{"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/grad","entry":"grad","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":23,"n_papers_ran":8,"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":20,"n_samples_ran":9,"n_samples_fingerprinted":4,"n_places":25,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":3,"ran_fixture":2,"ran":3,"unverified":11},"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":"2506.05454","paper":"/paper/zeroth-order-optimization-finds-flat-minima","title":"Zeroth-Order Optimization Finds Flat Minima","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Liang137/FlatZero","path":"test_func/run_toy.py","file_url":"https://github.com/Liang137/FlatZero/blob/HEAD/test_func/run_toy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f05d08ea970e9e2f","mcp_get_code":{"code_sha256":"f05d08ea970e9e2f"}},{"arxiv_id":"2409.17880","paper":"/paper/self-distilled-depth-refinement-with-noisy","title":"Self-Distilled Depth Refinement with Noisy Poisson Fusion","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lijia7/sddr","path":"utils/loss.py","file_url":"https://github.com/lijia7/sddr/blob/HEAD/utils/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc7d07b4f4b62c14","mcp_get_code":{"code_sha256":"fc7d07b4f4b62c14"}},{"arxiv_id":"2403.12309","paper":"/paper/reinforcement-learning-from-delayed","title":"Reinforcement Learning from Delayed Observations via World Models","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"indylab/delayeddreamer","path":"dreamerv3/ninjax.py","file_url":"https://github.com/indylab/delayeddreamer/blob/HEAD/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ad869363216c281","mcp_get_code":{"code_sha256":"1ad869363216c281"}},{"arxiv_id":"2403.04253","paper":"/paper/mastering-memory-tasks-with-world-models","title":"Mastering Memory Tasks with World Models","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chandar-lab/Recall2Imagine","path":"recall2imagine/ninjax.py","file_url":"https://github.com/chandar-lab/Recall2Imagine/blob/HEAD/recall2imagine/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ad869363216c281","mcp_get_code":{"code_sha256":"1ad869363216c281"}},{"arxiv_id":"2402.11173","paper":"/paper/how-to-make-the-gradients-small-privately","title":"How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lowya/how-to-make-the-gradients-small-privately","path":"mod_smallgradients_trig_icml24_V3.py","file_url":"https://github.com/lowya/how-to-make-the-gradients-small-privately/blob/HEAD/mod_smallgradients_trig_icml24_V3.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"5d5c9ec5efaf2f23","mcp_get_code":{"code_sha256":"5d5c9ec5efaf2f23"}},{"arxiv_id":"2310.00344","paper":"/paper/harmony-world-models-boosting-sample","title":"HarmonyDream: Task Harmonization Inside World Models","date":"2023-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/HarmonyDream","path":"dreamerv3-jax/dreamerv3/ninjax.py","file_url":"https://github.com/thuml/HarmonyDream/blob/HEAD/dreamerv3-jax/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ad869363216c281","mcp_get_code":{"code_sha256":"1ad869363216c281"}},{"arxiv_id":"2307.07176","paper":"/paper/safe-dreamerv3-safe-reinforcement-learning","title":"SafeDreamer: Safe Reinforcement Learning with World Models","date":"2023-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-Alignment/SafeDreamer","path":"SafeDreamer/ninjax.py","file_url":"https://github.com/PKU-Alignment/SafeDreamer/blob/HEAD/SafeDreamer/ninjax.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":"1ad869363216c281","mcp_get_code":{"code_sha256":"1ad869363216c281"}},{"arxiv_id":"2306.11488","paper":"/paper/informed-pomdp-leveraging-additional","title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"glambrechts/informed-dreamer","path":"dreamerv3/ninjax.py","file_url":"https://github.com/glambrechts/informed-dreamer/blob/HEAD/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ad869363216c281","mcp_get_code":{"code_sha256":"1ad869363216c281"}},{"arxiv_id":"2306.01794","paper":"/paper/diffpack-a-torsional-diffusion-model-for","title":"DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DeepGraphLearning/DiffPack","path":"diffpack/schedule.py","file_url":"https://github.com/DeepGraphLearning/DiffPack/blob/HEAD/diffpack/schedule.