{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I6BU24ZKQIFSJITZ5EPE3G4VPI","short_pith_number":"pith:I6BU24ZK","canonical_record":{"source":{"id":"2506.19399","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T08:08:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc5e84c22f2a2b93b3143bcfa2f78417484070dfcde4cfa93dcd3efafafa96a5","abstract_canon_sha256":"056d4b5eba92979bc1a3f8f0376b9f0c169887d9b5325f001cda093dfea077a9"},"schema_version":"1.0"},"canonical_sha256":"47834d732a820b24a279e91e4d9b957a26b669ab4df9a846444d312f74a280c2","source":{"kind":"arxiv","id":"2506.19399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19399","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19399v1","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19399","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"pith_short_12","alias_value":"I6BU24ZKQIFS","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"pith_short_16","alias_value":"I6BU24ZKQIFSJITZ","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"pith_short_8","alias_value":"I6BU24ZK","created_at":"2026-07-05T11:26:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I6BU24ZKQIFSJITZ5EPE3G4VPI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.19399","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T08:08:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc5e84c22f2a2b93b3143bcfa2f78417484070dfcde4cfa93dcd3efafafa96a5","abstract_canon_sha256":"056d4b5eba92979bc1a3f8f0376b9f0c169887d9b5325f001cda093dfea077a9"},"schema_version":"1.0"},"canonical_sha256":"47834d732a820b24a279e91e4d9b957a26b669ab4df9a846444d312f74a280c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:14.629795Z","signature_b64":"reL/2uQyWOX74M4bQcneVtyJpjKaDjzTtCfsMhq6d/9DcnO3wF+VkWteCeU3k3+B0WU/9P8V3Teq5tNQevkXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47834d732a820b24a279e91e4d9b957a26b669ab4df9a846444d312f74a280c2","last_reissued_at":"2026-07-05T11:26:14.629257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:14.629257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.19399","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":"2026-07-05T11:26:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhQYVorrWipBs0gvE83GkqBF375O1ZqDnjR4RFL94VwwlP2ULkdqV2i+1cVNXBgSTSb6KViPCNwUcxGBQvydAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:14:41.196224Z"},"content_sha256":"613de55cde92f51c231c6dd45cff0c3399aaad63d434ad53cdc26f342465eb35","schema_version":"1.0","event_id":"sha256:613de55cde92f51c231c6dd45cff0c3399aaad63d434ad53cdc26f342465eb35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I6BU24ZKQIFSJITZ5EPE3G4VPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Detection of Pre-training Text in Black-box LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiankun Peng, Ruihan Hu, Wei Luo, Xi Zhang, Yazhe Wang, Yu-Ming Shang","submitted_at":"2025-06-24T08:08:15Z","abstract_excerpt":"Detecting whether a given text is a member of the pre-training data of Large Language Models (LLMs) is crucial for ensuring data privacy and copyright protection. Most existing methods rely on the LLM's hidden information (e.g., model parameters or token probabilities), making them ineffective in the black-box setting, where only input and output texts are accessible. Although some methods have been proposed for the black-box setting, they rely on massive manual efforts such as designing complicated questions or instructions. To address these issues, we propose VeilProbe, the first framework f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19399","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/2506.19399/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":"2026-07-05T11:26:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bEANCcgy3h+2iUK5jYczv9TsN2W3VjtpabBsCbQaVa2Fq/DoJ/8QztyrJtUERDP4BHt7PON435OKCVMQYG+gDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:14:41.196748Z"},"content_sha256":"86cf8f1382d7bd8619785157555fac90b05e86bca4f91a7cc125a397148012b5","schema_version":"1.0","event_id":"sha256:86cf8f1382d7bd8619785157555fac90b05e86bca4f91a7cc125a397148012b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6BU24ZKQIFSJITZ5EPE3G4VPI/bundle.json","