{"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-into-chunks","entry":"split_into_chunks","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":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":9,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":6},"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":"2605.17041","paper":"/paper/arxiv-2605-17041","title":"Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"chuckmy/agentic-translator","path":"chunker.py","file_url":"https://github.com/chuckmy/agentic-translator/blob/HEAD/chunker.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c58837277e00d2ee","mcp_get_code":{"code_sha256":"c58837277e00d2ee"}},{"arxiv_id":"2510.14374","paper":"/paper/arxiv-2510-14374","title":"Spatial Preference Rewarding for MLLMs Spatial Understanding","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"hanqiu-hq/SPR","path":"construct_data/ferret_score_siglip.py","file_url":"https://github.com/hanqiu-hq/SPR/blob/HEAD/construct_data/ferret_score_siglip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c4c913b24137e65","mcp_get_code":{"code_sha256":"5c4c913b24137e65"}},{"arxiv_id":"2410.22564","paper":"/paper/vertical-federated-learning-with-missing","title":"Vertical Federated Learning with Missing Features During Training and Inference","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Valdeira/LASER-VFL","path":"models/lstm.py","file_url":"https://github.com/Valdeira/LASER-VFL/blob/HEAD/models/lstm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d2e97e2a9f5617b","mcp_get_code":{"code_sha256":"8d2e97e2a9f5617b"}},{"arxiv_id":"2405.15523","paper":"/paper/mosaic-memory-fuzzy-duplication-in-copyright","title":"The Mosaic Memory of Large Language Models","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"computationalprivacy/mosaic_memory","path":"src/fine_tune_model.py","file_url":"https://github.com/computationalprivacy/mosaic_memory/blob/HEAD/src/fine_tune_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a838ebb710694579","mcp_get_code":{"code_sha256":"a838ebb710694579"}},{"arxiv_id":"2404.10774","paper":"/paper/minicheck-efficient-fact-checking-of-llms-on","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyan06/minicheck","path":"synthetic_data_gen/D2C_gen.py","file_url":"https://github.com/liyan06/minicheck/blob/HEAD/synthetic_data_gen/D2C_gen.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":"4cb70b41a391c83d","mcp_get_code":{"code_sha256":"4cb70b41a391c83d"}},{"arxiv_id":"2402.11733","paper":"/paper/the-effectiveness-of-random-forgetting-for","title":"The Effectiveness of Random Forgetting for Robust Generalization","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"orrzohar/FOMO","path":"models/FOMO.py","file_url":"https://github.com/orrzohar/FOMO/blob/HEAD/models/FOMO.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2518fe5e601e8f3a","mcp_get_code":{"code_sha256":"2518fe5e601e8f3a"}},{"arxiv_id":"2402.09154","paper":"/paper/attacking-large-language-models-with","title":"Attacking Large Language Models with Projected Gradient Descent","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sigeisler/reinforce-attacks-llms","path":"baselines/reinforce/pgd_adapter.py","file_url":"https://github.com/sigeisler/reinforce-attacks-llms/blob/HEAD/baselines/reinforce/pgd_adapter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6b3bb30734078091","mcp_get_code":{"code_sha256":"6b3bb30734078091"}},{"arxiv_id":"2109.02303","paper":"/paper/encoder-decoder-with-multi-level-attention","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","date":"2021-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziniuwan/maed","path":"lib/data_utils/img_utils.py","file_url":"https://github.com/ziniuwan/maed/blob/HEAD/lib/data_utils/img_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5af3953b1583f4d","mcp_get_code":{"code_sha256":"a5af3953b1583f4d"}},{"arxiv_id":"2107.03374","paper":"/paper/evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codedotal/gpt-code-clippy","path":"data_processing/download_license_info.py","file_url":"https://github.com/codedotal/gpt-code-clippy/blob/HEAD/data_processing/download_license_info.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":"d27e3a9c64e09294","mcp_get_code":{"code_sha256":"d27e3a9c64e09294"}}]}