SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.08883 · 2023

Versatile Neural Processes for Learning Implicit Neural Representations

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 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/2301.08883.json · badge: /api/ran/2301.08883.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
zongyuguo/versatile-np canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
make_cfg Ran
ran; our contract draft was wrong, not the code
zongyuguo/versatile-np/exp3D/run_trainer.py
code served (permissive licence) · get_code("ff250f977653485a")
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 dict. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 os
import yaml
import torch
import tempfile

torch.manual_seed(0)

# Create a temporary YAML config file
temp_dir = tempfile.mkdtemp()
cfg_path = os.path.join(temp_dir, "test_config.yaml")

config_content = """
Lambda: 0.5
model:
  name: test_model
  path: $load_root$/model.pt
training:
  lr: 0.001
  epochs: 10
  data_path: $load_root$/data
"""

with open(cfg_path, 'w') as f:
    f.write(config_content)

# Create a simple args object
class Args:
    def __init__(self):
        self.cfg = cfg_path
        self.load_root = "/data/models"
        self.Lambda = 0.5
        self.name = None
        self.tag = None
        self.save_root = temp_dir
        self.cudnn = True
        self.port_offset = 0
        self.wandb_upload = False

ARGS = {
    'args': Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Representing a signal as a continuous function parameterized by neural network (a.k.a. Implicit Neural Representations, INRs) has attracted increasing attention in recent years. Neural Processes (NPs), which model the distributions over functions conditioned on partial observations (context set), provide a practical solution for fast inference of continuous functions. However, existing NP architectures suffer from inferior modeling capability for complex signals. In this paper, we propose an efficient NP framework dubbed Versatile Neural Processes (VNP), which largely increases the capability of approximating functions. Specifically, we introduce a bottleneck encoder that produces fewer and informative context tokens, relieving the high computational cost while providing high modeling capability. At the decoder side, we hierarchically learn multiple global latent variables that jointly model the global structure and the uncertainty of a function, enabling our model to capture the distribution of complex signals. We demonstrate the effectiveness of the proposed VNP on a variety of tasks involving 1D, 2D and 3D signals. Particularly, our method shows promise in learning accurate INRs w.r.t. a 3D scene without further finetuning. Code is available at https://github.com/ZongyuGuo/Versatile-NP .

For agents

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

get_harvested_code_for_paper("2301.08883")
get_code_for_paper("2301.08883")
have("2301.08883")

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

curl https://syntology.ai/api/ran/2301.08883.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.08883.svg)](https://syntology.ai/paper/2301.08883)

Connect an agent — have() is free.