{"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/em-2","entry":"EM","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":6,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2410.06617","paper":"/paper/learning-evolving-tools-for-large-language","title":"Learning Evolving Tools for Large Language Models","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Chen-GX/ToolEVO","path":"MCTS/src/evaluation.py","file_url":"https://github.com/Chen-GX/ToolEVO/blob/HEAD/MCTS/src/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21aa81edfe5a0c85","mcp_get_code":{"code_sha256":"21aa81edfe5a0c85"}},{"arxiv_id":"2403.00843","paper":"/paper/enhancing-long-term-recommendation-with-bi","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jizhi-zhang/billp","path":"Agents/agent_reflexion.py","file_url":"https://github.com/jizhi-zhang/billp/blob/HEAD/Agents/agent_reflexion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20c8a77ea03b234c","mcp_get_code":{"code_sha256":"20c8a77ea03b234c"}},{"arxiv_id":"2402.03659","paper":"/paper/learning-to-generate-explainable-stock","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"koa-fin/sep","path":"explain_module/agents.py","file_url":"https://github.com/koa-fin/sep/blob/HEAD/explain_module/agents.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6296f4fd5cc3db50","mcp_get_code":{"code_sha256":"6296f4fd5cc3db50"}},{"arxiv_id":"2306.13304","paper":"/paper/toolqa-a-dataset-for-llm-question-answering-1","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","date":"2023-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"night-chen/toolqa","path":"benchmark/ReAct/code/environment.py","file_url":"https://github.com/night-chen/toolqa/blob/HEAD/benchmark/ReAct/code/environment.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":"898fb37499d60ace","mcp_get_code":{"code_sha256":"898fb37499d60ace"}},{"arxiv_id":"2303.11366","paper":"/paper/reflexion-language-agents-with-verbal","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","date":"2023-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noahshinn/reflexion","path":"hotpotqa_runs/environment.py","file_url":"https://github.com/noahshinn/reflexion/blob/HEAD/hotpotqa_runs/environment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f79fe1ce6d553fa","mcp_get_code":{"code_sha256":"6f79fe1ce6d553fa"}},{"arxiv_id":"1908.11515","paper":"/paper/practical-and-robust-privacy-amplification","title":"Improving Utility and Security of the Shuffler-based Differential Privacy","date":"2019-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vvv214/LDP_Protocols","path":"sw.py","file_url":"https://github.com/vvv214/LDP_Protocols/blob/HEAD/sw.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a132c0ee784427bc","mcp_get_code":{"code_sha256":"a132c0ee784427bc"}}]}