Pith Number

pith:JKNNJPLS

pith:2026:JKNNJPLSCSGNRU22IWJJDO5F3S

not attested not anchored not stored refs resolved

LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map

Jinzhou Tang, Keze Wang, Sidi Liu, Waikit Xiu, Weixing Chen

A dual-memory architecture with contrastive spatio-temporal learning builds latent cognitive maps for embodied agents.

arxiv:2605.16899 v1 · 2026-05-16 · 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{JKNNJPLSCSGNRU22IWJJDO5F3S}

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

Experiments demonstrate that our method achieves 2%-3.5% gains in both zero-shot generalization on standard VLN-CE and VSI-Bench benchmarks. We also demonstrate that our proposed cognitive map has high self-consistency.

C2weakest assumption

Foundational approaches rooted in action-centric tasks (e.g., VLN) and reasoning-centric tasks (e.g., EQA) lack a learning signal that forces them to encode fine-grained spatial relationships (like topology or distance) over long-range, fragmented experiences; the ST-CRL objective is assumed to supply exactly that missing signal.

C3one line summary

LASAR pairs a dual-memory system with spatio-temporal contrastive learning to induce latent cognitive maps, reporting 2-3.5% zero-shot gains on VLN-CE and VSI-Bench plus high map self-consistency.

References

73 extracted · 73 resolved · 12 Pith anchors

[1] Self-supervised object detection from egocentric videos 2023

[2] Vision- and-language navigation: Interpreting visually-grounded navigation instructions in real environments 2018

[3] org/abs/2510.19818 2025

[4] Clark, and Aaron Wilber 2020

[5] Rt-2: Vision-language-action mod- els transfer web knowledge to robotic control, 2023 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:29.055379Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4a9ad4bd72148cd8d35a459291bba5dcacfabdc1c6ad4938c7d7095b52ad75b7

Aliases

arxiv: 2605.16899 · arxiv_version: 2605.16899v1 · doi: 10.48550/arxiv.2605.16899 · pith_short_12: JKNNJPLSCSGN · pith_short_16: JKNNJPLSCSGNRU22 · pith_short_8: JKNNJPLS

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/JKNNJPLSCSGNRU22IWJJDO5F3S \
  | 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: 4a9ad4bd72148cd8d35a459291bba5dcacfabdc1c6ad4938c7d7095b52ad75b7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a0868a8cc29d741c352a9586f2097b2fc0b66b488480360a47911409940c3283",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T09:21:56Z",
    "title_canon_sha256": "0402443ec61ebc687c11219e67b4f7113293ef06658ea8b2079b07c075110e0a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16899",
    "kind": "arxiv",
    "version": 1
  }
}