{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3L2HJXP4BXKIT3Q7MODPLU6B4G","short_pith_number":"pith:3L2HJXP4","canonical_record":{"source":{"id":"2604.01904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-02T11:19:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a7bddefc960448db626ab16f960d7ac9086ae91a0266abd765d2fd8b00c87c51","abstract_canon_sha256":"5ca247c6849c621acd1e5ef22424cdef2696c3a9dc1ee2e2863cf08e5660ae69"},"schema_version":"1.0"},"canonical_sha256":"daf474ddfc0dd489ee1f6386f5d3c1e1a8cd08b462a5533c28ec599c12511717","source":{"kind":"arxiv","id":"2604.01904","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.01904","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2604.01904v2","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01904","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"3L2HJXP4BXKI","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"3L2HJXP4BXKIT3Q7","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"3L2HJXP4","created_at":"2026-05-29T02:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3L2HJXP4BXKIT3Q7MODPLU6B4G","target":"record","payload":{"canonical_record":{"source":{"id":"2604.01904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-02T11:19:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a7bddefc960448db626ab16f960d7ac9086ae91a0266abd765d2fd8b00c87c51","abstract_canon_sha256":"5ca247c6849c621acd1e5ef22424cdef2696c3a9dc1ee2e2863cf08e5660ae69"},"schema_version":"1.0"},"canonical_sha256":"daf474ddfc0dd489ee1f6386f5d3c1e1a8cd08b462a5533c28ec599c12511717","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:44.152201Z","signature_b64":"ne301cyHlsiKlPHcjWaAxwSCmViumMUBNox5osAIM3DgXkoigA6FXgXA7id2g3hurrBzobMa5t01QeQ0T2B1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daf474ddfc0dd489ee1f6386f5d3c1e1a8cd08b462a5533c28ec599c12511717","last_reissued_at":"2026-05-29T02:05:44.151203Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:44.151203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.01904","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":"2026-05-29T02:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xu8ymRTRBY1edYDXeE5oIiM6hEsiH5IAUedZ1oYSFqrWwdozVomBRO/++5ia4fvbED3Yvg9+47+6I/12ZMxPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:53:42.748593Z"},"content_sha256":"f996f18e8c032e8316b7231fc6bc6efb42c33da17dcbee52ff0bafe572eb3b46","schema_version":"1.0","event_id":"sha256:f996f18e8c032e8316b7231fc6bc6efb42c33da17dcbee52ff0bafe572eb3b46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3L2HJXP4BXKIT3Q7MODPLU6B4G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combating Data Laundering in LLM Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Feng Liu, Muxing Li, Sharon Li, Zesheng Ye","submitted_at":"2026-04-02T11:19:49Z","abstract_excerpt":"Data rights owners can detect unauthorized data use in large language model (LLM) training by querying with proprietary samples. Often, superior performance (e.g., higher confidence or lower loss) on a sample relative to the untrained data implies it was part of the training corpus, as LLMs tend to perform better on data they have seen during training. However, this detection becomes fragile under data laundering, a practice of transforming the stylistic form of proprietary data, while preserving critical information to obfuscate data provenance. When an LLM is trained exclusively on such laun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.01904","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/2604.01904/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":"2026-05-29T02:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1rVknhKM99mt4ML//8K2Lcjud95e4PDIXatVWeCpzb4DIiUt7yW8iTEF5dnTwCh34igcVitIpIV/th/C4kcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:53:42.748977Z"},"content_sha256":"806ef5404558f4b38998f65057404fca7eb815dcee50b1119cdf964c3bc38fea","schema_version":"1.0","event_id":"sha256:806ef5404558f4b38998f65057404fca7eb815dcee50b1119cdf964c3bc38fea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3L2HJXP4BXKIT3Q7MODPLU6B4G/bundle.json","state_url":"https://pith.science/pith/3L2HJXP4BXKIT3Q7MODPLU6B4G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3L2HJXP4BXKIT3Q7MODPLU6B4G/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":"2026-05-31T16:53:42Z","links":{"resolver":"https://pith.science/pith/3L2HJXP4BXKIT3Q7MODPLU6B4G","bundle":"https://pith.science/pith/3L2HJXP4BXKIT3Q7MODPLU6B4G/bundle.json","state":"https://pith.science/pith/3L2HJXP4BXKIT3Q7MODPLU6B4G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3L2HJXP4BXKIT3Q7MODPLU6B4G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3L2HJXP4BXKIT3Q7MODPLU6B4G","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":"5ca247c6849c621acd1e5ef22424cdef2696c3a9dc1ee2e2863cf08e5660ae69","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-02T11:19:49Z","title_canon_sha256":"a7bddefc960448db626ab16f960d7ac9086ae91a0266abd765d2fd8b00c87c51"},"schema_version":"1.0","source":{"id":"2604.01904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.01904","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2604.01904v2","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01904","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"3L2HJXP4BXKI","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"3L2HJXP4BXKIT3Q7","created_at":"2026-05-29T02:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"3L2HJXP4","created_at":"2026-05-29T02:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:806ef5404558f4b38998f65057404fca7eb815dcee50b1119cdf964c3bc38fea","target":"graph","created_at":"2026-05-29T02:05:44Z","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/2604.01904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data rights owners can detect unauthorized data use in large language model (LLM) training by querying with proprietary samples. Often, superior performance (e.g., higher confidence or lower loss) on a sample relative to the untrained data implies it was part of the training corpus, as LLMs tend to perform better on data they have seen during training. However, this detection becomes fragile under data laundering, a practice of transforming the stylistic form of proprietary data, while preserving critical information to obfuscate data provenance. When an LLM is trained exclusively on such laun","authors_text":"Feng Liu, Muxing Li, Sharon Li, Zesheng Ye","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-02T11:19:49Z","title":"Combating Data Laundering in LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.01904","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:f996f18e8c032e8316b7231fc6bc6efb42c33da17dcbee52ff0bafe572eb3b46","target":"record","created_at":"2026-05-29T02:05:44Z","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":"5ca247c6849c621acd1e5ef22424cdef2696c3a9dc1ee2e2863cf08e5660ae69","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-02T11:19:49Z","title_canon_sha256":"a7bddefc960448db626ab16f960d7ac9086ae91a0266abd765d2fd8b00c87c51"},"schema_version":"1.0","source":{"id":"2604.01904","kind":"arxiv","version":2}},"canonical_sha256":"daf474ddfc0dd489ee1f6386f5d3c1e1a8cd08b462a5533c28ec599c12511717","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"daf474ddfc0dd489ee1f6386f5d3c1e1a8cd08b462a5533c28ec599c12511717","first_computed_at":"2026-05-29T02:05:44.151203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:44.151203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ne301cyHlsiKlPHcjWaAxwSCmViumMUBNox5osAIM3DgXkoigA6FXgXA7id2g3hurrBzobMa5t01QeQ0T2B1Aw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:44.152201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.01904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f996f18e8c032e8316b7231fc6bc6efb42c33da17dcbee52ff0bafe572eb3b46","sha256:806ef5404558f4b38998f65057404fca7eb815dcee50b1119cdf964c3bc38fea"],"state_sha256":"2989425777c30a7607efa9f1cd893afa07c061db5eccf82a3f2bbdd3e9baced6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ClssmUtxdPC0T528KsSNbS8UBaEL8wetxZpox+dXlHwTVtZxMc5H8WdShTKgvXIcXDkUJL0sWThGtNkZTetDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T16:53:42.751527Z","bundle_sha256":"a402ca659f261b7043496ca4634d144dd5bb5639462f5de7aefbd323c47b3f89"}}