Pith Number

pith:XZ7356RA

pith:2026:XZ7356RACVIGFLLJUSPJGGD2GV

not attested not anchored not stored refs resolved

Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning

Rikui Huang, Shengzhe Zhang, Wei Wei

A strikingness measure shows that temporal knowledge graph models degrade on rare outstanding events and that ensemble gains often come from fitting trivial repetitions instead.

arxiv:2605.13153 v1 · 2026-05-13 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{XZ7356RACVIGFLLJUSPJGGD2GV}

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

Experiments on four TKG benchmarks reveal that all representative models perform worse as event strikingness increases, path-based methods excel on low-strikingness events while representation-based ones excel on high-strikingness events, and an ensemble method's gains stem from fitting trivial events rather than reasoning improvement.

C2weakest assumption

That the rule-based strikingness measuring framework accurately identifies events whose prediction requires deeper reasoning by comparing expected occurrence against peer events derived from temporal rules extracted from the same data.

C3one line summary

A rule-based strikingness measure is added to TKGR metrics to weight rare events higher, revealing that models weaken on striking events and ensemble gains come mostly from trivial fits.

References

73 extracted · 73 resolved · 0 Pith anchors

[1] ACM Computing Surveys , volume = 2022 · doi:10.1145/3450287

[2] International studies review , volume= 2010

[3] Coutinho and Sagi Eppel and Jacob Gates Foster and Andrew Gritsevskiy and Harlin Lee and Yichao Lu and Jo 2023 · doi:10.1038/s42256-023-00735-0

[4] ISA annual convention , volume= 1979

[5] IEEE Transactions on Pattern Analysis and Machine Intelligence , author = 2024 · doi:10.1109/tpami.2024.3417451

Receipt and verification

First computed	2026-05-18T03:08:57.076931Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

be7fbefa20155062ad69a49e93187a356a8eb3aa6f3e505e579e6222de10c808

Aliases

arxiv: 2605.13153 · arxiv_version: 2605.13153v1 · doi: 10.48550/arxiv.2605.13153 · pith_short_12: XZ7356RACVIG · pith_short_16: XZ7356RACVIGFLLJ · pith_short_8: XZ7356RA

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/XZ7356RACVIGFLLJUSPJGGD2GV \
  | 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: be7fbefa20155062ad69a49e93187a356a8eb3aa6f3e505e579e6222de10c808

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b33dd82b932514ea497c29560e32b72fc1ddc729e38e1548a38bd17ddde1203b",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T08:17:54Z",
    "title_canon_sha256": "266cbd1d0f89791f59a15ed3a4a3320ed904690d05b8a1406cbbdaa616828a8e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13153",
    "kind": "arxiv",
    "version": 1
  }
}