{"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-words","entry":"tokenize_words","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":1,"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":1,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2603.22075","paper":"/paper/arxiv-2603-22075","title":"Autoregressive vs. Masked Diffusion Language Models: A Controlled Comparison","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"caiovicentino/arche","path":"eval_diversity.py","file_url":"https://github.com/caiovicentino/arche/blob/HEAD/eval_diversity.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"059f792a8b4f7d6e","mcp_get_code":{"code_sha256":"059f792a8b4f7d6e"}},{"arxiv_id":"2408.04259","paper":"/paper/efficientrag-efficient-retriever-for-multi","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nil-zhuang/efficientrag-official","path":"src/efficientrag_retrieve.py","file_url":"https://github.com/nil-zhuang/efficientrag-official/blob/HEAD/src/efficientrag_retrieve.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2701b7e8a6ec84fe","mcp_get_code":{"code_sha256":"2701b7e8a6ec84fe"}},{"arxiv_id":"2310.01188","paper":"/paper/quantifying-the-plausibility-of-context","title":"Quantifying the Plausibility of Context Reliance in Neural Machine Translation","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gsarti/pecore","path":"pecore/alignment_utils.py","file_url":"https://github.com/gsarti/pecore/blob/HEAD/pecore/alignment_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2815c122de006aab","mcp_get_code":{"code_sha256":"2815c122de006aab"}},{"arxiv_id":"2106.01703","paper":"/paper/fingerprinting-fine-tuned-language-models-in","title":"Fingerprinting Fine-tuned Language Models in the Wild","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LCS2-IIITD/ACL-FFLM","path":"preprocess/create_full_dataset.py","file_url":"https://github.com/LCS2-IIITD/ACL-FFLM/blob/HEAD/preprocess/create_full_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61dfa1c9e178c8b1","mcp_get_code":{"code_sha256":"61dfa1c9e178c8b1"}},{"arxiv_id":"1906.06606","paper":"/paper/multi-hop-paragraph-retrieval-for-open-domain","title":"Multi-Hop Paragraph Retrieval for Open-Domain Question Answering","date":"2019-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yairf11/MUPPET","path":"hotpot/scripts/train_eval/hotpot_qa_distractors_eval.py","file_url":"https://github.com/yairf11/MUPPET/blob/HEAD/hotpot/scripts/train_eval/hotpot_qa_distractors_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"dccdf913187eca57","mcp_get_code":{"code_sha256":"dccdf913187eca57"}},{"arxiv_id":"2023.findings-acl.765","paper":null,"title":"arXiv:2023.findings-acl.765","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qtli/EIB","path":"code/BottleSum/gpt2_token_mod.py","file_url":"https://github.com/qtli/EIB/blob/HEAD/code/BottleSum/gpt2_token_mod.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":"ed4f5a97389b95c0","mcp_get_code":{"code_sha256":"ed4f5a97389b95c0"}}]}