{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MZFLF22BL44WUK6RUE24I554PL","short_pith_number":"pith:MZFLF22B","canonical_record":{"source":{"id":"2508.14683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T12:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"eb970d203b54f1cba5e08ab87139899e6560d27671dc020e2b4b9668d84df07f","abstract_canon_sha256":"de06dec8e884ac548462a513cb7ddfb7ba2a9d080ff3bcb9d4e83e16038bdde7"},"schema_version":"1.0"},"canonical_sha256":"664ab2eb415f396a2bd1a135c477bc7af5cb41eb7f51f12dd3f1ec484d0ae1fa","source":{"kind":"arxiv","id":"2508.14683","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14683","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14683v1","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14683","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"pith_short_12","alias_value":"MZFLF22BL44W","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"pith_short_16","alias_value":"MZFLF22BL44WUK6R","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"pith_short_8","alias_value":"MZFLF22B","created_at":"2026-07-05T11:56:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MZFLF22BL44WUK6RUE24I554PL","target":"record","payload":{"canonical_record":{"source":{"id":"2508.14683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T12:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"eb970d203b54f1cba5e08ab87139899e6560d27671dc020e2b4b9668d84df07f","abstract_canon_sha256":"de06dec8e884ac548462a513cb7ddfb7ba2a9d080ff3bcb9d4e83e16038bdde7"},"schema_version":"1.0"},"canonical_sha256":"664ab2eb415f396a2bd1a135c477bc7af5cb41eb7f51f12dd3f1ec484d0ae1fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:36.763726Z","signature_b64":"DTfX9/XSwxj7OsmOKmw/i+uSJy3OAEkbqTdbYIBjqJuMrAgOa3frCMZ1xjacqbz4obt7jqxplKQlQ/AWmuH2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"664ab2eb415f396a2bd1a135c477bc7af5cb41eb7f51f12dd3f1ec484d0ae1fa","last_reissued_at":"2026-07-05T11:56:36.763248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:36.763248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.14683","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":"2026-07-05T11:56:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6L7aMiua4ysS0i7IIni7lROfJczqPTaStI+txHSuCX/XucyTQRTVPx8r38ivLp+cHq1uSOlzUrY7kQAza3tAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:08:46.059241Z"},"content_sha256":"f5bf8d3cf6dbe8ea1c5d1fe1984c26763907bd188925d08d440975883b73f420","schema_version":"1.0","event_id":"sha256:f5bf8d3cf6dbe8ea1c5d1fe1984c26763907bd188925d08d440975883b73f420"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MZFLF22BL44WUK6RUE24I554PL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Fairness in Graph Neural Networks via Counterfactual Debiasing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Liu, Minglai Shao, Wenjun Wang, Yumeng Wang, Zengyi Wo","submitted_at":"2025-08-20T12:59:05Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been successful in modeling graph-structured data. However, similar to other machine learning models, GNNs can exhibit bias in predictions based on attributes like race and gender. Moreover, bias in GNNs can be exacerbated by the graph structure and message-passing mechanisms. Recent cutting-edge methods propose mitigating bias by filtering out sensitive information from input or representations, like edge dropping or feature masking. Yet, we argue that such strategies may unintentionally eliminate non-sensitive features, leading to a compromised balance betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14683","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/2508.14683/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":"2026-07-05T11:56:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T0JrNXGjl4Nl5d8xO+TJjMm6ljZhhc+zilPvbehwGkrkD2AtoozHinrLavWpGLEEvpTDJi4UU0qHDphm0G2hCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:08:46.060349Z"},"content_sha256":"836b3a2349c396d2ac6446f0c107320652a1647de50702614bccedef802720ad","schema_version":"1.0","event_id":"sha256:836b3a2349c396d2ac6446f0c107320652a1647de50702614bccedef802720ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZFLF22BL44WUK6RUE24I554PL/bundle.json","state_url":"https