pith. sign in
Pith Number

pith:D2LFRPRG

pith:2026:D2LFRPRGCNIY3JMNB7QHIGS3US
not attested not anchored not stored refs resolved

RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search

Daiting Shi, Dawei Yin, Ge Chen, Li Gao, Lixin Su, Tingyu Chen, Wenkai Zhang

Large language models infer query-specific validity horizons to replace static time filters in web search.

arxiv:2605.13052 v1 · 2026-05-13 · cs.IR · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{D2LFRPRGCNIY3JMNB7QHIGS3US}

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

Our framework extracts fine-grained temporal contexts from documents and leverages LLMs to deduce a query-specific 'validity horizon' ... Results demonstrate significant improvements in search freshness and user experience metrics, validating the effectiveness of LLM-driven reasoning for solving semantic expiration at an industrial scale.

C2weakest assumption

That LLMs can reliably infer query-specific semantic expiration boundaries from document text with only the described hallucination mitigation strategies, without introducing systematic errors that would negate the reported A/B gains.

C3one line summary

An LLM framework with RAG predicts query-specific validity horizons for web content expiration and shows gains in production A/B tests.

References

21 extracted · 21 resolved · 2 Pith anchors

[1] Tempretriever: Fusion-based temporal dense passage retri eval for time-sensitive questions 2025
[2] Anlei Dong, Yi Chang, Zhaohui Zheng, Gilad Mishne, Jing Bai, Ruiqiang Zhang, Karolina Buchner, Ciya Liao, and Fernando Diaz. 2010. Towards recency ranking in web search. InProceedings of the Third ACM 2010
[3] Anlei Dong, Ruiqiang Zhang, Pranam Kolari, Jing Bai, Fernando Diaz, Yi Chang, Zhaohui Zheng, and Hongyuan Zha. 2010. Time is of the essence: improv- ing recency ranking using Twitter data. InProceedin 2010 · doi:10.1145/1772690.1772725
[4] Rujun Han, Xiang Ren, and Nanyun Peng. 2021. ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning. arXiv:2012.15283 [cs.CL] https://arxiv.org/abs/2012.15283 2021
[5] Sufficient context: A new lens on retrieval augmented generation systems.arXiv preprint arXiv:2411.06037.2024 2025
Receipt and verification
First computed 2026-05-18T03:08:59.281183Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

1e9658be2613518da58d0fe0741a5ba4aea3fbd1ec9bb737add23929a9e7a770

Aliases

arxiv: 2605.13052 · arxiv_version: 2605.13052v1 · doi: 10.48550/arxiv.2605.13052 · pith_short_12: D2LFRPRGCNIY · pith_short_16: D2LFRPRGCNIY3JMN · pith_short_8: D2LFRPRG
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US \
  | 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: 1e9658be2613518da58d0fe0741a5ba4aea3fbd1ec9bb737add23929a9e7a770
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "73199040857af0483f146ca09c99ea8b040094cb3ec2c78d5f9251c4d6b48874",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-13T06:20:28Z",
    "title_canon_sha256": "3a3eb5a32fd3ea38a1f33e237171581644c2f64d4486226e1f22ef12525e371d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13052",
    "kind": "arxiv",
    "version": 1
  }
}