Metraipolis › archive › dc_bcbefc6988d2

More Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev — arXiv:2609.36154

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36154
License (as archived)
CC0-1.0
Archived
2026-10-07T16:22:19.345Z
SHA-256 of the archived text
b701ea6ba3583689003378cf4c4055b0f4ab5695dc58428edcbacfcf6de08477
Stable URL of this page
https://metraipolis.com/documento/dc_bcbefc6988d2

How to cite

More Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev — arXiv:2609.36154 — arXiv (en), https://arxiv.org/abs/2609.36154 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcbefc6988d2 (Metraipolis archive dc_bcbefc6988d2, sha256 b701ea6ba3583689003378cf4c4055b0f4ab5695dc58428edcbacfcf6de08477)
BibTeX
@misc{dcbcbefc6988d2,
  title = {More Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev — arXiv:2609.36154},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36154},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcbefc6988d2; sha256 b701ea6ba3583689003378cf4c4055b0f4ab5695dc58428edcbacfcf6de08477},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36154. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General-purpose models promise sensor-based decisions without training a task-specific classifier, which could reduce the dependence of Human Activity Recognition (HAR) on labeled data. Yet it remains unclear whether such models can directly interpret deterministic descriptions of physical sensor signals well enough to replace or complement trained HAR models. We study this question using Jev, a fixed general-purpose probabilistic decision model, on 1,800 class-balanced accelerometer windows from WISDM, UCI341, and PAMAP2. Jev receives no labeled examples, retrieval context, or HAR-specific parameter updates. We evaluate three deterministic sensor representations and compare 5,400 Jev decisions with a generative baseline and three supervised HAR models. Jev remains far below supervised recognition, with its strongest representation reaching macro-F1 of 0.038, 0.118, and 0.089 across the three datasets, compared with 0.686 to 0.907 for the supervised models. More numerical features do not improve Jev. Instead, they reduce recognition on all three datasets, while augmenting the same numerical evidence with a deterministic semantic rendering partially recovers performance, although the experiment does not isolate semantics from the accompanying serialization and redundancy changes. Jev is fast and inexpensive to query, but its probabilities are not reliably calibrated for recognition. A post-hoc fusion analysis finds a small improvement on WISDM that does not replicate on UCI341 or PAMAP2. These results show that training-free sensor decisions depend not only on the information available in the signal, but also on whether the model can use the representation through which that information is exposed. The sensor-to-model interface should therefore be treated as part of the model evaluation rather than as a neutral preprocessing step.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.36154 — 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 2026-10-07T15:54:53.471Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).