{"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/split-text","entry":"split_text","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":6,"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":7,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":2},"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":"2606.00610","paper":"/paper/arxiv-2606-00610","title":"MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"XMUDeepLIT/MemGraphRAG","path":"code/index.py","file_url":"https://github.com/XMUDeepLIT/MemGraphRAG/blob/HEAD/code/index.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d30b7275852c019","mcp_get_code":{"code_sha256":"5d30b7275852c019"}},{"arxiv_id":"2508.14723","paper":"/paper/arxiv-2508-14723","title":"Transplant Then Regenerate: A New Paradigm for Text Data Augmentation","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"1024er/cbert_aug","path":"text_classification/nlp_utils.py","file_url":"https://github.com/1024er/cbert_aug/blob/HEAD/text_classification/nlp_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"644dffbb82a01ffc","mcp_get_code":{"code_sha256":"644dffbb82a01ffc"}},{"arxiv_id":"2312.02073","paper":"/paper/a-glitch-in-the-matrix-locating-and-detecting","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"epfl-dlab/llm-grounding-analysis","path":"filter_data.py","file_url":"https://github.com/epfl-dlab/llm-grounding-analysis/blob/HEAD/filter_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":"c9cbe06f9880641d","mcp_get_code":{"code_sha256":"c9cbe06f9880641d"}},{"arxiv_id":"2308.13418","paper":"/paper/nougat-neural-optical-understanding-for","title":"Nougat: Neural Optical Understanding for Academic Documents","date":"2023-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/nougat","path":"nougat/metrics.py","file_url":"https://github.com/facebookresearch/nougat/blob/HEAD/nougat/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ac9cf29dfbcd872","mcp_get_code":{"code_sha256":"1ac9cf29dfbcd872"}},{"arxiv_id":"2308.07317","paper":"/paper/platypus-quick-cheap-and-powerful-refinement","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arielnlee/Platypus","path":"data_pipeline/guanaco_format.py","file_url":"https://github.com/arielnlee/Platypus/blob/HEAD/data_pipeline/guanaco_format.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"671f2229be78fcc8","mcp_get_code":{"code_sha256":"671f2229be78fcc8"}},{"arxiv_id":"2307.03115","paper":"/paper/korc-knowledge-oriented-reading-comprehension","title":"KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding","date":"2023-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-keg/korc","path":"RAG/openqa_dataset.py","file_url":"https://github.com/thu-keg/korc/blob/HEAD/RAG/openqa_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b86ae69734a1fa4","mcp_get_code":{"code_sha256":"8b86ae69734a1fa4"}},{"arxiv_id":"1808.08745","paper":"/paper/dont-give-me-the-details-just-the-summary","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","date":"2018-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pltrdy/extoracle_summarization","path":"extoracle/extoracle.py","file_url":"https://github.com/pltrdy/extoracle_summarization/blob/HEAD/extoracle/extoracle.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":"8e675d0bebfa35fb","mcp_get_code":{"code_sha256":"8e675d0bebfa35fb"}},{"arxiv_id":"2023.findings-acl.743","paper":null,"title":"arXiv:2023.findings-acl.743","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"THU-KEG/KoRC","path":"RAG/openqa_dataset.py","file_url":"https://github.com/THU-KEG/KoRC/blob/HEAD/RAG/openqa_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b86ae69734a1fa4","mcp_get_code":{"code_sha256":"8b86ae69734a1fa4"}}]}