{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7OXLBSVOIWP2JAL52E5QETU5XE","short_pith_number":"pith:7OXLBSVO","canonical_record":{"source":{"id":"2605.23239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T05:18:18Z","cross_cats_sorted":[],"title_canon_sha256":"1b33e803c2887039c5b61414de5bf90fabe9daf945a339c45e878552bdaeb159","abstract_canon_sha256":"72a723ecbb4a1c6a3196aa87b70b18050e5629522c656f6fd74fb86efcc3efb6"},"schema_version":"1.0"},"canonical_sha256":"fbaeb0caae459fa4817dd13b024e9db91510899bc67c7953e408fff49b9391ce","source":{"kind":"arxiv","id":"2605.23239","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23239","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23239v1","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23239","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"7OXLBSVOIWP2","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"7OXLBSVOIWP2JAL5","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"7OXLBSVO","created_at":"2026-05-25T02:01:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7OXLBSVOIWP2JAL52E5QETU5XE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T05:18:18Z","cross_cats_sorted":[],"title_canon_sha256":"1b33e803c2887039c5b61414de5bf90fabe9daf945a339c45e878552bdaeb159","abstract_canon_sha256":"72a723ecbb4a1c6a3196aa87b70b18050e5629522c656f6fd74fb86efcc3efb6"},"schema_version":"1.0"},"canonical_sha256":"fbaeb0caae459fa4817dd13b024e9db91510899bc67c7953e408fff49b9391ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:45.182681Z","signature_b64":"W8purKqN0UnqN0505fgKWomUSklkgDPULyNTWTEc4ZqAqrBgFGOZwy5UwBWJ2jy0sWFIC6riK+z/nwehSyeLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbaeb0caae459fa4817dd13b024e9db91510899bc67c7953e408fff49b9391ce","last_reissued_at":"2026-05-25T02:01:45.180357Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:45.180357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23239","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":"2026-05-25T02:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8pgvxgtU5k/d+FkGnliEqMQTuLJCltIraw387O7LFXpmbKeRhTGYZmCVxv5WOgFrpp4zYzxFCABRYuqHNx2CCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:58:03.662247Z"},"content_sha256":"01b21fd0d0a570f8a179cc9820b34cb0aadc171992bf57d9f4e2e4bffa8cccc3","schema_version":"1.0","event_id":"sha256:01b21fd0d0a570f8a179cc9820b34cb0aadc171992bf57d9f4e2e4bffa8cccc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7OXLBSVOIWP2JAL52E5QETU5XE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised Adversarial Purification for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hogun Park, Woohyun Lee","submitted_at":"2026-05-22T05:18:18Z","abstract_excerpt":"Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicting objectives within a single classifier. To overcome this limitation, we propose a self-supervised adversarial purification framework. We separate robustness from the classifier by introducing a dedicated purifier, which cleanses the input data before classification. In contrast to prior adversarial purification methods, we propose GPR-GAE, a novel graph auto-encoder (GAE), as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23239","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/2605.23239/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":"2026-05-25T02:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8zamWCnKgWKAXNJh7BSF6Fqk5PMfNAxZnfIUzXWwZZK8wZY+odPHUpBzz+RI2Z/k7vWtlSLATCKbpZPhelpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:58:03.662656Z"},"content_sha256":"1be762a6efb2a6b32d5107866ddc8919017d87c9661547f5f4a27e71379473a0","schema_version":"1.0","event_id":"sha256:1be762a6efb2a6b32d5107866ddc8919017d87c9661547f5f4a27e71379473a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7OXLBSVOIWP2JAL52E5QETU5XE/bundle.json","state_url":"https://pith.science/pith/7OXLBSVOIWP2JAL52E5QETU5XE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7OXLBSVOIWP2JAL52E5QETU5XE/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":"2026-05-30T11:58:03Z","links":{"resolver":"https://pith.science/pith/7OXLBSVOIWP2JAL52E5QETU5XE","bundle":"https://pith.science/pith/7OXLBSVOIWP2JAL52E5QETU5XE/bundle.json","state":"https://pith.science/pith/7OXLBSVOIWP2JAL52E5QETU5XE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7OXLBSVOIWP2JAL52E5QETU5XE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7OXLBSVOIWP2JAL52E5QETU5XE","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":"72a723ecbb4a1c6a3196aa87b70b18050e5629522c656f6fd74fb86efcc3efb6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T05:18:18Z","title_canon_sha256":"1b33e803c2887039c5b61414de5bf90fabe9daf945a339c45e878552bdaeb159"},"schema_version":"1.0","source":{"id":"2605.23239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23239","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23239v1","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23239","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"7OXLBSVOIWP2","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"7OXLBSVOIWP2JAL5","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"7OXLBSVO","created_at":"2026-05-25T02:01:45Z"}],"graph_snapshots":[{"event_id":"sha256:1be762a6efb2a6b32d5107866ddc8919017d87c9661547f5f4a27e71379473a0","target":"graph","created_at":"2026-05-25T02:01:45Z","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/2605.23239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicting objectives within a single classifier. To overcome this limitation, we propose a self-supervised adversarial purification framework. We separate robustness from the classifier by introducing a dedicated purifier, which cleanses the input data before classification. In contrast to prior adversarial purification methods, we propose GPR-GAE, a novel graph auto-encoder (GAE), as","authors_text":"Hogun Park, Woohyun Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T05:18:18Z","title":"Self-supervised Adversarial Purification for Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23239","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":"sha256:01b21fd0d0a570f8a179cc9820b34cb0aadc171992bf57d9f4e2e4bffa8cccc3","target":"record","created_at":"2026-05-25T02:01:45Z","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":"72a723ecbb4a1c6a3196aa87b70b18050e5629522c656f6fd74fb86efcc3efb6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T05:18:18Z","title_canon_sha256":"1b33e803c2887039c5b61414de5bf90fabe9daf945a339c45e878552bdaeb159"},"schema_version":"1.0","source":{"id":"2605.23239","kind":"arxiv","version":1}},"canonical_sha256":"fbaeb0caae459fa4817dd13b024e9db91510899bc67c7953e408fff49b9391ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbaeb0caae459fa4817dd13b024e9db91510899bc67c7953e408fff49b9391ce","first_computed_at":"2026-05-25T02:01:45.180357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:45.180357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W8purKqN0UnqN0505fgKWomUSklkgDPULyNTWTEc4ZqAqrBgFGOZwy5UwBWJ2jy0sWFIC6riK+z/nwehSyeLAQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:45.182681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01b21fd0d0a570f8a179cc9820b34cb0aadc171992bf57d9f4e2e4bffa8cccc3","sha256:1be762a6efb2a6b32d5107866ddc8919017d87c9661547f5f4a27e71379473a0"],"state_sha256":"775f098011dd8395e1094249cb2a077a0202767762d929aa5e7ad75b6f33dab3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lesXFn/7QgXorId5tDxexxZgYA+D/pzGqfr5KmxDJMpttEgliN10bLlleUfByEzMM7WrgbZrBQ9UuT8Tgk4MDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:58:03.666919Z","bundle_sha256":"862ecade47a99af5f7637ef6c109e647a19f8aa7fd4d62e40c10b5a8bc3451d9"}}