{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GCQGTOZIFA3WDC3BBK4UE4ZVTA","short_pith_number":"pith:GCQGTOZI","schema_version":"1.0","canonical_sha256":"30a069bb282837618b610ab942733598173a2b67ccad7af32a05842672d37612","source":{"kind":"arxiv","id":"2606.06946","version":1},"attestation_state":"computed","paper":{"title":"Auditing Training Data in Domain-adapted LLMs: LoRA-MINT","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aythami Morales, Daniel DeAlcala, Francisco Jurado, Gonzalo Mancera, Julian Fierrez, Ruben Tolosana","submitted_at":"2026-06-05T06:19:03Z","abstract_excerpt":"We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA). The primary goal is to assess whether individual samples were part of the training data of these adapted models, providing a useful auditing tool for the management of intellectual property and sensitive data. Our analysis explores the relationship between model perplexity and membership status, providing a systematic framework for estimating data exposure in fine-tuned LLM"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.06946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T06:19:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68a6e286a64b88bf540ea67f204305ca95c1fa934e00c98b8f73f0c7c3fe8a39","abstract_canon_sha256":"cf2b45e23191380419138f4211031d554c284f4e861dd25298778c3d667f4f8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:37.394740Z","signature_b64":"wcvU6kOfJ4IRd6s09Kcd6VTAX0l/1sdtS49gXoTMNtI8EHsu36qUSHTVYA3me98FCVRMN7W+z+L0ZqMRHPfcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a069bb282837618b610ab942733598173a2b67ccad7af32a05842672d37612","last_reissued_at":"2026-06-08T01:04:37.393840Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:37.393840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auditing Training Data in Domain-adapted LLMs: LoRA-MINT","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aythami Morales, Daniel DeAlcala, Francisco Jurado, Gonzalo Mancera, Julian Fierrez, Ruben Tolosana","submitted_at":"2026-06-05T06:19:03Z","abstract_excerpt":"We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA). The primary goal is to assess whether individual samples were part of the training data of these adapted models, providing a useful auditing tool for the management of intellectual property and sensitive data. Our analysis explores the relationship between model perplexity and membership status, providing a systematic framework for estimating data exposure in fine-tuned LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06946","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.06946/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.06946","created_at":"2026-06-08T01:04:37.393987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06946v1","created_at":"2026-06-08T01:04:37.393987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06946","created_at":"2026-06-08T01:04:37.393987+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCQGTOZIFA3W","created_at":"2026-06-08T01:04:37.393987+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCQGTOZIFA3WDC3B","created_at":"2026-06-08T01:04:37.393987+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCQGTOZI","created_at":"2026-06-08T01:04:37.393987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA","json":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA.json","graph_json":"https://pith.science/api/pith-number/GCQGTOZIFA3WDC3BBK4UE4ZVTA/graph.json","events_json":"https://pith.science/api/pith-number/GCQGTOZIFA3WDC3BBK4UE4ZVTA/events.json","paper":"https://pith.science/paper/GCQGTOZI"},"agent_actions":{"view_html":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA","download_json":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA.json","view_paper":"https://pith.science/paper/GCQGTOZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06946&json=true","fetch_graph":"https://pith.science/api/pith-number/GCQGTOZIFA3WDC3BBK4UE4ZVTA/graph.json","fetch_events":"https://pith.science/api/pith-number/GCQGTOZIFA3WDC3BBK4UE4ZVTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA/action/storage_attestation","attest_author":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA/action/author_attestation","sign_citation":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA/action/citation_signature","submit_replication":"https://pith.science/pith/GCQGTOZIFA3WDC3BBK4UE4ZVTA/action/replication_record"}},"created_at":"2026-06-08T01:04:37.393987+00:00","updated_at":"2026-06-08T01:04:37.393987+00:00"}