Metraipolis › archive › dc_a07e41d7be60
Towards Automatic Evolution Tree Generation from Citation Graphs — arXiv:2609.09561
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09561
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:51:10.458Z
- SHA-256 of the archived text
e34e5f6333138b0ca791ab76707e106e93eb1bba7eb80abecd6ff6223ee3aebe- Stable URL of this page
https://metraipolis.com/documento/dc_a07e41d7be60
How to cite
Towards Automatic Evolution Tree Generation from Citation Graphs — arXiv:2609.09561 — arXiv (en), https://arxiv.org/abs/2609.09561 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a07e41d7be60 (Metraipolis archive dc_a07e41d7be60, sha256 e34e5f6333138b0ca791ab76707e106e93eb1bba7eb80abecd6ff6223ee3aebe)
BibTeX
@misc{dca07e41d7be60,
title = {Towards Automatic Evolution Tree Generation from Citation Graphs — arXiv:2609.09561},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09561},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a07e41d7be60; sha256 e34e5f6333138b0ca791ab76707e106e93eb1bba7eb80abecd6ff6223ee3aebe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09561. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-induction methods are largely leaf-bound and time-agnostic; they tend to force transitional papers into mature leaves and can create topological inversions between ancestors and descendants. We propose EvoTree, a staged framework that decouples conceptual backbone learning from temporal refinement: a graph-aware encoder with distribution-based hierarchical clustering yields a stable taxonomy backbone; temporal fine-tuning then re-attaches marginal papers to internal nodes under monotonic-path constraints; a final LLM pass labels concepts without altering the topology. We release the first annotated benchmark for this task across 11 AI subfields. EvoTree attains the highest NMI and citation-direction accuracy among all baselines and the best concept purity on the annotated benchmark, and is the only method with non-trivial marginal-paper detection on the annotated set. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.09561 — 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 2026-10-16T07:24:00.879Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).