{"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-state","entry":"get_state","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":13,"n_papers_ran":7,"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":11,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":1,"ran":1,"unverified":6},"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":"2511.08043","paper":"/paper/arxiv-2511-08043","title":"DYNAACT: Large Language Model Reasoning with Dynamic Action Spaces","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"zhaoxlpku/DynaAct","path":"utils.py","file_url":"https://github.com/zhaoxlpku/DynaAct/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":"5e1f27c865cc2cc2","mcp_get_code":{"code_sha256":"5e1f27c865cc2cc2"}},{"arxiv_id":"2404.09349","paper":"/paper/adversarial-robustness-limits-via-scaling-law","title":"Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies","date":"2024-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bbartoldson/adversarial-robustness-limits","path":"submit.py","file_url":"https://github.com/bbartoldson/adversarial-robustness-limits/blob/HEAD/submit.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":"4fc810a6b13b1408","mcp_get_code":{"code_sha256":"4fc810a6b13b1408"}},{"arxiv_id":"2310.12565","paper":"/paper/open-world-lifelong-graph-learning","title":"Open-World Lifelong Graph Learning","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bobowner/open-world-lgl","path":"handle_meta_data.py","file_url":"https://github.com/bobowner/open-world-lgl/blob/HEAD/handle_meta_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d5ebd613cef4acf2","mcp_get_code":{"code_sha256":"d5ebd613cef4acf2"}},{"arxiv_id":"2307.07859","paper":"/paper/unified-adversarial-patch-for-cross-modal","title":"Unified Adversarial Patch for Cross-modal Attacks in the Physical World","date":"2023-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aries-iai/cross-modal_patch_attack","path":"spline_DE_attack.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/spline_DE_attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aab637864c086647","mcp_get_code":{"code_sha256":"aab637864c086647"}},{"arxiv_id":"2302.10342","paper":"/paper/fantastic-rewards-and-how-to-tame-them-a-case","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","date":"2023-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shentao-yang/fantastic_reward_iclr2023","path":"EstimateBehaviorPolicy.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/EstimateBehaviorPolicy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f76b00aa1bb20bf","mcp_get_code":{"code_sha256":"7f76b00aa1bb20bf"}},{"arxiv_id":"2205.14495","paper":"/paper/task-agnostic-continual-reinforcement","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","date":"2022-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-research/replay-based-recurrent-rl","path":"code/misc/torch_utility.py","file_url":"https://github.com/amazon-research/replay-based-recurrent-rl/blob/HEAD/code/misc/torch_utility.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":"a61f2ad7df535ba0","mcp_get_code":{"code_sha256":"a61f2ad7df535ba0"}},{"arxiv_id":"2110.01528","paper":"/paper/large-batch-experience-replay","title":"Large Batch Experience Replay","date":"2021-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sureli/laber","path":"MinAtar_experiments/agents/dqn_LABER.py","file_url":"https://github.com/sureli/laber/blob/HEAD/MinAtar_experiments/agents/dqn_LABER.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"acd5bcd47c0df9f6","mcp_get_code":{"code_sha256":"acd5bcd47c0df9f6"}},{"arxiv_id":"1903.03176","paper":"/paper/minatar-an-atari-inspired-testbed-for-more","title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","date":"2019-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"acd5bcd47c0df9f6","mcp_get_code":{"code_sha256":"acd5bcd47c0df9f6"}},{"arxiv_id":"1812.02690","paper":"/paper/provably-efficient-maximum-entropy","title":"Provably Efficient Maximum Entropy Exploration","date":"2018-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abbyvansoest/maxent","path":"ant/ant_soft_actor_critic.py","file_url":"https://github.com/abbyvansoest/maxent/blob/HEAD/ant/ant_soft_actor_critic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b35e42973a59560","mcp_get_code":{"code_sha256":"2b35e42973a59560"}},{"arxiv_id":"1806.01830","paper":"/paper/relational-deep-reinforcement-learning","title":"Relational Deep Reinforcement Learning","date":"2018-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicoladainese96/RelationalDeepRL","path":"Utils/train_agent.py","file_url":"https://github.com/nicoladainese96/RelationalDeepRL/blob/HEAD/Utils/train_agent.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":"2840e9977435e9ff","mcp_get_code":{"code_sha256":"2840e9977435e9ff"}},{"arxiv_id":"1705.03633","paper":"/paper/inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","date":"2017-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/clevr-iep","path":"scripts/train_model.py","file_url":"https://github.com/facebookresearch/clevr-iep/blob/HEAD/scripts/train_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"13ab7b9cc80a2b9b","mcp_get_code":{"code_sha256":"13ab7b9cc80a2b9b"}},{"arxiv_id":"1606.02396","paper":"/paper/deep-successor-reinforcement-learning","title":"Deep Successor Reinforcement Learning","date":"2016-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ardavans/DSR","path":"dsr/doom.py","file_url":"https://github.com/Ardavans/DSR/blob/HEAD/dsr/doom.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"734ef573d15eb87b","mcp_get_code":{"code_sha256":"734ef573d15eb87b"}},{"arxiv_id":"1207.4708","paper":"/paper/the-arcade-learning-environment-an-evaluation","title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","date":"2012-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"acd5bcd47c0df9f6","mcp_get_code":{"code_sha256":"acd5bcd47c0df9f6"}}]}