{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4RV4Q7GXJZPQFPDW2CZU5KUENP","short_pith_number":"pith:4RV4Q7GX","schema_version":"1.0","canonical_sha256":"e46bc87cd74e5f02bc76d0b34eaa846bd4b2c2c40a66252d3ce6f93a1fb0c580","source":{"kind":"arxiv","id":"2605.26133","version":1},"attestation_state":"computed","paper":{"title":"Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Feifei Sun, Le Minh Nguyen, Ziyi Tong","submitted_at":"2026-05-21T10:32:33Z","abstract_excerpt":"Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure (PDE) increase due to the scale and opacity of training datasets.\n  PDE refers to determining whether specific data appeared in an LLM's pretraining corpus. It is critical for ensuring evaluation integrity and protecting privacy, intersecting two key areas: data contamination and membership inference. Though conceptually related, these areas have often been studied in isolation. This paper offers the f"},"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":"2605.26133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T10:32:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5b94f245c6b6af2433391eba533ac87a69afdc2a627255307ac54c934d224bc3","abstract_canon_sha256":"7dadb6e66c0aaad4d01dc389f6c62101819b0dd52f60e7d3b95ad528463adbfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T00:04:25.383370Z","signature_b64":"yh41ZdlJnhMhEWki71jFbl9+5G3jZEG6vZNvO28lLsHJ1HxcVkdV/MGTKjbE+Tue4FTSlXstU7yRVg7S08K/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e46bc87cd74e5f02bc76d0b34eaa846bd4b2c2c40a66252d3ce6f93a1fb0c580","last_reissued_at":"2026-05-27T00:04:25.382720Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T00:04:25.382720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Feifei Sun, Le Minh Nguyen, Ziyi Tong","submitted_at":"2026-05-21T10:32:33Z","abstract_excerpt":"Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure (PDE) increase due to the scale and opacity of training datasets.\n  PDE refers to determining whether specific data appeared in an LLM's pretraining corpus. It is critical for ensuring evaluation integrity and protecting privacy, intersecting two key areas: data contamination and membership inference. Though conceptually related, these areas have often been studied in isolation. This paper offers the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26133","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/2605.26133/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":"2605.26133","created_at":"2026-05-27T00:04:25.382789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26133v1","created_at":"2026-05-27T00:04:25.382789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26133","created_at":"2026-05-27T00:04:25.382789+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RV4Q7GXJZPQ","created_at":"2026-05-27T00:04:25.382789+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RV4Q7GXJZPQFPDW","created_at":"2026-05-27T00:04:25.382789+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RV4Q7GX","created_at":"2026-05-27T00:04:25.382789+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/4RV4Q7GXJZPQFPDW2CZU5KUENP","json":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP.json","graph_json":"https://pith.science/api/pith-number/4RV4Q7GXJZPQFPDW2CZU5KUENP/graph.json","events_json":"https://pith.science/api/pith-number/4RV4Q7GXJZPQFPDW2CZU5KUENP/events.json","paper":"https://pith.science/paper/4RV4Q7GX"},"agent_actions":{"view_html":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP","download_json":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP.json","view_paper":"https://pith.science/paper/4RV4Q7GX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26133&json=true","fetch_graph":"https://pith.science/api/pith-number/4RV4Q7GXJZPQFPDW2CZU5KUENP/graph.json","fetch_events":"https://pith.science/api/pith-number/4RV4Q7GXJZPQFPDW2CZU5KUENP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP/action/storage_attestation","attest_author":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP/action/author_attestation","sign_citation":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP/action/citation_signature","submit_replication":"https://pith.science/pith/4RV4Q7GXJZPQFPDW2CZU5KUENP/action/replication_record"}},"created_at":"2026-05-27T00:04:25.382789+00:00","updated_at":"2026-05-27T00:04:25.382789+00:00"}