{"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/process-item","entry":"process_item","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":12,"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":12,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":10},"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":"2511.13223","paper":"/paper/arxiv-2511-13223","title":"TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"zhangyx1122/TokenSqueeze","path":"step5_generate_rewrite_dpo_pair.py","file_url":"https://github.com/zhangyx1122/TokenSqueeze/blob/HEAD/step5_generate_rewrite_dpo_pair.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62c0b9272e324d3a","mcp_get_code":{"code_sha256":"62c0b9272e324d3a"}},{"arxiv_id":"2509.23415","paper":"/paper/arxiv-2509-23415","title":"From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"glee4810/EHR-ChatQA","path":"src/utils.py","file_url":"https://github.com/glee4810/EHR-ChatQA/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a2449ed9e9ab30f6","mcp_get_code":{"code_sha256":"a2449ed9e9ab30f6"}},{"arxiv_id":"2504.06514","paper":"/paper/missing-premise-exacerbates-overthinking-are","title":"Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?","date":"2025-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianyi-lab/mip-overthinking","path":"api_inference/deepseek_infer.py","file_url":"https://github.com/tianyi-lab/mip-overthinking/blob/HEAD/api_inference/deepseek_infer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c9900f5a052994bd","mcp_get_code":{"code_sha256":"c9900f5a052994bd"}},{"arxiv_id":"2503.23513","paper":"/paper/rare-retrieval-augmented-reasoning-modeling","title":"RARE: Retrieval-Augmented Reasoning Modeling","date":"2025-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-dataflow/rare","path":"process/process_pubhealth.py","file_url":"https://github.com/open-dataflow/rare/blob/HEAD/process/process_pubhealth.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":"5d7f6062b1de0214","mcp_get_code":{"code_sha256":"5d7f6062b1de0214"}},{"arxiv_id":"2503.20752","paper":"/paper/reason-rft-reinforcement-fine-tuning-for","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tanhuajie/reason-rft","path":"utils/distill_cot_data.py","file_url":"https://github.com/tanhuajie/reason-rft/blob/HEAD/utils/distill_cot_data.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":"4e7ac788ac1a18f4","mcp_get_code":{"code_sha256":"4e7ac788ac1a18f4"}},{"arxiv_id":"2503.20752","paper":"/paper/reason-rft-reinforcement-fine-tuning-for","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tanhuajie/reason-rft","path":"utils/distill_cot_data_trance.py","file_url":"https://github.com/tanhuajie/reason-rft/blob/HEAD/utils/distill_cot_data_trance.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":"752bd3dc3a39db9a","mcp_get_code":{"code_sha256":"752bd3dc3a39db9a"}},{"arxiv_id":"2501.00353","paper":"/paper/rag-instruct-boosting-llms-with-diverse","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","date":"2024-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/rag-instruct","path":"retrieval_lm/passage_retrieval.py","file_url":"https://github.com/freedomintelligence/rag-instruct/blob/HEAD/retrieval_lm/passage_retrieval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a08200e3e35e3bc","mcp_get_code":{"code_sha256":"0a08200e3e35e3bc"}},{"arxiv_id":"2411.08147","paper":"/paper/large-language-models-can-self-improve-in","title":"Large Language Models Can Self-Improve in Long-context Reasoning","date":"2024-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sihengli99/sealong","path":"process_data.py","file_url":"https://github.com/sihengli99/sealong/blob/HEAD/process_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bdc3d946a1bd95c1","mcp_get_code":{"code_sha256":"bdc3d946a1bd95c1"}},{"arxiv_id":"2406.07230","paper":"/paper/needle-in-a-multimodal-haystack","title":"Needle In A Multimodal Haystack","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/mm-niah","path":"visualization.py","file_url":"https://github.com/opengvlab/mm-niah/blob/HEAD/visualization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"28f7f0fe58d8ed3e","mcp_get_code":{"code_sha256":"28f7f0fe58d8ed3e"}},{"arxiv_id":"2312.15960","paper":"/paper/motcoder-elevating-large-language-models-with","title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","date":"2023-12-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/motcoder","path":"eval/vllm_fix.py","file_url":"https://github.com/dvlab-research/motcoder/blob/HEAD/eval/vllm_fix.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"258657af338c1b25","mcp_get_code":{"code_sha256":"258657af338c1b25"}},{"arxiv_id":"1912.05372","paper":"/paper/flaubert-unsupervised-language-model-pre","title":"FlauBERT: Unsupervised Language Model Pre-training for French","date":"2019-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TheophileBlard/french-sentiment-analysis-with-bert","path":"utils_acl.py","file_url":"https://github.com/TheophileBlard/french-sentiment-analysis-with-bert/blob/HEAD/utils_acl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fbdb4336ee093312","mcp_get_code":{"code_sha256":"fbdb4336ee093312"}},{"arxiv_id":"2025.findings-acl.150","paper":null,"title":"arXiv:2025.findings-acl.150","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Ymm-cll/NetSafe","path":"moderation.py","file_url":"https://github.com/Ymm-cll/NetSafe/blob/HEAD/moderation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ed4ba63a84cce1a","mcp_get_code":{"code_sha256":"3ed4ba63a84cce1a"}},{"arxiv_id":"2025.emnlp-main.192","paper":null,"title":"arXiv:2025.emnlp-main.192","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"FreedomIntelligence/RAG-Instruct","path":"retrieval_lm/passage_retrieval.py","file_url":"https://github.com/FreedomIntelligence/RAG-Instruct/blob/HEAD/retrieval_lm/passage_retrieval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a08200e3e35e3bc","mcp_get_code":{"code_sha256":"0a08200e3e35e3bc"}}]}