Pith Number

pith:MYGD3NWE

pith:2026:MYGD3NWEKSFVOOJ3YWMEISCQLI

not attested not anchored not stored refs resolved

Conditional Compatibility Learning for Context-Dependent Anomaly Detection

Didier Stricker, Jason Rambach, Shashank Mishra

Global representations that mix subject and context are provably non-identifiable for context-dependent anomalies.

arxiv:2601.22868 v3 · 2026-01-30 · cs.CV · 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{MYGD3NWEKSFVOOJ3YWMEISCQLI}

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

any detector reasoning from a global representation that conflates subject and context is provably non-identifiable: two different subject-context configurations can map to the same embedding while requiring opposite labels, and no such detector can be correct on both.

C2weakest assumption

That the proposed disentangled subject- and context-aware representations in CC-CLIP can be learned from single images without additional supervision or labels that would reintroduce the original identifiability problem.

C3one line summary

Conditional compatibility learning reframes anomaly detection as checking subject-context fit rather than global deviation, with CC-CLIP delivering state-of-the-art performance on contextual anomalies and competitive results on structural ones.

References

14 extracted · 14 resolved · 0 Pith anchors

[1] URL https://cdn.openai.com/papers/ gpt-4.pdf. Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. Learning transferable visua 2021 · doi:10.1016/j.neucom.2020.11.018

[2] Section A presents additional model details

[3] Section B describes implementation and training de- tails

[4] Section C reports extended ablation studies and addi- tional quantitative results

[5] Section D details the construction, annotation protocol, and evaluation splits of the CAAD-3K dataset

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:31.737338Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

660c3db6c4548b57393bc5984448505a3260422ebd7833fbb5da35ab993ec508

Aliases

arxiv: 2601.22868 · arxiv_version: 2601.22868v3 · doi: 10.48550/arxiv.2601.22868 · pith_short_12: MYGD3NWEKSFV · pith_short_16: MYGD3NWEKSFVOOJ3 · pith_short_8: MYGD3NWE

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/MYGD3NWEKSFVOOJ3YWMEISCQLI \
  | 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: 660c3db6c4548b57393bc5984448505a3260422ebd7833fbb5da35ab993ec508

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9ae38fb2e0cb2959d59975bb53fdee75512685ee0c57ba91b68fe946e20a8d59",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-01-30T11:48:20Z",
    "title_canon_sha256": "7262d7d8cad66331ec68cbe120b1474dfbc2a2007e0e037e0b6115e240bc0928"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.22868",
    "kind": "arxiv",
    "version": 3
  }
}