{"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/clean-output","entry":"clean_output","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":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":9,"n_samples_ran":6,"n_samples_fingerprinted":6,"n_places":9,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":4,"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":"2410.00151","paper":"/paper/scheherazade-evaluating-chain-of-thought-math","title":"Scheherazade: Evaluating Chain-of-Thought Math Reasoning in LLMs with Chain-of-Problems","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yoshikitakashima/scheherazade-code-data","path":"chaining.py","file_url":"https://github.com/yoshikitakashima/scheherazade-code-data/blob/HEAD/chaining.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e933aaa6c0a5b92","mcp_get_code":{"code_sha256":"3e933aaa6c0a5b92"}},{"arxiv_id":"2407.04108","paper":"/paper/future-events-as-backdoor-triggers","title":"Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sbp354/future_triggered_backdoors","path":"future_probing/fcc/utils.py","file_url":"https://github.com/sbp354/future_triggered_backdoors/blob/HEAD/future_probing/fcc/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"559ab80369898623","mcp_get_code":{"code_sha256":"559ab80369898623"}},{"arxiv_id":"2404.04659","paper":"/paper/multilingual-pretraining-and-instruction","title":"Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rivergao/clika","path":"x_copa/eval_xcopa_performance_fixed_en_prompt.py","file_url":"https://github.com/rivergao/clika/blob/HEAD/x_copa/eval_xcopa_performance_fixed_en_prompt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"587728d8906a8a0f","mcp_get_code":{"code_sha256":"587728d8906a8a0f"}},{"arxiv_id":"2404.04659","paper":"/paper/multilingual-pretraining-and-instruction","title":"Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rivergao/clika","path":"x_copa/generate_input_data.py","file_url":"https://github.com/rivergao/clika/blob/HEAD/x_copa/generate_input_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f90c0248efc97be","mcp_get_code":{"code_sha256":"7f90c0248efc97be"}},{"arxiv_id":"2401.12554","paper":"/paper/can-large-language-models-write-parallel-code","title":"Can Large Language Models Write Parallel Code?","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"parallelcodefoundry/ParEval","path":"generate/clean-outputs.py","file_url":"https://github.com/parallelcodefoundry/ParEval/blob/HEAD/generate/clean-outputs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b588819cf6250c27","mcp_get_code":{"code_sha256":"b588819cf6250c27"}},{"arxiv_id":"2311.08377","paper":"/paper/learning-to-filter-context-for-retrieval","title":"Learning to Filter Context for Retrieval-Augmented Generation","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zorazrw/filco","path":"query.py","file_url":"https://github.com/zorazrw/filco/blob/HEAD/query.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"CC-BY-SA-4.0","inline_ok":false,"code_sha256_prefix":"55061ae7830bd037","mcp_get_code":{"code_sha256":"55061ae7830bd037"}},{"arxiv_id":"2108.01850","paper":"/paper/controlled-text-generation-as-continuous","title":"Controlled Text Generation as Continuous Optimization with Multiple Constraints","date":"2021-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sachin19/mucoco","path":"mucoco/decode.py","file_url":"https://github.com/sachin19/mucoco/blob/HEAD/mucoco/decode.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc5d4721f229761e","mcp_get_code":{"code_sha256":"cc5d4721f229761e"}},{"arxiv_id":"1901.08149","paper":"/paper/transfertransfo-a-transfer-learning-approach","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","date":"2019-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noriyukipy/gptchat","path":"gptchat/chatlm/lib.py","file_url":"https://github.com/noriyukipy/gptchat/blob/HEAD/gptchat/chatlm/lib.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a6666cf079c15e4","mcp_get_code":{"code_sha256":"8a6666cf079c15e4"}},{"arxiv_id":"Zhang_Critic-V_VLM_Critics_Help_Catch_VLM_Errors_in_Multimodal_Reasoning_CVPR_2025_paper","paper":null,"title":"arXiv:Zhang_Critic-V_VLM_Critics_Help_Catch_VLM_Errors_in_Multimodal_Reasoning_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kyrieLei/Critic-V","path":"data_utils/utils/format.py","file_url":"https://github.com/kyrieLei/Critic-V/blob/HEAD/data_utils/utils/format.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"75e7795f7c4953c8","mcp_get_code":{"code_sha256":"75e7795f7c4953c8"}}]}