Pith Number

pith:XJIJEQJ4

pith:2026:XJIJEQJ44MTYBQE2ZJXPTRSTDC

not attested not anchored not stored refs resolved

Context Training with Active Information Seeking

Adhiguna Kuncoro, Arthur Szlam, Jiajun Shen, Lucio Dery, Marc'Aurelio Ranzato, Qixuan Feng, Zeyu Huang

Pairing search tools with multi-candidate pruning during context training produces consistent LLM gains without weight updates.

arxiv:2605.13050 v2 · 2026-05-13 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{XJIJEQJ44MTYBQE2ZJXPTRSTDC}

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

when paired with a search-based training procedure that maintains and prunes multiple candidate contexts, active information seeking delivers consistent and substantial gains

C2weakest assumption

That the external search tools return sufficiently accurate and relevant passages and that the pruning step can reliably discard noisy or misleading contexts without discarding useful ones.

C3one line summary

Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.

References

67 extracted · 67 resolved · 8 Pith anchors

[1] Mastering the game of 2016

[2] Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs , author=. 2024 , eprint= 2024

[3] Arora and Jason Wei and Rebecca Soskin Hicks and Preston Bowman and Joaquin Qui

[4] Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwa

[5] Mondal and Jyoti Prakash Sahoo , title =

Receipt and verification

First computed	2026-05-18T03:08:59.334343Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ba5092413ce32780c09aca6ef9c6531894b166e0eba24a62102e2415e73c8ff5

Aliases

arxiv: 2605.13050 · arxiv_version: 2605.13050v2 · doi: 10.48550/arxiv.2605.13050 · pith_short_12: XJIJEQJ44MTY · pith_short_16: XJIJEQJ44MTYBQE2 · pith_short_8: XJIJEQJ4

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/XJIJEQJ44MTYBQE2ZJXPTRSTDC \
  | 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: ba5092413ce32780c09aca6ef9c6531894b166e0eba24a62102e2415e73c8ff5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ba72141cdedaed3fe8fc260214b46024b12ab3ea8afdd5b7b98e1f5ecfc19c6f",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T06:15:32Z",
    "title_canon_sha256": "02b8f238bb5de79e2caa4bb12872c45e676aa76eef55f0d07d474f89fcc6523d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13050",
    "kind": "arxiv",
    "version": 2
  }
}