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35d120ffc51b9534","mcp_get_code":{"code_sha256":"35d120ffc51b9534"}},{"arxiv_id":"2305.17945","paper":"/paper/communication-efficient-distributed-newton-1","title":"Communication Efficient Distributed Newton Method with Fast Convergence Rates","date":null,"month_inferred_from_arxiv_id":"2023-05","title_source":"archive","repo":"7ccliu/c2eden","path":"a9a.convex.py","file_url":"https://github.com/7ccliu/c2eden/blob/HEAD/a9a.convex.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"92fe91e9375f75e3","mcp_get_code":{"code_sha256":"92fe91e9375f75e3"}},{"arxiv_id":"2305.17945","paper":"/paper/communication-efficient-distributed-newton-1","title":"Communication Efficient Distributed Newton Method with Fast Convergence Rates","date":null,"month_inferred_from_arxiv_id":"2023-05","title_source":"archive","repo":"7ccliu/c2eden","path":"a9a.nonconvex.py","file_url":"https://github.com/7ccliu/c2eden/blob/HEAD/a9a.nonconvex.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"756164c90fc0bde4","mcp_get_code":{"code_sha256":"756164c90fc0bde4"}},{"arxiv_id":"2305.14343","paper":"/paper/video-prediction-models-as-rewards-for","title":"Video Prediction Models as Rewards for Reinforcement Learning","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alescontrela/viper_rl","path":"viper_rl/dreamerv3/ninjax.py","file_url":"https://github.com/Alescontrela/viper_rl/blob/HEAD/viper_rl/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"afd5fe78d3d65a81","mcp_get_code":{"code_sha256":"afd5fe78d3d65a81"}},{"arxiv_id":"2303.03226","paper":"/paper/safe-reinforcement-learning-via-probabilistic","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","date":"2023-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sacktock/ambs","path":"dreamerV3-base/ninjax.py","file_url":"https://github.com/sacktock/ambs/blob/HEAD/dreamerV3-base/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ad869363216c281","mcp_get_code":{"code_sha256":"1ad869363216c281"}},{"arxiv_id":"2206.09909","paper":"/paper/low-precision-stochastic-gradient-langevin-1","title":"Low-Precision Stochastic Gradient Langevin Dynamics","date":"2022-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruqizhang/low-precision-sgld","path":"gaussian/gaussian.py","file_url":"https://github.com/ruqizhang/low-precision-sgld/blob/HEAD/gaussian/gaussian.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0f4ae257ee7047a9","mcp_get_code":{"code_sha256":"0f4ae257ee7047a9"}},{"arxiv_id":"2206.07767","paper":"/paper/kantorovich-strikes-back-wasserstein-gans-are","title":"Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?","date":"2022-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justkolesov/Wasserstein1Benchmark","path":"src/utils.py","file_url":"https://github.com/justkolesov/Wasserstein1Benchmark/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3248168eb0e100b","mcp_get_code":{"code_sha256":"e3248168eb0e100b"}},{"arxiv_id":"2205.00202","paper":"/paper/explainable-artificial-intelligence-for-6","title":"Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics","date":"2022-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maikejulie/DNN4Cli","path":"THOR/BayesianApproach/shap_ensemble.py","file_url":"https://github.com/maikejulie/DNN4Cli/blob/HEAD/THOR/BayesianApproach/shap_ensemble.