://pith.science/pith/MZFLF22BL44WUK6RUE24I554PL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZFLF22BL44WUK6RUE24I554PL/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":"2026-08-04T22:08:46Z","links":{"resolver":"https://pith.science/pith/MZFLF22BL44WUK6RUE24I554PL","bundle":"https://pith.science/pith/MZFLF22BL44WUK6RUE24I554PL/bundle.json","state":"https://pith.science/pith/MZFLF22BL44WUK6RUE24I554PL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZFLF22BL44WUK6RUE24I554PL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MZFLF22BL44WUK6RUE24I554PL","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":"de06dec8e884ac548462a513cb7ddfb7ba2a9d080ff3bcb9d4e83e16038bdde7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T12:59:05Z","title_canon_sha256":"eb970d203b54f1cba5e08ab87139899e6560d27671dc020e2b4b9668d84df07f"},"schema_version":"1.0","source":{"id":"2508.14683","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14683","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14683v1","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14683","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"pith_short_12","alias_value":"MZFLF22BL44W","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"pith_short_16","alias_value":"MZFLF22BL44WUK6R","created_at":"2026-07-05T11:56:36Z"},{"alias_kind":"pith_short_8","alias_value":"MZFLF22B","created_at":"2026-07-05T11:56:36Z"}],"graph_snapshots":[{"event_id":"sha256:836b3a2349c396d2ac6446f0c107320652a1647de50702614bccedef802720ad","target":"graph","created_at":"2026-07-05T11:56:36Z","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/2508.14683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) have been successful in modeling graph-structured data. However, similar to other machine learning models, GNNs can exhibit bias in predictions based on attributes like race and gender. Moreover, bias in GNNs can be exacerbated by the graph structure and message-passing mechanisms. Recent cutting-edge methods propose mitigating bias by filtering out sensitive information from input or representations, like edge dropping or feature masking. Yet, we argue that such strategies may unintentionally eliminate non-sensitive features, leading to a compromised balance betwe","authors_text":"Chang Liu, Minglai Shao, Wenjun Wang, Yumeng Wang, Zengyi Wo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T12:59:05Z","title":"Improving Fairness in Graph Neural Networks via Counterfactual Debiasing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14683","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:f5bf8d3cf6dbe8ea1c5d1fe1984c26763907bd188925d08d440975883b73f420","target":"record","created_at":"2026-07-05T11:56:36Z","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":"de06dec8e884ac548462a513cb7ddfb7ba2a9d080ff3bcb9d4e83e16038bdde7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T12:59:05Z","title_canon_sha256":"eb970d203b54f1cba5e08ab87139899e6560d27671dc020e2b4b9668d84df07f"},"schema_version":"1.0","source":{"id":"2508.14683","kind":"arxiv","version":1}},"canonical_sha256":"664ab2eb415f396a2bd1a135c477bc7af5cb41eb7f51f12dd3f1ec484d0ae1fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"664ab2eb415f396a2bd1a135c477bc7af5cb41eb7f51f12dd3f1ec484d0ae1fa","first_computed_at":"2026-07-05T11:56:36.763248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:36.763248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DTfX9/XSwxj7OsmOKmw/i+uSJy3OAEkbqTdbYIBjqJuMrAgOa3frCMZ1xjacqbz4obt7jqxplKQlQ/AWmuH2DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:36.763726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14683","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5bf8d3cf6dbe8ea1c5d1fe1984c26763907bd188925d08d440975883b73f420","sha256:836b3a2349c396d2ac6446f0c107320652a1647de50702614bccedef802720ad"],"state_sha256":"8c573339fd29fea97a98dba062c8ad5a0c6cfba9670c39e6c5df6bae2ee1537b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ETApqqwoM/e8z3wyqqo7qzzc8PQIf9JCAWHuHDZ5F/c3MhMuuTSrx46PjPrgVyaV/OKAkeRcRRNxKaMyti8dDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:08:46.067813Z","bundle_sha256":"85025ce9646da8ee2f1f9cf6c78c1238abeebc392d7c385d1684a66d690bc6c2"}}