SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.11845 · EACL Findings · 2023

Learning the Effects of Physical Actions in a Multi-modal Environment

Gautier Dagan, Frank Keller, Alex Lascarides

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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 6 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2301.11845.json · badge: /api/ran/2301.11845.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
gautierdag/piglet-vis canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
calculate_attention_weights_per_pixel Ran
ran on a synthesized input
gautierdag/piglet-vis/pigletvis/models/analysis.py
code served (permissive licence) · get_code("0dcac92ca797debf")
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 3, dtype family float, shape (384, 640, 1) 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)

# The function expects:
# - bboxes: iterable of boxes, each box is [x_min, y_min, x_max, y_max]
# - scores: iterable of scores (numeric values)

bboxes = [
    [10, 20, 50, 80],
    [100, 150, 200, 300]
]

scores = [
    0.5,
    0.8
]

ARGS = {
    "bboxes": bboxes,
    "scores": scores
}
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 3, dtype family float, shape (384, 640, 1) — shape (384, 640, 1) 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
denormalize_image Ran
ran on a synthesized input
gautierdag/piglet-vis/pigletvis/dataset.py
code served (permissive licence) · get_code("6efdc3a8c781e0d6")
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 3, dtype family float, shape (3, 4, 4) 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)

# The function expects an image tensor with shape (C, H, W)
# where C=3 (RGB channels), H and W are spatial dimensions
# Create a small normalized image tensor
image = torch.randn(3, 4, 4)

ARGS = {
    "image": image
}
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 3, dtype family float, shape (3, 4, 4) — shape (3, 4, 4) 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
get_actions_mapper Ran
ran on a synthesized input
gautierdag/piglet-vis/pigletvis/models/mappings.py
code served (permissive licence) · get_code("91c0a36505acdbe3")
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 dict. 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 pickle
import tempfile
import os

# Create a temporary directory for test data
temp_dir = tempfile.mkdtemp()

# Create the reverse action mapping pickle files
reverse_action_mapping = {
    0: "action_0",
    1: "action_1",
    2: "action_2",
    3: "action_3"
}

reverse_action_mapping_full = {
    0: "full_action_0",
    1: "full_action_1",
    2: "full_action_2",
    3: "full_action_3",
    4: "full_action_4"
}

# Write the pickle files
with open(f'{temp_dir}/reverse_action_mapping.pkl', 'wb') as f:
    pickle.dump(reverse_action_mapping, f)

with open(f'{temp_dir}/reverse_action_mapping_full.pkl', 'wb') as f:
    pickle.dump(reverse_action_mapping_full, f)

ARGS = {
    'data_dir_path': temp_dir,
    'use_full': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
get_cmap Ran
ran on a synthesized input
gautierdag/piglet-vis/pigletvis/models/analysis.py
code served (permissive licence) · get_code("bf535327d6a8febe")
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 LinearSegmentedColormap. 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 matplotlib.colors as mcolors
import matplotlib.pyplot as plt
import numpy as np

# The function get_cmap takes two parameters:
# - cm: a string that should be a valid matplotlib colormap name
# - N: an integer for the number of colors in the colormap

ARGS = {
    'cm': 'jet',
    'N': 256
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LinearSegmentedColormap — a LinearSegmentedColormap output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LinearSegmentedColormap 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
get_objects_mapper Ran
ran on a synthesized input
gautierdag/piglet-vis/pigletvis/models/mappings.py
code served (permissive licence) · get_code("15a878e324f6f04e")
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 dict. 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 pickle
import tempfile
import os
from typing import Dict

# Create a temporary directory for the pickle file
temp_dir = tempfile.mkdtemp()

# Create a mock reverse_object_mapping dictionary
mock_mapping = {
    0: {0: "person", 1: "car", 2: "dog"},
    1: {0: "bicycle", 1: "cat", 2: "bird"}
}

# Save the mock mapping to a pickle file
pickle_path = os.path.join(temp_dir, 'reverse_object_mapping.pkl')
with open(pickle_path, 'wb') as f:
    pickle.dump(mock_mapping, f)

# Save the full version as well
pickle_path_full = os.path.join(temp_dir, 'reverse_object_mapping_full.pkl')
with open(pickle_path_full, 'wb') as f:
    pickle.dump(mock_mapping, f)

ARGS = {
    'data_dir_path': temp_dir,
    'use_full': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
load_image_from_path Ran
ran on a synthesized input
gautierdag/piglet-vis/pigletvis/dataset.py
code served (permissive licence) · get_code("8dfe65bed1c3a905")
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 3, dtype family float, shape (4, 3, 3) 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 numpy as np
import torch
from PIL import Image
import tempfile
import os

# Create a temporary image file
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a small test image (4x3 RGB)
img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
img = Image.fromarray(img_array, mode='RGB')
img.save(temp_image_path)

ARGS = {
    "path": temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 3) 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
get_image_feature_extractor Not yet run
unverified (harvested, no recorded run)
gautierdag/piglet-vis/pigletvis/models/image_models.py
code served (permissive licence) · get_code("e940eca6fbf5e7a1")
How it ran

no invocation recorded.

plot_effect_grid Not yet run
unverified (harvested, no recorded run)
gautierdag/piglet-vis/pigletvis/models/analysis.py
code served (permissive licence) · get_code("b2aae85256af5069")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 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.

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

Large Language Models (LLMs) handle physical commonsense information inadequately. As a result of being trained in a disembodied setting, LLMs often fail to predict an action's outcome in a given environment. However, predicting the effects of an action before it is executed is crucial in planning, where coherent sequences of actions are often needed to achieve a goal. Therefore, we introduce the multi-modal task of predicting the outcomes of actions solely from realistic sensory inputs (images and text). Next, we extend an LLM to model latent representations of objects to better predict action outcomes in an environment. We show that multi-modal models can capture physical commonsense when augmented with visual information. Finally, we evaluate our model's performance on novel actions and objects and find that combining modalities help models to generalize and learn physical commonsense reasoning better.

For agents

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

get_harvested_code_for_paper("2301.11845")
get_code_for_paper("2301.11845")
have("2301.11845")

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

curl https://syntology.ai/api/ran/2301.11845.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.11845.svg)](https://syntology.ai/paper/2301.11845)

Connect an agent — have() is free.