Pith Number

pith:SMJ4MA32

pith:2026:SMJ4MA32Y4H3NHK7IGTVA7RZ4D

not attested not anchored not stored refs pending

LLM Flow Processes for Text-Conditioned Regression

Felix Biggs, Samuel Willis

LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process.

arxiv:2601.06147 v2 · 2026-01-05 · cs.LG · cs.CL · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SMJ4MA32Y4H3NHK7IGTVA7RZ4D}

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

Combining these densities with a lightweight (diffusion-based) neural process leads to better-calibrated predictions overall, outputs locally consistent trajectories, and leads to text-conditioned function space selection in the meta-learner. We propose a gradient-free (and non-Monte Carlo) method for sampling from a product-of-experts of a score model and an 'expert' (here the LLM predictive densities).

C2weakest assumption

The assumption that marginal LLM predictions can be convolved with a Gaussian in closed form, enabling the proposed gradient-free sampling method, and that the lightweight neural process can correct over-broad densities without introducing new inconsistencies or requiring extensive tuning.

C3one line summary

LLM densities fused with a diffusion neural process yield better-calibrated, locally consistent text-conditioned regression predictions plus a gradient-free product-of-experts sampler.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Conditioning Gaussian Processes on Almost Anything

Receipt and verification

First computed	2026-05-18T02:45:12.061099Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e

Aliases

arxiv: 2601.06147 · arxiv_version: 2601.06147v2 · doi: 10.48550/arxiv.2601.06147 · pith_short_12: SMJ4MA32Y4H3 · pith_short_16: SMJ4MA32Y4H3NHK7 · pith_short_8: SMJ4MA32

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/SMJ4MA32Y4H3NHK7IGTVA7RZ4D \
  | 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: 9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "91e1b2339f784b968fd167e9afade6a71377db857ba4a60b42866bebd568ec53",
    "cross_cats_sorted": [
      "cs.CL",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-01-05T21:20:38Z",
    "title_canon_sha256": "8cb6e12ecb0c442675d2fa76ab8a39b1a96505f8abaaccef6561ab8efbaf7cfb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.06147",
    "kind": "arxiv",
    "version": 2
  }
}