state_url":"https://pith.science/pith/I6BU24ZKQIFSJITZ5EPE3G4VPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6BU24ZKQIFSJITZ5EPE3G4VPI/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":"2026-08-04T07:14:41Z","links":{"resolver":"https://pith.science/pith/I6BU24ZKQIFSJITZ5EPE3G4VPI","bundle":"https://pith.science/pith/I6BU24ZKQIFSJITZ5EPE3G4VPI/bundle.json","state":"https://pith.science/pith/I6BU24ZKQIFSJITZ5EPE3G4VPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6BU24ZKQIFSJITZ5EPE3G4VPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I6BU24ZKQIFSJITZ5EPE3G4VPI","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":"056d4b5eba92979bc1a3f8f0376b9f0c169887d9b5325f001cda093dfea077a9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T08:08:15Z","title_canon_sha256":"cc5e84c22f2a2b93b3143bcfa2f78417484070dfcde4cfa93dcd3efafafa96a5"},"schema_version":"1.0","source":{"id":"2506.19399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19399","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19399v1","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19399","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"pith_short_12","alias_value":"I6BU24ZKQIFS","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"pith_short_16","alias_value":"I6BU24ZKQIFSJITZ","created_at":"2026-07-05T11:26:14Z"},{"alias_kind":"pith_short_8","alias_value":"I6BU24ZK","created_at":"2026-07-05T11:26:14Z"}],"graph_snapshots":[{"event_id":"sha256:86cf8f1382d7bd8619785157555fac90b05e86bca4f91a7cc125a397148012b5","target":"graph","created_at":"2026-07-05T11:26:14Z","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/2506.19399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting whether a given text is a member of the pre-training data of Large Language Models (LLMs) is crucial for ensuring data privacy and copyright protection. Most existing methods rely on the LLM's hidden information (e.g., model parameters or token probabilities), making them ineffective in the black-box setting, where only input and output texts are accessible. Although some methods have been proposed for the black-box setting, they rely on massive manual efforts such as designing complicated questions or instructions. To address these issues, we propose VeilProbe, the first framework f","authors_text":"Jiankun Peng, Ruihan Hu, Wei Luo, Xi Zhang, Yazhe Wang, Yu-Ming Shang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T08:08:15Z","title":"Automated Detection of Pre-training Text in Black-box LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19399","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":"sha256:613de55cde92f51c231c6dd45cff0c3399aaad63d434ad53cdc26f342465eb35","target":"record","created_at":"2026-07-05T11:26:14Z","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":"056d4b5eba92979bc1a3f8f0376b9f0c169887d9b5325f001cda093dfea077a9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T08:08:15Z","title_canon_sha256":"cc5e84c22f2a2b93b3143bcfa2f78417484070dfcde4cfa93dcd3efafafa96a5"},"schema_version":"1.0","source":{"id":"2506.19399","kind":"arxiv","version":1}},"canonical_sha256":"47834d732a820b24a279e91e4d9b957a26b669ab4df9a846444d312f74a280c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47834d732a820b24a279e91e4d9b957a26b669ab4df9a846444d312f74a280c2","first_computed_at":"2026-07-05T11:26:14.629257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:14.629257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"reL/2uQyWOX74M4bQcneVtyJpjKaDjzTtCfsMhq6d/9DcnO3wF+VkWteCeU3k3+B0WU/9P8V3Teq5tNQevkXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:14.629795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:613de55cde92f51c231c6dd45cff0c3399aaad63d434ad53cdc26f342465eb35","sha256:86cf8f1382d7bd8619785157555fac90b05e86bca4f91a7cc125a397148012b5"],"state_sha256":"e4a120a311abf962796b4c3c570f2a596d3cb9c47678f29dac872329ab5401b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ERv4j3FQb55IeVjPr0njWkiEO5e5GmxYDAWfYzm0j4eBZtaWnmTb3PvcmSDhK9Og3AEzSF6ZrYA/gnZyI+vMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:14:41.202074Z","bundle_sha256":"f03617d96a7c491293db3f80966733f70abcb70fee2afad6fbc35581e720c8f3"}}