SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1701.02426 · 2017

Scene Graph Generation by Iterative Message Passing

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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 1 has no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/1701.02426.json · badge: /api/ran/1701.02426.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
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
joshuafeinglass/vl-detector-eval community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
bknyaz/sgg reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
F1 Ran
ran on a synthesized input
joshuafeinglass/vl-detector-eval/detector_benchmark/evaluate_proposals.py
code served (permissive licence) · get_code("733cc400578ca922")
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 float, 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.

import torch
import numpy as np

torch.manual_seed(0)

# Analyze F1:
# - Takes two parameters: a and b
# - Performs arithmetic operations (abs, division, multiplication)
# - Compares with 0
# - Works with numeric types

# F1 expects numeric inputs that support:
# - abs()
# - Addition, division, multiplication
# - Comparison with 0

# Create simple numeric test values
a = 0.5
b = 0.3

ARGS = {
    'a': a,
    'b': b
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
calculate_mR_from_evaluator_list Ran
ran; our contract draft was wrong, not the code
bknyaz/sgg/lib/sgg_eval.py
pointer only (licence: NOASSERTION) · get_code("3e90e5ade2fe74e6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bknyaz/sgg (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.

edge_losses Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from bknyaz/sgg
pointer only; the stored copy get_code serves, from bknyaz/sgg, is pointer only (licence: NOASSERTION) · get_code("4ef3ac0549c0f1e4")
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.

node_losses Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from bknyaz/sgg
pointer only; the stored copy get_code serves, from bknyaz/sgg, is pointer only (licence: NOASSERTION) · get_code("1ae3ab9cda78eb00")
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.

summarize Not yet run
unverified (harvested, no recorded run)
joshuafeinglass/vl-detector-eval/detector_benchmark/modified_coco_eval_summarize.py
code served (permissive licence) · get_code("d206668e99641ddb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
edge_losses 2 other papers
2 later
1711.06640 (2017-11)
Neural Motifs: Scene Graph Parsing with Global Context
2005.08230 (2020-05)
Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
node_losses 2 other papers
2 later
1711.06640 (2017-11)
Neural Motifs: Scene Graph Parsing with Global Context
2005.08230 (2020-05)
Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image. We propose a novel end-to-end model that generates such structured scene representation from an input image. The model solves the scene graph inference problem using standard RNNs and learns to iteratively improves its predictions via message passing. Our joint inference model can take advantage of contextual cues to make better predictions on objects and their relationships. The experiments show that our model significantly outperforms previous methods for generating scene graphs using Visual Genome dataset and inferring support relations with NYU Depth v2 dataset.

For agents

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

get_harvested_code_for_paper("1701.02426")
get_code_for_paper("1701.02426")
have("1701.02426")

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

curl https://syntology.ai/api/ran/1701.02426.json

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

[![Syntology run record](https://syntology.ai/api/ran/1701.02426.svg)](https://syntology.ai/paper/1701.02426)

Connect an agent — have() is free.