{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QIPR3BEPFDNBMYTP7ES6FMPHIC","short_pith_number":"pith:QIPR3BEP","canonical_record":{"source":{"id":"2407.21248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T23:43:59Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"67aa71942ccf03fe6caf96dbef9b3787810d6e747de2a11e47140495b99149a9","abstract_canon_sha256":"692abb2b88af1c29e7957978376ed6e110be7c5cc65a370ebd6a49d5b19b65ad"},"schema_version":"1.0"},"canonical_sha256":"821f1d848f28da16626ff925e2b1e74081780bcccb642c7b9f8530edba53f9ec","source":{"kind":"arxiv","id":"2407.21248","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21248","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21248v1","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21248","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"QIPR3BEPFDNB","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"pith_short_16","alias_value":"QIPR3BEPFDNBMYTP","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"pith_short_8","alias_value":"QIPR3BEP","created_at":"2026-07-05T08:50:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QIPR3BEPFDNBMYTP7ES6FMPHIC","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T23:43:59Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"67aa71942ccf03fe6caf96dbef9b3787810d6e747de2a11e47140495b99149a9","abstract_canon_sha256":"692abb2b88af1c29e7957978376ed6e110be7c5cc65a370ebd6a49d5b19b65ad"},"schema_version":"1.0"},"canonical_sha256":"821f1d848f28da16626ff925e2b1e74081780bcccb642c7b9f8530edba53f9ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:36.539523Z","signature_b64":"4ttIHIA9biCwxPOwVwytQdBgJHrZ55nBvyHprFXg3REqELttiEV2EApDjCwiRwzFJZ04+8DYc5GfuqMmZr2LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"821f1d848f28da16626ff925e2b1e74081780bcccb642c7b9f8530edba53f9ec","last_reissued_at":"2026-07-05T08:50:36.539109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:36.539109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21248","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":"2026-07-05T08:50:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yqYE55ezpXmZF1F3Sc9suI7oGz/XRMsBi01EVhE62dp1U8hAlA5XmAaa3KZubQsu9lJjKe0i9B25BirgxrDFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:29:15.786032Z"},"content_sha256":"087736444bcf33f38175e859ff0d0a096c97147b10f53d25f399bf38a471ffdf","schema_version":"1.0","event_id":"sha256:087736444bcf33f38175e859ff0d0a096c97147b10f53d25f399bf38a471ffdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QIPR3BEPFDNBMYTP7ES6FMPHIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anqi Zhang, Chaofeng Wu","submitted_at":"2024-07-30T23:43:59Z","abstract_excerpt":"While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current solutions to this problem leverage techniques explored in machine learning privacy such as Membership Inference Attacks (MIAs), which heavily depend on LLMs' capability of verbatim memorization. However, this reliance presents challenges, especially given the vast amount of training data and the restricted number of effective training epochs. In this paper, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21248","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/2407.21248/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":"2026-07-05T08:50:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4gEbNb4pW/VdIiXn7l7Yoeq1VMkkEmlpNGsmUMCbBf6/6qf4Izu1DzN0YcRUSEgRKjLxbY9ICDMFkwQ0CZLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:29:15.786999Z"},"content_sha256":"5e552b3fa5fc85a99ef4c32c7fb900018e87cf38167ac3220d75f3ed9b1e82f3","schema_version":"1.0","event_id":"sha256:5e552b3fa5fc85a99ef4c32c7fb900018e87cf38167ac3220d75f3ed9b1e82f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QIPR3BEPFDNBMYTP7ES6FMPHIC/bundle.json","state_url":"https://pith.science/pith/QIPR3BEPFDNBMYTP7ES6FMPHIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QIPR3BEPFDNBMYTP7ES6FMPHIC/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":"2026-08-07T22:29:15Z","links":{"resolver":"https://pith.science/pith/QIPR3BEPFDNBMYTP7ES6FMPHIC","bundle":"https://pith.science/pith/QIPR3BEPFDNBMYTP7ES6FMPHIC/bundle.json","state":"https://pith.science/pith/QIPR3BEPFDNBMYTP7ES6FMPHIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QIPR3BEPFDNBMYTP7ES6FMPHIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QIPR3BEPFDNBMYTP7ES6FMPHIC","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":"692abb2b88af1c29e7957978376ed6e110be7c5cc65a370ebd6a49d5b19b65ad","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T23:43:59Z","title_canon_sha256":"67aa71942ccf03fe6caf96dbef9b3787810d6e747de2a11e47140495b99149a9"},"schema_version":"1.0","source":{"id":"2407.21248","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21248","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21248v1","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21248","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"QIPR3BEPFDNB","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"pith_short_16","alias_value":"QIPR3BEPFDNBMYTP","created_at":"2026-07-05T08:50:36Z"},{"alias_kind":"pith_short_8","alias_value":"QIPR3BEP","created_at":"2026-07-05T08:50:36Z"}],"graph_snapshots":[{"event_id":"sha256:5e552b3fa5fc85a99ef4c32c7fb900018e87cf38167ac3220d75f3ed9b1e82f3","target":"graph","created_at":"2026-07-05T08:50:36Z","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/2407.21248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current solutions to this problem leverage techniques explored in machine learning privacy such as Membership Inference Attacks (MIAs), which heavily depend on LLMs' capability of verbatim memorization. However, this reliance presents challenges, especially given the vast amount of training data and the restricted number of effective training epochs. In this paper, ","authors_text":"Anqi Zhang, Chaofeng Wu","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T23:43:59Z","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21248","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":"sha256:087736444bcf33f38175e859ff0d0a096c97147b10f53d25f399bf38a471ffdf","target":"record","created_at":"2026-07-05T08:50:36Z","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":"692abb2b88af1c29e7957978376ed6e110be7c5cc65a370ebd6a49d5b19b65ad","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T23:43:59Z","title_canon_sha256":"67aa71942ccf03fe6caf96dbef9b3787810d6e747de2a11e47140495b99149a9"},"schema_version":"1.0","source":{"id":"2407.21248","kind":"arxiv","version":1}},"canonical_sha256":"821f1d848f28da16626ff925e2b1e74081780bcccb642c7b9f8530edba53f9ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"821f1d848f28da16626ff925e2b1e74081780bcccb642c7b9f8530edba53f9ec","first_computed_at":"2026-07-05T08:50:36.539109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:36.539109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ttIHIA9biCwxPOwVwytQdBgJHrZ55nBvyHprFXg3REqELttiEV2EApDjCwiRwzFJZ04+8DYc5GfuqMmZr2LCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:36.539523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21248","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:087736444bcf33f38175e859ff0d0a096c97147b10f53d25f399bf38a471ffdf","sha256:5e552b3fa5fc85a99ef4c32c7fb900018e87cf38167ac3220d75f3ed9b1e82f3"],"state_sha256":"f802734bafe78a2a36d2190e478121daf9c848a38db4a9ca95056d766fa44b2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PCrqDYtZ3k/UBXiQ5EhmAe/xA7otTUSDf2d8pc9LHKirggQfGCDY40l4/vG5BigflhheuJZ29ddA/9PEBx6/DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:29:15.791906Z","bundle_sha256":"384a97e966a48d87181c7d9ec6fb48842d01428f562864c93e709ddee3977f60"}}