Pith Number

pith:AQZLYLHO

pith:2025:AQZLYLHOLDHJDQ73OE5MWIIPTS

not attested not anchored not stored refs pending

Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models

Lan-Zhe Guo, Rui Zhu, Song-Lin Lv, Zi-Kang Wang

Bi-CoG produces higher-quality pseudo-labels for vision-language models by checking consistency both across models and inside a single model.

arxiv:2510.20477 v3 · 2025-10-23 · 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{AQZLYLHOLDHJDQ73OE5MWIIPTS}

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

Bi-CoG assigns high-quality and low-bias pseudo-labels by simultaneously exploiting inter-model and intra-model consistency, along with an error-aware dynamic pseudo-label assignment strategy, and consistently and significantly improves the performance of existing methods over 14 datasets.

C2weakest assumption

The assumption that simultaneous inter-model and intra-model consistency, together with the error-aware dynamic strategy, reliably produces pseudo-labels that are both high-quality and low-bias without introducing new forms of confirmation bias or hyperparameter sensitivity, as implied by the claim that this addresses the limitations of prior consistency or threshold-based methods.

C3one line summary

Bi-CoG improves semi-supervised fine-tuning of vision-language models by assigning higher-quality pseudo-labels through simultaneous inter-model and intra-model consistency checks combined with dynamic error-aware selection.

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-26T01:03:17.164579Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a

Aliases

arxiv: 2510.20477 · arxiv_version: 2510.20477v3 · doi: 10.48550/arxiv.2510.20477 · pith_short_12: AQZLYLHOLDHJ · pith_short_16: AQZLYLHOLDHJDQ73 · pith_short_8: AQZLYLHO

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/AQZLYLHOLDHJDQ73OE5MWIIPTS \
  | 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: 0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "676828eb599c82787e70d879d5be1b9078b18f36b3bebe32ce9e00128b2cb323",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-10-23T12:16:41Z",
    "title_canon_sha256": "4df7e32150b77cd9747f6830b14f5e201a60620f782f396b9495efd6d9fb6f5a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.20477",
    "kind": "arxiv",
    "version": 3
  }
}