{"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/tokenize-dataset","entry":"tokenize_dataset","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":6,"n_papers_ran":3,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2607.19450","paper":"/paper/arxiv-2607-19450","title":"REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"yunjie-sysu/REGEN","path":"regen_train.py","file_url":"https://github.com/yunjie-sysu/REGEN/blob/HEAD/regen_train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9bfd42700dff8e8f","mcp_get_code":{"code_sha256":"9bfd42700dff8e8f"}},{"arxiv_id":"2409.01193","paper":"/paper/clibe-detecting-dynamic-backdoors-in","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raytsang123/clibe","path":"discriminative_backdoors/detection/corpus.py","file_url":"https://github.com/raytsang123/clibe/blob/HEAD/discriminative_backdoors/detection/corpus.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":"db25d29cbbbb61ca","mcp_get_code":{"code_sha256":"db25d29cbbbb61ca"}},{"arxiv_id":"2407.07890","paper":"/paper/training-on-the-test-task-confounds","title":"Training on the Test Task Confounds Evaluation and Emergence","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"socialfoundations/training-on-the-test-task","path":"experiments/data_utils.py","file_url":"https://github.com/socialfoundations/training-on-the-test-task/blob/HEAD/experiments/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f067ba5db73dc40a","mcp_get_code":{"code_sha256":"f067ba5db73dc40a"}},{"arxiv_id":"2311.00144","paper":"/paper/backdoor-threats-from-compromised-foundation","title":"Backdoor Threats from Compromised Foundation Models to Federated Learning","date":null,"month_inferred_from_arxiv_id":"2023-11","title_source":"archive","repo":"lixi1994/backdoor_fm_fl","path":"utils.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c6b24333a4021f6","mcp_get_code":{"code_sha256":"9c6b24333a4021f6"}},{"arxiv_id":"1409.3215","paper":"/paper/sequence-to-sequence-learning-with-neural","title":"Sequence to Sequence Learning with Neural Networks","date":"2014-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"la-serene/English-German-Translation-System","path":"prepare_data.py","file_url":"https://github.com/la-serene/English-German-Translation-System/blob/HEAD/prepare_data.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":"2be8d8a248dd1ac5","mcp_get_code":{"code_sha256":"2be8d8a248dd1ac5"}},{"arxiv_id":"2022.emnlp-industry.44","paper":null,"title":"arXiv:2022.emnlp-industry.44","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"VectorInstitute/NAA","path":"responsegeneration/DataLoader/dataset_utils.py","file_url":"https://github.com/VectorInstitute/NAA/blob/HEAD/responsegeneration/DataLoader/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":"17d4868e5ac260c7","mcp_get_code":{"code_sha256":"17d4868e5ac260c7"}}]}