SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.15467 · 2026

Evaluating Time Awareness and Cross-modal Active Perception of Large Models via 4D Escape Room Task

Yang Liu, Peng Li, Ziyue Wang, Fuwen Luo, Yurui Dong, Dairu Liu, Xuechen Liu, Shuyun Lu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 3 failures of our instrument; 1 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/2603.15467.json · badge: /api/ran/2603.15467.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
THUNLP-MT/EscapeCraft-4D canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
apply_rotation_to_size Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THUNLP-MT/EscapeCraft-4D/src/SceneGeneration.py
code served (permissive licence) · get_code("4caee8e0db3112ac")
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 list, ndim 1, dtype family int; 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
import numpy as np

torch.manual_seed(0)

# Construct arguments for apply_rotation_to_size
size = [10, 20, 30]
rotation = [90, 0, 0]

ARGS = {
    "size": size,
    "rotation": rotation,
}
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 list, ndim 1, dtype family int — a list 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
configure_logger Ran
ran; our contract draft was wrong, not the code
THUNLP-MT/EscapeCraft-4D/src/log_config.py
code served (permissive licence) · get_code("2a2fd003bfd35764")
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 Logger. 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 logging

GLOBAL_LOG_LEVEL = logging.DEBUG

class ColoredFormatter(logging.Formatter):
    COLOR_CODES = {'DEBUG': '\x1b[94m', 'INFO': '\x1b[92m', 'WARNING': '\x1b[93m', 'ERROR': '\x1b[91m', 'CRITICAL': '\x1b[91m', 'ITEM': '\x1b[95m', 'RESET': '\x1b[0m'}

    def format(self, record):
        msg = super().format(record)
        color = self.COLOR_CODES.get(record.levelname, self.COLOR_CODES['RESET'])
        return f"{color}{msg}{self.COLOR_CODES['RESET']}"

def configure_logger(name):
    logger = logging.getLogger(name)
    if not logger.hasHandlers():
        logger.setLevel(GLOBAL_LOG_LEVEL)
        ch = logging.StreamHandler()
        ch.setLevel(GLOBAL_LOG_LEVEL)
        formatter = ColoredFormatter('[%(asctime)s] - file: %(name)s - level: [%(levelname)s] : %(message)s')
        ch.setFormatter(formatter)
        if not logger.handlers:
            logger.addHandler(ch)
    return logger

ARGS = {
    "name": "test_logger"
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
resolve_path Ran
ran; our contract draft was wrong, not the code
THUNLP-MT/EscapeCraft-4D/src/utils.py
code served (permissive licence) · get_code("a7a8ec786dbc6b2e")
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 str. 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 os
import tempfile

# Create a temporary directory to use as a working directory
temp_dir = tempfile.mkdtemp()

# Set CURRENT_DIR and PROJECT_ROOT for the resolve_path function
CURRENT_DIR = temp_dir
PROJECT_ROOT = os.path.dirname(temp_dir)

# Define test arguments for the resolve_path function
ARGS = {
    "path": "assets/test.txt"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
format_scene Not yet run
unverified (harvested, no recorded run)
THUNLP-MT/EscapeCraft-4D/src/utils.py
code served (permissive licence) · get_code("74404e983c31ab1f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 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.

FunctionAlso present inEarliest-datedOthers named
apply_rotation_to_size 1 other paper
1 dated earlier
Wang_How_Do_Multimodal_Large_Language_Models_Handle_Complex_Multimodal_Reasoning_ICCV_2025_paper (2025 (year only))
How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game
configure_logger 1 other paper
1 dated earlier
Wang_How_Do_Multimodal_Large_Language_Models_Handle_Complex_Multimodal_Reasoning_ICCV_2025_paper (2025 (year only))
How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game

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

Multimodal Large Language Models (MLLMs) have recently made rapid progress toward unified Omni models that integrate vision, language, and audio. However, existing environments largely focus on 2D or 3D visual context and vision-language tasks, offering limited support for temporally dependent auditory signals and selective cross-modal integration, where different modalities may provide complementary or interfering information, which are essential capabilities for realistic multimodal reasoning. As a result, whether models can actively coordinate modalities and reason under time-varying, irreversible conditions remains underexplored. To this end, we introduce EscapeCraft-4D, a customizable 4D environment for assessing selective cross-modal perception and time awareness in Omni models. It incorporates trigger-based auditory sources, temporally transient evidence, and location-dependent cues, requiring agents to perform spatio-temporal reasoning and proactive multimodal integration under time constraints. Building on this environment, we curate a benchmark to evaluate corresponding abilities across powerful models. Evaluation results suggest that models struggle with modality bias, and reveal significant gaps in current model's ability to integrate multiple modalities under time constraints. Further in-depth analysis uncovers how multiple modalities interact and jointly influence model decisions in complex multimodal reasoning environments. a a GitHub repo: https://github.com/THUNLP-MT/EscapeCraft-4D.

For agents

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

get_harvested_code_for_paper("2603.15467")
get_code_for_paper("2603.15467")
have("2603.15467")

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

curl https://syntology.ai/api/ran/2603.15467.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.15467.svg)](https://syntology.ai/paper/2603.15467)

Connect an agent — have() is free.