SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.21063 · 2024

Neural Network Verification with Branch-and-Bound for General Nonlinearities

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 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; 9 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2405.21063.json · badge: /api/ran/2405.21063.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
huanzhang12/alpha-beta-CROWN canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
verified-intelligence/auto_lirpa canonical (classifier label)
classifier basis: classifier_2025
3 ran · 2 no recorded run
Verified-Intelligence/alpha-beta-CROWN_vnncomp2024 canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
ResNet18 Ran
ran; our contract draft was wrong, not the code
huanzhang12/alpha-beta-CROWN/complete_verifier/model_defs.py
pointer only (licence: NOASSERTION) · get_code("a95d3680efa231cc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huanzhang12/alpha-beta-CROWN (NOASSERTION). 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.

build_beta Ran
ran; our contract draft was wrong, not the code
verified-intelligence/auto_lirpa/auto_LiRPA/beta_crown.py
pointer only (licence: NOASSERTION) · get_code("9537dbcc162a7f8c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, verified-intelligence/auto_lirpa (NOASSERTION). 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.

concretize_bound Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from verified-intelligence/auto_lirpa
pointer only; the stored copy get_code serves, from verified-intelligence/auto_lirpa, is pointer only (licence: NOASSERTION) · get_code("f2689b948e0d82a5")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

crown_ibp_model_a_b Ran
ran; our contract draft was wrong, not the code
huanzhang12/alpha-beta-CROWN/complete_verifier/model_defs.py
pointer only (licence: NOASSERTION) · get_code("3a7d902c8dd6235a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huanzhang12/alpha-beta-CROWN (NOASSERTION). 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.

deep_update Ran
ran; our contract draft was wrong, not the code
huanzhang12/alpha-beta-CROWN/complete_verifier/load_model.py
pointer only (licence: NOASSERTION) · get_code("1c11a3ea527b1755")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huanzhang12/alpha-beta-CROWN (NOASSERTION). 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.

deprecated Ran
ran; our contract draft was wrong, not the code
huanzhang12/alpha-beta-CROWN/complete_verifier/bab.py
pointer only (licence: NOASSERTION) · get_code("02af614e12c22731")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huanzhang12/alpha-beta-CROWN (NOASSERTION). 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_split_depth Ran
ran, honoured the contract we drafted
huanzhang12/alpha-beta-CROWN/complete_verifier/bab.py
pointer only (licence: NOASSERTION) · get_code("e1af324f19462f68")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huanzhang12/alpha-beta-CROWN (NOASSERTION). 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_split_nodes Ran
ran; our contract draft was wrong, not the code
verified-intelligence/auto_lirpa/auto_LiRPA/beta_crown.py
pointer only (licence: NOASSERTION) · get_code("68a6ab5e9a20bbfa")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, verified-intelligence/auto_lirpa (NOASSERTION). 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_unstable_size Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from Verified-Intelligence/alpha-beta-CROWN_vnncomp2024
pointer only; the stored copy get_code serves, from Verified-Intelligence/alpha-beta-CROWN_vnncomp2024, is pointer only (licence: NOASSERTION) · get_code("d5f02d6ed407b5ca")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

model_resnet Ran
ran; our contract draft was wrong, not the code
huanzhang12/alpha-beta-CROWN/complete_verifier/model_defs.py
pointer only (licence: NOASSERTION) · get_code("4a4fb84ab3edf916")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huanzhang12/alpha-beta-CROWN (NOASSERTION). 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.

set_beta Ran
ran; our contract draft was wrong, not the code
verified-intelligence/auto_lirpa/auto_LiRPA/beta_crown.py
pointer only (licence: NOASSERTION) · get_code("8aad4c1ed274989b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, verified-intelligence/auto_lirpa (NOASSERTION). 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.

batched_backward Not yet run
unverified (harvested, no recorded run)
verified-intelligence/auto_lirpa/auto_LiRPA/backward_bound.py
pointer only (licence: NOASSERTION) · get_code("ca36eb77350ff0f7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, verified-intelligence/auto_lirpa (NOASSERTION). 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.

beta_crown_backward_bound Not yet run
unverified (harvested, no recorded run)
Verified-Intelligence/alpha-beta-CROWN_vnncomp2024/auto_LiRPA/beta_crown.py
pointer only (licence: NOASSERTION) · get_code("bfecf96d0739bbf1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Verified-Intelligence/alpha-beta-CROWN_vnncomp2024 (NOASSERTION). 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.

beta_crown_backward_bound Not yet run
unverified (harvested, no recorded run)
verified-intelligence/auto_lirpa/auto_LiRPA/beta_crown.py
pointer only (licence: NOASSERTION) · get_code("5192518593b660cb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, verified-intelligence/auto_lirpa (NOASSERTION). 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.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 0 later) and 8 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.

FunctionAlso present inEarliest-datedOthers named
get_unstable_size 2 other papers
2 dated earlier
2011.13824 (2020-11)
Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
2210.07394 (2022-10)
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
ResNet18 1 other paper
1 the same month
2405.10143 (2024-05)
Relational DNN Verification With Cross Executional Bound Refinement
batched_backward 1 other paper
1 dated earlier
2210.07394 (2022-10)
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
beta_crown_backward_bound
brick of this paper's assembly: entry
1 other paper
1 dated earlier
2103.06624 (2021-03)
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification
concretize_bound 1 other paper
1 dated earlier
2210.07394 (2022-10)
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

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

Branch-and-bound (BaB) is among the most effective techniques for neural network (NN) verification. However, existing works on BaB for NN verification have mostly focused on NNs with piecewise linear activations, especially ReLU networks. In this paper, we develop a general framework, named GenBaB, to conduct BaB on general nonlinearities to verify NNs with general architectures, based on linear bound propagation for NN verification. To decide which neuron to branch, we design a new branching heuristic which leverages linear bounds as shortcuts to efficiently estimate the potential improvement after branching. To decide nontrivial branching points for general nonlinear functions, we propose to pre-optimize branching points, which can be efficiently leveraged during verification with a lookup table. We demonstrate the effectiveness of our GenBaB on verifying a wide range of NNs, including NNs with activation functions such as Sigmoid, Tanh, Sine and GeLU, as well as NNs involving multi-dimensional nonlinear operations such as multiplications in LSTMs and Vision Transformers. Our framework also allows the verification of general nonlinear computation graphs and enables verification applications beyond simple NNs, particularly for AC Optimal Power Flow (ACOPF). GenBaB is part of the latest $α$,$β$-CROWN, the winner of the 4th and the 5th International Verification of Neural Networks Competition (VNN-COMP 2023 and 2024). Code for reproducing the experiments is available at https://github.com/shizhouxing/GenBaB.

For agents

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

get_harvested_code_for_paper("2405.21063")
get_code_for_paper("2405.21063")
have("2405.21063")

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

curl https://syntology.ai/api/ran/2405.21063.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.21063.svg)](https://syntology.ai/paper/2405.21063)

Connect an agent — have() is free.