{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KMS5R6TJ23LX4EWE56G2VQDQ6T","short_pith_number":"pith:KMS5R6TJ","canonical_record":{"source":{"id":"2201.03681","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T22:44:30Z","cross_cats_sorted":[],"title_canon_sha256":"88ced77b394a6ba8b040d4c18e1d421862b0c4f5398bb134e563cb64a2f394f1","abstract_canon_sha256":"bf94d4f23eef87776710e4b8b1e8f4cc00e4e0182ab140373695ea29226c9f6c"},"schema_version":"1.0"},"canonical_sha256":"5325d8fa69d6d77e12c4ef8daac070f4fa1b1dd26115630b5862c23bd4e40981","source":{"kind":"arxiv","id":"2201.03681","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.03681","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"2201.03681v3","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03681","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"KMS5R6TJ23LX","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"pith_short_16","alias_value":"KMS5R6TJ23LX4EWE","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"pith_short_8","alias_value":"KMS5R6TJ","created_at":"2026-07-05T03:57:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KMS5R6TJ23LX4EWE56G2VQDQ6T","target":"record","payload":{"canonical_record":{"source":{"id":"2201.03681","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T22:44:30Z","cross_cats_sorted":[],"title_canon_sha256":"88ced77b394a6ba8b040d4c18e1d421862b0c4f5398bb134e563cb64a2f394f1","abstract_canon_sha256":"bf94d4f23eef87776710e4b8b1e8f4cc00e4e0182ab140373695ea29226c9f6c"},"schema_version":"1.0"},"canonical_sha256":"5325d8fa69d6d77e12c4ef8daac070f4fa1b1dd26115630b5862c23bd4e40981","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:30.882906Z","signature_b64":"+zAGFmJG/nYRrxMBz2PqYILaA+C6isu3s+scSN53GsbHJDw5hTAphu2YuyI9hzPn8MQiny7wOPlDswsmrGyxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5325d8fa69d6d77e12c4ef8daac070f4fa1b1dd26115630b5862c23bd4e40981","last_reissued_at":"2026-07-05T03:57:30.882332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:30.882332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.03681","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWAdEf3Jgf7uRHafqR2TxSFkjJ+ub+pLNaKuGfORcOR+4wXBwg73G+9VvsZhcBjwQNZsx8l4IR6kAeVR0g5/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:46:52.667925Z"},"content_sha256":"42eb91a25e55b8d22ec398baa129d7067c32d1db3172c338f0c7dc506657218d","schema_version":"1.0","event_id":"sha256:42eb91a25e55b8d22ec398baa129d7067c32d1db3172c338f0c7dc506657218d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KMS5R6TJ23LX4EWE56G2VQDQ6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaresh Farrokh Bhathena, Donald Loveland, Jiayi Pan, Yiyang Lu","submitted_at":"2022-01-10T22:44:30Z","abstract_excerpt":"Graph Neural Networks (GNNs) have proven to excel in predictive modeling tasks where the underlying data is a graph. However, as GNNs are extensively used in human-centered applications, the issue of fairness has arisen. While edge deletion is a common method used to promote fairness in GNNs, it fails to consider when data is inherently missing fair connections. In this work we consider the unexplored method of edge addition, accompanied by deletion, to promote fairness. We propose two model-agnostic algorithms to perform edge editing: a brute force approach and a continuous approximation appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03681","kind":"arxiv","version":3},"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/2201.03681/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":"2026-07-05T03:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LsERkvgSfXKZ2OHAuNL/Bf2lqF/F8CW6pXo8Jg3VbnI60fO+bdidpMuadYRCm5tGovG9N4GFx9nVVkfyV0CdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:46:52.669558Z"},"content_sha256":"153bd622bf2e8c8b1febc3e7b07c10d0fbe044ddb1216c3202ff49fbf0526514","schema_version":"1.0","event_id":"sha256:153bd622bf2e8c8b1febc3e7b07c10d0fbe044ddb1216c3202ff49fbf0526514"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KMS5R6TJ23LX4EWE56G2VQDQ6T/bundle.json","state_url":"https://pith.science/pith/KMS5R6TJ23LX4EWE56G2VQDQ6