{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7UUXQWL7FZMP7EYAFKXIF47Q7Y","short_pith_number":"pith:7UUXQWL7","schema_version":"1.0","canonical_sha256":"fd2978597f2e58ff93002aae82f3f0fe1c9e11c6414b3142ba36356791ac5ddb","source":{"kind":"arxiv","id":"2405.03004","version":1},"attestation_state":"computed","paper":{"title":"Exploring prompts to elicit memorization in masked language model-based named entity recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasiia Sedova, Benjamin Roth, Lisa Nu{\\ss}baumer, Pedro Henrique Luz de Araujo, Vasiliki Kougia, Yuxi Xia","submitted_at":"2024-05-05T17:19:35Z","abstract_excerpt":"Training data memorization in language models impacts model capability (generalization) and safety (privacy risk). This paper focuses on analyzing prompts' impact on detecting the memorization of 6 masked language model-based named entity recognition models. Specifically, we employ a diverse set of 400 automatically generated prompts, and a pairwise dataset where each pair consists of one person's name from the training set and another name out of the set. A prompt completed with a person's name serves as input for getting the model's confidence in predicting this name. Finally, the prompt per"},"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":"2405.03004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-05T17:19:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"629b9fc9ad0a07c5545a92e4faeb03c3b75c1d2d85fcf0457545fc1679d9f937","abstract_canon_sha256":"a8ada24a699048f322d7d1ef651e968b025930bf0259934daac6639c3a7eeec8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:57.166132Z","signature_b64":"jETlDDrrI3FuShVclsblCtb8BDv9F0YGXcMb8UR4dFXDTbvznC5RuRvOfSIj8v6VPnijQ/MAiNIAg4dqx/63DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd2978597f2e58ff93002aae82f3f0fe1c9e11c6414b3142ba36356791ac5ddb","last_reissued_at":"2026-07-05T08:15:57.165699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:57.165699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring prompts to elicit memorization in masked language model-based named entity recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasiia Sedova, Benjamin Roth, Lisa Nu{\\ss}baumer, Pedro Henrique Luz de Araujo, Vasiliki Kougia, Yuxi Xia","submitted_at":"2024-05-05T17:19:35Z","abstract_excerpt":"Training data memorization in language models impacts model capability (generalization) and safety (privacy risk). This paper focuses on analyzing prompts' impact on detecting the memorization of 6 masked language model-based named entity recognition models. Specifically, we employ a diverse set of 400 automatically generated prompts, and a pairwise dataset where each pair consists of one person's name from the training set and another name out of the set. A prompt completed with a person's name serves as input for getting the model's confidence in predicting this name. Finally, the prompt per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03004","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/2405.03004/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":"2405.03004","created_at":"2026-07-05T08:15:57.165765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03004v1","created_at":"2026-07-05T08:15:57.165765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03004","created_at":"2026-07-05T08:15:57.165765+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UUXQWL7FZMP","created_at":"2026-07-05T08:15:57.165765+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UUXQWL7FZMP7EYA","created_at":"2026-07-05T08:15:57.165765+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UUXQWL7","created_at":"2026-07-05T08:15:57.165765+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/7UUXQWL7FZMP7EYAFKXIF47Q7Y","json":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y.json","graph_json":"https://pith.science/api/pith-number/7UUXQWL7FZMP7EYAFKXIF47Q7Y/graph.json","events_json":"https://pith.science/api/pith-number/7UUXQWL7FZMP7EYAFKXIF47Q7Y/events.json","paper":"https://pith.science/paper/7UUXQWL7"},"agent_actions":{"view_html":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y","download_json":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y.json","view_paper":"https://pith.science/paper/7UUXQWL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03004&json=true","fetch_graph":"https://pith.science/api/pith-number/7UUXQWL7FZMP7EYAFKXIF47Q7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7UUXQWL7FZMP7EYAFKXIF47Q7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y/action/storage_attestation","attest_author":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y/action/author_attestation","sign_citation":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y/action/citation_signature","submit_replication":"https://pith.science/pith/7UUXQWL7FZMP7EYAFKXIF47Q7Y/action/replication_record"}},"created_at":"2026-07-05T08:15:57.165765+00:00","updated_at":"2026-07-05T08:15:57.165765+00:00"}