{"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/load-hf-dataset","entry":"load_hf_dataset","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":0,"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":5,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":5},"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":"2403.13027","paper":"/paper/towards-better-statistical-understanding-of","title":"Towards Better Statistical Understanding of Watermarking LLMs","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhongzecai/dualga","path":"WatermarkAlgorithm/utils/data_processing.py","file_url":"https://github.com/zhongzecai/dualga/blob/HEAD/WatermarkAlgorithm/utils/data_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"86b01270fe49c4d1","mcp_get_code":{"code_sha256":"86b01270fe49c4d1"}},{"arxiv_id":"2402.03660","paper":"/paper/cross-task-linearity-emerges-in-the","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzp1012/cross-task-linearity","path":"task_arithemetic_t5/data_utils.py","file_url":"https://github.com/zzp1012/cross-task-linearity/blob/HEAD/task_arithemetic_t5/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":"598fb7842545bd8e","mcp_get_code":{"code_sha256":"598fb7842545bd8e"}},{"arxiv_id":"2401.11374","paper":"/paper/language-models-as-hierarchy-encoders","title":"Language Models as Hierarchy Encoders","date":"2024-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krr-oxford/hierarchytransformers","path":"src/hierarchy_transformers/datasets/load.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/datasets/load.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":"67ff2eddd3f6c090","mcp_get_code":{"code_sha256":"67ff2eddd3f6c090"}},{"arxiv_id":"2201.03514","paper":"/paper/black-box-tuning-for-language-model-as-a","title":"Black-Box Tuning for Language-Model-as-a-Service","date":"2022-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jubgjf/plmtuningcompetition","path":"dataloader.py","file_url":"https://github.com/jubgjf/plmtuningcompetition/blob/HEAD/dataloader.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":"94689a629c7580ff","mcp_get_code":{"code_sha256":"94689a629c7580ff"}},{"arxiv_id":"1910.10683","paper":"/paper/exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shivamraval98/multitask-t5_ae","path":"src/models/T5Model/t5_utils.py","file_url":"https://github.com/shivamraval98/multitask-t5_ae/blob/HEAD/src/models/T5Model/t5_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"189deed085d33fb1","mcp_get_code":{"code_sha256":"189deed085d33fb1"}}]}