{"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/deduplicate","entry":"deduplicate","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":4,"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":4,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":5},"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":"2506.04178","paper":"/paper/openthoughts-data-recipes-for-reasoning","title":"OpenThoughts: Data Recipes for Reasoning Models","date":"2025-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-thoughts/open-thoughts","path":"open_thoughts/deduplicate.py","file_url":"https://github.com/open-thoughts/open-thoughts/blob/HEAD/open_thoughts/deduplicate.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":"d1c3dd92128dd7b2","mcp_get_code":{"code_sha256":"d1c3dd92128dd7b2"}},{"arxiv_id":"2412.14063","paper":"/paper/rango-adaptive-retrieval-augmented-proving","title":"Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rkthomps/coq-modeling","path":"src/data_management/jsonl_utils.py","file_url":"https://github.com/rkthomps/coq-modeling/blob/HEAD/src/data_management/jsonl_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8e3d3ad58fa6224","mcp_get_code":{"code_sha256":"d8e3d3ad58fa6224"}},{"arxiv_id":"2402.18815","paper":"/paper/how-do-large-language-models-handle","title":"How do Large Language Models Handle Multilingualism?","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/multilingual_analysis","path":"neuron_enhancement/train_neuron.py","file_url":"https://github.com/damo-nlp-sg/multilingual_analysis/blob/HEAD/neuron_enhancement/train_neuron.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"351bf96fa5d82bb3","mcp_get_code":{"code_sha256":"351bf96fa5d82bb3"}},{"arxiv_id":"2311.09774","paper":"/paper/huatuogpt-ii-one-stage-training-for-medical","title":"HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/huatuogpt-ii","path":"evaluation/eval_huatuo_inst.py","file_url":"https://github.com/freedomintelligence/huatuogpt-ii/blob/HEAD/evaluation/eval_huatuo_inst.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c39574f5e470abf","mcp_get_code":{"code_sha256":"1c39574f5e470abf"}},{"arxiv_id":"2310.03714","paper":"/paper/dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stanfordnlp/dsp","path":"dspy/dsp/utils/utils.py","file_url":"https://github.com/stanfordnlp/dsp/blob/HEAD/dspy/dsp/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8823c5b244127289","mcp_get_code":{"code_sha256":"8823c5b244127289"}},{"arxiv_id":"2305.13917","paper":"/paper/generating-data-for-symbolic-language-with","title":"Generating Data for Symbolic Language with Large Language Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkunlp/symgen","path":"src/dataset_readers/index_dsr.py","file_url":"https://github.com/hkunlp/symgen/blob/HEAD/src/dataset_readers/index_dsr.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":"46ac634191da2933","mcp_get_code":{"code_sha256":"46ac634191da2933"}},{"arxiv_id":"2301.07779","paper":"/paper/understanding-and-detecting-hallucinations-in","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","date":"2023-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weijia-xu/hallucinations-in-nmt","path":"code/classifier.py","file_url":"https://github.com/weijia-xu/hallucinations-in-nmt/blob/HEAD/code/classifier.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1d7ded7fe1a46f9","mcp_get_code":{"code_sha256":"b1d7ded7fe1a46f9"}},{"arxiv_id":"aaai_29778","paper":null,"title":"arXiv:aaai_29778","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"NLPCode/LIFE","path":"utils/text_process.py","file_url":"https://github.com/NLPCode/LIFE/blob/HEAD/utils/text_process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3fda699df5d07d18","mcp_get_code":{"code_sha256":"3fda699df5d07d18"}},{"arxiv_id":"2025.findings-emnlp.136","paper":null,"title":"arXiv:2025.findings-emnlp.136","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HCY123902/DCRM","path":"create_best_of_n2_dataset.py","file_url":"https://github.com/HCY123902/DCRM/blob/HEAD/create_best_of_n2_dataset.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":"6edb5aabb8bca170","mcp_get_code":{"code_sha256":"6edb5aabb8bca170"}}]}