Pith Number

pith:DUUXOOSS

pith:2019:DUUXOOSSGDYCH27PYPTPBK5HDJ

not attested not anchored not stored refs resolved

Invariant Risk Minimization

David Lopez-Paz, Ishaan Gulrajani, L\'eon Bottou, Martin Arjovsky

Invariant Risk Minimization finds a data representation where the same classifier is optimal for every training distribution.

arxiv:1907.02893 v3 · 2019-07-05 · stat.ML · cs.AI · 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{DUUXOOSSGDYCH27PYPTPBK5HDJ}

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

Through theory and experiments, we show how the invariances learned by IRM relate to the causal structures governing the data and enable out-of-distribution generalization.

C2weakest assumption

The training distributions must share the same underlying causal mechanisms while differing in non-causal aspects, allowing the shared optimal classifier to identify the invariant causal features.

C3one line summary

IRM learns representations such that the optimal classifier is the same across training distributions, linking invariances to causal structures for improved out-of-distribution generalization.

References

58 extracted · 58 resolved · 0 Pith anchors

[1] John Aldrich. Autonomy. Oxford Economic Papers, 1989 1989

[2] Robust supervised learning 2005

[3] Peter L. Bartlett, Philip M. Long, G´ abor Lugosi, and Alexander Tsigler. Benign Overﬁtting in Linear Regression. arXiv, 2019 2019

[4] Recognition in terra incognita 2018

[5] Analysis of representations for domain adaptation 2007

Formal links

2 machine-checked theorem links

Cited by

139 papers in Pith

TRACE-Seg3D: Counterfactual Context Auditing For Robust 3D Glioma Segmentation Under Institutional Shift

Platonic Projection Structures: Operator-Induced Observability in Representation Learning

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

Learning Subset-Shared Invariances for Domain Generalization with Mixture-of-Experts

Assessing Distribution Shift in Human Activity Recognition for Domain Generalization

Receipt and verification

First computed	2026-07-05T00:51:03.107447Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1d29773a5230f023ebefc3e6f0aba71a6398e4ff029ffe9d2a9cf98e37c550c2

Aliases

arxiv: 1907.02893 · arxiv_version: 1907.02893v3 · doi: 10.48550/arxiv.1907.02893 · pith_short_12: DUUXOOSSGDYC · pith_short_16: DUUXOOSSGDYCH27P · pith_short_8: DUUXOOSS

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/DUUXOOSSGDYCH27PYPTPBK5HDJ \
  | 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: 1d29773a5230f023ebefc3e6f0aba71a6398e4ff029ffe9d2a9cf98e37c550c2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3dde677f4e6417c0e3d979f253b506fc0a18500296598fec10b5fba21ec328cf",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2019-07-05T15:26:26Z",
    "title_canon_sha256": "d5e2e0d066b2cba1ece5bd866d795ec1c67ad6b3384c25724a3b812bcd096f61"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1907.02893",
    "kind": "arxiv",
    "version": 3
  }
}