Pith Number

pith:HLQVQ6CP

pith:2026:HLQVQ6CPFXAJDK3E4VBUPKRVIP

not attested not anchored not stored refs pending

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs

Di Huang, Huiqun Wang, Zhenghao Chen

EgoMind activates spatial reasoning in MLLMs through purely linguistic chain-of-thought without 3D geometry or priors.

arxiv:2604.03318 v2 · 2026-04-01 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{HLQVQ6CPFXAJDK3E4VBUPKRVIP}

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

we propose EgoMind, a Chain-of-Thought framework that enables geometry-free spatial reasoning through Role-Play Caption, which jointly constructs a coherent linguistic scene graph across frames, and Progressive Spatial Analysis, which progressively reasons toward task-specific questions. With only 5K auto-generated SFT samples and 20K RL samples, EgoMind achieves competitive results on VSI-Bench, SPAR-Bench, SITE-Bench, and SPBench

C2weakest assumption

That purely linguistic role-play captions can reliably construct cross-frame spatial relationships sufficient for competitive benchmark performance without any geometric supervision or 3D priors.

C3one line summary

EgoMind activates spatial cognition in MLLMs via linguistic Role-Play Caption and Progressive Spatial Analysis, reaching competitive results on VSI-Bench, SPAR-Bench, SITE-Bench and SPBench with only 5K SFT and 20K RL samples.

Formal links

3 machine-checked theorem links

Cited by

1 paper in Pith

SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs

Receipt and verification

First computed	2026-05-26T02:05:08.816284Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3ae158784f2dc091ab64e54347aa3543fd8f9301accc5699f68c598194ac3b5b

Aliases

arxiv: 2604.03318 · arxiv_version: 2604.03318v2 · doi: 10.48550/arxiv.2604.03318 · pith_short_12: HLQVQ6CPFXAJ · pith_short_16: HLQVQ6CPFXAJDK3E · pith_short_8: HLQVQ6CP

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/HLQVQ6CPFXAJDK3E4VBUPKRVIP \
  | 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: 3ae158784f2dc091ab64e54347aa3543fd8f9301accc5699f68c598194ac3b5b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "debf54fb9214e3d4166bcffd176ade6884cc8f0355ae695f4ba3c8adbf478895",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-01T15:28:13Z",
    "title_canon_sha256": "5ed9a9fe5370727cc641da44d7aa6ad3382d53375190f16aa191747cdee6b394"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.03318",
    "kind": "arxiv",
    "version": 2
  }
}