{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/conjugate-gradient","entry":"conjugate_gradient","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":12,"n_papers_ran":10,"n_papers_ran_no_instrument_failure":5,"n_papers_ran_instrument_only":5,"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":12,"n_samples_ran":10,"n_samples_constructed":0,"n_samples_ran_checked":5,"n_samples_instrument":5,"n_samples_unverified":2,"n_samples_fingerprinted":1,"n_places":13,"n_places_pointer_only":3,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":2,"ran":5,"unverified":2},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2605.18591","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-18591","title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"agent-lab/ICML2026-RAT","path":"utils/cg.py","file_url":"https://github.com/agent-lab/ICML2026-RAT/blob/HEAD/utils/cg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"30a3ae0cf5fb6225","code_sha256_prefix":"30a3ae0cf5fb6225","mcp_get_code":{"code_sha256":"30a3ae0cf5fb6225"}},{"arxiv_id":"2604.22893","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-22893","title":"Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"BDS-SDU/utility-aware-data-pricing","path":"data_pricing/valuation.py","file_url":"https://github.com/BDS-SDU/utility-aware-data-pricing/blob/HEAD/data_pricing/valuation.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b53e5c166ea9d86c","code_sha256_prefix":"b53e5c166ea9d86c","mcp_get_code":{"code_sha256":"b53e5c166ea9d86c"}},{"arxiv_id":"2409.05208","arxiv_id_is_arxiv":true,"paper":"/paper/influence-based-attributions-can-be","title":"Influence-based Attributions can be Manipulated","date":"2024-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"infinite-pursuits/influence-based-attributions-can-be-manipulated","path":"downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","file_url":"https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated/blob/HEAD/downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, infinite-pursuits/influence-based-attributions-can-be-manipulated when it was checked","code_sha256":"f4c9f096d90e61e3","code_sha256_prefix":"f4c9f096d90e61e3","mcp_get_code":{"code_sha256":"f4c9f096d90e61e3"}},{"arxiv_id":"2310.10603","arxiv_id_is_arxiv":true,"paper":"/paper/exploring-the-power-of-graph-neural-networks","title":"Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chendiqian/IPM_MPNN","path":"solver/customized_solver.py","file_url":"https://github.com/chendiqian/IPM_MPNN/blob/HEAD/solver/customized_solver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, chendiqian/IPM_MPNN when it was checked","code_sha256":"7955265e3c15e7cf","code_sha256_prefix":"7955265e3c15e7cf","mcp_get_code":{"code_sha256":"7955265e3c15e7cf"}},{"arxiv_id":"2305.16368","arxiv_id_is_arxiv":true,"paper":"/paper/neural-incomplete-factorization-learning","title":"Neural incomplete factorization: learning preconditioners for the conjugate gradient method","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paulhausner/neural-incomplete-factorization","path":"krylov/cg.py","file_url":"https://github.com/paulhausner/neural-incomplete-factorization/blob/HEAD/krylov/cg.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b79bc91c137be572","code_sha256_prefix":"b79bc91c137be572","mcp_get_code":{"code_sha256":"b79bc91c137be572"}},{"arxiv_id":"2204.03640","arxiv_id_is_arxiv":true,"paper":"/paper/equivariance-discovery-by-learned-parameter","title":"Equivariance Discovery by Learned Parameter-Sharing","date":"2022-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raymondyeh07/equivariance_discovery","path":"struct_discovery/solver/hypergrad/conjugate_gradient.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/solver/hypergrad/conjugate_gradient.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a74effb2b7707ed5","code_sha256_prefix":"a74effb2b7707ed5","mcp_get_code":{"code_sha256":"a74effb2b7707ed5"}},{"arxiv_id":"2109.12286","arxiv_id_is_arxiv":true,"paper":"/paper/stackelberg-actor-critic-game-theoretic","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","date":"2021-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leozhengzly/stackelberg-actor-critic-algos","path":"spinup/algos/pytorch/stddpg/stddpg.py","file_url":"https://github.com/leozhengzly/stackelberg-actor-critic-algos/blob/HEAD/spinup/algos/pytorch/stddpg/stddpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":false,"withheld_clause":"MIT, as GitHub detects it on this paper's repository, leozhengzly/stackelberg-actor-critic-algos, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","code_sha256":"aeec4c7d37de2213","code_sha256_prefix":"aeec4c7d37de2213","mcp_get_code":{"code_sha256":"aeec4c7d37de2213"}},{"arxiv_id":"2106.04753","arxiv_id_is_arxiv":true,"paper":"/paper/on-sample-based-explanation-methods-for-nlp","title":"On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/TracInF","path":"code/pif/influence_functions/hvp_grad.py","file_url":"https://github.com/IBM/TracInF/blob/HEAD/code/pif/influence_functions/hvp_grad.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f4c9f096d90e61e3","code_sha256_prefix":"f4c9f096d90e61e3","mcp_get_code":{"code_sha256":"f4c9f096d90e61e3"}},{"arxiv_id":"2006.10611","arxiv_id_is_arxiv":true,"paper":"/paper/competitive-policy-optimization","title":"Competitive Policy Optimization","date":"2020-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manish-pra/copg","path":"copg_optim/utils.py","file_url":"https://github.com/manish-pra/copg/blob/HEAD/copg_optim/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e32c644998154590","code_sha256_prefix":"e32c644998154590","mcp_get_code":{"code_sha256":"e32c644998154590"}},{"arxiv_id":"2005.10099","arxiv_id_is_arxiv":true,"paper":"/paper/nonparametric-score-estimators","title":"Nonparametric Score Estimators","date":"2020-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miskcoo/kscore","path":"kscore/estimators/tikhonov.py","file_url":"https://github.com/miskcoo/kscore/blob/HEAD/kscore/estimators/tikhonov.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"8a283ce3ca6eff56","code_sha256_prefix":"8a283ce3ca6eff56","mcp_get_code":{"code_sha256":"8a283ce3ca6eff56"}},{"arxiv_id":"1803.06396","arxiv_id_is_arxiv":true,"paper":"/paper/reviving-and-improving-recurrent-back","title":"Reviving and Improving Recurrent Back-Propagation","date":"2018-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lrjconan/RBP","path":"utils/model_helper.py","file_url":"https://github.com/lrjconan/RBP/blob/HEAD/utils/model_helper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"7cfbfdb527b1aff5","code_sha256_prefix":"7cfbfdb527b1aff5","mcp_get_code":{"code_sha256":"7cfbfdb527b1aff5"}},{"arxiv_id":"1703.03400","arxiv_id_is_arxiv":true,"paper":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-larx/attack_metarl","path":"maml_rl/metalearners/maml_trpo.py","file_url":"https://github.com/nyu-larx/attack_metarl/blob/HEAD/maml_rl/metalearners/maml_trpo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c4daaf04c83ccbd2","code_sha256_prefix":"c4daaf04c83ccbd2","mcp_get_code":{"code_sha256":"c4daaf04c83ccbd2"}},{"arxiv_id":"1703.03400","arxiv_id_is_arxiv":true,"paper":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MoritzTaylor/maml-rl-tf2","path":"maml_rl/optimizers/conjugate_gradient_optimizer.py","file_url":"https://github.com/MoritzTaylor/maml-rl-tf2/blob/HEAD/maml_rl/optimizers/conjugate_gradient_optimizer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"fa6e636313bab28d","code_sha256_prefix":"fa6e636313bab28d","mcp_get_code":{"code_sha256":"fa6e636313bab28d"}}],"record_sha256":"e31119e71194c9555ddfe5cf3a85132cf464704c66f9a94cb0f73f61266139cd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}