Metraipolis › archive › dc_f2ae36057c3f

TRIPROBE: Probing Task Separability Beyond Classification for XAI — arXiv:2609.18525

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18525
License (as archived)
CC0-1.0
Archived
2026-10-15T15:08:04.385Z
SHA-256 of the archived text
45b2ab53f35932e844b589dbc2de8fd95c3ccb2e0aa05c1d5a81432eb9dc3fd1
Stable URL of this page
https://metraipolis.com/documento/dc_f2ae36057c3f

How to cite

TRIPROBE: Probing Task Separability Beyond Classification for XAI — arXiv:2609.18525 — arXiv (en), https://arxiv.org/abs/2609.18525 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f2ae36057c3f (Metraipolis archive dc_f2ae36057c3f, sha256 45b2ab53f35932e844b589dbc2de8fd95c3ccb2e0aa05c1d5a81432eb9dc3fd1)
BibTeX
@misc{dcf2ae36057c3f,
  title = {TRIPROBE: Probing Task Separability Beyond Classification for XAI — arXiv:2609.18525},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18525},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f2ae36057c3f; sha256 45b2ab53f35932e844b589dbc2de8fd95c3ccb2e0aa05c1d5a81432eb9dc3fd1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18525. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses this gap with a multi-level probing framework for explainable diagnosis of task separability. Rather than treating models as black boxes, TriProbe traces how separability evolves across inputs, learned features, and final classifiers. It decomposes multi-task problems into binary subtasks and applies three complementary probes: a Foundational Probe on input spaces, a Latent Probe on feature representations, and a Final Probe on classifier outputs. Using Maximum Fisher's Discriminant Ratio as a principled separability metric, TriProbe identifies bottlenecks and affected task pairs. Experiments on the Roshambo sEMG benchmark show how TriProbe reveals hidden breakdowns, guiding data collection, validation, and architecture design.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.18525 — 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 2026-10-15T14:08:19.260Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).