SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.07971 · NeurIPS · 2024

Generalizable and Animatable Gaussian Head Avatar

Tatsuya Harada, Xuangeng Chu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2410.07971.json · badge: /api/ran/2410.07971.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
xg-chu/gagavatar canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
add_water_mark Ran
ran; our contract draft was wrong, not the code
xg-chu/gagavatar/inference.py
code served (permissive licence) · get_code("dbc17dad0be69522")
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) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 8, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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)

# Analyze the function:
# - image: indexed with [..., -water_mark.shape[-2]:, -water_mark.shape[-1]:]
#   so it needs at least 2 spatial dimensions, and supports batch dimensions
# - water_mark: has shape attributes accessed via .shape[-2] and .shape[-1]
#   indexed with [None, :3] and [None, 3:4], so needs at least 4 dimensions
#   and channel dimension of at least 4 (RGBA)

# water_mark should be a 4D tensor: (C, H, W) -> add batch -> (1, C, H, W)
# But the indexing [None, :3] suggests it's (C, H, W) initially
# Actually looking closer: water_mark[None, :3] adds batch dim, then slices channels
# So water_mark is shape (C, H, W) where C >= 4

# image needs to support the same spatial indexing and be broadcastable
# image[..., -water_mark.shape[-2]:, -water_mark.shape[-1]:] 
# This suggests image is (B, C, H, W) or similar

# Let's construct:
# water_mark: (4, 3, 5) - 4 channels (RGBA), 3 height, 5 width
water_mark = torch.randn(4, 3, 5)

# image: (2, 3, 8, 5) - batch of 2, 3 channels (RGB), 8 height, 5 width
# The last 3 rows and 5 cols will be replaced with watermark
image = torch.randn(2, 3, 8, 5)

ARGS = {
    "image": image,
    "water_mark": water_mark,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 4, dtype family float, shape (2, 3, 8, 5) — shape (2, 3, 8, 5) as a later run recorded it
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
is_image Ran
ran, violated the contract we drafted
xg-chu/gagavatar/inference.py
code served (permissive licence) · get_code("1afd34bb3f88aa49")
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) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.

# Setup code for is_image function

ARGS = {
    'image_path': 'photo.jpg'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Figure 1: Our method can reconstruct animatable avatars from a single image, offering strong generalization and controllability with real-time reenactment speeds.

For agents

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

get_harvested_code_for_paper("2410.07971")
get_code_for_paper("2410.07971")
have("2410.07971")

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

curl https://syntology.ai/api/ran/2410.07971.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.07971.svg)](https://syntology.ai/paper/2410.07971)

Connect an agent — have() is free.