Pith Number

pith:NAIWJV5T

pith:2026:NAIWJV5T3OTIAPR236GFNEF5UM

not attested not anchored not stored refs pending

Learning to Predict Future-Aligned Research Proposals with Language Models

Haofei Yu, Heng Ji, Heng Wang, Jiashuo Sun, Jiawei Han, Pengcheng Jiang, Zhiyi Shi

Tuning language models on past research data improves their ability to forecast future-aligned research proposals.

arxiv:2603.27146 v3 · 2026-03-28 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{NAIWJV5T3OTIAPR236GFNEF5UM}

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

Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality. Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method.

C2weakest assumption

That semantic similarity between a generated proposal and future published papers, measured via retrieval and LLM-based scoring, serves as a valid proxy for the proposal's novelty, soundness, and overall quality.

C3one line summary

LLMs fine-tuned on time-sliced paper data generate proposals with up to 10.6% higher Future Alignment Score against actual later publications, with human experts and real implementations confirming gains.

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-27T01:04:57.433251Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7

Aliases

arxiv: 2603.27146 · arxiv_version: 2603.27146v3 · doi: 10.48550/arxiv.2603.27146 · pith_short_12: NAIWJV5T3OTI · pith_short_16: NAIWJV5T3OTIAPR2 · pith_short_8: NAIWJV5T

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/NAIWJV5T3OTIAPR236GFNEF5UM \
  | 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: 681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ed901b210b9f3c46cff3cab48342a42ffc0d06299b857cea1597ca8e8770804e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-03-28T05:41:15Z",
    "title_canon_sha256": "62778adf0200f2921e3fed3605c1962c537526af6a758f24a8872ce1cf6c1cde"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.27146",
    "kind": "arxiv",
    "version": 3
  }
}