Metraipolis › archive › dc_dc73cd9a2696
DrawOffer: Evidence-Grounded Longitudinal User-State Modeling for Career Support — arXiv:2611.02793
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02793
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:23:58.341Z
- SHA-256 of the archived text
1729d37b3f5cced940632c797bb41204909be0a201f3af165d7c327520b6e2b6- Stable URL of this page
https://metraipolis.com/documento/dc_dc73cd9a2696
How to cite
DrawOffer: Evidence-Grounded Longitudinal User-State Modeling for Career Support — arXiv:2611.02793 — arXiv (en), https://arxiv.org/abs/2611.02793 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc73cd9a2696 (Metraipolis archive dc_dc73cd9a2696, sha256 1729d37b3f5cced940632c797bb41204909be0a201f3af165d7c327520b6e2b6)
BibTeX
@misc{dcdc73cd9a2696,
title = {DrawOffer: Evidence-Grounded Longitudinal User-State Modeling for Career Support — arXiv:2611.02793},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02793},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc73cd9a2696; sha256 1729d37b3f5cced940632c797bb41204909be0a201f3af165d7c327520b6e2b6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02793. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Career-support assistants must distinguish user claims from evidence of current ability and withhold judgments when evidence is insufficient. DrawOffer separates language-model observation extraction from deterministic inference over source-linked records to maintain uncertain ability estimates, experience assessments, and revisable issues. We evaluate 102 fictional personas with 580 scored checkpoints, a historical full-context and Mem0 comparison, and three auxiliary knowledge-tracing datasets. On 37 test personas, DrawOffer passes 169/210 checkpoints; checkpoint-defined issue precision and recall are 0.875 and 0.636. Across three development simulations, 87.0% of checkpoint verdicts agree, including persistent failures. A cache-only development ablation replacing answer-evidence requirements with confidence-only settlement reduces majority-vote passes from 306 to 293 of 370 and issue precision from 0.927 to 0.725. Equalizing positive source weights improves predictive metrics without changing total passes; removing decay gives mixed results. These findings support an exploratory systems contribution centered on evidence sufficiency. Developer-authored scenarios, unmatched baseline models, historical test exposure, and incomplete public artifacts limit generalization and independent reproduction. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.02793 — 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 2026-11-03T10:19:49.907Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).