Pith Number

pith:TIF5RJQR

pith:2026:TIF5RJQRETUPTW5RKR64H42REY

not attested not anchored not stored refs resolved

ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles

Chunmeizi Su, Francesco Bailo, Huaming Chen, Linghan Huang, Yiqi Zhu, Yiqun Duan, Yitian Yang

ScioMind integrates memory-anchored belief updates, hierarchical memory, and dynamic profiles to enhance behavioral realism in LLM-based multi-agent social simulations.

arxiv:2605.13725 v1 · 2026-05-13 · cs.AI · cs.SI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TIF5RJQRETUPTW5RKR64H42REY}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Across metrics including polarisation, diversity, extremization, and trajectory stability, the proposed components consistently yield improvements in behavioural realism. In particular, dynamic profiles increase opinion diversity, memory and reflection reduce unstable oscillation, and anchoring induces persistent belief trajectories that better align with patterns reported in political psychology.

C2weakest assumption

That LLM agents equipped with the memory-anchored update rule, hierarchical memory, and dynamic profiles will produce belief dynamics that genuinely reflect human cognitive processes rather than artifacts of the LLM's training data or the specific prompting choices.

C3one line summary

ScioMind combines anchoring-based belief updates, hierarchical memory, and dynamic profiles in LLM multi-agent systems to produce more stable, diverse, and psychologically aligned opinion trajectories than prior fixed-rule or unconstrained approaches.

References

45 extracted · 45 resolved · 5 Pith anchors

[1] arXiv preprint arXiv:2602.00934 , year=

[2] Attention is All you Need , url =

[3] LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals · arXiv:2411.10109

[4] Park, Joon Sung and O'Brien, Joseph and Cai, Carrie Jun and Morris, Meredith Ringel and Liang, Percy and Bernstein, Michael S. , title =. Proceedings of the 36th Annual ACM Symposium on User Interface 2023 · doi:10.1145/3586183.3606763

[5] OASIS : Open agent social interaction simulations with one million agents

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:16.615542Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9a0bd8a61124e8f9dbb1547dc3f351261113e889f77f045056ab54e6a3b31587

Aliases

arxiv: 2605.13725 · arxiv_version: 2605.13725v1 · doi: 10.48550/arxiv.2605.13725 · pith_short_12: TIF5RJQRETUP · pith_short_16: TIF5RJQRETUPTW5R · pith_short_8: TIF5RJQR

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/TIF5RJQRETUPTW5RKR64H42REY \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 9a0bd8a61124e8f9dbb1547dc3f351261113e889f77f045056ab54e6a3b31587

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9a592015cb450eadb35290c49160213736406a06592c0d002a4cf7d8c4bf0c2d",
    "cross_cats_sorted": [
      "cs.SI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T16:07:00Z",
    "title_canon_sha256": "0012858538230f21b4fb8bc7a4b33435174a51dced0965278d0a749423e4b029"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13725",
    "kind": "arxiv",
    "version": 1
  }
}