Toward Auditable Neuro-Symbolic Reasoning in Pathology: SQL as an Explicit Trace of Evidence
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914233337249792 |
|---|---|
| author | Cao, Kewen Chen, Jianxu Zhang, Yongbing Zhang, Ye Wang, Hongxiao |
| author_facet | Cao, Kewen Chen, Jianxu Zhang, Yongbing Zhang, Ye Wang, Hongxiao |
| contents | Automated pathology image analysis is central to clinical diagnosis, but clinicians still ask which slide features drive a model's decision and why. Vision-language models can produce natural language explanations, but these are often correlational and lack verifiable evidence. In this paper, we introduce an SQL-centered agentic framework that enables both feature measurement and reasoning to be auditable. Specifically, after extracting human-interpretable cellular features, Feature Reasoning Agents compose and execute SQL queries over feature tables to aggregate visual evidence into quantitative findings. A Knowledge Comparison Agent then evaluates these findings against established pathological knowledge, mirroring how pathologists justify diagnoses from measurable observations. Extensive experiments evaluated on two pathology visual question answering datasets demonstrate our method improves interpretability and decision traceability while producing executable SQL traces that link cellular measurements to diagnostic conclusions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01875 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Auditable Neuro-Symbolic Reasoning in Pathology: SQL as an Explicit Trace of Evidence Cao, Kewen Chen, Jianxu Zhang, Yongbing Zhang, Ye Wang, Hongxiao Artificial Intelligence Quantitative Methods Automated pathology image analysis is central to clinical diagnosis, but clinicians still ask which slide features drive a model's decision and why. Vision-language models can produce natural language explanations, but these are often correlational and lack verifiable evidence. In this paper, we introduce an SQL-centered agentic framework that enables both feature measurement and reasoning to be auditable. Specifically, after extracting human-interpretable cellular features, Feature Reasoning Agents compose and execute SQL queries over feature tables to aggregate visual evidence into quantitative findings. A Knowledge Comparison Agent then evaluates these findings against established pathological knowledge, mirroring how pathologists justify diagnoses from measurable observations. Extensive experiments evaluated on two pathology visual question answering datasets demonstrate our method improves interpretability and decision traceability while producing executable SQL traces that link cellular measurements to diagnostic conclusions. |
| title | Toward Auditable Neuro-Symbolic Reasoning in Pathology: SQL as an Explicit Trace of Evidence |
| topic | Artificial Intelligence Quantitative Methods |
| url | https://arxiv.org/abs/2601.01875 |