{"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/lm1b-detokenizer","entry":"lm1b_detokenizer","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":12,"n_papers_ran":12,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":12,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"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":"2606.02241","paper":"/paper/arxiv-2606-02241","title":"BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jdeschena/blockgen","path":"dataloader.py","file_url":"https://github.com/jdeschena/blockgen/blob/HEAD/dataloader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2605.22765","paper":"/paper/arxiv-2605-22765","title":"Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"samsongourevitch/rev_udm","path":"src/dataloader.py","file_url":"https://github.com/samsongourevitch/rev_udm/blob/HEAD/src/dataloader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2605.11125","paper":"/paper/arxiv-2605-11125","title":"Language Modeling with Hyperspherical Flows","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"jdeschena/s-flm","path":"dataloader.py","file_url":"https://github.com/jdeschena/s-flm/blob/HEAD/dataloader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2510.24088","paper":"/paper/arxiv-2510-24088","title":"Information-Theoretic Discrete Diffusion","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Dongjae0324/infodis","path":"data.py","file_url":"https://github.com/Dongjae0324/infodis/blob/HEAD/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2509.18577","paper":"/paper/arxiv-2509-18577","title":"Prior-based Noisy Text Data Filtering: Fast and Strong Alternative For Perplexity","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ybseo-ac/prior_filter","path":"dataloader.py","file_url":"https://github.com/ybseo-ac/prior_filter/blob/HEAD/dataloader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2509.15188","paper":"/paper/arxiv-2509-15188","title":"Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ybseo-ac/Conv","path":"dataloader.py","file_url":"https://github.com/ybseo-ac/Conv/blob/HEAD/dataloader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2506.19935","paper":"/paper/any-order-gpt-as-masked-diffusion-model","title":"Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture","date":"2025-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scxue/ao-gpt-mdm","path":"data.py","file_url":"https://github.com/scxue/ao-gpt-mdm/blob/HEAD/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2505.18883","paper":"/paper/partition-generative-modeling-masked-modeling","title":"Partition Generative Modeling: Masked Modeling Without Masks","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuleshov-group/mdlm","path":"dataloader.py","file_url":"https://github.com/kuleshov-group/mdlm/blob/HEAD/dataloader.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":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2503.09573","paper":"/paper/block-diffusion-interpolating-between","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuleshov-group/bd3lms","path":"dataloader.py","file_url":"https://github.com/kuleshov-group/bd3lms/blob/HEAD/dataloader.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":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2412.10193","paper":"/paper/simple-guidance-mechanisms-for-discrete","title":"Simple Guidance Mechanisms for Discrete Diffusion Models","date":"2024-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuleshov-group/discrete-diffusion-guidance","path":"dataloader.py","file_url":"https://github.com/kuleshov-group/discrete-diffusion-guidance/blob/HEAD/dataloader.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":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2406.03736","paper":"/paper/your-absorbing-discrete-diffusion-secretly","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-gsai/radd","path":"data.py","file_url":"https://github.com/ml-gsai/radd/blob/HEAD/data.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":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}},{"arxiv_id":"2310.16834","paper":"/paper/discrete-diffusion-language-modeling-by","title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"louaaron/Score-Entropy-Discrete-Diffusion","path":"data.py","file_url":"https://github.com/louaaron/Score-Entropy-Discrete-Diffusion/blob/HEAD/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"576e1b9b9bcae8ff","mcp_get_code":{"code_sha256":"576e1b9b9bcae8ff"}}]}