<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roshchupkin-etal-2026-kg">
    <titleInfo>
        <title>KG-SFT Contracts: Auditing Evidence Lineage and Loader Retention in Enterprise RAG Adaptation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bogdan</namePart>
        <namePart type="family">Roshchupkin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Litvintsev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alina</namePart>
        <namePart type="family">Avanesyan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="family">Khodorchenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrei</namePart>
        <namePart type="family">Zhukov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Btissam</namePart>
            <namePart type="family">Er-Rahmadi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sébastien</namePart>
            <namePart type="family">Montella</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Damien</namePart>
            <namePart type="family">Graux</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">André</namePart>
            <namePart type="family">Melo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hajira</namePart>
            <namePart type="family">Jabeen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-457-6</identifier>
    </relatedItem>
    <abstract>KG-assisted supervised fine-tuning depends on evidence selection, context compilation, and data loading. We present KG-SFT Contracts, a provenance-aware interface that audits these stages and links model comparisons to their data and scoring records. In a retrospective Russian enterprise case, a pool of 484 graph candidates contributed no graph-origin distractors to the compiled corpus, and exact loader replay discarded 40 of 946 intended examples before splitting. Removing annotated non-support context restored every row while preserving questions, targets, and verified support. Downstream comparisons remained statistically inconclusive. Controlled checks on a public graph-bearing fixture show how cross-record validation detects unresolved graph references and conflicting source revisions alongside role-aware repair. The installable implementation includes fixture-level CPU measurements, incremental adoption guidance, and an official RuBQ schema-import check. The case illustrates how lineage and retention audits make adaptation pipelines inspectable before model effects are attributed to their configured inputs.</abstract>
    <identifier type="citekey">roshchupkin-etal-2026-kg</identifier>
    <location>
        <url>https://aclanthology.org/2026.nora-1.9/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>98</start>
            <end>108</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T KG-SFT Contracts: Auditing Evidence Lineage and Loader Retention in Enterprise RAG Adaptation
%A Roshchupkin, Bogdan
%A Litvintsev, Alexander
%A Avanesyan, Alina
%A Khodorchenko, Maria
%A Zhukov, Andrei
%Y Er-Rahmadi, Btissam
%Y Montella, Sébastien
%Y Graux, Damien
%Y Melo, André
%Y Jabeen, Hajira
%S Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-457-6
%F roshchupkin-etal-2026-kg
%X KG-assisted supervised fine-tuning depends on evidence selection, context compilation, and data loading. We present KG-SFT Contracts, a provenance-aware interface that audits these stages and links model comparisons to their data and scoring records. In a retrospective Russian enterprise case, a pool of 484 graph candidates contributed no graph-origin distractors to the compiled corpus, and exact loader replay discarded 40 of 946 intended examples before splitting. Removing annotated non-support context restored every row while preserving questions, targets, and verified support. Downstream comparisons remained statistically inconclusive. Controlled checks on a public graph-bearing fixture show how cross-record validation detects unresolved graph references and conflicting source revisions alongside role-aware repair. The installable implementation includes fixture-level CPU measurements, incremental adoption guidance, and an official RuBQ schema-import check. The case illustrates how lineage and retention audits make adaptation pipelines inspectable before model effects are attributed to their configured inputs.
%U https://aclanthology.org/2026.nora-1.9/
%P 98-108

Markdown (Informal)

[KG-SFT Contracts: Auditing Evidence Lineage and Loader Retention in Enterprise RAG Adaptation](https://aclanthology.org/2026.nora-1.9/) (Roshchupkin et al., NORA 2026)

• KG-SFT Contracts: Auditing Evidence Lineage and Loader Retention in Enterprise RAG Adaptation (Roshchupkin et al., NORA 2026)

ACL

• Bogdan Roshchupkin, Alexander Litvintsev, Alina Avanesyan, Maria Khodorchenko, and Andrei Zhukov. 2026. KG-SFT Contracts: Auditing Evidence Lineage and Loader Retention in Enterprise RAG Adaptation. In Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026), pages 98–108, Hengqin, China. Association for Computational Linguistics.