{"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-sentence","entry":"tokenize_sentence","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":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":4,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":2},"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":"2406.04286","paper":"/paper/abex-data-augmentation-for-low-resource-nlu","title":"ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sreyan88/ABEX","path":"amr_parser_spring/bin/eval_bleu.py","file_url":"https://github.com/Sreyan88/ABEX/blob/HEAD/amr_parser_spring/bin/eval_bleu.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e060ba08fb272f3","mcp_get_code":{"code_sha256":"5e060ba08fb272f3"}},{"arxiv_id":"2005.09123","paper":"/paper/gpt-too-a-language-model-first-approach-for","title":"GPT-too: A language-model-first approach for AMR-to-text generation","date":"2020-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/GPT-too-AMR2text","path":"extra/eval_sacrebleu.py","file_url":"https://github.com/IBM/GPT-too-AMR2text/blob/HEAD/extra/eval_sacrebleu.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":"5e060ba08fb272f3","mcp_get_code":{"code_sha256":"5e060ba08fb272f3"}},{"arxiv_id":"1908.11326","paper":"/paper/translate-and-label-an-encoder-decoder","title":"Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling","date":"2019-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Heidelberg-NLP/SRL-S2S","path":"pre_processing/Text_to_JSON.py","file_url":"https://github.com/Heidelberg-NLP/SRL-S2S/blob/HEAD/pre_processing/Text_to_JSON.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"09ae2a23502b9e12","mcp_get_code":{"code_sha256":"09ae2a23502b9e12"}},{"arxiv_id":"1904.03310","paper":"/paper/gender-bias-in-contextualized-word-embeddings","title":"Gender Bias in Contextualized Word Embeddings","date":"2019-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dadebias/genda-lens","path":"genda_lens/lm_tasks/abc_utils.py","file_url":"https://github.com/dadebias/genda-lens/blob/HEAD/genda_lens/lm_tasks/abc_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"754ad37cfcc6370c","mcp_get_code":{"code_sha256":"754ad37cfcc6370c"}},{"arxiv_id":"aaai_5722","paper":null,"title":"arXiv:aaai_5722","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/Distilled-Sentence-Embedding","path":"load_dse_checkpoint_example.py","file_url":"https://github.com/microsoft/Distilled-Sentence-Embedding/blob/HEAD/load_dse_checkpoint_example.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"76e26385240f1eb7","mcp_get_code":{"code_sha256":"76e26385240f1eb7"}}]}