{"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/format-step","entry":"format_step","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":10,"n_papers_ran":9,"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":5,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":10,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":1},"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":"2606.11063","paper":"/paper/arxiv-2606-11063","title":"CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"JoachimSchaeffer/CIAware-Bench","path":"cia/analysis/compare_interventions.py","file_url":"https://github.com/JoachimSchaeffer/CIAware-Bench/blob/HEAD/cia/analysis/compare_interventions.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fe9897f7e960225f","mcp_get_code":{"code_sha256":"fe9897f7e960225f"}},{"arxiv_id":"2403.03101","paper":"/paper/knowagent-knowledge-augmented-planning-for","title":"KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents","date":"2024-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/knowagent","path":"Path_Generation/hotpotqa_run/agent_arch.py","file_url":"https://github.com/zjunlp/knowagent/blob/HEAD/Path_Generation/hotpotqa_run/agent_arch.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":"84d28fbaf38b0a59","mcp_get_code":{"code_sha256":"84d28fbaf38b0a59"}},{"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_a2c.py","file_url":"https://github.com/jizhi-zhang/billp/blob/HEAD/Agents/agent_a2c.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7aa38bfabee25462","mcp_get_code":{"code_sha256":"7aa38bfabee25462"}},{"arxiv_id":"2402.14963","paper":"/paper/mirror-a-multiple-perspective-self-reflection","title":"Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanqi-qi/mirror","path":"agents_module.py","file_url":"https://github.com/hanqi-qi/mirror/blob/HEAD/agents_module.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":"84d28fbaf38b0a59","mcp_get_code":{"code_sha256":"84d28fbaf38b0a59"}},{"arxiv_id":"2402.01622","paper":"/paper/travelplanner-a-benchmark-for-real-world","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OSU-NLP-Group/TravelPlanner","path":"agents/tool_agents.py","file_url":"https://github.com/OSU-NLP-Group/TravelPlanner/blob/HEAD/agents/tool_agents.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":"84d28fbaf38b0a59","mcp_get_code":{"code_sha256":"84d28fbaf38b0a59"}},{"arxiv_id":"2401.05268","paper":"/paper/autoact-automatic-agent-learning-from-scratch","title":"AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning","date":"2024-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/autoact","path":"Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f62e3ab05a2163b7","mcp_get_code":{"code_sha256":"f62e3ab05a2163b7"}},{"arxiv_id":"2308.05960","paper":"/paper/bolaa-benchmarking-and-orchestrating-llm","title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/bolaa","path":"hotpotqa_run/agent_arch.py","file_url":"https://github.com/salesforce/bolaa/blob/HEAD/hotpotqa_run/agent_arch.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":"84d28fbaf38b0a59","mcp_get_code":{"code_sha256":"84d28fbaf38b0a59"}},{"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/agents.py","file_url":"https://github.com/night-chen/toolqa/blob/HEAD/benchmark/ReAct/code/agents.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":"84d28fbaf38b0a59","mcp_get_code":{"code_sha256":"84d28fbaf38b0a59"}},{"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/agents.py","file_url":"https://github.com/noahshinn/reflexion/blob/HEAD/hotpotqa_runs/agents.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":"84d28fbaf38b0a59","mcp_get_code":{"code_sha256":"84d28fbaf38b0a59"}},{"arxiv_id":"2203.04570","paper":"/paper/cp-vit-cascade-vision-transformer-pruning-via","title":"CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction","date":"2022-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ok858ok/CP-ViT","path":"CP-ViT/utils/dist_util.py","file_url":"https://github.com/ok858ok/CP-ViT/blob/HEAD/CP-ViT/utils/dist_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c60b852fb7e92a0d","mcp_get_code":{"code_sha256":"c60b852fb7e92a0d"}}]}