{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JA7ORS6I3FHP4QPVDNVLXVGX66","short_pith_number":"pith:JA7ORS6I","canonical_record":{"source":{"id":"2503.17514","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-21T19:57:04Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"15d2df015c9c141836ad16a584153638b1f17a9ec560b4c94f50ad333b71b1dd","abstract_canon_sha256":"79d31b9243bf42349c710945458d59e048eba1c74d0a1cb9283bcabdec41ec28"},"schema_version":"1.0"},"canonical_sha256":"483ee8cbc8d94efe41f51b6abbd4d7f79423076aaf0700fda3fd048c3cd2095e","source":{"kind":"arxiv","id":"2503.17514","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17514","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17514v2","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17514","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"JA7ORS6I3FHP","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"pith_short_16","alias_value":"JA7ORS6I3FHP4QPV","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"pith_short_8","alias_value":"JA7ORS6I","created_at":"2026-07-05T10:38:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JA7ORS6I3FHP4QPVDNVLXVGX66","target":"record","payload":{"canonical_record":{"source":{"id":"2503.17514","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-21T19:57:04Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"15d2df015c9c141836ad16a584153638b1f17a9ec560b4c94f50ad333b71b1dd","abstract_canon_sha256":"79d31b9243bf42349c710945458d59e048eba1c74d0a1cb9283bcabdec41ec28"},"schema_version":"1.0"},"canonical_sha256":"483ee8cbc8d94efe41f51b6abbd4d7f79423076aaf0700fda3fd048c3cd2095e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:45.539502Z","signature_b64":"0OStdV14cFGSRHL7Hd1Bk+Wx1/C+Lv9+N9cz2f+B4XuVUH64/Kmmd77mcaBSsmrngwopJR8D3nAZ1a5i++NQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"483ee8cbc8d94efe41f51b6abbd4d7f79423076aaf0700fda3fd048c3cd2095e","last_reissued_at":"2026-07-05T10:38:45.539007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:45.539007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.17514","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOooTN4xYr/+tgJ2QhZNznM0q6+yb96/bfyZV+o+DRXeWIuJ4ryKuMO+fakDYN+3r/8l9Z1nCSrVwqftdxmeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:54:43.212603Z"},"content_sha256":"47fdf7d3607ed35f3264c076c7ecd371377d139c82d072064fbec98fc23907a5","schema_version":"1.0","event_id":"sha256:47fdf7d3607ed35f3264c076c7ecd371377d139c82d072064fbec98fc23907a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JA7ORS6I3FHP4QPVDNVLXVGX66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models May Verbatim Complete Text They Were Not Explicitly Trained On","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christopher A. Choquette-Choo, Ken Ziyu Liu, Matthew Jagielski, Nicolas Papernot, Percy Liang, Peter Kairouz, Sanmi Koyejo","submitted_at":"2025-03-21T19:57:04Z","abstract_excerpt":"An important question today is whether a given text was used to train a large language model (LLM). A \\emph{completion} test is often employed: check if the LLM completes a sufficiently complex text. This, however, requires a ground-truth definition of membership; most commonly, it is defined as a member based on the $n$-gram overlap between the target text and any text in the dataset. In this work, we demonstrate that this $n$-gram based membership definition can be effectively gamed. We study scenarios where sequences are \\emph{non-members} for a given $n$ and we find that completion tests s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17514","kind":"arxiv","version":2},"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/2503.17514/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":"2026-07-05T10:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+TjMt4vMIXtEK9MODTtFFVnEZaVcNEk513qHZqXDs+HCaN3unN7rHqDHazK7fNsinJ5+nkKwLYDf0uodbOi2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:54:43.213115Z"},"content_sha256":"ebe6bd1dd5714ca25f9179d973707f99412d1556bd118029e0f21b84a8ac2ee2","schema_version":"1.0","event_id":"sha256:ebe6bd1dd5714ca25f9179d973707f99412d1556bd118029e0f21b84a8ac2ee2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JA7ORS6I3FHP4QPVDNVLXVGX66/bundle.json","state_url":"https://pith.science/pith/JA7ORS6I3FHP4QPVDNVLXVGX66