Papers › WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales

WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales

7 May 2025arXiv:2505.04608archive 2025-07-28

Drew Prinster, Xing Han, Anqi Liu, Suchi Saria

Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but moreover continual, post-deployment monitoring to quickly detect and address any unsafe behavior. Statistical methods for nonparametric change-point detection -- especially the tools of conformal test martingales (CTMs) and anytime-valid inference -- offer promising approaches to this monitoring task. However, existing methods are restricted to monitoring limited hypothesis classes or ``alarm criteria'' (such as data shifts that violate certain exchangeability assumptions), do not allow for online adaptation in response to shifts, and/or do not enable root-cause analysis of any degradation. In this paper, we expand the scope of these monitoring methods by proposing a weighted generalization of conformal test martingales (WCTMs), which lay a theoretical foundation for online monitoring for any unexpected changepoints in the data distribution while controlling false-alarms. For practical applications, we propose specific WCTM algorithms that adapt online to mild covariate shifts (in the marginal input distribution) while quickly detecting and diagnosing more severe shifts, such as concept shifts (in the conditional label distribution) or extreme (out-of-support) covariate shifts that cannot be easily adapted to. On real-world datasets, we demonstrate improved performance relative to state-of-the-art baselines.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 24 code samples harvested from 2 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 21 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); found in paper text by Syntology: 21 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

aaronhan223/wtr officialpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

24 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 21 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran; the contract check could not run
1ran
21unverified

Licence: 0 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

aaronhan223/wtr official repository 3 samples, 2 ran (1 instrument-failed) · 1 unverified
calculate_p_values src/p_values.py ran · violated contract fingerprinted BSD-3-Clause (permissive) · 1036ba3a48cac196 · report fixture: signature conformity_scores:ndarray/1/float · returned ndarray · level recorded 2026-09-22
calculate_p_values_and_quantiles src/p_values.py ran; the contract check could not run (RAISES) fingerprinted BSD-3-Clause (permissive) · 52fbf28f44e10714 · report fixture: signature conformity_scores:ndarray/1/float, alpha:float/0/float, cs_type:str/0/str · returned tuple · level recorded 2026-09-22
calculate_weighted_p_values_and_quantiles src/p_values.py unverified BSD-3-Clause (permissive) · 5085978d4817f000 · report
aaronhan223/watch found in paper text by Syntology 21 samples, 1 ran (0 instrument-failed) · 20 unverified
train_one_epoch in 50 papers src/main_mnist_cifar.py ran BSD-3-Clause (permissive) · e224e4494d78ef17 · report fixture: signature model:callable/0/?, device:str/0/str, train_loader:list/1/tuple, optimizer:SGD/0/? · returned tuple · level recorded 2026-09-25
ResNet20 in 5 papers src/resnet.py unverified BSD-3-Clause (permissive) · 24e257d88b978945 · report
ResNet32 in 5 papers src/resnet.py unverified BSD-3-Clause (permissive) · d6c9d2e6d30cf13c · report
brier_scores src/podkopaev_ramdas/tests.py unverified BSD-3-Clause (permissive) · 3fe446beed24ab8f · report
cusum_procedure src/martingales.py unverified BSD-3-Clause (permissive) · 1e117d22b7948cfc · report
effective_sample_size_est src/utils.py unverified BSD-3-Clause (permissive) · f7f73cf99f559888 · report
eval_loss_prob src/main_mnist_cifar.py unverified BSD-3-Clause (permissive) · 8e67a8dac730d3c1 · report
evaluate in 514 papers src/main_mnist_cifar.py unverified BSD-3-Clause (permissive) · 920241d05b739b86 · report
fit in 23 papers src/main_pod_ram.py unverified BSD-3-Clause (permissive) · 3dcf309104240174 · report
get_meps_data src/utils.py unverified BSD-3-Clause (permissive) · 2a5d22e9de647d4d · report
hoeffding_ci_lower_limit src/podkopaev_ramdas/concentrations.py unverified BSD-3-Clause (permissive) · e3886065919c0b20 · report
hoeffding_ci_upper_limit src/podkopaev_ramdas/concentrations.py unverified BSD-3-Clause (permissive) · bf57bb6d7f52d5f9 · report
logistic_regression_weight_est src/p_values.py unverified BSD-3-Clause (permissive) · 75e33f5c90046614 · report
misclas_losses src/podkopaev_ramdas/tests.py unverified BSD-3-Clause (permissive) · 3616d89ef8f11c25 · report
phi_h src/podkopaev_ramdas/concentrations.py unverified BSD-3-Clause (permissive) · 4987abbabf98f992 · report
podkopaev_ramdas_algorithm1 src/podkopaev_ramdas/baseline_alg.py unverified BSD-3-Clause (permissive) · d5786e025273c2db · report
podkopaev_ramdas_changepoint_detection src/podkopaev_ramdas/baseline_alg.py unverified BSD-3-Clause (permissive) · c00e01fba06c1cf4 · report
random_forest_weight_est src/p_values.py unverified BSD-3-Clause (permissive) · 0a2eccd55a3473c8 · report
shiryaev_roberts_procedure src/martingales.py unverified BSD-3-Clause (permissive) · eee24789b6e59613 · report
top_label_brier_scores src/podkopaev_ramdas/tests.py unverified BSD-3-Clause (permissive) · 0eba4f72b27f3a5d · report
ville_procedure src/martingales.py unverified BSD-3-Clause (permissive) · 0c6a35aaa8280481 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Weighted-Conformal Martingales (WCTMs) (graph method: Weighted-Conformal Martingales (WCTMs)). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. calculate_weighted_p_values_and_quantiles entry · level 0 · unverified · 5085978d4817f000
  2. calculate_p_values_and_quantiles helper · level 1 · ran; the contract check could not run (RAISES) · 52fbf28f44e10714
  3. calculate_p_values helper · level 1 · ran · violated contract · 1036ba3a48cac196

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2505.04608") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Change Point Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections