- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper investigates the dissemination, persistence, and mitigation of false claims in multi-agent social networks through the lens of the "Mandela Effect." The authors build a controlled environment connecting neighbor communication, private memory, and a shared searchable web. Fabricator agents implant false claims via messages and articles, while honest agents evaluate them and may republish accepted information as searchable articles. Using 540 fabricated claims across eight domains and four plausibility levels, the study evaluates acceptance rates across ten models and three topologies. Results show that post-interaction acceptance is significantly higher than the direct-query baseline. After fabricators withdraw, acceptance largely persists due to retained web pages and memories. Targeted refutations and platform corrections outperform generic preventive measures but fail to eliminate false acceptance entirely.
Critical strengths
- Meaningful perspective on group information ecology: The paper addresses how local errors evolve into shared misjudgments when agents both consume and produce information. Content generated by one agent can be retrieved as corroborating evidence by others, creating a feedback loop. This perspective better reflects the reliability challenges in continuously interacting systems than isolated evaluations, providing a valuable entry point for studying group errors.
- Insightful study on misinformation persistence post-source: Examining whether misinformation persists after the source exits raises a crucial governance question: is blocking new malicious inputs sufficient to restore a polluted environment? Experiments show acceptance remains high after fabricator withdrawal. This suggests agent safety must address both attack prevention and the cleanup of already polluted information.
Critical weaknesses
- Limited extrapolation to real-world agent ecologies: Agents interact around a single claim using a fixed protocol (search, judge, update, publish) with the claim itself as the query. This lacks real-world behaviors like autonomous query reformulation, proactive source verification, or selective propagation. While the appendix tests some variables, the reliance on this rigid protocol limits the extrapolation of propagation dynamics to more realistic, autonomous agent networks.
- Insufficient separation of memory persistence vs. repeated evidence exposure: After withdrawal, fake articles and memories remain. Sustained acceptance shows the impact outlives the source, but it fails to disentangle internal false memory retention from continuous external reinforcement via polluted search results. To strengthen the "Mandela Effect" analogy, the paper must clarify how it isolates memory-level persistence from mere repeated exposure to a contaminated environment.
Questions for authors
If agents could autonomously reformulate queries, proactively verify sources, or choose whether to publish, would the main conclusions hold? Which current results help assess the impact of the fixed interaction protocol?
4 comments
Response (2/2): Memory persistence and repeated exposure
Weakness 2: Memory persistence and repeated exposure.
Response. We tested the two channels after withdrawal. Acceptance remained high when either repeated exposure or memory was disabled, and dropped substantially only when a one-time cleanup removed both. With supporting articles removed and web search disabled, acceptance for Qwen3-8B remained at 81.2% through private memory and neighbor conversations. With private memory cleared and disabled, it remained at 88.8% through web search and neighbor conversations. Clearing both reduced acceptance to 17.2%, 23.3%, and 25.0% for the three models.
Cleanup setting. To separate memory persistence from repeated exposure to supporting articles, we remove supporting articles, clear private memories, or do both after withdrawal, and compare the results. Table 3 in our submitted paper reports that after the fabricator withdraws midway through the interaction, acceptance changes by at most 0.8 percentage points at every plausibility level for Qwen3-8B and Llama-3.1-8B. At withdrawal, the new experiment applies one cleanup before the next honest turn in the fully connected network. Qwen3-8B and Llama-3.1-8B each use all claims in the main dataset. GPT-5.5 uses 100 claims (same as those used in the mixed-model setting, Appendices B.1 and C.1). Afterward honest agents continue searching, writing memory, and publishing. The table reports mean acceptance, with all claims weighted equally.
