Pith Number

pith:EXQNZOXA

pith:2026:EXQNZOXAQJUXJ7PEJANKKHMECX

not attested not anchored not stored refs resolved

Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction

Kejun Ren, Lei Jin, Lianming Xu, Li Wang, Tianxin Huang

A scalar frame-level gate computed from internal feature changes extends effective memory in recurrent 3D reconstruction without added cost or training.

arxiv:2605.16981 v1 · 2026-05-16 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EXQNZOXAQJUXJ7PEJANKKHMECX}

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

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

Our gate cuts ATE by 51% on long TUM-RGBD pose sequences, reduces AbsRel by 12.8% on Bonn video depth, and on KITTI long-sequence pose estimation surpasses both LongStream and Keyframe-VO, while retaining strictly constant memory at zero training cost.

C2weakest assumption

Frame-to-frame changes of internal features can be used to derive in closed form a scalar α_t that correctly determines how strongly each frame should contribute to the recurrent state, serving as a content-independent continuous relaxation of classical SLAM keyframe selection.

C3one line summary

A closed-form scalar frame-level gate α_t derived from internal feature changes extends effective memory in recurrent 3D reconstruction and improves accuracy on long sequences up to 4541 frames.

References

31 extracted · 31 resolved · 7 Pith anchors

[1] Neural rgb-d surface reconstruction 2022

[2] Orb- slam3: An accurate open-source library for visual, visual–inertial, and multimap slam.IEEE transactions on robotics, 37(6):1874–1890, 2021 2021

[3] TTT3R: 3D Reconstruction as Test-Time Training 2025 · arXiv:2509.26645

[4] Long3r: Long sequence streaming 3d reconstruction 2025

[5] Longstream: Long-sequence streaming autoregressive visual geometry 2026

Receipt and verification

First computed	2026-05-20T00:03:34.300713Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

25e0dcbae0826974fde4481aa51d8415f60ebce0be03c0dd063fa5a3b846d0e2

Aliases

arxiv: 2605.16981 · arxiv_version: 2605.16981v1 · doi: 10.48550/arxiv.2605.16981 · pith_short_12: EXQNZOXAQJUX · pith_short_16: EXQNZOXAQJUXJ7PE · pith_short_8: EXQNZOXA

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/EXQNZOXAQJUXJ7PEJANKKHMECX \
  | 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: 25e0dcbae0826974fde4481aa51d8415f60ebce0be03c0dd063fa5a3b846d0e2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1c3b015c024990a672519fde5c56113184486eac6fd37de8d5ff14fc82dcb68c",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T13:00:49Z",
    "title_canon_sha256": "6b5db4fd1aa168ba6b99db5e48d4ff6e681c78435c524d78409314b11bf27f5d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16981",
    "kind": "arxiv",
    "version": 1
  }
}