{"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/detokenize","entry":"detokenize","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":14,"n_papers_ran":8,"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":10,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":1,"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":"2509.07730","paper":"/paper/arxiv-2509-07730","title":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Lzx-ZBC/M-BRe","path":"NER/bbn_afet/token_train.py","file_url":"https://github.com/Lzx-ZBC/M-BRe/blob/HEAD/NER/bbn_afet/token_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"adea75a78ac69445","mcp_get_code":{"code_sha256":"adea75a78ac69445"}},{"arxiv_id":"2508.20718","paper":"/paper/arxiv-2508-20718","title":"Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"ryehr/Consistency","path":"src/tokenization_consistency/tokenization.py","file_url":"https://github.com/ryehr/Consistency/blob/HEAD/src/tokenization_consistency/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e44617c05f9e47c","mcp_get_code":{"code_sha256":"3e44617c05f9e47c"}},{"arxiv_id":"2411.15102","paper":"/paper/attribot-a-bag-of-tricks-for-efficiently","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"r-three/AttriBoT","path":"context_attribution/model_utils.py","file_url":"https://github.com/r-three/AttriBoT/blob/HEAD/context_attribution/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc9e1a7a9d9105cd","mcp_get_code":{"code_sha256":"cc9e1a7a9d9105cd"}},{"arxiv_id":"2402.17733","paper":"/paper/tower-an-open-multilingual-large-language","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deep-spin/tower-eval","path":"tower_eval/utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"342c2ee4d566cd68","mcp_get_code":{"code_sha256":"342c2ee4d566cd68"}},{"arxiv_id":"2309.06363","paper":"/paper/2309-06363","title":"Learning to Predict Concept Ordering for Common Sense Generation","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianhuizhang/concept_ordering","path":"bert-gen/decode_seq2seq.py","file_url":"https://github.com/tianhuizhang/concept_ordering/blob/HEAD/bert-gen/decode_seq2seq.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"633d1e424a09eb70","mcp_get_code":{"code_sha256":"633d1e424a09eb70"}},{"arxiv_id":"2105.07911","paper":"/paper/sead-end-to-end-text-to-sql-generation-with","title":"SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising","date":"2021-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/WikiSQL","path":"lib/common.py","file_url":"https://github.com/salesforce/WikiSQL/blob/HEAD/lib/common.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":"f7c43aab1b165185","mcp_get_code":{"code_sha256":"f7c43aab1b165185"}},{"arxiv_id":"2009.07032","paper":"/paper/noisy-self-knowledge-distillation-for-text","title":"Noisy Self-Knowledge Distillation for Text Summarization","date":"2020-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlpyang/NoisySumm","path":"src/decode_seq2seq.py","file_url":"https://github.com/nlpyang/NoisySumm/blob/HEAD/src/decode_seq2seq.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"633d1e424a09eb70","mcp_get_code":{"code_sha256":"633d1e424a09eb70"}},{"arxiv_id":"1911.09709","paper":"/paper/automatically-neutralizing-subjective-bias-in","title":"Automatically Neutralizing Subjective Bias in Text","date":"2019-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rpryzant/neutralizing-bias","path":"deprecated/eval/score_results.py","file_url":"https://github.com/rpryzant/neutralizing-bias/blob/HEAD/deprecated/eval/score_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b9b755d273ab7e3","mcp_get_code":{"code_sha256":"4b9b755d273ab7e3"}},{"arxiv_id":"1909.11059","paper":"/paper/unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LuoweiZhou/VLP","path":"vlp/decode_img2txt.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/decode_img2txt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"633d1e424a09eb70","mcp_get_code":{"code_sha256":"633d1e424a09eb70"}},{"arxiv_id":"1909.02209","paper":"/paper/semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cooelf/SemBERT","path":"data_process/util.py","file_url":"https://github.com/cooelf/SemBERT/blob/HEAD/data_process/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"517a71720243fbf7","mcp_get_code":{"code_sha256":"517a71720243fbf7"}},{"arxiv_id":"1902.04094","paper":"/paper/bert-has-a-mouth-and-it-must-speak-bert-as-a","title":"BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model","date":"2019-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"swastishreya/BERT_as_a_conditional_generative_model","path":"bert-babble.py","file_url":"https://github.com/swastishreya/BERT_as_a_conditional_generative_model/blob/HEAD/bert-babble.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"992ab7ae4b4bf55c","mcp_get_code":{"code_sha256":"992ab7ae4b4bf55c"}},{"arxiv_id":"1604.00788","paper":"/paper/achieving-open-vocabulary-neural-machine","title":"Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models","date":"2016-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Waino/hnmt","path":"hnmt.py","file_url":"https://github.com/Waino/hnmt/blob/HEAD/hnmt.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":"94e0944c2b466a91","mcp_get_code":{"code_sha256":"94e0944c2b466a91"}},{"arxiv_id":"aaai_21432","paper":null,"title":"arXiv:aaai_21432","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/DialogLM","path":"DialogLM_UniLM/DialogLM/decode_seq2seq.py","file_url":"https://github.com/microsoft/DialogLM/blob/HEAD/DialogLM_UniLM/DialogLM/decode_seq2seq.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"633d1e424a09eb70","mcp_get_code":{"code_sha256":"633d1e424a09eb70"}},{"arxiv_id":"2021.findings-emnlp.347","paper":null,"title":"arXiv:2021.findings-emnlp.347","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wentinghome/AMG","path":"biunilm/decode_all_domains.py","file_url":"https://github.com/wentinghome/AMG/blob/HEAD/biunilm/decode_all_domains.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"633d1e424a09eb70","mcp_get_code":{"code_sha256":"633d1e424a09eb70"}}]}