{"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/build-tokenizer","entry":"build_tokenizer","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":19,"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":21,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":21,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":17},"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":"2605.06885","paper":"/paper/arxiv-2605-06885","title":"Don't Retrain-Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pengzhangzhi/Open-dLLM","path":"veomni/models/auto.py","file_url":"https://github.com/pengzhangzhi/Open-dLLM/blob/HEAD/veomni/models/auto.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":"7c6cb8d3e6d5a33b","mcp_get_code":{"code_sha256":"7c6cb8d3e6d5a33b"}},{"arxiv_id":"2410.24105","paper":"/paper/matchmaker-self-improving-large-language","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JZCS2018/SMAT","path":"data_utils.py","file_url":"https://github.com/JZCS2018/SMAT/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"49fe481db3ed5ef0","mcp_get_code":{"code_sha256":"49fe481db3ed5ef0"}},{"arxiv_id":"2409.05395","paper":"/paper/shaking-up-vlms-comparing-transformers-and","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","date":"2024-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpantaz/vl_mamba","path":"src/vl_mamba/train_hf.py","file_url":"https://github.com/gpantaz/vl_mamba/blob/HEAD/src/vl_mamba/train_hf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6f70d524bb042b8","mcp_get_code":{"code_sha256":"b6f70d524bb042b8"}},{"arxiv_id":"2409.05395","paper":"/paper/shaking-up-vlms-comparing-transformers-and","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","date":"2024-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpantaz/vl_mamba","path":"src/vl_mamba/evaluation/base_evaluator.py","file_url":"https://github.com/gpantaz/vl_mamba/blob/HEAD/src/vl_mamba/evaluation/base_evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f151d425fafa70f","mcp_get_code":{"code_sha256":"6f151d425fafa70f"}},{"arxiv_id":"2409.04431","paper":"/paper/theory-analysis-and-best-practices-for","title":"Theory, Analysis, and Best Practices for Sigmoid Self-Attention","date":"2024-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-sigmoid-attention","path":"attention_simulator/examples/language_modeling/train_autoregressive_language_model.py","file_url":"https://github.com/apple/ml-sigmoid-attention/blob/HEAD/attention_simulator/examples/language_modeling/train_autoregressive_language_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f4ff8259db7ed4ff","mcp_get_code":{"code_sha256":"f4ff8259db7ed4ff"}},{"arxiv_id":"2408.11791","paper":"/paper/critique-out-loud-reward-models","title":"Critique-out-Loud Reward Models","date":"2024-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zankner/cloud","path":"cloud/train/utils.py","file_url":"https://github.com/zankner/cloud/blob/HEAD/cloud/train/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2ac2186c8e723169","mcp_get_code":{"code_sha256":"2ac2186c8e723169"}},{"arxiv_id":"2407.09941","paper":"/paper/hydra-bidirectional-state-space-models","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","date":"2024-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goombalab/hydra","path":"hydra/bert/src/text_data.py","file_url":"https://github.com/goombalab/hydra/blob/HEAD/hydra/bert/src/text_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d30f2c46fd5058c","mcp_get_code":{"code_sha256":"9d30f2c46fd5058c"}},{"arxiv_id":"2402.00786","paper":"/paper/croissantllm-a-truly-bilingual-french-english","title":"CroissantLLM: A Truly Bilingual French-English Language Model","date":"2024-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manuelfay/llm-data-hub","path":"dataset_construction/fit_tokenizer.py","file_url":"https://github.com/manuelfay/llm-data-hub/blob/HEAD/dataset_construction/fit_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2acdc362a8126567","mcp_get_code":{"code_sha256":"2acdc362a8126567"}},{"arxiv_id":"2310.00752","paper":"/paper/tigerscore-towards-building-explainable","title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","date":"2023-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TIGER-AI-Lab/TIGERScore","path":"tigerscore/candidates_generation/model_utils.py","file_url":"https://github.com/TIGER-AI-Lab/TIGERScore/blob/HEAD/tigerscore/candidates_generation/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"200483ce1173890a","mcp_get_code":{"code_sha256":"200483ce1173890a"}},{"arxiv_id":"2309.15701","paper":"/paper/hyporadise-an-open-baseline-for-generative-1","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","date":"2023-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hypotheses-paradise/hypo2trans","path":"generate_data/whisper/whisper/tokenizer.