{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I6E5ZWE67WPLKEJEERW6GNESBI","short_pith_number":"pith:I6E5ZWE6","canonical_record":{"source":{"id":"2410.03537","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T15:54:49Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"bbc762980ad766117348d3aafa9774a0024b5f46514c2cc77d8adac565fcb40c","abstract_canon_sha256":"4ef5277538193da1279c5973c132f5e2fd4a3b03a3b3f62c0d78c3892deb8827"},"schema_version":"1.0"},"canonical_sha256":"4789dcd89efd9eb51124246de334920a306efc5c23e440389c2e236580759859","source":{"kind":"arxiv","id":"2410.03537","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03537","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03537v2","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03537","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"I6E5ZWE67WPL","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"I6E5ZWE67WPLKEJE","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"I6E5ZWE6","created_at":"2026-07-05T10:19:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I6E5ZWE67WPLKEJEERW6GNESBI","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03537","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T15:54:49Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"bbc762980ad766117348d3aafa9774a0024b5f46514c2cc77d8adac565fcb40c","abstract_canon_sha256":"4ef5277538193da1279c5973c132f5e2fd4a3b03a3b3f62c0d78c3892deb8827"},"schema_version":"1.0"},"canonical_sha256":"4789dcd89efd9eb51124246de334920a306efc5c23e440389c2e236580759859","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:29.146615Z","signature_b64":"2Bu5fKVLoqujqom8LbY8RmHIPuo7gcjjGP1daVO+qiM3tvkT2/GINqu02glZUOKEUEUQDHEpR2vp9LMVmhPpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4789dcd89efd9eb51124246de334920a306efc5c23e440389c2e236580759859","last_reissued_at":"2026-07-05T10:19:29.146141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:29.146141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03537","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":"2026-07-05T10:19:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S4jRoQcmp0lT6ccypwakSBnQNl6zD2qkJgueulJTJWr8Su8lekwDUqCoj0z50XAxnRYK5H3vw/oaNtP8MTlnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:09:01.074122Z"},"content_sha256":"63cebd74189fdae7afcacecb0c1ac897dc718c655338ec33e8fdc01092511199","schema_version":"1.0","event_id":"sha256:63cebd74189fdae7afcacecb0c1ac897dc718c655338ec33e8fdc01092511199"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I6E5ZWE67WPLKEJEERW6GNESBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Martin Vechev, Maximilian Baader, Nikola Jovanovi\\'c, Robin Staab","submitted_at":"2024-10-04T15:54:49Z","abstract_excerpt":"RAG enables LLMs to easily incorporate external data, raising concerns for data owners regarding unauthorized usage of their content. The challenge of detecting such unauthorized usage remains underexplored, with datasets and methods from adjacent fields being ill-suited for its study. We take several steps to bridge this gap. First, we formalize this problem as (black-box) RAG Dataset Inference (RAG-DI). We then introduce a novel dataset designed for realistic benchmarking of RAG-DI methods, alongside a set of baselines. Finally, we propose Ward, a method for RAG-DI based on LLM watermarks th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03537","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/2410.03537/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":"2026-07-05T10:19:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eddk50NMLYeyXPNTtitfCFiTblD74JSQNXnzwCfmL8D/PlK4TwsAOuShBD2QjBUPJ9zROoCceRLdI4zboapGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:09:01.074519Z"},"content_sha256":"9399f8b11d5419cb3ed8055e73ff8ca3875a6da68af2664db1b36a4ef417f145","schema_version":"1.0","event_id":"sha256:9399f8b11d5419cb3ed8055e73ff8ca3875a6da68af2664db1b36a4ef417f145"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6E5ZWE67WPLKEJEERW6GNESBI/bundle.json","state_url":"https://pith.science/pith/I6E5ZWE67WPLKEJEERW6GNESBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6E5ZWE67WPLKEJEERW6GNESBI/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":"2026-08-22T05:09:01Z","links":{"resolver":"https://pith.science/pith/I6E5ZWE67WPLKEJEERW6GNESBI","bundle":"https://pith.science/pith/I6E5ZWE67WPLKEJEERW6GNESBI/bundle.json","state":"https://pith.science/pith/I6E5ZWE67WPLKEJEERW6GNESBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6E5ZWE67WPLKEJEERW6GNESBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I6E5ZWE67WPLKEJEERW6GNESBI","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":"4ef5277538193da1279c5973c132f5e2fd4a3b03a3b3f62c0d78c3892deb8827","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T15:54:49Z","title_canon_sha256":"bbc762980ad766117348d3aafa9774a0024b5f46514c2cc77d8adac565fcb40c"},"schema_version":"1.0","source":{"id":"2410.03537","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03537","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03537v2","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03537","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"I6E5ZWE67WPL","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"I6E5ZWE67WPLKEJE","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"I6E5ZWE6","created_at":"2026-07-05T10:19:29Z"}],"graph_snapshots":[{"event_id":"sha256:9399f8b11d5419cb3ed8055e73ff8ca3875a6da68af2664db1b36a4ef417f145","target":"graph","created_at":"2026-07-05T10:19:29Z","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/2410.03537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"RAG enables LLMs to easily incorporate external data, raising concerns for data owners regarding unauthorized usage of their content. The challenge of detecting such unauthorized usage remains underexplored, with datasets and methods from adjacent fields being ill-suited for its study. We take several steps to bridge this gap. First, we formalize this problem as (black-box) RAG Dataset Inference (RAG-DI). We then introduce a novel dataset designed for realistic benchmarking of RAG-DI methods, alongside a set of baselines. Finally, we propose Ward, a method for RAG-DI based on LLM watermarks th","authors_text":"Martin Vechev, Maximilian Baader, Nikola Jovanovi\\'c, Robin Staab","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T15:54:49Z","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03537","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":"sha256:63cebd74189fdae7afcacecb0c1ac897dc718c655338ec33e8fdc01092511199","target":"record","created_at":"2026-07-05T10:19:29Z","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":"4ef5277538193da1279c5973c132f5e2fd4a3b03a3b3f62c0d78c3892deb8827","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T15:54:49Z","title_canon_sha256":"bbc762980ad766117348d3aafa9774a0024b5f46514c2cc77d8adac565fcb40c"},"schema_version":"1.0","source":{"id":"2410.03537","kind":"arxiv","version":2}},"canonical_sha256":"4789dcd89efd9eb51124246de334920a306efc5c23e440389c2e236580759859","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4789dcd89efd9eb51124246de334920a306efc5c23e440389c2e236580759859","first_computed_at":"2026-07-05T10:19:29.146141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:29.146141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Bu5fKVLoqujqom8LbY8RmHIPuo7gcjjGP1daVO+qiM3tvkT2/GINqu02glZUOKEUEUQDHEpR2vp9LMVmhPpAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:29.146615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03537","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63cebd74189fdae7afcacecb0c1ac897dc718c655338ec33e8fdc01092511199","sha256:9399f8b11d5419cb3ed8055e73ff8ca3875a6da68af2664db1b36a4ef417f145"],"state_sha256":"ba3479a0860357881e0f2d9524d5e6ea07783d4b524b8070320038e77dc35dbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4yFEczUlokrc65GdPgfKCl4k4vSfwar4ERp//spZWqwk60RwbnyXlNB9PUd3QslV2I4Whz9WXzb4RNmzsJEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:09:01.077402Z","bundle_sha256":"d06adc9854c37d68b146e2c3fd06a39af7e2797e98b1e2241fa88649084bdf98"}}