Laurence Aitchison, Maxime Robeyns, Michele Garibbo
1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2302.14182.json · badge: /api/ran/2302.14182.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| nnaisense/MAGE | community Papers with Code archive |
1 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| swish | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
nnaisense/MAGE/models.py pointer only (licence: NONE) · get_code("107bf3b7b61a9085") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, nnaisense/MAGE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| EnsembleDenseLayer | Not yet run unverified (harvested, no recorded run) |
nnaisense/MAGE/models.py pointer only (licence: NONE) · get_code("03541bd8df5fe228") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, nnaisense/MAGE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
| Model | Not yet run unverified (harvested, no recorded run) |
nnaisense/MAGE/models.py pointer only (licence: NONE) · get_code("d52544da3f6742c0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, nnaisense/MAGE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| swish brick of this paper's assembly: helper |
3 other papers 3 later |
2308.12465 (2023-08) InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model |
2404.13640 (2024-04) Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer 2509.22583 (2025-09) Orochi: Versatile Biomedical Image Processor |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Many reinforcement learning approaches rely on temporal-difference (TD) learning to learn a critic. However, TD-learning updates can be high variance. Here, we introduce a model-based RL framework, Taylor TD, which reduces this variance in continuous state-action settings. Taylor TD uses a first-order Taylor series expansion of TD updates. This expansion allows Taylor TD to analytically integrate over stochasticity in the action-choice, and some stochasticity in the state distribution for the initial state and action of each TD update. We include theoretical and empirical evidence that Taylor TD updates are indeed lower variance than standard TD updates. Additionally, we show Taylor TD has the same stable learning guarantees as standard TD-learning with linear function approximation under a reasonable assumption. Next, we combine Taylor TD with the TD3 algorithm, forming TaTD3. We show TaTD3 performs as well, if not better, than several stateof-the art model-free and model-based baseline algorithms on a set of standard benchmark tasks. large distribution of state-action pairs, Dyna methods still rely on the same, potentially high-variance (sample-based) TD-updates as standard TD-learning. We address the issue of high-variance TD-updates by formulating an expected TD-update over a small distribution of state-action pairs. We show this expected update can analytically be estimated with a first-order Taylor expansion for continuous state-action spaces, in an approach we call Taylor TD. By analytically estimating this expected update, rather than exclusively relying on sample-based estimates (as in e.g. Dyna), we get lower variance TD updates. Additionally, we show Taylor TD does not affect the stable learning guarantees of TD-learning under linear function approximation [for a fixed policy as shown by 46]. Next, we propose a model-based off-policy algorithm, Taylor TD3 (TaTD3), which uses Taylor TD in combination with the TD3 algorithm [18]. We show TaTD3 performs as well as if not better than several state-of-the art model-free and model-based baseline algorithms on a set of standard benchmark tasks. Finally, we compare TaTD3 to its "Dyna" equivalent, which exclusively relies on sample-based TD-updates. We found the largest benefits of Taylor TD may appear in high dimensional state-action spaces. Reinforcement learning aims to learn reward-maximising behaviour by interacting with the surrounding environment. At each discrete time step, t, the agent in state s ∈ S, chooses an action a ∈ A based on a policy π : S → A, and observes a scalar reward, r and a new state s ′ ∈ S from the environment. The agent's goal is to find the policy that maximises the expected sum of rewards (i.e. the expected return), from a distribution of initial states (or state-action pairs). As such, it is usually necessary to compute the expected return for a state-action pair (s, a) and a policy π; which we can do with a value function. Given a policy π and an initial state-action pair (s, a), we define the value function , where R t = T i=t γ i-t r i is the discounted sum of future rewards from the current time step t until termination T , with discount factor γ ∈ [0, 1]. The value function or critic, Q π , quantifies how good the policy, π, is in terms of its expected return when taking action a in state s and following the policy π thereafter.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.14182")
get_code_for_paper("2302.14182")
have("2302.14182")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2302.14182.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2302.14182)
Connect an agent — have() is free.