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KMS5R6TJ23LX4EWE56G2VQDQ6T/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":"2026-08-18T00:46:52Z","links":{"resolver":"https://pith.science/pith/KMS5R6TJ23LX4EWE56G2VQDQ6T","bundle":"https://pith.science/pith/KMS5R6TJ23LX4EWE56G2VQDQ6T/bundle.json","state":"https://pith.science/pith/KMS5R6TJ23LX4EWE56G2VQDQ6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KMS5R6TJ23LX4EWE56G2VQDQ6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KMS5R6TJ23LX4EWE56G2VQDQ6T","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":"bf94d4f23eef87776710e4b8b1e8f4cc00e4e0182ab140373695ea29226c9f6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T22:44:30Z","title_canon_sha256":"88ced77b394a6ba8b040d4c18e1d421862b0c4f5398bb134e563cb64a2f394f1"},"schema_version":"1.0","source":{"id":"2201.03681","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.03681","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"2201.03681v3","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03681","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"KMS5R6TJ23LX","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"pith_short_16","alias_value":"KMS5R6TJ23LX4EWE","created_at":"2026-07-05T03:57:30Z"},{"alias_kind":"pith_short_8","alias_value":"KMS5R6TJ","created_at":"2026-07-05T03:57:30Z"}],"graph_snapshots":[{"event_id":"sha256:153bd622bf2e8c8b1febc3e7b07c10d0fbe044ddb1216c3202ff49fbf0526514","target":"graph","created_at":"2026-07-05T03:57:30Z","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/2201.03681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) have proven to excel in predictive modeling tasks where the underlying data is a graph. However, as GNNs are extensively used in human-centered applications, the issue of fairness has arisen. While edge deletion is a common method used to promote fairness in GNNs, it fails to consider when data is inherently missing fair connections. In this work we consider the unexplored method of edge addition, accompanied by deletion, to promote fairness. We propose two model-agnostic algorithms to perform edge editing: a brute force approach and a continuous approximation appr","authors_text":"Aaresh Farrokh Bhathena, Donald Loveland, Jiayi Pan, Yiyang Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T22:44:30Z","title":"FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03681","kind":"arxiv","version":3},"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":"sha256:42eb91a25e55b8d22ec398baa129d7067c32d1db3172c338f0c7dc506657218d","target":"record","created_at":"2026-07-05T03:57:30Z","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":"bf94d4f23eef87776710e4b8b1e8f4cc00e4e0182ab140373695ea29226c9f6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T22:44:30Z","title_canon_sha256":"88ced77b394a6ba8b040d4c18e1d421862b0c4f5398bb134e563cb64a2f394f1"},"schema_version":"1.0","source":{"id":"2201.03681","kind":"arxiv","version":3}},"canonical_sha256":"5325d8fa69d6d77e12c4ef8daac070f4fa1b1dd26115630b5862c23bd4e40981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5325d8fa69d6d77e12c4ef8daac070f4fa1b1dd26115630b5862c23bd4e40981","first_computed_at":"2026-07-05T03:57:30.882332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:57:30.882332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+zAGFmJG/nYRrxMBz2PqYILaA+C6isu3s+scSN53GsbHJDw5hTAphu2YuyI9hzPn8MQiny7wOPlDswsmrGyxBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:57:30.882906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.03681","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42eb91a25e55b8d22ec398baa129d7067c32d1db3172c338f0c7dc506657218d","sha256:153bd622bf2e8c8b1febc3e7b07c10d0fbe044ddb1216c3202ff49fbf0526514"],"state_sha256":"a530ceef46375b2fd0fb544e591f48a4b84b9d3a6c201ef8b7b110b474d9d0bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lhfwBNH1IeLon4SBpGInsXgkN58y2pXf91UxHevluZZhBV0hs1qpUMcIezZtoUzIazUhVx/KWJXPSFinLXb0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:46:52.675177Z","bundle_sha256":"72317443c7f67ff3e52d1ee3b17187a314c64bb971aff288781f0bd7169a7d58"}}