{"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-data","entry":"tokenize_data","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":8,"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":8,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2604.21365","paper":"/paper/arxiv-2604-21365","title":"mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"kinit-sk/mcdok-semeval2026","path":"mcdokA.py","file_url":"https://github.com/kinit-sk/mcdok-semeval2026/blob/HEAD/mcdokA.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"44bf0edcdaf9015c","mcp_get_code":{"code_sha256":"44bf0edcdaf9015c"}},{"arxiv_id":"2511.19635","paper":"/paper/arxiv-2511-19635","title":"Agint: Agentic Graph Compilation for Software Engineering Agents","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"AgintHub/nifty-wilson","path":"outputs/dagify/train_large_language_model/code/tokenize_data.py","file_url":"https://github.com/AgintHub/nifty-wilson/blob/HEAD/outputs/dagify/train_large_language_model/code/tokenize_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6eb857d2fdd36c7","mcp_get_code":{"code_sha256":"e6eb857d2fdd36c7"}},{"arxiv_id":"2402.17762","paper":"/paper/massive-activations-in-large-language-models","title":"Massive Activations in Large Language Models","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bluorion-com/refine_massive_activations","path":"utils/data.py","file_url":"https://github.com/bluorion-com/refine_massive_activations/blob/HEAD/utils/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"37c41fc5246ced6c","mcp_get_code":{"code_sha256":"37c41fc5246ced6c"}},{"arxiv_id":"2311.16079","paper":"/paper/meditron-70b-scaling-medical-pretraining-for","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"epfllm/meditron","path":"finetuning/sft.py","file_url":"https://github.com/epfllm/meditron/blob/HEAD/finetuning/sft.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":"42f0d9df1f4e7733","mcp_get_code":{"code_sha256":"42f0d9df1f4e7733"}},{"arxiv_id":"2311.12022","paper":"/paper/gpqa-a-graduate-level-google-proof-q-a","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","date":"2023-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idavidrein/gpqa","path":"baselines/answer_cbow.py","file_url":"https://github.com/idavidrein/gpqa/blob/HEAD/baselines/answer_cbow.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38400f169c72be8d","mcp_get_code":{"code_sha256":"38400f169c72be8d"}},{"arxiv_id":"2311.07172","paper":"/paper/veritymath-advancing-mathematical-reasoning","title":"VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vernontoh/veritymath","path":"utils.py","file_url":"https://github.com/vernontoh/veritymath/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3423603fcee1d1b","mcp_get_code":{"code_sha256":"f3423603fcee1d1b"}},{"arxiv_id":"2211.02729","paper":"/paper/1cademy-causal-news-corpus-2022-leveraging","title":"1Cademy @ Causal News Corpus 2022: Leveraging Self-Training in Causality Classification of Socio-Political Event Data","date":"2022-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gzhang-umich/1cademyteamofcase","path":"model_testing/train_model.py","file_url":"https://github.com/gzhang-umich/1cademyteamofcase/blob/HEAD/model_testing/train_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94245ab92fde8113","mcp_get_code":{"code_sha256":"94245ab92fde8113"}},{"arxiv_id":"2204.00185","paper":"/paper/distill-vq-learning-retrieval-oriented-vector","title":"Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings","date":"2022-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"staoxiao/libvq","path":"LibVQ/dataset/preprocess.py","file_url":"https://github.com/staoxiao/libvq/blob/HEAD/LibVQ/dataset/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"637f46b59be670f3","mcp_get_code":{"code_sha256":"637f46b59be670f3"}}]}