{"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-fn","entry":"tokenize_fn","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":9,"n_papers_ran":4,"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":2,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":4},"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":"2508.15868","paper":"/paper/arxiv-2508-15868","title":"CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"WNQzhu/CARFT","path":"code/mwp_ReFT/sampling.py","file_url":"https://github.com/WNQzhu/CARFT/blob/HEAD/code/mwp_ReFT/sampling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"951fe709737c50b9","mcp_get_code":{"code_sha256":"951fe709737c50b9"}},{"arxiv_id":"2502.11089","paper":"/paper/native-sparse-attention-hardware-aligned-and","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","date":"2025-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/seerattention","path":"distillation_decode.py","file_url":"https://github.com/microsoft/seerattention/blob/HEAD/distillation_decode.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ef366d8b91a362a","mcp_get_code":{"code_sha256":"3ef366d8b91a362a"}},{"arxiv_id":"2502.11089","paper":"/paper/native-sparse-attention-hardware-aligned-and","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","date":"2025-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/seerattention","path":"distillation_prefill.py","file_url":"https://github.com/microsoft/seerattention/blob/HEAD/distillation_prefill.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9963e3bc9860eda","mcp_get_code":{"code_sha256":"f9963e3bc9860eda"}},{"arxiv_id":"2409.12181","paper":"/paper/a-controlled-study-on-long-context-extension","title":"A Controlled Study on Long Context Extension and Generalization in LLMs","date":"2024-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leooyii/lceg","path":"continuous_finetuning/fine-tune.py","file_url":"https://github.com/leooyii/lceg/blob/HEAD/continuous_finetuning/fine-tune.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":"ad4c52b7c7083143","mcp_get_code":{"code_sha256":"ad4c52b7c7083143"}},{"arxiv_id":"2408.16967","paper":"/paper/memlong-memory-augmented-retrieval-for-long","title":"MemLong: Memory-Augmented Retrieval for Long Text Modeling","date":"2024-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bui1dmysea/memlong","path":"eval/language_modeling/MemLong/utils.py","file_url":"https://github.com/bui1dmysea/memlong/blob/HEAD/eval/language_modeling/MemLong/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c78930a2d9e9be54","mcp_get_code":{"code_sha256":"c78930a2d9e9be54"}},{"arxiv_id":"2404.03592","paper":"/paper/reft-representation-finetuning-for-language","title":"ReFT: Representation Finetuning for Language Models","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lqtrung1998/mwp_reft","path":"sampling.py","file_url":"https://github.com/lqtrung1998/mwp_reft/blob/HEAD/sampling.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":"951fe709737c50b9","mcp_get_code":{"code_sha256":"951fe709737c50b9"}},{"arxiv_id":"2402.10835","paper":"/paper/time-series-forecasting-with-llms","title":"Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyuj666/time-series-forecasting-with-llms","path":"models/gpt.py","file_url":"https://github.com/mingyuj666/time-series-forecasting-with-llms/blob/HEAD/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0974c070244bffa0","mcp_get_code":{"code_sha256":"0974c070244bffa0"}},{"arxiv_id":"2401.08967","paper":"/paper/reft-reasoning-with-reinforced-fine-tuning","title":"ReFT: Reasoning with Reinforced Fine-Tuning","date":"2024-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lqtrung1998/mwp_ReFT","path":"sampling.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/sampling.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":"951fe709737c50b9","mcp_get_code":{"code_sha256":"951fe709737c50b9"}},{"arxiv_id":"2309.12307","paper":"/paper/longlora-efficient-fine-tuning-of-long","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dexter-gt-86/sinklora","path":"fine-tune.py","file_url":"https://github.com/dexter-gt-86/sinklora/blob/HEAD/fine-tune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad4c52b7c7083143","mcp_get_code":{"code_sha256":"ad4c52b7c7083143"}},{"arxiv_id":"aaai_34662","paper":null,"title":"arXiv:aaai_34662","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"maxindian/3D-RPE-Long-Contex-Modeling","path":"fine-tune-cpe-llm.py","file_url":"https://github.com/maxindian/3D-RPE-Long-Contex-Modeling/blob/HEAD/fine-tune-cpe-llm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad4c52b7c7083143","mcp_get_code":{"code_sha256":"ad4c52b7c7083143"}}]}