{"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-policy","entry":"get_policy","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":4,"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":4,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":1,"unverified":4},"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":"2311.13569","paper":"/paper/combinatorial-optimization-with-policy","title":"Combinatorial Optimization with Policy Adaptation using Latent Space Search","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"instadeepai/compass","path":"compass/trainers/trainer_utils.py","file_url":"https://github.com/instadeepai/compass/blob/HEAD/compass/trainers/trainer_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1a99ce058696a299","mcp_get_code":{"code_sha256":"1a99ce058696a299"}},{"arxiv_id":"2304.04858","paper":"/paper/simulated-annealing-in-early-layers-leads-to","title":"Simulated Annealing in Early Layers Leads to Better Generalization","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amiiir-sarfi/seal","path":"core.py","file_url":"https://github.com/amiiir-sarfi/seal/blob/HEAD/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"84121d5fa2d05bf2","mcp_get_code":{"code_sha256":"84121d5fa2d05bf2"}},{"arxiv_id":"2304.04782","paper":"/paper/reinforcement-learning-from-passive-data-via","title":"Reinforcement Learning from Passive Data via Latent Intentions","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dibyaghosh/icvf_release","path":"experiments/antmaze/train_icvf.py","file_url":"https://github.com/dibyaghosh/icvf_release/blob/HEAD/experiments/antmaze/train_icvf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7efb230a126ddd62","mcp_get_code":{"code_sha256":"7efb230a126ddd62"}},{"arxiv_id":"2106.05087","paper":"/paper/who-is-the-strongest-enemy-towards-optimal","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/paad_adv_rl","path":"code_atari/paad_rl/trainer_adv/a2c_pa_attacker.py","file_url":"https://github.com/umd-huang-lab/paad_adv_rl/blob/HEAD/code_atari/paad_rl/trainer_adv/a2c_pa_attacker.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf1679c31b6bfadf","mcp_get_code":{"code_sha256":"bf1679c31b6bfadf"}},{"arxiv_id":"2103.05152","paper":"/paper/knowledge-evolution-in-neural-networks","title":"Knowledge Evolution in Neural Networks","date":"2021-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahmdtaha/knowledge_evolution","path":"KE_model.py","file_url":"https://github.com/ahmdtaha/knowledge_evolution/blob/HEAD/KE_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"680e25d1c3bf5523","mcp_get_code":{"code_sha256":"680e25d1c3bf5523"}},{"arxiv_id":"2004.14288","paper":"/paper/actor-critic-reinforcement-learning-for","title":"Actor-Critic Reinforcement Learning for Control with Stability Guarantee","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hithmh/Actor-critic-with-stability-guarantee","path":"variant.py","file_url":"https://github.com/hithmh/Actor-critic-with-stability-guarantee/blob/HEAD/variant.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e452799839fcb1c2","mcp_get_code":{"code_sha256":"e452799839fcb1c2"}},{"arxiv_id":"1904.09728","paper":"/paper/socialiqa-commonsense-reasoning-about-social","title":"SocialIQA: Commonsense Reasoning about Social Interactions","date":"2019-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clear-nus/llm-human-model","path":"table_clearing/table_clearing_trust_pomdp/evaluate/llm_policy.py","file_url":"https://github.com/clear-nus/llm-human-model/blob/HEAD/table_clearing/table_clearing_trust_pomdp/evaluate/llm_policy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f5e0055352d005b6","mcp_get_code":{"code_sha256":"f5e0055352d005b6"}},{"arxiv_id":"1710.03740","paper":"/paper/mixed-precision-training","title":"Mixed Precision Training","date":"2017-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmind/jmp","path":"jmp/_src/policy.py","file_url":"https://github.com/deepmind/jmp/blob/HEAD/jmp/_src/policy.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":"6fcfc8688017b242","mcp_get_code":{"code_sha256":"6fcfc8688017b242"}}]}