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f475a7a8460e2abc","mcp_get_code":{"code_sha256":"f475a7a8460e2abc"}},{"arxiv_id":"2306.02561","paper":"/paper/llm-blender-ensembling-large-language-models","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuchenlin/LLM-Blender","path":"llm_blender/candidates_generation/model_utils.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/candidates_generation/model_utils.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":"9e63c7f428bcf976","mcp_get_code":{"code_sha256":"9e63c7f428bcf976"}},{"arxiv_id":"2306.02561","paper":"/paper/llm-blender-ensembling-large-language-models","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuchenlin/LLM-Blender","path":"llm_blender/pair_ranker/model_util.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/pair_ranker/model_util.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":"dea0c7d7d27028b1","mcp_get_code":{"code_sha256":"dea0c7d7d27028b1"}},{"arxiv_id":"2212.04356","paper":"/paper/robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"briansidp/whisperbiasing","path":"whisper/tokenizer.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"acb6a55d43c7f465","mcp_get_code":{"code_sha256":"acb6a55d43c7f465"}},{"arxiv_id":"2210.15230","paper":"/paper/how-well-can-text-to-image-generative-models","title":"How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?","date":"2022-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hritikbansal/entigen_emnlp","path":"models/minDALL-E/dalle/models/tokenizer.py","file_url":"https://github.com/hritikbansal/entigen_emnlp/blob/HEAD/models/minDALL-E/dalle/models/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d23c31b80ba171d","mcp_get_code":{"code_sha256":"0d23c31b80ba171d"}},{"arxiv_id":"2206.01299","paper":"/paper/fine-tuning-language-models-over-slow","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","date":"2022-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DS3Lab/AC-SGD","path":"modules/tokenizer.py","file_url":"https://github.com/DS3Lab/AC-SGD/blob/HEAD/modules/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0c8736d6680465b","mcp_get_code":{"code_sha256":"b0c8736d6680465b"}},{"arxiv_id":"2204.09222","paper":"/paper/k-lite-learning-transferable-visual-models","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","date":"2022-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/klite","path":"model/model.py","file_url":"https://github.com/microsoft/klite/blob/HEAD/model/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7ee228866431711","mcp_get_code":{"code_sha256":"d7ee228866431711"}},{"arxiv_id":"2109.07177","paper":"/paper/adversarial-mixing-policy-for-relaxing","title":"Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup","date":"2021-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"songyouwei/ABSA-PyTorch","path":"data_utils.py","file_url":"https://github.com/songyouwei/ABSA-PyTorch/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b97da16eaf330fad","mcp_get_code":{"code_sha256":"b97da16eaf330fad"}},{"arxiv_id":"1512.01100","paper":"/paper/effective-lstms-for-target-dependent","title":"Effective LSTMs for Target-Dependent Sentiment Classification","date":"2015-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hiyouga/PBAN-PyTorch","path":"data_utils.py","file_url":"https://github.com/hiyouga/PBAN-PyTorch/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3477796acf72175a","mcp_get_code":{"code_sha256":"3477796acf72175a"}},{"arxiv_id":"aaai_6517","paper":null,"title":"arXiv:aaai_6517","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hiyouga/RepWalk","path":"data_utils.py","file_url":"https://github.com/hiyouga/RepWalk/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5a2f8b523c09f5d","mcp_get_code":{"code_sha256":"a5a2f8b523c09f5d"}},{"arxiv_id":"aaai_29911","paper":null,"title":"arXiv:aaai_29911","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"shuoyinn/TextGT","path":"data_utils.py","file_url":"https://github.com/shuoyinn/TextGT/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcd67ca3bd9006fa","mcp_get_code":{"code_sha256":"bcd67ca3bd9006fa"}},{"arxiv_id":"2025.findings-acl.1207","paper":null,"title":"arXiv:2025.findings-acl.1207","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"EIT-NLP/StreamingLLM","path":"StreamingThinker/finetune_streaming.py","file_url":"https://github.com/EIT-NLP/StreamingLLM/blob/HEAD/StreamingThinker/finetune_streaming.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":"263c52767281b14d","mcp_get_code":{"code_sha256":"263c52767281b14d"}}]}