{"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/verify","entry":"verify","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":8,"n_papers_ran":1,"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":8,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"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":"2607.11506","paper":"/paper/arxiv-2607-11506","title":"SCOPE-RL: Optimizing Reasoning Paths Before and After Success","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"tokencraft-lab/SCOPE-RL","path":"verl/recipe/scope_rl/reward_score/step_quality.py","file_url":"https://github.com/tokencraft-lab/SCOPE-RL/blob/HEAD/verl/recipe/scope_rl/reward_score/step_quality.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8ba769426b876be2","mcp_get_code":{"code_sha256":"8ba769426b876be2"}},{"arxiv_id":"2605.26971","paper":"/paper/arxiv-2605-26971","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Celine-hxy/ATLAS","path":"verl/verl/utils/reward_score/math_dapo.py","file_url":"https://github.com/Celine-hxy/ATLAS/blob/HEAD/verl/verl/utils/reward_score/math_dapo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8df35abb6563b077","mcp_get_code":{"code_sha256":"8df35abb6563b077"}},{"arxiv_id":"2506.07972","paper":"/paper/heurigym-an-agentic-benchmark-for-llm-crafted","title":"HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cornell-zhang/heurigym","path":"egraph_extraction/program/verifier.py","file_url":"https://github.com/cornell-zhang/heurigym/blob/HEAD/egraph_extraction/program/verifier.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":"4fa724a25bba66d7","mcp_get_code":{"code_sha256":"4fa724a25bba66d7"}},{"arxiv_id":"2504.19298","paper":"/paper/androidgen-building-an-android-language-agent","title":"AndroidGen: Building an Android Language Agent under Data Scarcity","date":"2025-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/AndroidGen","path":"model/judge/judge.py","file_url":"https://github.com/THUDM/AndroidGen/blob/HEAD/model/judge/judge.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":"142a9897a3c875e4","mcp_get_code":{"code_sha256":"142a9897a3c875e4"}},{"arxiv_id":"2410.05165","paper":"/paper/efficient-inference-for-large-language-model","title":"Efficient Inference for Large Language Model-based Generative Recommendation","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Linxyhaha/AtSpeed","path":"code/beamSD.py","file_url":"https://github.com/Linxyhaha/AtSpeed/blob/HEAD/code/beamSD.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f10b46ee09ea6eb9","mcp_get_code":{"code_sha256":"f10b46ee09ea6eb9"}},{"arxiv_id":"2404.04815","paper":"/paper/allo-a-programming-model-for-composable","title":"Allo: A Programming Model for Composable Accelerator Design","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cornell-zhang/allo","path":"allo/verify.py","file_url":"https://github.com/cornell-zhang/allo/blob/HEAD/allo/verify.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":"aa240a45a4e178b7","mcp_get_code":{"code_sha256":"aa240a45a4e178b7"}},{"arxiv_id":"2210.03629","paper":"/paper/react-synergizing-reasoning-and-acting-in","title":"ReAct: Synergizing Reasoning and Acting in Language Models","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sierra-research/tau-bench","path":"tau_bench/agents/chat_react_agent.py","file_url":"https://github.com/sierra-research/tau-bench/blob/HEAD/tau_bench/agents/chat_react_agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0ead272d4fc4589","mcp_get_code":{"code_sha256":"e0ead272d4fc4589"}},{"arxiv_id":"1710.10766","paper":"/paper/pixeldefend-leveraging-generative-models-to","title":"PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Microsoft/PixelDefend","path":"utils.py","file_url":"https://github.com/Microsoft/PixelDefend/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b84804b8fc540494","mcp_get_code":{"code_sha256":"b84804b8fc540494"}}]}