# TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA

arXiv: https://arxiv.org/abs/2609.38861 · HTML: https://mlsanity.com/paper/2609.38861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Schema-Driven Information Extraction from Heterogeneous Tables](https://mlsanity.com/paper/2305.14336/) (2023)
- [Where Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous Driving](https://mlsanity.com/paper/2606.09644/) (2026)
- [LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering](https://mlsanity.com/paper/2608.07370/) (2026)
- [S2abEL: A Dataset for Entity Linking from Scientific Tables](https://mlsanity.com/paper/2305.00366/) (2023)
- [ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery](https://mlsanity.com/paper/2604.09237/) (2026)

## Abstract (arXiv)

Finding a relevant paper is not the same as producing a verifiable answer from it. LitTraceQA requires canonical paper identifiers, exact evidence at the page or object level, and typed answers that match the evaluator. We call the separation between source access and scorer-visible correctness the grounding contract gap. TRACE - Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction - addresses this gap with target-grouped retrieval, independent typed evidence localization, multimodal table extraction, schema-driven table construction, and fail-closed validation. It indexes 27,487 papers through passage, object, alias, citation, and dense representations while retaining the question target behind each signal. For tables, TRACE predicts the observation unit before extracting values and assembles rows with evaluator-compatible key normalization. Our audited selected clean-track artifact scores 0.760613 on the official 71-question test set, including 0.9728 paper F1, 0.6847 evidence F1, 0.9800 multiple-choice accuracy, 0.5423 table-row F1, and 0.3508 macro cell accuracy. On 11 public-development table records, a clean baseline and coordinate-aware visual fill obtain row F1 of 0.291 and 0.411, respectively; this diagnostic comparison includes fallback outputs and is not an official-test claim. Remaining errors chiefly concern locator, observation-unit, row-key, and source-value identity.