| Setting | Mean R (↓) | Unanimous U (↓) |
|---|---|---|
| Qwen3-8B | ||
| Keep articles and memory | 84.5 | 81.7 |
| Remove supporting articles | 82.0 | 78.1 |
| Clear private memory | 87.2 | 85.0 |
| Clear both | 17.2 | 15.9 |
| Llama-3.1-8B | ||
| Keep articles and memory | 64.7 | 53.9 |
| Remove supporting articles | 61.1 | 48.1 |
| Clear private memory | 80.2 | 73.3 |
| Clear both | 23.3 | 15.6 |
| GPT-5.5 | ||
| Keep articles and memory | 53.2 | 48.0 |
| Remove supporting articles | 52.6 | 51.0 |
| Clear private memory | 59.2 | 55.0 |
| Clear both | 25.0 | 25.0 |
Disabling one channel after cleanup. For Qwen3-8B, we compared each cleanup on its own with the same cleanup followed by disabling the corresponding channel. Neighbor conversations remained available in all four settings.
| Setting | Mean R (↓) | Unanimous U (↓) |
|---|---|---|
| Remove supporting articles | 82.0 | 78.1 |
| Remove supporting articles and disable web search and publication | 81.2 | 77.2 |
| Clear private memory | 87.2 | 85.0 |
| Clear private memory and disable memory reads and writes | 88.8 | 88.3 |
Acceptance persisted without further direct exposure to supporting articles when private memory and neighbor conversations remained available. It also stayed high without private memory when web search, publication, and neighbor conversations remained available.
Joint cleanup. Clearing both supporting articles and private memory substantially reduced mean acceptance across the three models, to 17.2%, 23.3%, and 25.0%. After cleanup, agents could still see earlier neighbor messages, update their private memories, and publish and retrieve new articles. In Qwen3-8B, every agent who still accepted had seen an earlier message from a neighbor who accepted the claim and had retrieved supporting articles that honest agents wrote after cleanup.
Write-back controls. In all four Qwen3-8B settings, we first removed the existing supporting articles and cleared private memory. Search and neighbor conversations remained available. We then varied whether agents could publish new articles and whether they could read and write private memory.
| Honest publication | Private memory | Mean R (↓) |
|---|---|---|
| Enabled | Enabled | 17.2 |
| Disabled | Enabled | 12.6 |
| Enabled | Disabled | 16.9 |
| Disabled | Disabled | 6.3 |
Disabling both publication and private memory further reduced acceptance after cleanup.
Revision. Appendix C.8 reports the cleanup and channel comparisons, along with the exposure analysis after clearing both supporting articles and private memories.
Thank you again for your constructive review. We hope these results address your concerns. We are happy to discuss any further questions.
Thank you for the detailed response and new experiments. The additional results on agent autonomy demonstrate that the fixed interaction protocol does not artificially inflate the dissemination rates. Furthermore, the new cleanup ablations successfully disentangle the effects of private memory retention from repeated exposure to polluted web evidence, providing a much clearer explanation of the persistence mechanism. My concerns are fully addressed, and I will keep my original score.
Dear Reviewer kStc,
Thank you for taking the time to read our responses. We are glad they addressed your concerns.
Response (1/2): Autonomous search, verification, and publication
Dear Reviewer kStc,
Thank you for your detailed review. We appreciate your recognition that agents retrieving one another's content creates an important feedback loop, and your positive assessment of our study of misinformation persistence after source withdrawal.
Response. Thank you for the constructive suggestion to let agents act more autonomously. Acceptance remains as high as in the main setting when agents write their own search queries, decide whether to verify a claim, or decide whether to publish. We added an experiment for each of these behaviors with Qwen3-8B agents. Acceptance ranged from 84.6% to 86.1% across these settings, compared with 84.4% in the main setting.
Under "Publication choice (Accept)", agents could publish only if they accepted the claim. Under "Publication choice (Any stance)", agents could choose to publish whether they accepted, rejected, or were uncertain about the claim.
Mean and unanimous acceptance stayed close to the main setting across these experiments, showing that false beliefs still spread widely when agents write their own queries, verify claims, or choose whether to publish.
Regarding which current results help assess the fixed protocol, we varied the publication rule in the submitted paper. Acceptance is 84.4%, 83.1%, and 80.4% when honest agents publish only after accepting, never publish, or publish at any stance (Table 11, Appendix C.5).
Revision. Appendix C.12 reports the results and prompts.