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99af607d774eb893","mcp_get_code":{"code_sha256":"99af607d774eb893"}},{"arxiv_id":"2111.02458","paper":"/paper/perturb-and-max-product-sampling-and-learning","title":"Perturb-and-max-product: Sampling and learning in discrete energy-based models","date":"2021-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vicariousinc/perturb_and_max_product","path":"pmap/rbm_modeling.py","file_url":"https://github.com/vicariousinc/perturb_and_max_product/blob/HEAD/pmap/rbm_modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba817fe401de23e8","mcp_get_code":{"code_sha256":"ba817fe401de23e8"}},{"arxiv_id":"2108.07356","paper":"/paper/stochastic-optimization-under-time-drift","title":"Stochastic Optimization under Distributional Drift","date":"2021-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshuacutler/TimeDriftExperiments","path":"LogisticRegression/LR.py","file_url":"https://github.com/joshuacutler/TimeDriftExperiments/blob/HEAD/LogisticRegression/LR.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e106aedb0c789b9b","mcp_get_code":{"code_sha256":"e106aedb0c789b9b"}},{"arxiv_id":"2006.05164","paper":"/paper/ar-dae-towards-unbiased-neural-entropy","title":"AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation","date":"2020-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lim0606/pytorch-ardae-rl","path":"models/graddae/mlp.py","file_url":"https://github.com/lim0606/pytorch-ardae-rl/blob/HEAD/models/graddae/mlp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6481d3c86e5d4089","mcp_get_code":{"code_sha256":"6481d3c86e5d4089"}},{"arxiv_id":"1909.00025","paper":"/paper/meta-learning-with-warped-gradient-descent","title":"Meta-Learning with Warped Gradient Descent","date":"2019-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"flennerhag/warpgrad","path":"src/warpgrad/warpgrad/utils.py","file_url":"https://github.com/flennerhag/warpgrad/blob/HEAD/src/warpgrad/warpgrad/utils.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":"9031a2aac8c79c7a","mcp_get_code":{"code_sha256":"9031a2aac8c79c7a"}},{"arxiv_id":"1905.09050","paper":"/paper/beyond-alternating-updates-for-matrix","title":"Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms","date":"2019-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mmahesh/cocain-bpg-matrix-factorization","path":"my_functions.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-factorization/blob/HEAD/my_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"7de0fb631a5ab4ea","mcp_get_code":{"code_sha256":"7de0fb631a5ab4ea"}},{"arxiv_id":"1904.03537","paper":"/paper/convex-concave-backtracking-for-inertial","title":"Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization","date":"2019-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mmahesh/cocain-bpg-escapes-spurious-stationary-points","path":"my_functions.py","file_url":"https://github.com/mmahesh/cocain-bpg-escapes-spurious-stationary-points/blob/HEAD/my_functions.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"64e23227316b67fc","mcp_get_code":{"code_sha256":"64e23227316b67fc"}},{"arxiv_id":"1904.03537","paper":"/paper/convex-concave-backtracking-for-inertial","title":"Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization","date":"2019-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mmahesh/cocain-bpg-phase-retrieval","path":"my_functions.py","file_url":"https://github.com/mmahesh/cocain-bpg-phase-retrieval/blob/HEAD/my_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"1b20d466ab5027ec","mcp_get_code":{"code_sha256":"1b20d466ab5027ec"}},{"arxiv_id":"1901.06314","paper":"/paper/physics-constrained-deep-learning-for-high","title":"Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data","date":"2019-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cics-nd/pde-surrogate","path":"models/darcy.py","file_url":"https://github.com/cics-nd/pde-surrogate/blob/HEAD/models/darcy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bd3f3e9983573cd2","mcp_get_code":{"code_sha256":"bd3f3e9983573cd2"}},{"arxiv_id":"1806.09055","paper":"/paper/darts-differentiable-architecture-search","title":"DARTS: Differentiable Architecture Search","date":"2018-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leopard-ai/betty","path":"betty/hypergradient/darts.py","file_url":"https://github.com/leopard-ai/betty/blob/HEAD/betty/hypergradient/darts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"28b087ea0aa9ba9d","mcp_get_code":{"code_sha256":"28b087ea0aa9ba9d"}}]}