Xi Peng, Ziyu Yao, Mengmeng Ma, Yunxiang Peng, B Metrics, Acc Ood
12 of 15 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 3 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/2604.08192.json · badge: /api/ran/2604.08192.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 |
|---|---|---|
| deep-real/GenCircuit | canonical (classifier label) classifier basis: census |
12 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| bernoulli_kl | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/dataset_utils.py pointer only (licence: NONE) · get_code("62435ebddf0bbc18") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| collate_EAP | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/dataset.py pointer only (licence: NONE) · get_code("f663999fde37d3ca") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| compute_groupwise_accuracy | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/model_zoo/acc_eval.py pointer only (licence: NONE) · get_code("d74b7285b967fee4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| convert_hf_to_hookedvit | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/model_utils.py pointer only (licence: NONE) · get_code("cbb0c42794d625dd") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| flatten_metric_output | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/compute_metrics.py pointer only (licence: NONE) · get_code("e4314f14cae629b0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| get_failure_list | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
deep-real/GenCircuit/dataset_utils.py pointer only (licence: NONE) · get_code("7d7e38335fc8dce2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| get_layer_index | Ran ran, honoured the contract we drafted |
deep-real/GenCircuit/compute_metrics.py pointer only (licence: NONE) · get_code("86e7460cce433ff9") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| numel | Ran ran, honoured the contract we drafted |
deep-real/GenCircuit/model_zoo/cmnist_consistency.py pointer only (licence: NONE) · get_code("689bb797ea2eebd9") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| randomsvd | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/model_zoo/coupling_jacobian.py pointer only (licence: NONE) · get_code("80901b7355cb5d7d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| svd | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/model_zoo/coupling_jacobian.py pointer only (licence: NONE) · get_code("f1d6ff8b5691ff6a") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| topk_accuracy | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
deep-real/GenCircuit/metrics.py pointer only (licence: NONE) · get_code("0a359b702f5ab47d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| vit_hidden_states_timm | Ran ran; our contract draft was wrong, not the code |
deep-real/GenCircuit/model_zoo/coupling_eval.py pointer only (licence: NONE) · get_code("8a9cf5ce54bd0f16") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| get_transform | Not yet run unverified (harvested, no recorded run) |
deep-real/GenCircuit/dataset_utils.py pointer only (licence: NONE) · get_code("2732127dfe219441") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| jacobian | Not yet run unverified (harvested, no recorded run) |
deep-real/GenCircuit/model_zoo/coupling_jacobian.py pointer only (licence: NONE) · get_code("9f7585ff134e843d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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. |
| normalized_logit | Not yet run unverified (harvested, no recorded run) |
deep-real/GenCircuit/metrics.py pointer only (licence: NONE) · get_code("1a6f60a202e7f9a5") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, deep-real/GenCircuit 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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 15 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.
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.
Reliable generalization metrics are fundamental to the evaluation of machine learning models. Especially in highstakes applications where labeled target data are scarce, evaluation of models' generalization performance under distribution shift is a pressing need. We focus on two practical scenarios: (1) Before deployment, how to select the best model for unlabeled target data? (2) After deployment, how to monitor model performance under distribution shift? The central need in both cases is a reliable and label-free proxy metric. Yet existing proxy metrics, such as model confidence or accuracy-on-the-line, are often unreliable as they only assess model output while ignoring the internal mechanisms that produce them. We address this limitation by introducing a new perspective: using the inner workings of a model, i.e., circuits, as a predictive metric of generalization performance. Leveraging circuit discovery, we extract the causal interactions between internal representations as a circuit, from which we derive two metrics tailored to the two practical scenarios. (1) Before deployment, we introduce Dependency Depth Bias, which measures different models' generalization capability on target data. (2) After deployment, we propose Circuit Shift Score, which predicts a model's generalization under different distribution shifts. Across various tasks, both metrics demonstrate significantly improved correlation with generalization performance, outperforming existing proxies by an average of 13.4% and 34.1%, respectively. Our code is available at https://github.com/deep-real/GenCircuit.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2604.08192")
get_code_for_paper("2604.08192")
have("2604.08192")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2604.08192.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2604.08192)
Connect an agent — have() is free.