{"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/conjugate-gradients","entry":"conjugate_gradients","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":7,"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":6,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"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":"2606.10228","paper":"/paper/arxiv-2606-10228","title":"SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"montrealrobotics/shapo","path":"safepo/single_agent/shapo.py","file_url":"https://github.com/montrealrobotics/shapo/blob/HEAD/safepo/single_agent/shapo.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":"66ed7b1d9ea7acbc","mcp_get_code":{"code_sha256":"66ed7b1d9ea7acbc"}},{"arxiv_id":"2103.05910","paper":"/paper/learning-from-imperfect-demonstrations-from","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","date":"2021-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Stanford-ILIAD/Learn-Imperfect-Varying-Dynamics","path":"trpo.py","file_url":"https://github.com/Stanford-ILIAD/Learn-Imperfect-Varying-Dynamics/blob/HEAD/trpo.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"918891131c62a121","mcp_get_code":{"code_sha256":"918891131c62a121"}},{"arxiv_id":"2003.04108","paper":"/paper/stable-policy-optimization-via-off-policy","title":"Stable Policy Optimization via Off-Policy Divergence Regularization","date":"2020-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/ppo-dice","path":"trpo/opt.py","file_url":"https://github.com/facebookresearch/ppo-dice/blob/HEAD/trpo/opt.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"918891131c62a121","mcp_get_code":{"code_sha256":"918891131c62a121"}},{"arxiv_id":"1705.10528","paper":"/paper/constrained-policy-optimization","title":"Constrained Policy Optimization","date":"2017-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sapanachaudhary/pytorch-cpo","path":"algos/cpo.py","file_url":"https://github.com/sapanachaudhary/pytorch-cpo/blob/HEAD/algos/cpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aad2ffc14dc1c396","mcp_get_code":{"code_sha256":"aad2ffc14dc1c396"}},{"arxiv_id":"1609.04802","paper":"/paper/photo-realistic-single-image-super-resolution","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","date":"2016-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shirsenduhalder/SRResGAN-Improved-Perceptual","path":"basic_utils.py","file_url":"https://github.com/shirsenduhalder/SRResGAN-Improved-Perceptual/blob/HEAD/basic_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d594866e7355287","mcp_get_code":{"code_sha256":"2d594866e7355287"}},{"arxiv_id":"1502.05477","paper":"/paper/trust-region-policy-optimization","title":"Trust Region Policy Optimization","date":"2015-02-19","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":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"918891131c62a121","mcp_get_code":{"code_sha256":"918891131c62a121"}},{"arxiv_id":"1502.05477","paper":"/paper/trust-region-policy-optimization","title":"Trust Region Policy Optimization","date":"2015-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Khrylx/PyTorch-RL","path":"core/trpo.py","file_url":"https://github.com/Khrylx/PyTorch-RL/blob/HEAD/core/trpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8946170b041be61b","mcp_get_code":{"code_sha256":"8946170b041be61b"}},{"arxiv_id":"aaai_16817","paper":null,"title":"arXiv:aaai_16817","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Akella17/Deep-Bayesian-Quadrature-Policy-Optimization","path":"optimization.py","file_url":"https://github.com/Akella17/Deep-Bayesian-Quadrature-Policy-Optimization/blob/HEAD/optimization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac81cfb2bd5616e5","mcp_get_code":{"code_sha256":"ac81cfb2bd5616e5"}}]}