@inproceedings{arun-etal-2026-temporal,
title = "Temporal Epistemic Graph of Thought: Uncertainty over Latent Reasoning Structure for Selective Abstention in Clinical Prediction",
author = "Arun, Govind and
Bathini, Sadhvik and
Bhasuran, Balu",
editor = "Atwell, Katherine and
Borah, Angana and
Dementieva, Daryna and
Kreiss, Elisa and
Kotonya, Neema and
Liu, Jiarui and
Olson, Liz and
Wan, Ruyuan and
Zhao, Jieyu",
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Positive Impact ({NLP}4{PI})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4pi-1.37/",
pages = "482--492",
ISBN = "979-8-89176-495-8",
abstract = "Reliable clinical prediction requires both accuracy and principled uncertainty quantification, so that a model can flag cases where it lacks a coherent basis for its prediction and defer to a clinician. We introduce the Temporal Epistemic Graph of Thought (TEGoT), a framework that fuses free-text clinical notes with structured temporal events and models uncertainty over latent reasoning structure. Patient trajectories are represented as temporal graphs integrated with note embeddings, and a variational reasoning graph induces a distribution over latent topologies, decomposing predictive uncertainty into aleatoric, epistemic, and structural components, where structural uncertainty measures variability across inferred reasoning graphs. On a retrospective MIMIC-IV ICU mortality task, using structured events available before 12 hours and discharge-summary-derived note embeddings as a proof-of-concept text source, TEGoT reaches AUROC 0.931, AUPRC 0.655, and ECE 0.021 after temperature scaling, comparable to or above tabular, neural, and graph baselines under the same cohort. Structural uncertainty gives stronger error detection (AUROC 0.724) than standard epistemic uncertainty (0.681), and its weak correlation with epistemic uncertainty ($\rho{=}0.19$) indicates a complementary signal rather than a repackaging of dropout variance. Using this signal for selective prediction raises retained AUROC from 0.931 to 0.963 at 50{\%} coverage, with a net benefit of $+0.083$ over treat-all and a decision-curve-positive range of $[0.05, 0.42]$, supporting reliable abstention. We argue that the social value of a clinical model should be measured not by discrimination alone but by the harm it averts when it defers, and we show that net benefit and risk{--}coverage trade-offs offer concrete, deployment-relevant ways to quantify that benefit."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arun-etal-2026-temporal">
<titleInfo>
<title>Temporal Epistemic Graph of Thought: Uncertainty over Latent Reasoning Structure for Selective Abstention in Clinical Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Govind</namePart>
<namePart type="family">Arun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadhvik</namePart>
<namePart type="family">Bathini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balu</namePart>
<namePart type="family">Bhasuran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angana</namePart>
<namePart type="family">Borah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Kreiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neema</namePart>
<namePart type="family">Kotonya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liz</namePart>
<namePart type="family">Olson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruyuan</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-495-8</identifier>
</relatedItem>
<abstract>Reliable clinical prediction requires both accuracy and principled uncertainty quantification, so that a model can flag cases where it lacks a coherent basis for its prediction and defer to a clinician. We introduce the Temporal Epistemic Graph of Thought (TEGoT), a framework that fuses free-text clinical notes with structured temporal events and models uncertainty over latent reasoning structure. Patient trajectories are represented as temporal graphs integrated with note embeddings, and a variational reasoning graph induces a distribution over latent topologies, decomposing predictive uncertainty into aleatoric, epistemic, and structural components, where structural uncertainty measures variability across inferred reasoning graphs. On a retrospective MIMIC-IV ICU mortality task, using structured events available before 12 hours and discharge-summary-derived note embeddings as a proof-of-concept text source, TEGoT reaches AUROC 0.931, AUPRC 0.655, and ECE 0.021 after temperature scaling, comparable to or above tabular, neural, and graph baselines under the same cohort. Structural uncertainty gives stronger error detection (AUROC 0.724) than standard epistemic uncertainty (0.681), and its weak correlation with epistemic uncertainty (ρ=0.19) indicates a complementary signal rather than a repackaging of dropout variance. Using this signal for selective prediction raises retained AUROC from 0.931 to 0.963 at 50% coverage, with a net benefit of +0.083 over treat-all and a decision-curve-positive range of [0.05, 0.42], supporting reliable abstention. We argue that the social value of a clinical model should be measured not by discrimination alone but by the harm it averts when it defers, and we show that net benefit and risk–coverage trade-offs offer concrete, deployment-relevant ways to quantify that benefit.</abstract>
<identifier type="citekey">arun-etal-2026-temporal</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4pi-1.37/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>482</start>
<end>492</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporal Epistemic Graph of Thought: Uncertainty over Latent Reasoning Structure for Selective Abstention in Clinical Prediction
%A Arun, Govind
%A Bathini, Sadhvik
%A Bhasuran, Balu
%Y Atwell, Katherine
%Y Borah, Angana
%Y Dementieva, Daryna
%Y Kreiss, Elisa
%Y Kotonya, Neema
%Y Liu, Jiarui
%Y Olson, Liz
%Y Wan, Ruyuan
%Y Zhao, Jieyu
%S Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-495-8
%F arun-etal-2026-temporal
%X Reliable clinical prediction requires both accuracy and principled uncertainty quantification, so that a model can flag cases where it lacks a coherent basis for its prediction and defer to a clinician. We introduce the Temporal Epistemic Graph of Thought (TEGoT), a framework that fuses free-text clinical notes with structured temporal events and models uncertainty over latent reasoning structure. Patient trajectories are represented as temporal graphs integrated with note embeddings, and a variational reasoning graph induces a distribution over latent topologies, decomposing predictive uncertainty into aleatoric, epistemic, and structural components, where structural uncertainty measures variability across inferred reasoning graphs. On a retrospective MIMIC-IV ICU mortality task, using structured events available before 12 hours and discharge-summary-derived note embeddings as a proof-of-concept text source, TEGoT reaches AUROC 0.931, AUPRC 0.655, and ECE 0.021 after temperature scaling, comparable to or above tabular, neural, and graph baselines under the same cohort. Structural uncertainty gives stronger error detection (AUROC 0.724) than standard epistemic uncertainty (0.681), and its weak correlation with epistemic uncertainty (ρ=0.19) indicates a complementary signal rather than a repackaging of dropout variance. Using this signal for selective prediction raises retained AUROC from 0.931 to 0.963 at 50% coverage, with a net benefit of +0.083 over treat-all and a decision-curve-positive range of [0.05, 0.42], supporting reliable abstention. We argue that the social value of a clinical model should be measured not by discrimination alone but by the harm it averts when it defers, and we show that net benefit and risk–coverage trade-offs offer concrete, deployment-relevant ways to quantify that benefit.
%U https://aclanthology.org/2026.nlp4pi-1.37/
%P 482-492
Markdown (Informal)
[Temporal Epistemic Graph of Thought: Uncertainty over Latent Reasoning Structure for Selective Abstention in Clinical Prediction](https://aclanthology.org/2026.nlp4pi-1.37/) (Arun et al., NLP4PI 2026)
ACL