Metraipolis › archive › dc_7a4624316c69

ScalarLens: Numerical Embeddings with Stable Coordinates and Contextual Responses for CTR Prediction — arXiv:2609.29182

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29182
License (as archived)
CC0-1.0
Archived
2026-10-08T06:43:56.392Z
SHA-256 of the archived text
6a8eedb4a84c1bc2c756b90a92881e5b2d233318b4181984a42b20e75bae3eb5
Stable URL of this page
https://metraipolis.com/documento/dc_7a4624316c69

How to cite

ScalarLens: Numerical Embeddings with Stable Coordinates and Contextual Responses for CTR Prediction — arXiv:2609.29182 — arXiv (en), https://arxiv.org/abs/2609.29182 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a4624316c69 (Metraipolis archive dc_7a4624316c69, sha256 6a8eedb4a84c1bc2c756b90a92881e5b2d233318b4181984a42b20e75bae3eb5)
BibTeX
@misc{dc7a4624316c69,
  title = {ScalarLens: Numerical Embeddings with Stable Coordinates and Contextual Responses for CTR Prediction — arXiv:2609.29182},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29182},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a4624316c69; sha256 6a8eedb4a84c1bc2c756b90a92881e5b2d233318b4181984a42b20e75bae3eb5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29182. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Numerical embeddings for click-through rate (CTR) prediction are built on a convenient but restrictive premise: a scalar has one representation. This premise conflates where a value lies with what it means for the current sample. On the Criteo validation split, the same numerical interval carries residual click evidence with opposite signs across categorical and numerical contexts, even after additive main effects are removed. Production pipelines compound this mismatch because externally normalized features require transformations and statistics to remain synchronized between training and serving. We introduce ScalarLens, a numerical embedding that preserves what a value is while adapting how it should be interpreted. A monotone local mesh constructs a stable coordinate from the focal scalar alone; bounded low-rank dynamics then produce a contextual response without moving that coordinate or replacing categorical tokens and the CTR backbone. In a 1,539-run primary evaluation covering 19 representations, three datasets, nine backbones, and three seeds, ScalarLens ranks first in 25 of 27 settings on original numerical scales and second in the remaining two. Matched ablations show that scale correction, additional local capacity, and generic conditioning do not reproduce the gain. A controlled study further recovers categorical, numerical, and mixed response mechanisms under context shift while the focal coordinate remains exactly invariant. A complete rerun under shared standardization retains significant advantages over DEER, DAES, and NaryDis, showing that the result is not explained by tolerance to raw scales alone. ScalarLens therefore recasts numerical embedding as a measurement problem: coordinates belong to values, while predictive responses belong to values in context.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.29182 — 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 2026-10-08T06:09:07.176Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).