SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.14033 · 2026

Private Prediction via PAC Privacy

Xiaochen Zhu, Srinivas Devadas, Mayuri Sridhar

arXiv · PDF · Open in the Atlas

Code that ran

11 of 11 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 0 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/2601.14033.json · badge: /api/ran/2601.14033.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.

RepositoryRoleRan
zhxchd/pac canonical (classifier label)
classifier basis: census
11 ran · 0 no recorded run
FunctionStatusWhere it lives
format_speedup Ran
ran; our contract draft was wrong, not the code
zhxchd/pac/benchmark/pac_microbench/analyze_results.py
pointer only (licence: AGPL-3.0) · get_code("d3d043a94061ac4b")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

load_count_data Ran
ran, honoured the contract we drafted
zhxchd/pac/benchmark/pac_microbench/plot_simd_improvements.py
pointer only (licence: AGPL-3.0) · get_code("ae7710cefa40c439")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

load_csv Ran
ran; our contract draft was wrong, not the code
zhxchd/pac/benchmark/pac_microbench/analyze_results.py
pointer only (licence: AGPL-3.0) · get_code("8ed50327556b3ce0")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

load_max_data Ran
ran, honoured the contract we drafted
zhxchd/pac/benchmark/pac_microbench/plot_simd_improvements.py
pointer only (licence: AGPL-3.0) · get_code("533e12652fcd27c2")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

load_platform_data Ran
ran, honoured the contract we drafted
zhxchd/pac/benchmark/pac_microbench/plot_count_optimizations.py
pointer only (licence: AGPL-3.0) · get_code("4140d9c2479cfd91")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

load_platform_data Ran
ran; our contract draft was wrong, not the code
zhxchd/pac/benchmark/pac_microbench/plot_minmax_optimizations.py
pointer only (licence: AGPL-3.0) · get_code("f27165dbb923fbbb")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

load_platform_data Ran
ran, honoured the contract we drafted
zhxchd/pac/benchmark/pac_microbench/plot_sum_optimizations.py
pointer only (licence: AGPL-3.0) · get_code("d7e42368061c248b")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

load_sum_data Ran
ran, honoured the contract we drafted
zhxchd/pac/benchmark/pac_microbench/plot_simd_improvements.py
pointer only (licence: AGPL-3.0) · get_code("20dc761c8b0f329a")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

prepare_data Ran
ran; our contract draft was wrong, not the code
zhxchd/pac/benchmark/pac_microbench/plot_count_optimizations.py
pointer only (licence: AGPL-3.0) · get_code("976f3b887f3cba61")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

prepare_data Ran
ran; our contract draft was wrong, not the code
zhxchd/pac/benchmark/pac_microbench/plot_minmax_optimizations.py
pointer only (licence: AGPL-3.0) · get_code("4ded2594ae261b11")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

prepare_data Ran
ran; our contract draft was wrong, not the code
zhxchd/pac/benchmark/pac_microbench/plot_sum_optimizations.py
pointer only (licence: AGPL-3.0) · get_code("2b9892ed735bb83a")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, zhxchd/pac, is not in the permissive set Syntology serves inline. 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.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Machine learning models are increasingly served behind APIs. This renders private prediction, i.e., privatizing a model's outputs rather than its parameters, a natural privacy target: model outputs are lower-dimensional and far more stable to training-data changes than weights. While differential privacy (DP) cannot effectively exploit this as it calibrates noise to worst-case sensitivity that is intractable to bound for non-convex models, we argue that PAC privacy is a natural fit for private prediction. It is instance-based, and calibrates noise to a black-box function's empirical stability to control mutual-information (MI) leakage. The missing ingredient is efficient, adaptive composition. Serving predictions means answering a long stream of adaptively chosen queries from untrusted users; existing composition either fails under adaptivity, grows quadratically, or reverts to input-independent, DP-like noise. We close this gap with a new adversarial composition result via adaptive noise calibration and prove that MI accumulates only linearly under adaptive and adversarial querying. Experiments across modalities show that prediction stability enables high utility even at a tiny per-query budget: on CIFAR-10, we achieve 87.79% accuracy with a per-query MI budget of 2 -32 . This enables serving one million queries while provably bounding membership-inference success to 51.08%the same guarantee as (0.04, 10 -5 )-DP. Further, in the presence of auxiliary public data, the large volume of PAC-private predictions enables us to distill a publishable model that can be queried without limit. Concretely, 210,000 private labels on an ImageNet subset distill into a student reaching 91.86% accuracy on CIFAR-10 with membership inference success bounded by 50.49%, comparable to (0.02, 10 -5 )-DP.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.14033")
get_code_for_paper("2601.14033")
have("2601.14033")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2601.14033.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2601.14033.svg)](https://syntology.ai/paper/2601.14033)

Connect an agent — have() is free.