{"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/get-query","entry":"get_query","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":19,"n_papers_ran":14,"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":5,"n_samples_fingerprinted":2,"n_places":22,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":1,"ran":1,"unverified":7},"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":"2603.03292","paper":"/paper/arxiv-2603-03292","title":"From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"NJU-RL/MA-RAG","path":"utils.py","file_url":"https://github.com/NJU-RL/MA-RAG/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c0aed1d15d52f57","mcp_get_code":{"code_sha256":"4c0aed1d15d52f57"}},{"arxiv_id":"2602.04417","paper":"/paper/arxiv-2602-04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"LunjunZhang/ema-pg","path":"search/infer.py","file_url":"https://github.com/LunjunZhang/ema-pg/blob/HEAD/search/infer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8709b4b7236b87d7","mcp_get_code":{"code_sha256":"8709b4b7236b87d7"}},{"arxiv_id":"2601.14896","paper":"/paper/arxiv-2601-14896","title":"Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Cherry-qwq/LcRL-Open","path":"infer.py","file_url":"https://github.com/Cherry-qwq/LcRL-Open/blob/HEAD/infer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8709b4b7236b87d7","mcp_get_code":{"code_sha256":"8709b4b7236b87d7"}},{"arxiv_id":"2510.25808","paper":"/paper/arxiv-2510-25808","title":"PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"mlvlab/PRESTO","path":"Induction/automatic_prompt_engineer/generate.py","file_url":"https://github.com/mlvlab/PRESTO/blob/HEAD/Induction/automatic_prompt_engineer/generate.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":"71e7c70faf29eeee","mcp_get_code":{"code_sha256":"71e7c70faf29eeee"}},{"arxiv_id":"2510.25808","paper":"/paper/arxiv-2510-25808","title":"PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"mlvlab/PRESTO","path":"Induction/experiments/evaluation/instruction_induction/exec_accuracy.py","file_url":"https://github.com/mlvlab/PRESTO/blob/HEAD/Induction/experiments/evaluation/instruction_induction/exec_accuracy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9475219c55847f4d","mcp_get_code":{"code_sha256":"9475219c55847f4d"}},{"arxiv_id":"2507.11275","paper":null,"title":"arXiv:2507.11275","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"JadeXie1205/FMC","path":"autoformalization_pipeline/nli.py","file_url":"https://github.com/JadeXie1205/FMC/blob/HEAD/autoformalization_pipeline/nli.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":"09b53e19654743bd","mcp_get_code":{"code_sha256":"09b53e19654743bd"}},{"arxiv_id":"2507.11275","paper":null,"title":"arXiv:2507.11275","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"JadeXie1205/FMC","path":"autoformalization_pipeline/translate.py","file_url":"https://github.com/JadeXie1205/FMC/blob/HEAD/autoformalization_pipeline/translate.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":"4ca3cf4c670997b9","mcp_get_code":{"code_sha256":"4ca3cf4c670997b9"}},{"arxiv_id":"2506.09033","paper":"/paper/router-r1-teaching-llms-multi-round-routing","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ulab-uiuc/Router-R1","path":"infer_vllm.py","file_url":"https://github.com/ulab-uiuc/Router-R1/blob/HEAD/infer_vllm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"96a56033ae39159f","mcp_get_code":{"code_sha256":"96a56033ae39159f"}},{"arxiv_id":"2505.15117","paper":"/paper/an-empirical-study-on-reinforcement-learning","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"8709b4b7236b87d7","mcp_get_code":{"code_sha256":"8709b4b7236b87d7"}},{"arxiv_id":"2505.07596","paper":"/paper/reinforced-internal-external-knowledge","title":"Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hzy312/knowledge-r1","path":"infer.py","file_url":"https://github.com/hzy312/knowledge-r1/blob/HEAD/infer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8709b4b7236b87d7","mcp_get_code":{"code_sha256":"8709b4b7236b87d7"}},{"arxiv_id":"2505.04588","paper":"/paper/zerosearch-incentivize-the-search-capability","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","date":"2025-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-nlp/zerosearch","path":"inference.py","file_url":"https://github.com/alibaba-nlp/zerosearch/blob/HEAD/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8709b4b7236b87d7","mcp_get_code":{"code_sha256":"8709b4b7236b87d7"}},{"arxiv_id":"2503.09516","paper":"/paper/search-r1-training-llms-to-reason-and","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"8709b4b7236b87d7","mcp_get_code":{"code_sha256":"8709b4b7236b87d7"}},{"arxiv_id":"2405.17346","paper":"/paper/prompt-optimization-with-human-feedback","title":"Prompt Optimization with Human Feedback","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xqlin98/apohf","path":"Induction/automatic_prompt_engineer/generate.py","file_url":"https://github.com/xqlin98/apohf/blob/HEAD/Induction/automatic_prompt_engineer/generate.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":"71e7c70faf29eeee","mcp_get_code":{"code_sha256":"71e7c70faf29eeee"}},{"arxiv_id":"2405.17346","paper":"/paper/prompt-optimization-with-human-feedback","title":"Prompt Optimization with Human Feedback","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xqlin98/apohf","path":"Induction/experiments/evaluation/instruction_induction/exec_accuracy.py","file_url":"https://github.com/xqlin98/apohf/blob/HEAD/Induction/experiments/evaluation/instruction_induction/exec_accuracy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9475219c55847f4d","mcp_get_code":{"code_sha256":"9475219c55847f4d"}},{"arxiv_id":"2405.02814","paper":"/paper/negativeprompt-leveraging-psychology-for","title":"NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli","date":"2024-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangxu0820/NegativePrompt","path":"exec_accuracy.py","file_url":"https://github.com/wangxu0820/NegativePrompt/blob/HEAD/exec_accuracy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d1cc7c58c450ad86","mcp_get_code":{"code_sha256":"d1cc7c58c450ad86"}},{"arxiv_id":"2403.07773","paper":"/paper/semcity-semantic-scene-generation-with","title":"SemCity: Semantic Scene Generation with Triplane Diffusion","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zoomin-lee/semcity","path":"dataset/kitti_dataset.py","file_url":"https://github.com/zoomin-lee/semcity/blob/HEAD/dataset/kitti_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a009f7bfad56ea2","mcp_get_code":{"code_sha256":"9a009f7bfad56ea2"}},{"arxiv_id":"2310.02905","paper":"/paper/use-your-instinct-instruction-optimization","title":"Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xqlin98/INSTINCT","path":"COT/automatic_prompt_engineer/generate.py","file_url":"https://github.com/xqlin98/INSTINCT/blob/HEAD/COT/automatic_prompt_engineer/generate.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":"71e7c70faf29eeee","mcp_get_code":{"code_sha256":"71e7c70faf29eeee"}},{"arxiv_id":"2306.03082","paper":"/paper/instructzero-efficient-instruction","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lichang-chen/instructzero","path":"InstructZero/experiments/automatic_prompt_engineer/generate.py","file_url":"https://github.com/lichang-chen/instructzero/blob/HEAD/InstructZero/experiments/automatic_prompt_engineer/generate.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":"71e7c70faf29eeee","mcp_get_code":{"code_sha256":"71e7c70faf29eeee"}},{"arxiv_id":"2205.10186","paper":"/paper/bayesian-active-learning-with-fully-bayesian-1","title":"Bayesian Active Learning with Fully Bayesian Gaussian Processes","date":"2022-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"coriis/active-learning-fbgp","path":"utils/active_learning.py","file_url":"https://github.com/coriis/active-learning-fbgp/blob/HEAD/utils/active_learning.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"3fbc8ed21ce1e422","mcp_get_code":{"code_sha256":"3fbc8ed21ce1e422"}},{"arxiv_id":"2106.09179","paper":"/paper/amortized-auto-tuning-cost-efficient-transfer","title":"Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaoyuxin1002/amortized-auto-tuning","path":"code/util.py","file_url":"https://github.com/xiaoyuxin1002/amortized-auto-tuning/blob/HEAD/code/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a17d6a46039e7358","mcp_get_code":{"code_sha256":"a17d6a46039e7358"}},{"arxiv_id":"2025.emnlp-main.965","paper":null,"title":"arXiv:2025.emnlp-main.965","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"salmakh1/ACING","path":"Induction/automatic_prompt_engineer/generate.py","file_url":"https://github.com/salmakh1/ACING/blob/HEAD/Induction/automatic_prompt_engineer/generate.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":"71e7c70faf29eeee","mcp_get_code":{"code_sha256":"71e7c70faf29eeee"}},{"arxiv_id":"2024.findings-emnlp.927","paper":null,"title":"arXiv:2024.findings-emnlp.927","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hwy9855/GSR","path":"src/preprocess/get_freebase_examples.py","file_url":"https://github.com/hwy9855/GSR/blob/HEAD/src/preprocess/get_freebase_examples.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa6b3768fa0972c3","mcp_get_code":{"code_sha256":"aa6b3768fa0972c3"}}]}