{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MYCPAVIDKUTAMLAII2RTNIL7LD","short_pith_number":"pith:MYCPAVID","canonical_record":{"source":{"id":"2503.10544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T16:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"b3e244c6e225d013edf5e3a15771ad69c978cc8f9938d34e7dc9bb916ed507cc","abstract_canon_sha256":"3a3fe7e9e760e4ea825a36d1b2b40c7644c9a58059b380d0ec5863b6f095f85c"},"schema_version":"1.0"},"canonical_sha256":"6604f055035526062c0846a336a17f58ed41759d53a39b8a9d76df9188f16f67","source":{"kind":"arxiv","id":"2503.10544","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10544","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10544v2","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10544","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"MYCPAVIDKUTA","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_16","alias_value":"MYCPAVIDKUTAMLAI","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_8","alias_value":"MYCPAVID","created_at":"2026-07-05T10:41:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MYCPAVIDKUTAMLAII2RTNIL7LD","target":"record","payload":{"canonical_record":{"source":{"id":"2503.10544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T16:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"b3e244c6e225d013edf5e3a15771ad69c978cc8f9938d34e7dc9bb916ed507cc","abstract_canon_sha256":"3a3fe7e9e760e4ea825a36d1b2b40c7644c9a58059b380d0ec5863b6f095f85c"},"schema_version":"1.0"},"canonical_sha256":"6604f055035526062c0846a336a17f58ed41759d53a39b8a9d76df9188f16f67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:21.513305Z","signature_b64":"GB+sdbQtmKNzVifmIVN54mWsfAj7072qDBfPhQjhKsc8B4yb5b3D9qLuLN/gPGTywhOVPivixO0tLq25gtfvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6604f055035526062c0846a336a17f58ed41759d53a39b8a9d76df9188f16f67","last_reissued_at":"2026-07-05T10:41:21.512813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:21.512813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.10544","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":"2026-07-05T10:41:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kIAQUU4WoDAxLvbQpi3THMz/5McHAjrVtXLMIP/yHDOInxVb5tcy+HOvH7BQ9tN4E+KzI6kmc5ak0kTtCzuEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:18:01.402308Z"},"content_sha256":"8189092b00809a7e4565c41711f61772637d2ab0d3a55356fc2e83348c5f3729","schema_version":"1.0","event_id":"sha256:8189092b00809a7e4565c41711f61772637d2ab0d3a55356fc2e83348c5f3729"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MYCPAVIDKUTAMLAII2RTNIL7LD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DP-GPL: Differentially Private Graph Prompt Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Dziedzic, Franziska Boenisch, Iyiola Emmanuel Olatunji, Jing Xu","submitted_at":"2025-03-13T16:58:07Z","abstract_excerpt":"Graph Neural Networks (GNNs) have shown remarkable performance in various applications. Recently, graph prompt learning has emerged as a powerful GNN training paradigm, inspired by advances in language and vision foundation models. Here, a GNN is pre-trained on public data and then adapted to sensitive tasks using lightweight graph prompts. However, using prompts from sensitive data poses privacy risks. In this work, we are the first to investigate these practical risks in graph prompts by instantiating a membership inference attack that reveals significant privacy leakage. We also find that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10544","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/2503.10544/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":"2026-07-05T10:41:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1tPAULlK5VdcZsmqpUKPwij/wEG5NkLmufTNf5cZu25IeEgSOMqkKUDGGtgcceHT5cbegnYAnk2mWh5JXUqPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:18:01.402840Z"},"content_sha256":"9734be810e9a332338678336fc79e6ec9ae447de4fa0760172b58d32a4203a13","schema_version":"1.0","event_id":"sha256:9734be810e9a332338678336fc79e6ec9ae447de4fa0760172b58d32a4203a13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYCPAVIDKUTAMLAII2RTNIL7LD/bundle.json","state_url":"https://pith.science/pith/MYCPAVIDKUTAMLAII2RTNIL7LD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYCPAVIDKUTAMLAII2RTNIL7LD/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":"2026-08-05T22:18:01Z","links":{"resolver":"https://pith.science/pith/MYCPAVIDKUTAMLAII2RTNIL7LD","bundle":"https://pith.science/pith/MYCPAVIDKUTAMLAII2RTNIL7LD/bundle.json","state":"https://pith.science/pith/MYCPAVIDKUTAMLAII2RTNIL7LD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYCPAVIDKUTAMLAII2RTNIL7LD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MYCPAVIDKUTAMLAII2RTNIL7LD","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":"3a3fe7e9e760e4ea825a36d1b2b40c7644c9a58059b380d0ec5863b6f095f85c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T16:58:07Z","title_canon_sha256":"b3e244c6e225d013edf5e3a15771ad69c978cc8f9938d34e7dc9bb916ed507cc"},"schema_version":"1.0","source":{"id":"2503.10544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10544","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10544v2","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10544","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"MYCPAVIDKUTA","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_16","alias_value":"MYCPAVIDKUTAMLAI","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_8","alias_value":"MYCPAVID","created_at":"2026-07-05T10:41:21Z"}],"graph_snapshots":[{"event_id":"sha256:9734be810e9a332338678336fc79e6ec9ae447de4fa0760172b58d32a4203a13","target":"graph","created_at":"2026-07-05T10:41:21Z","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/2503.10544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) have shown remarkable performance in various applications. Recently, graph prompt learning has emerged as a powerful GNN training paradigm, inspired by advances in language and vision foundation models. Here, a GNN is pre-trained on public data and then adapted to sensitive tasks using lightweight graph prompts. However, using prompts from sensitive data poses privacy risks. In this work, we are the first to investigate these practical risks in graph prompts by instantiating a membership inference attack that reveals significant privacy leakage. We also find that t","authors_text":"Adam Dziedzic, Franziska Boenisch, Iyiola Emmanuel Olatunji, Jing Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T16:58:07Z","title":"DP-GPL: Differentially Private Graph Prompt Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10544","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":"sha256:8189092b00809a7e4565c41711f61772637d2ab0d3a55356fc2e83348c5f3729","target":"record","created_at":"2026-07-05T10:41:21Z","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":"3a3fe7e9e760e4ea825a36d1b2b40c7644c9a58059b380d0ec5863b6f095f85c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T16:58:07Z","title_canon_sha256":"b3e244c6e225d013edf5e3a15771ad69c978cc8f9938d34e7dc9bb916ed507cc"},"schema_version":"1.0","source":{"id":"2503.10544","kind":"arxiv","version":2}},"canonical_sha256":"6604f055035526062c0846a336a17f58ed41759d53a39b8a9d76df9188f16f67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6604f055035526062c0846a336a17f58ed41759d53a39b8a9d76df9188f16f67","first_computed_at":"2026-07-05T10:41:21.512813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:21.512813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GB+sdbQtmKNzVifmIVN54mWsfAj7072qDBfPhQjhKsc8B4yb5b3D9qLuLN/gPGTywhOVPivixO0tLq25gtfvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:21.513305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8189092b00809a7e4565c41711f61772637d2ab0d3a55356fc2e83348c5f3729","sha256:9734be810e9a332338678336fc79e6ec9ae447de4fa0760172b58d32a4203a13"],"state_sha256":"7db41891fd83f580da1e93ad4154a78890390e541af47e64038171e88fd1a18c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iew7t0Kcc4PVUhaBz+Usdd0yLzEDfXJMxted3yXkP+2P1+aY20Xb2+/VDmfxLZyzDgB7ST1/9TDPfONr4zCjCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:18:01.407492Z","bundle_sha256":"8ecc4e746e3b5e28736947acdb0bae37cd79c5c6e7d670fd2b35fe0dcdb11853"}}