SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.12828 · CVPR · 2023

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries

Richard Baraniuk, Ahmed Humayun, Randall Balestriero, Guha Balakrishnan

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 4 have no contract verdict; 0 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/2302.12828.json · badge: /api/ran/2302.12828.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
ahmedimtiazprio/splinecam canonical (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
FunctionStatusWhere it lives
centrality Ran
ran on a synthesized input
ahmedimtiazprio/splinecam/splinecam/utils.py
code served (permissive licence) · get_code("97296af4c6809fbd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects 'polys' - a list of tensors
# Each tensor in polys represents a polygon with vertices
# The function does: verts = torch.vstack([each[:-1] for each in polys])
# So each element needs to be sliceable with [:-1]
# Then it stacks them vertically and computes centroid-based distances

# Create 2 small polygons, each with 3 vertices + 1 extra dimension
# Shape: (4, 2) means 4 points with 2 coordinates each
poly1 = torch.randn(4, 2)
poly2 = torch.randn(4, 2)

polys = [poly1, poly2]

ARGS = {
    "polys": polys
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
find_intersection_2D Ran
ran on a synthesized input
ahmedimtiazprio/splinecam/splinecam/graph.py
code served (permissive licence) · get_code("2224961f4642cfe9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small batch of 2D lines in the form [a, b, c] representing ax + by + c = 0
# Shape: batch_size x 3
batch_size = 2
line1 = torch.tensor([
    [1.0, 2.0, -3.0],
    [2.0, 1.0, -4.0]
], dtype=torch.float32)

line2 = torch.tensor([
    [2.0, -1.0, 1.0],
    [1.0, -1.0, 2.0]
], dtype=torch.float32)

ARGS = {
    "line1": line1,
    "line2": line2,
    "eps": 1e-07,
    "verify": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_line_2D Ran
ran on a synthesized input
ahmedimtiazprio/splinecam/splinecam/graph.py
code served (permissive licence) · get_code("e8adb92f78fc66d6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create two batches of 2D vertices
# vert1: batchsize x 2
# vert2: batchsize x 2
vert1 = torch.tensor([[1.0, 2.0], [3.0, 4.0]], dtype=torch.float32)
vert2 = torch.tensor([[5.0, 6.0], [7.0, 8.0]], dtype=torch.float32)

ARGS = {
    "vert1": vert1,
    "vert2": vert2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
region_area_2d Ran
ran on a synthesized input
ahmedimtiazprio/splinecam/splinecam/utils.py
code served (permissive licence) · get_code("68e77b6a0c56d250")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects a 2D polygon represented as a tensor
# where each row is a point [x, y] coordinate
# The function removes the last point (poly[:-1]) and computes area using shoelace formula

# Create a simple polygon (e.g., a triangle or quadrilateral)
# Shape: (n_points, 2) where n_points includes the closing point
poly = torch.tensor([
    [0.0, 0.0],
    [4.0, 0.0],
    [4.0, 3.0],
    [0.0, 3.0],
    [0.0, 0.0]  # closing point (will be removed by poly[:-1])
], dtype=torch.float32)

ARGS = {
    "poly": poly
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_intersection_pattern Not yet run
unverified (harvested, no recorded run)
ahmedimtiazprio/splinecam/splinecam/graph.py
code served (permissive licence) · get_code("7aac90f6b8284800")
How it ran

no invocation recorded.

vgg11_bn Not yet run
unverified (harvested, no recorded run)
ahmedimtiazprio/splinecam/splinecam/models.py
code served (permissive licence) · get_code("d13139f6d7bfd8d6")
How it ran

no invocation recorded.

vgg16_bn Not yet run
unverified (harvested, no recorded run)
ahmedimtiazprio/splinecam/splinecam/models.py
code served (permissive licence) · get_code("af5f5c8e7c5775d4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Current Deep Network (DN) visualization and interpretability methods rely heavily on data space visualizations such as scoring which dimensions of the data are responsible for their associated prediction or generating new data features or samples that best match a given DN unit or representation. In this paper, we go one step further by developing the first provably exact method for computing the geometry of a DN's mapping -including its decision boundary -over a specified region of the data space. By leveraging the theory of Continuous Piece-Wise Linear (CPWL) spline DNs, SplineCam exactly computes a DN's geometry without resorting to approximations such as sampling or architecture simplification. SplineCam applies to any DN architecture based on CPWL activation nonlinearities, including (leaky) ReLU, absolute value, maxout, and maxpooling and can also be applied to regression DNs such as implicit neural representations. Beyond decision boundary visualization and characterization, SplineCam enables one to compare architectures, measure generalizability, and sample from the decision boundary on or off the data manifold. Project website: bit.ly/splinecam.

For agents

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

get_harvested_code_for_paper("2302.12828")
get_code_for_paper("2302.12828")
have("2302.12828")

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

curl https://syntology.ai/api/ran/2302.12828.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.12828.svg)](https://syntology.ai/paper/2302.12828)

Connect an agent — have() is free.