Provenance Before Prose: Claim-Locked Reporting

• URL: http://arxiv.org/abs/2608.25336v1
• Date: Wed, 26 Aug 2026 03:41:17 GMT
• Title: Provenance Before Prose: Claim-Locked Reporting
• Abstract summary: We frame these failures as a control problem: the evidence-bearing content of a scientific report should be fixed by structured statistical results rather than sampled during prose generation.<n>We propose claim-locked reporting, a provenance-before-prose protocol that fixes the evidence source, numbers, direction, and allowed language strength of each reportable claim.
• Score: 9.106326969263483
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) can fluently verbalize statistical evidence, yet statistical reports can still drift numerical values, invert effect directions, or restate thresholded contrasts as categorical effects. We frame these failures as a control problem: the evidence-bearing content of a scientific report should be fixed by structured statistical results rather than sampled during prose generation. We therefore use cross-run reproducibility to stress-test whether report-visible numbers and claims are bound before prose generation. Existing controls operate at the text or slot level; a deterministic hybrid template reproduces only 61.1% of report-visible numerical content across seeds because the LLM still selects which findings and numbers the template renders. We propose claim-locked reporting, a provenance-before-prose protocol that fixes the evidence source, numbers, direction, and allowed language strength of each reportable claim before the LLM writes only connective prose. Across fMRI functional-connectivity reporting and randomized controlled trial reporting on Evidence Inference 2.0, claim-locked reporting improves reproducibility over the hybrid template by 37.4 and 20.5 points, respectively. Blinded human audits support the observed direction-preservation and governance trends. In an fMRI cost analysis with DeepSeek, claim-locked reporting also yields the lowest observed token use and median generation latency.

Related papers

• Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence [0.0]
  Multi-agent AI systems improve inference by spawning agents and synthesizing reports.<n>But apparently independent reports may descend from the same evidence, and genuinely independent evidence can produce nearly identical reports.<n>No report-only aggregator can generally distinguish replication from independent corroboration.
  arXiv  Detail & Related papers  (2026-09-01T21:11:27Z)
• White Box Evidence Packages for Policy Audit Reports [0.0]
  We show that internal evidence changes how reports cite and reason about evidence, but more internal citations do not by themselves make a report more valid.<n>This study reframes internal model access as an evidence design problem for audit, rather than as a guarantee of transparency.
  arXiv  Detail & Related papers  (2026-07-23T16:06:42Z)
• Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation [0.0]
  We show that models possess the capability to detect fabricated statistics but do not recruit this capability during multi-source synthesis.<n>Specifically, source influence is governed by a methodology-register gate that responds to the distributional register of analytical text but not to numeric validity.
  arXiv  Detail & Related papers  (2026-06-03T20:15:48Z)
• What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrieval [42.66754319854329]
  We recast stimulus-locked MEG-to-audio retrieval as an auditing framework.<n>We use structural shortcuts, window-level stimulus-locked evidence, and cross-window contextual aggregation.<n>These results suggest that brain-to-language performance should be source-attributed, not merely reported.
  arXiv  Detail & Related papers  (2026-05-23T11:23:39Z)
• FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification [57.196748998757954]
  We present FactReview, an evidence-grounded reviewing system that combines claim extraction, literature positioning, and execution-based claim verification.<n>Given a submission, FactReview identifies major claims and reported results, retrieves nearby work to clarify the paper's technical position, and, when code is available, executes the released repository.<n>It then produces a concise review and an evidence report that assigns each major claim one of five labels: Supported, Supported by the paper, Partially supported, In conflict, or Inconclusive.
  arXiv  Detail & Related papers  (2026-04-05T11:45:22Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents [64.43980129731587]
  We propose a causal-inspired inference-time debiasing method called Causal Diagnosis and Correction (CDC)<n>CDC first diagnoses the bias effect of the perplexity and then separates the bias effect from the overall relevance score.<n> Experimental results across three domains demonstrate the superior debiasing effectiveness.
  arXiv  Detail & Related papers  (2025-03-11T17:59:00Z)
• Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generation [20.173287130474797]
  generative medical Vision Large Language Models (VLLMs) are prone to hallucinations and can produce inaccurate diagnostic information.<n>We introduce a novel Semantic Consistency-Based Uncertainty Quantification framework that provides both report-level and sentence-level uncertainties.<n>Our approach improves factuality scores by $10$%, achieved by rejecting $20$% of reports using the textttRadialog model on the MIMIC-CXR dataset.
  arXiv  Detail & Related papers  (2024-12-05T20:43:39Z)
• CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation [76.31621715032558]
  Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses. We introduce CaLM, a novel verification framework. Our framework empowers smaller LMs, which rely less on parametric memory, to validate the output of larger LMs.
  arXiv  Detail & Related papers  (2024-06-08T06:04:55Z)
• AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation [57.8363998797433]
  We propose AMRFact, a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs) Our approach parses factually consistent summaries into AMR graphs and injects controlled factual inconsistencies to create negative examples, allowing for coherent factually inconsistent summaries to be generated with high error-type coverage.
  arXiv  Detail & Related papers  (2023-11-16T02:56:29Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• Making Document-Level Information Extraction Right for the Right Reasons [19.00249049142611]
  Document-level information extraction is a flexible framework compatible with applications where information is not necessarily localized in a single sentence. This work studies how to ensure that document-level neural models make correct inferences from complex text and make those inferences in an auditable way.
  arXiv  Detail & Related papers  (2021-10-14T19:52:47Z)
• CLARA: Clinical Report Auto-completion [56.206459591367405]
  CLinicit Al it Report it Auto-completion (CLARA) is an interactive method that generates reports in a sentence by sentence fashion based on doctors' anchor words and partially completed sentences. In our experimental evaluation, CLARA achieved 0.393 CIDEr and 0.248 BLEU-4 on X-ray reports and 0.482 CIDEr and 0.491 BLEU-4 for EEG reports for sentence-level generation.
  arXiv  Detail & Related papers  (2020-02-26T18:45:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.