","paper":"/paper/continual-pre-training-mitigates-forgetting","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","date":"2022-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andreacossu/continual-pretraining-nlp-vision","path":"utils.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/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":"219b7aaf978adc4f","mcp_get_code":{"code_sha256":"219b7aaf978adc4f"}},{"arxiv_id":"1904.04792","paper":"/paper/quizbowl-the-case-for-incremental-question","title":"Quizbowl: The Case for Incremental Question Answering","date":"2019-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"h-j-han/automatic_explicitation","path":"autoexpl/tokenizer.py","file_url":"https://github.com/h-j-han/automatic_explicitation/blob/HEAD/autoexpl/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a3254eef985754fe","mcp_get_code":{"code_sha256":"a3254eef985754fe"}},{"arxiv_id":"1409.0473","paper":"/paper/neural-machine-translation-by-jointly","title":"Neural Machine Translation by Jointly Learning to Align and Translate","date":"2014-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prakhargurawa/Neural-Machine-Translation-Keras-German-English","path":"translation_neural_network_model.py","file_url":"https://github.com/prakhargurawa/Neural-Machine-Translation-Keras-German-English/blob/HEAD/translation_neural_network_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad4e30338e48aa2c","mcp_get_code":{"code_sha256":"ad4e30338e48aa2c"}}]}