{"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/chunked","entry":"chunked","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":2,"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":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":3},"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":"2609.12584","paper":"/paper/arxiv-2609-12584","title":"Clustering-Based Balanced Sampling and Allocation with Data Parallelism for High-Performance Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"kaist-dmlab/CluSTER","path":"src/CluSTER/utils.py","file_url":"https://github.com/kaist-dmlab/CluSTER/blob/HEAD/src/CluSTER/utils.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":"e7d9061ac996d800","mcp_get_code":{"code_sha256":"e7d9061ac996d800"}},{"arxiv_id":"2605.18959","paper":"/paper/arxiv-2605-18959","title":"Hyrax: An Extensible Framework for Rapid ML Experimentation and Unsupervised Discovery in the Era of Rubin, Roman, and Euclid","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"more-itertools/more-itertools","path":"more_itertools/more.py","file_url":"https://github.com/more-itertools/more-itertools/blob/HEAD/more_itertools/more.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b48f7f6e8e3e149","mcp_get_code":{"code_sha256":"9b48f7f6e8e3e149"}},{"arxiv_id":"2412.21199","paper":"/paper/humaneval-pro-and-mbpp-pro-evaluating-large","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","date":"2024-12-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CodeEval-Pro/CodeEval-Pro","path":"eval/inference.py","file_url":"https://github.com/CodeEval-Pro/CodeEval-Pro/blob/HEAD/eval/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b62d2bbf854c35b","mcp_get_code":{"code_sha256":"2b62d2bbf854c35b"}},{"arxiv_id":"2410.24198","paper":"/paper/selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigcode-project/starcoder2-self-align","path":"src/star_align/utils.py","file_url":"https://github.com/bigcode-project/starcoder2-self-align/blob/HEAD/src/star_align/utils.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":"a6974ed3c2ddb7eb","mcp_get_code":{"code_sha256":"a6974ed3c2ddb7eb"}},{"arxiv_id":"2406.01006","paper":"/paper/semcoder-training-code-language-models-with","title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ARiSE-Lab/SemCoder","path":"src/utils.py","file_url":"https://github.com/ARiSE-Lab/SemCoder/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8fbbf1d9e53be9ec","mcp_get_code":{"code_sha256":"8fbbf1d9e53be9ec"}}]}