SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.03066 · ICML · 2026

CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection

Zhun Zhong, Yaxiong Wang, Nan Pu, Lechao Cheng, Tianrui Hui, Zhihui Li, Jinjie Shen, {�, Yujiao Wu, } {�, Santa Claus, Glenn Danzig

arXiv · PDF

Code that ran

15 of 17 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 13 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2606.03066.json · badge: /api/ran/2606.03066.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
shen8424/CORE canonical (classifier label)
classifier basis: census
15 ran · 2 no recorded run
FunctionStatusWhere it lives
load_yaml Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/code/train_stage_pipeline.py
pointer only (licence: NONE) · get_code("83396ec95592fb23")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

default_repair_messages Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/libs/swift/llm/dataset/preprocessor/core.py
pointer only (licence: NONE) · get_code("892509bb501cfb21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

get_imports Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/libs/transformers/dynamic_module_utils.py
pointer only (licence: NONE) · get_code("fd6301ff8929a985")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

get_lora_checkpoints Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/code/sft-stage1or2.py
pointer only (licence: NONE) · get_code("e331a3ccee1e278a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

get_relative_import_files Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/libs/transformers/dynamic_module_utils.py
pointer only (licence: NONE) · get_code("7a7bfcbbe9e6611e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

get_relative_imports Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/libs/transformers/dynamic_module_utils.py
pointer only (licence: NONE) · get_code("35034aa4f89388d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

infer_metric_tags_from_eval_results Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/libs/transformers/modelcard.py
pointer only (licence: NONE) · get_code("dd8f7751ef859581")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

is_layer_block Ran
ran, violated the contract we drafted
shen8424/CORE/libs/transformers/model_debugging_utils.py
pointer only (licence: NONE) · get_code("84c65f990fc244a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

parse_keras_history Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/libs/transformers/modelcard.py
pointer only (licence: NONE) · get_code("e6632a5722f0840d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

prepare_fa2_from_position_ids Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/libs/transformers/modeling_flash_attention_utils.py
pointer only (licence: NONE) · get_code("93e50e3428eab46d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

quick_gelu Ran
ran, honoured the contract we drafted
shen8424/CORE/libs/transformers/modeling_flax_utils.py
pointer only (licence: NONE) · get_code("a66d2b78670c85e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

rename_key_and_reshape_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shen8424/CORE/libs/transformers/modeling_flax_pytorch_utils.py
pointer only (licence: NONE) · get_code("30d50ff2ced6b7a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

resolve_repo_path Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/code/sft-stage1or2.py
pointer only (licence: NONE) · get_code("d3be3946b15d75c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

resolve_repo_paths Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/code/sft-stage1or2.py
pointer only (licence: NONE) · get_code("83676309669d7196")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

resolve_repo_paths Ran
ran; our contract draft was wrong, not the code
shen8424/CORE/code/train_stage_pipeline.py
pointer only (licence: NONE) · get_code("3d3611aad8ea9011")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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.

is_hf_dataset Not yet run
unverified (harvested, no recorded run)
shen8424/CORE/libs/transformers/modelcard.py
pointer only (licence: NONE) · get_code("ec7b1528a936234d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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. No invocation recorded.

read_field Not yet run
unverified (harvested, no recorded run)
shen8424/CORE/libs/transformers/modeling_gguf_pytorch_utils.py
pointer only (licence: NONE) · get_code("9aeec6efae4fb215")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen8424/CORE when it was checked. 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. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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
infer_metric_tags_from_eval_results 19 other papers
19 dated earlier
2022.findings-emnlp.427 (2022 (year only))
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
and 16 more not named here
quick_gelu 17 other papers
17 dated earlier
2022.findings-emnlp.427 (2022 (year only))
2303.14582 (2023-03)
Identification of Negative Transfers in Multitask Learning Using Surrogate Models
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
and 14 more not named here
is_hf_dataset 16 other papers
16 dated earlier
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 13 more not named here
parse_keras_history 16 other papers
16 dated earlier
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 13 more not named here
rename_key_and_reshape_tensor 7 other papers
7 dated earlier
2403.09766 (2024-03)
An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
2403.13263 (2024-03)
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
2406.02395 (2024-06)
GrootVL: Tree Topology is All You Need in State Space Model
and 4 more not named here
load_yaml 4 other papers
4 dated earlier
2411.00204 (2024-11)
RESTOR: Knowledge Recovery in Machine Unlearning
2506.20941 (2025-06)
Revisiting the Past: Data Unlearning with Model State History
2511.00117 (2025-11)
DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads
and 1 more not named here
read_field 2 other papers
2 dated earlier
2002.01685 (2020-02)
Parsing as Pretraining
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

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

The rapid rise of generative AI has made multimodal fake news increasingly realistic and pervasive, posing severe threats to public trust and social stability. Existing detection methods rely heavily on manipulation-specific models and large-scale labeled data, resulting in poor generalization to emerging manipulation types. We observed that the essence of manipulated misinformation lies in its intrinsic conflicts, i.e., semantic or physical inconsistencies either across modalities or with common world knowledge. Inspired by this observation, we propose Conflict-Oriented REasoning (CORE) framework, an effective paradigm that learns to endows multimodal large language models (MLLMs) with explicit conflictcapturing capability. To this end, CORE first constructs the Conflict Attribution Corpus (CAC) with fine-grained annotations of conflict factors and sources, providing essential data support for subsequent conflict perception training. By performing conflict-oriented representation enhancement and reasoning based on CAC, CORE achieves robust and generalizable conflict detection, effectively and rapidly adapting to unseen manipulation types with a few samples or in even zero-shot settings. Extensive experiments demonstrate that CORE surpasses state-of-the-art models. The dataset and code are publicly available at https://github.com/shen8424/CORE.

For agents

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

get_harvested_code_for_paper("2606.03066")
get_code_for_paper("2606.03066")
have("2606.03066")

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

curl https://syntology.ai/api/ran/2606.03066.json

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

[![Syntology run record](https://syntology.ai/api/ran/2606.03066.svg)](https://syntology.ai/paper/2606.03066)

Connect an agent — have() is free.