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JA7ORS6I3FHP4QPVDNVLXVGX66/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":"2026-08-19T15:54:43Z","links":{"resolver":"https://pith.science/pith/JA7ORS6I3FHP4QPVDNVLXVGX66","bundle":"https://pith.science/pith/JA7ORS6I3FHP4QPVDNVLXVGX66/bundle.json","state":"https://pith.science/pith/JA7ORS6I3FHP4QPVDNVLXVGX66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JA7ORS6I3FHP4QPVDNVLXVGX66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JA7ORS6I3FHP4QPVDNVLXVGX66","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":"79d31b9243bf42349c710945458d59e048eba1c74d0a1cb9283bcabdec41ec28","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-21T19:57:04Z","title_canon_sha256":"15d2df015c9c141836ad16a584153638b1f17a9ec560b4c94f50ad333b71b1dd"},"schema_version":"1.0","source":{"id":"2503.17514","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17514","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17514v2","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17514","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"JA7ORS6I3FHP","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"pith_short_16","alias_value":"JA7ORS6I3FHP4QPV","created_at":"2026-07-05T10:38:45Z"},{"alias_kind":"pith_short_8","alias_value":"JA7ORS6I","created_at":"2026-07-05T10:38:45Z"}],"graph_snapshots":[{"event_id":"sha256:ebe6bd1dd5714ca25f9179d973707f99412d1556bd118029e0f21b84a8ac2ee2","target":"graph","created_at":"2026-07-05T10:38:45Z","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/2503.17514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An important question today is whether a given text was used to train a large language model (LLM). A \\emph{completion} test is often employed: check if the LLM completes a sufficiently complex text. This, however, requires a ground-truth definition of membership; most commonly, it is defined as a member based on the $n$-gram overlap between the target text and any text in the dataset. In this work, we demonstrate that this $n$-gram based membership definition can be effectively gamed. We study scenarios where sequences are \\emph{non-members} for a given $n$ and we find that completion tests s","authors_text":"Christopher A. Choquette-Choo, Ken Ziyu Liu, Matthew Jagielski, Nicolas Papernot, Percy Liang, Peter Kairouz, Sanmi Koyejo","cross_cats":["cs.AI","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-21T19:57:04Z","title":"Language Models May Verbatim Complete Text They Were Not Explicitly Trained On"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17514","kind":"arxiv","version":2},"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":"sha256:47fdf7d3607ed35f3264c076c7ecd371377d139c82d072064fbec98fc23907a5","target":"record","created_at":"2026-07-05T10:38:45Z","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":"79d31b9243bf42349c710945458d59e048eba1c74d0a1cb9283bcabdec41ec28","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-21T19:57:04Z","title_canon_sha256":"15d2df015c9c141836ad16a584153638b1f17a9ec560b4c94f50ad333b71b1dd"},"schema_version":"1.0","source":{"id":"2503.17514","kind":"arxiv","version":2}},"canonical_sha256":"483ee8cbc8d94efe41f51b6abbd4d7f79423076aaf0700fda3fd048c3cd2095e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"483ee8cbc8d94efe41f51b6abbd4d7f79423076aaf0700fda3fd048c3cd2095e","first_computed_at":"2026-07-05T10:38:45.539007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:45.539007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0OStdV14cFGSRHL7Hd1Bk+Wx1/C+Lv9+N9cz2f+B4XuVUH64/Kmmd77mcaBSsmrngwopJR8D3nAZ1a5i++NQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:45.539502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17514","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47fdf7d3607ed35f3264c076c7ecd371377d139c82d072064fbec98fc23907a5","sha256:ebe6bd1dd5714ca25f9179d973707f99412d1556bd118029e0f21b84a8ac2ee2"],"state_sha256":"7b7dc1ee98c290144af5d2adbdec7eb323764c4057d4306798f3282b3ad44e0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8mhnfvL65Ak5gBgaWhnVX0cf/hV1I3bextLi6x+w7tWjy+pQ7jSduYSidsV7G2jyKSzn1TBuFhEjc6TizU1WBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:54:43.218210Z","bundle_sha256":"062cf7b7f406d277b943db027fb0ffd949d5c7e47290ae93fbbf6e1e8cfdfe02"}}