{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:352HU6VSPL6HRSXSSKSVLBON6Z","short_pith_number":"pith:352HU6VS","canonical_record":{"source":{"id":"2504.18353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T13:45:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"970c67a20a0795c8dc9174cfce1ef82b03b8e07ae67296211fc5248acd514f16","abstract_canon_sha256":"8229db417c3b115babf45a486e259114fe0dbff0af8e2119f89d123992928b58"},"schema_version":"1.0"},"canonical_sha256":"df747a7ab27afc78caf292a55585cdf668886d1c800083570e52c6f3710b9ac9","source":{"kind":"arxiv","id":"2504.18353","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18353","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18353v1","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18353","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"352HU6VSPL6H","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"352HU6VSPL6HRSXS","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"352HU6VS","created_at":"2026-07-05T10:54:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:352HU6VSPL6HRSXSSKSVLBON6Z","target":"record","payload":{"canonical_record":{"source":{"id":"2504.18353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T13:45:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"970c67a20a0795c8dc9174cfce1ef82b03b8e07ae67296211fc5248acd514f16","abstract_canon_sha256":"8229db417c3b115babf45a486e259114fe0dbff0af8e2119f89d123992928b58"},"schema_version":"1.0"},"canonical_sha256":"df747a7ab27afc78caf292a55585cdf668886d1c800083570e52c6f3710b9ac9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:05.873072Z","signature_b64":"wLklAck0BDBifVYLvCJY8b3h84XR+8LwHs0qx0E9boKjOOz4Lzpkx+io97ARYtHeXKcOTBdKIhLFrFHdZYRiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df747a7ab27afc78caf292a55585cdf668886d1c800083570e52c6f3710b9ac9","last_reissued_at":"2026-07-05T10:54:05.872593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:05.872593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.18353","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":"2026-07-05T10:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4MsIa7GEn+x5FuloGFs8EOD8GU2eylnJreLniRLVxXhkEoEE5S7c2GjzwnanBoETK58doXgcP9qxBwCoSVjjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:49:04.327030Z"},"content_sha256":"48fdbf1f3724953bf3f7745f7346d1e37c0683062ed6ddeaba01a7ed33044998","schema_version":"1.0","event_id":"sha256:48fdbf1f3724953bf3f7745f7346d1e37c0683062ed6ddeaba01a7ed33044998"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:352HU6VSPL6HRSXSSKSVLBON6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Testing Individual Fairness in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Roya Nasiri","submitted_at":"2025-04-25T13:45:24Z","abstract_excerpt":"The biases in artificial intelligence (AI) models can lead to automated decision-making processes that discriminate against groups and/or individuals based on sensitive properties such as gender and race. While there are many studies on diagnosing and mitigating biases in various AI models, there is little research on individual fairness in Graph Neural Networks (GNNs). Unlike traditional models, which treat data features independently and overlook their inter-relationships, GNNs are designed to capture graph-based structure where nodes are interconnected. This relational approach enables GNNs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18353","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/2504.18353/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":"2026-07-05T10:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M3FejFG84xioZNWbHp/DtcKybz7aw78/OsQnobJ8oxdFyGw9vS3qI8BZHo6CkT1uRGUUDglLIOrzIConDgNEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:49:04.327900Z"},"content_sha256":"04ad76b3762253ad49f6f78913a535a74b8577ac3c17c0ae6d2a941af3ea2a5e","schema_version":"1.0","event_id":"sha256:04ad76b3762253ad49f6f78913a535a74b8577ac3c17c0ae6d2a941af3ea2a5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/352HU6VSPL6HRSXSSKSVLBON6Z/bundle.json","state_url":"https://pith.science/pith/352HU6VSPL6HRSXSSKSVLBON6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/352HU6VSPL6HRSXSSKSVLBON6Z/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":"2026-08-20T21:49:04Z","links":{"resolver":"https://pith.science/pith/352HU6VSPL6HRSXSSKSVLBON6Z","bundle":"https://pith.science/pith/352HU6VSPL6HRSXSSKSVLBON6Z/bundle.json","state":"https://pith.science/pith/352HU6VSPL6HRSXSSKSVLBON6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/352HU6VSPL6HRSXSSKSVLBON6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:352HU6VSPL6HRSXSSKSVLBON6Z","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":"8229db417c3b115babf45a486e259114fe0dbff0af8e2119f89d123992928b58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T13:45:24Z","title_canon_sha256":"970c67a20a0795c8dc9174cfce1ef82b03b8e07ae67296211fc5248acd514f16"},"schema_version":"1.0","source":{"id":"2504.18353","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18353","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18353v1","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18353","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"352HU6VSPL6H","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"352HU6VSPL6HRSXS","created_at":"2026-07-05T10:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"352HU6VS","created_at":"2026-07-05T10:54:05Z"}],"graph_snapshots":[{"event_id":"sha256:04ad76b3762253ad49f6f78913a535a74b8577ac3c17c0ae6d2a941af3ea2a5e","target":"graph","created_at":"2026-07-05T10:54:05Z","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/2504.18353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The biases in artificial intelligence (AI) models can lead to automated decision-making processes that discriminate against groups and/or individuals based on sensitive properties such as gender and race. While there are many studies on diagnosing and mitigating biases in various AI models, there is little research on individual fairness in Graph Neural Networks (GNNs). Unlike traditional models, which treat data features independently and overlook their inter-relationships, GNNs are designed to capture graph-based structure where nodes are interconnected. This relational approach enables GNNs","authors_text":"Roya Nasiri","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T13:45:24Z","title":"Testing Individual Fairness in Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18353","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":"sha256:48fdbf1f3724953bf3f7745f7346d1e37c0683062ed6ddeaba01a7ed33044998","target":"record","created_at":"2026-07-05T10:54:05Z","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":"8229db417c3b115babf45a486e259114fe0dbff0af8e2119f89d123992928b58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T13:45:24Z","title_canon_sha256":"970c67a20a0795c8dc9174cfce1ef82b03b8e07ae67296211fc5248acd514f16"},"schema_version":"1.0","source":{"id":"2504.18353","kind":"arxiv","version":1}},"canonical_sha256":"df747a7ab27afc78caf292a55585cdf668886d1c800083570e52c6f3710b9ac9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df747a7ab27afc78caf292a55585cdf668886d1c800083570e52c6f3710b9ac9","first_computed_at":"2026-07-05T10:54:05.872593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:05.872593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wLklAck0BDBifVYLvCJY8b3h84XR+8LwHs0qx0E9boKjOOz4Lzpkx+io97ARYtHeXKcOTBdKIhLFrFHdZYRiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:05.873072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18353","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48fdbf1f3724953bf3f7745f7346d1e37c0683062ed6ddeaba01a7ed33044998","sha256:04ad76b3762253ad49f6f78913a535a74b8577ac3c17c0ae6d2a941af3ea2a5e"],"state_sha256":"1713f9564baac70bf91b624df8780818c2dc124dbddfd6ae885ab723f491c17d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FqYkLq12fCwC/z6pLch4Nu8ANV97WmJ1lstoClpXD5qqTUCPejY6Apyz+7hTq/81DfJ6CBkA/ekYXWHcRhaIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T21:49:04.334561Z","bundle_sha256":"60c12cb3c22dc07d6348ef6f852ea4166284eb4b76b84385dac4c909fb1b581d"}}