Metraipolis › archive › dc_5dd0c327cfaf
ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift — arXiv:2609.23659
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23659
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:07:17.714Z
- SHA-256 of the archived text
e3604824c33309fc1b637c84e33949fbbe84d0cfed587ffee391739b52c5a6ff- Stable URL of this page
https://metraipolis.com/documento/dc_5dd0c327cfaf
How to cite
ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift — arXiv:2609.23659 — arXiv (en), https://arxiv.org/abs/2609.23659 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5dd0c327cfaf (Metraipolis archive dc_5dd0c327cfaf, sha256 e3604824c33309fc1b637c84e33949fbbe84d0cfed587ffee391739b52c5a6ff)
BibTeX
@misc{dc5dd0c327cfaf,
title = {ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift — arXiv:2609.23659},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23659},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5dd0c327cfaf; sha256 e3604824c33309fc1b637c84e33949fbbe84d0cfed587ffee391739b52c5a6ff},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23659. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Ethereum decentralized finance (DeFi) provides a public, time-stamped record of transaction-level event streams, but the same public symbols can create strong machine-learning shortcuts. We introduce ETH-TraceBench, a benchmark for evaluating Ethereum DeFi representations under temporal, protocol, pool/infrastructure, and symbolic shift. The raw event universe covers January 2021-December 2025 and contains 1.35 billion transactions with logs and 5.01 billion raw log rows. Model evaluation uses a fixed 911,267-instance supervised sample, training on 2021-2024, selecting models on 2025H1, and testing on 2025H2. Simple models perform strongly on the aggregate temporal test: TraceStats-GB reaches 0.953 macro-F1 and TopicEmitterHashMLP 0.959 on the canonical DEX test set. Performance drops sharply under protocol novelty, with macro-F1 of 0.794, 0.743, and 0.766 for TraceStats-GB, TopicEmitterTrace-SGD, and TopicEmitterHashMLP, while strict unseen-pool scores remain 0.927, 0.897, and 0.935. Uniswap v4 and Ekubo v1, both absent from supervised training, are materially harder than the full test. Jointly masking emitter and topic identity reduces DEX macro-F1 to 0.916 and liquidation macro-F1 to 0.774 for TopicEmitterTrace-SGD. A standard Transformer over log-index-ordered events provides no consistent advantage over a deterministic shuffle of the same events, indicating that high aggregate scores can arise without sophisticated chronological modeling. A natural-prevalence audit estimates 2025H2 DEX prevalence among logged Ethereum transactions at about 22.5%, and a deterministic 400-transaction audit finds complete agreement with task label sources and independently re-queried raw-log counts. ETH-TraceBench therefore treats difficult transfer and controlled-input conditions, rather than a single aggregate score, as the main evaluation target. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.23659 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:58:09.317Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).