{"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/remove-after-return","entry":"remove_after_return","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":5,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"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":"2410.05357","paper":"/paper/model-glue-democratized-llm-scaling-for-a","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Model-GLUE/Model-GLUE","path":"bigcode_eval/utils.py","file_url":"https://github.com/Model-GLUE/Model-GLUE/blob/HEAD/bigcode_eval/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29ee1d8c120f674a","mcp_get_code":{"code_sha256":"29ee1d8c120f674a"}},{"arxiv_id":"2406.12809","paper":"/paper/can-large-language-models-always-solve-easy","title":"Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QwenLM/ConsisEval","path":"code_check/post_process.py","file_url":"https://github.com/QwenLM/ConsisEval/blob/HEAD/code_check/post_process.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29ee1d8c120f674a","mcp_get_code":{"code_sha256":"29ee1d8c120f674a"}},{"arxiv_id":"2406.11687","paper":"/paper/tokenization-falling-short-the-curse-of","title":"Tokenization Falling Short: On Subword Robustness in Large Language Models","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"floatai/tkeval","path":"evaluation/bigcode-evaluation-harness/bigcode_eval/utils.py","file_url":"https://github.com/floatai/tkeval/blob/HEAD/evaluation/bigcode-evaluation-harness/bigcode_eval/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29ee1d8c120f674a","mcp_get_code":{"code_sha256":"29ee1d8c120f674a"}},{"arxiv_id":"2308.07124","paper":"/paper/octopack-instruction-tuning-code-large","title":"OctoPack: Instruction Tuning Code Large Language Models","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigcode-project/bigcode-evaluation-harness","path":"bigcode_eval/utils.py","file_url":"https://github.com/bigcode-project/bigcode-evaluation-harness/blob/HEAD/bigcode_eval/utils.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":"29ee1d8c120f674a","mcp_get_code":{"code_sha256":"29ee1d8c120f674a"}},{"arxiv_id":"2024.findings-emnlp.86","paper":null,"title":"arXiv:2024.findings-emnlp.86","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"FloatAI/TKEval","path":"evaluation/bigcode-evaluation-harness/bigcode_eval/utils.py","file_url":"https://github.com/FloatAI/TKEval/blob/HEAD/evaluation/bigcode-evaluation-harness/bigcode_eval/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29ee1d8c120f674a","mcp_get_code":{"code_sha256":"29ee1d8c120f674a"}}]}