Pith Number

pith:4HT3Q46X

pith:2026:4HT3Q46XOBKAPZZHJBA2ZOWJZ4

not attested not anchored not stored refs resolved

Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers

Victor Norgren

Stateful sessions with persistent KV caches let streaming transformer queries run in time independent of context size.

arxiv:2605.13784 v1 · 2026-05-13 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{4HT3Q46XOBKAPZZHJBA2ZOWJZ4}

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

On streaming market-data benchmarks the reference implementation achieves up to 5.9x speedup over conventional inference engines (vLLM, SGLang, TensorRT-LLM, llama.cpp), holding query latency constant as accumulated context grows.

C2weakest assumption

That a multi-tenant continuous-batching scheduler with cell-budget admission and prefix-aware grouped prefill can maintain full quadratic self-attention across dozens of stateful sessions without correctness loss or prohibitive overhead.

C3one line summary

Stateful sessions with incremental KV cache and flash queries allow O(|q|) latency in streaming transformer inference, delivering up to 5.9x speedup over conventional engines while preserving full attention.

References

20 extracted · 20 resolved · 8 Pith anchors

[1] Lopez-Lira, A. and Tang, Y. Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models. SSRN, 2023 2023

[2] BloombergGPT: A Large Language Model for Finance 2023 · arXiv:2303.17564

[3] Lost in the Middle: How Language Models Use Long Contexts 2024

[4] Prompt Caching 2024

[5] Longformer: The Long-Document Transformer 2004 · arXiv:2004.05150

Receipt and verification

First computed	2026-05-18T02:44:15.703620Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e1e7b873d7705407e7274841acbac9cf35dc7ad4a60bb028b6753d9d4fd70f87

Aliases

arxiv: 2605.13784 · arxiv_version: 2605.13784v1 · doi: 10.48550/arxiv.2605.13784 · pith_short_12: 4HT3Q46XOBKA · pith_short_16: 4HT3Q46XOBKAPZZH · pith_short_8: 4HT3Q46X

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/4HT3Q46XOBKAPZZHJBA2ZOWJZ4 \
  | 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: e1e7b873d7705407e7274841acbac9cf35dc7ad4a60bb028b6753d9d4fd70f87

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bd29f8c25355fee4f2d5f38a0228802a52c9dc460029c06a1cb59b935799d4dc",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T17:06:15Z",
    "title_canon_sha256": "c02974716d1ef298f9e1780a9054c448f6d79e4fd29987f4ce8faa7df932c10d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13784",
    "kind": "arxiv",
    "version": 1
  }
}