{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BC4BZ7PBOIOIKNWKUU7XSGMGWY","short_pith_number":"pith:BC4BZ7PB","canonical_record":{"source":{"id":"2009.01454","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-03T05:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"9b6016cc403aa4c103834cfb8031e311ee89329aade23d0ba0eab8602cf421a4","abstract_canon_sha256":"49855a56a4b8f24a0dd728be378c1cacbf9fefc81fbd463e99558379eee8c3e4"},"schema_version":"1.0"},"canonical_sha256":"08b81cfde1721c8536caa53f791986b6156abfdbc18a094d2015eb664fa3f19f","source":{"kind":"arxiv","id":"2009.01454","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.01454","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2009.01454v5","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.01454","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"BC4BZ7PBOIOI","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"BC4BZ7PBOIOIKNWK","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"BC4BZ7PB","created_at":"2026-07-05T03:22:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BC4BZ7PBOIOIKNWKUU7XSGMGWY","target":"record","payload":{"canonical_record":{"source":{"id":"2009.01454","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-03T05:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"9b6016cc403aa4c103834cfb8031e311ee89329aade23d0ba0eab8602cf421a4","abstract_canon_sha256":"49855a56a4b8f24a0dd728be378c1cacbf9fefc81fbd463e99558379eee8c3e4"},"schema_version":"1.0"},"canonical_sha256":"08b81cfde1721c8536caa53f791986b6156abfdbc18a094d2015eb664fa3f19f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:57.195308Z","signature_b64":"zMi1VQHxFtTIsZmFxlxireUYqWkEUrd0BuOUTBZlMyXr7UphgAMCoXOMxO1Jy+unGPSPH8k4OYj8Odz+QZeGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b81cfde1721c8536caa53f791986b6156abfdbc18a094d2015eb664fa3f19f","last_reissued_at":"2026-07-05T03:22:57.194889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:57.194889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.01454","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:22:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m7otI4hSxvUezYySKu1PD8EgvuvpaVpCKh1/jHBq7czj0tH8KLN0tS/BMYiXUqqcOSwNykz4XIdUoxIdPTTQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:53:20.697994Z"},"content_sha256":"eec34d7a2b78fcd047a0a0907677a14086147c4d5e63bd8943820cca78c16a9e","schema_version":"1.0","event_id":"sha256:eec34d7a2b78fcd047a0a0907677a14086147c4d5e63bd8943820cca78c16a9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BC4BZ7PBOIOIKNWKUU7XSGMGWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Enyan Dai, Suhang Wang","submitted_at":"2020-09-03T05:17:30Z","abstract_excerpt":"Graph neural networks (GNNs) have shown great power in modeling graph structured data. However, similar to other machine learning models, GNNs may make predictions biased on protected sensitive attributes, e.g., skin color and gender. Because machine learning algorithms including GNNs are trained to reflect the distribution of the training data which often contains historical bias towards sensitive attributes. In addition, the discrimination in GNNs can be magnified by graph structures and the message-passing mechanism. As a result, the applications of GNNs in sensitive domains such as crime r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.01454","kind":"arxiv","version":5},"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/2009.01454/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":"2026-07-05T03:22:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GOX+RgwzeFuWptmEXlm7hQTiu7ax0WfVc8KVewc+ygVJ7wS17PG2SdGs48SdUbQZOcoN5vKdkBuJqKPOP1LBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:53:20.698570Z"},"content_sha256":"84e62469973ebdc445d187ab161a22ff3ea33396b89c7265593bcb3e82e76526","schema_version":"1.0","event_id":"sha256:84e62469973ebdc445d187ab161a22ff3ea33396b89c7265593bcb3e82e76526"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BC4BZ7PBOIOIKNWKUU7XSGMGWY/bundle.json","state_url":"https://pith.science/pith/BC4BZ7PBOIOIKNWKUU7XSGMGWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BC4BZ7PBOIOIKNWKUU7XSGMGWY/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":"2026-08-05T13:53:20Z","links":{"resolver":"https://pith.science/pith/BC4BZ7PBOIOIKNWKUU7XSGMGWY","bundle":"https://pith.science/pith/BC4BZ7PBOIOIKNWKUU7XSGMGWY/bundle.json","state":"https://pith.science/pith/BC4BZ7PBOIOIKNWKUU7XSGMGWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BC4BZ7PBOIOIKNWKUU7XSGMGWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BC4BZ7PBOIOIKNWKUU7XSGMGWY","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":"49855a56a4b8f24a0dd728be378c1cacbf9fefc81fbd463e99558379eee8c3e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-03T05:17:30Z","title_canon_sha256":"9b6016cc403aa4c103834cfb8031e311ee89329aade23d0ba0eab8602cf421a4"},"schema_version":"1.0","source":{"id":"2009.01454","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.01454","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2009.01454v5","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.01454","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"BC4BZ7PBOIOI","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"BC4BZ7PBOIOIKNWK","created_at":"2026-07-05T03:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"BC4BZ7PB","created_at":"2026-07-05T03:22:57Z"}],"graph_snapshots":[{"event_id":"sha256:84e62469973ebdc445d187ab161a22ff3ea33396b89c7265593bcb3e82e76526","target":"graph","created_at":"2026-07-05T03:22:57Z","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/2009.01454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks (GNNs) have shown great power in modeling graph structured data. However, similar to other machine learning models, GNNs may make predictions biased on protected sensitive attributes, e.g., skin color and gender. Because machine learning algorithms including GNNs are trained to reflect the distribution of the training data which often contains historical bias towards sensitive attributes. In addition, the discrimination in GNNs can be magnified by graph structures and the message-passing mechanism. As a result, the applications of GNNs in sensitive domains such as crime r","authors_text":"Enyan Dai, Suhang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-03T05:17:30Z","title":"Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.01454","kind":"arxiv","version":5},"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:eec34d7a2b78fcd047a0a0907677a14086147c4d5e63bd8943820cca78c16a9e","target":"record","created_at":"2026-07-05T03:22:57Z","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":"49855a56a4b8f24a0dd728be378c1cacbf9fefc81fbd463e99558379eee8c3e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-03T05:17:30Z","title_canon_sha256":"9b6016cc403aa4c103834cfb8031e311ee89329aade23d0ba0eab8602cf421a4"},"schema_version":"1.0","source":{"id":"2009.01454","kind":"arxiv","version":5}},"canonical_sha256":"08b81cfde1721c8536caa53f791986b6156abfdbc18a094d2015eb664fa3f19f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08b81cfde1721c8536caa53f791986b6156abfdbc18a094d2015eb664fa3f19f","first_computed_at":"2026-07-05T03:22:57.194889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:57.194889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zMi1VQHxFtTIsZmFxlxireUYqWkEUrd0BuOUTBZlMyXr7UphgAMCoXOMxO1Jy+unGPSPH8k4OYj8Odz+QZeGAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:57.195308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.01454","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eec34d7a2b78fcd047a0a0907677a14086147c4d5e63bd8943820cca78c16a9e","sha256:84e62469973ebdc445d187ab161a22ff3ea33396b89c7265593bcb3e82e76526"],"state_sha256":"db51e37e1353dd13f985b71836f1d5d65cb09a4b453e0a301bb40adaacd51f9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lELk0FSKMp3A79Mhrlla0PK8PqeMf+C4pdxf0KLq7VvrgxgAHxbr/QkXrNVxQ3lhuf/dRXaIIueRC3nXkkmdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:53:20.703109Z","bundle_sha256":"f2079ae572febdebfeaff019ef1b3cc1c43ac0294c36db2d8d65abebefe49d51"}}