{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ","short_pith_number":"pith:JV7CC5KX","canonical_record":{"source":{"id":"2305.16157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T15:23:29Z","cross_cats_sorted":[],"title_canon_sha256":"85873ef713f9e0239f0dbb94c9b93df00c75fc775fb278af23bebcb6be2fdc42","abstract_canon_sha256":"ee6477b8ed08a18194d620be8fc609a6466373101fc3a77568fdcf7017a5de74"},"schema_version":"1.0"},"canonical_sha256":"4d7e2175574f33c52fb99bf10002fd92726a2ca304d15e4d9f7815602f7b9d85","source":{"kind":"arxiv","id":"2305.16157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16157","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16157v1","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16157","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"JV7CC5KXJ4Z4","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"JV7CC5KXJ4Z4KL5Z","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"JV7CC5KX","created_at":"2026-07-05T06:14:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T15:23:29Z","cross_cats_sorted":[],"title_canon_sha256":"85873ef713f9e0239f0dbb94c9b93df00c75fc775fb278af23bebcb6be2fdc42","abstract_canon_sha256":"ee6477b8ed08a18194d620be8fc609a6466373101fc3a77568fdcf7017a5de74"},"schema_version":"1.0"},"canonical_sha256":"4d7e2175574f33c52fb99bf10002fd92726a2ca304d15e4d9f7815602f7b9d85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:00.088778Z","signature_b64":"6HDhusDKIY9m1xrU8urpuTzpd3X9FQrg7LI0Q6NI/bMiN9cR00xTOTngmIjA8BjW4KrsPdQikYvmSDCd/0ojBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d7e2175574f33c52fb99bf10002fd92726a2ca304d15e4d9f7815602f7b9d85","last_reissued_at":"2026-07-05T06:14:00.088367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:00.088367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16157","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gNIKJzZxaHR0sD+n0C5rtFMMGjpfEeo2gw3zKpqe9Pxd460SC58d05MIy6EaLb4lwkCEfT9Qb3fv9rCuso+dDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:47:55.781741Z"},"content_sha256":"7e5970674fb9c7887532cd42cda3146e47b2620edca4be184e81eb2ab97c300a","schema_version":"1.0","event_id":"sha256:7e5970674fb9c7887532cd42cda3146e47b2620edca4be184e81eb2ab97c300a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Data Extraction From Pre-trained Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shotaro Ishihara","submitted_at":"2023-05-25T15:23:29Z","abstract_excerpt":"As the deployment of pre-trained language models (PLMs) expands, pressing security concerns have arisen regarding the potential for malicious extraction of training data, posing a threat to data privacy. This study is the first to provide a comprehensive survey of training data extraction from PLMs. Our review covers more than 100 key papers in fields such as natural language processing and security. First, preliminary knowledge is recapped and a taxonomy of various definitions of memorization is presented. The approaches for attack and defense are then systemized. Furthermore, the empirical f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16157","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/2305.16157/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqP9fmcuLDFDGQcUXe/jWK8LOK8eE3XxQHu6XFKsOKMOVEkG75Hx9W1KNVZ54Z7lOCyAMGS4pqVmupXe4amVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:47:55.782270Z"},"content_sha256":"74ace83b555d3d8bcb03ac83fe2859d144ea00b15c3c1ca733dbf2e44c09550e","schema_version":"1.0","event_id":"sha256:74ace83b555d3d8bcb03ac83fe2859d144ea00b15c3c1ca733dbf2e44c09550e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ/bundle.json","state_url":"https://pith.science/pith/JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T09:47:55Z","links":{"resolver":"https://pith.science/pith/JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ","bundle":"https://pith.science/pith/JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ/bundle.json","state":"https://pith.science/pith/JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JV7CC5KXJ4Z4KL5ZTPYQAAX5SJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee6477b8ed08a18194d620be8fc609a6466373101fc3a77568fdcf7017a5de74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T15:23:29Z","title_canon_sha256":"85873ef713f9e0239f0dbb94c9b93df00c75fc775fb278af23bebcb6be2fdc42"},"schema_version":"1.0","source":{"id":"2305.16157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16157","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16157v1","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16157","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"JV7CC5KXJ4Z4","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"JV7CC5KXJ4Z4KL5Z","created_at":"2026-07-05T06:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"JV7CC5KX","created_at":"2026-07-05T06:14:00Z"}],"graph_snapshots":[{"event_id":"sha256:74ace83b555d3d8bcb03ac83fe2859d144ea00b15c3c1ca733dbf2e44c09550e","target":"graph","created_at":"2026-07-05T06:14:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.16157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the deployment of pre-trained language models (PLMs) expands, pressing security concerns have arisen regarding the potential for malicious extraction of training data, posing a threat to data privacy. This study is the first to provide a comprehensive survey of training data extraction from PLMs. Our review covers more than 100 key papers in fields such as natural language processing and security. First, preliminary knowledge is recapped and a taxonomy of various definitions of memorization is presented. The approaches for attack and defense are then systemized. Furthermore, the empirical f","authors_text":"Shotaro Ishihara","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T15:23:29Z","title":"Training Data Extraction From Pre-trained Language Models: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16157","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7e5970674fb9c7887532cd42cda3146e47b2620edca4be184e81eb2ab97c300a","target":"record","created_at":"2026-07-05T06:14:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee6477b8ed08a18194d620be8fc609a6466373101fc3a77568fdcf7017a5de74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T15:23:29Z","title_canon_sha256":"85873ef713f9e0239f0dbb94c9b93df00c75fc775fb278af23bebcb6be2fdc42"},"schema_version":"1.0","source":{"id":"2305.16157","kind":"arxiv","version":1}},"canonical_sha256":"4d7e2175574f33c52fb99bf10002fd92726a2ca304d15e4d9f7815602f7b9d85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d7e2175574f33c52fb99bf10002fd92726a2ca304d15e4d9f7815602f7b9d85","first_computed_at":"2026-07-05T06:14:00.088367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:00.088367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6HDhusDKIY9m1xrU8urpuTzpd3X9FQrg7LI0Q6NI/bMiN9cR00xTOTngmIjA8BjW4KrsPdQikYvmSDCd/0ojBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:00.088778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e5970674fb9c7887532cd42cda3146e47b2620edca4be184e81eb2ab97c300a","sha256:74ace83b555d3d8bcb03ac83fe2859d144ea00b15c3c1ca733dbf2e44c09550e"],"state_sha256":"0268d2748ff99f6d1c4484456e84afb647ca423fdd041768dc6aa34e1941b4dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kNKlZJSC/DgDlI1dqErjHXNyly0GSwqLODgzTPjJwNE6H6kiNDBIbIiNvNzjlJEO3qHP0Hz0u9MxmTOHVeSdDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:47:55.788143Z","bundle_sha256":"dd920d1c0b9955db05e2edf4feddd8cb9c03422b3855e51f2ab426e9d3339504"}}