{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KVO5JR5CA5KUPWVGHXMRGKXVRK","short_pith_number":"pith:KVO5JR5C","canonical_record":{"source":{"id":"2209.14107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T13:55:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"efa157957fa4df72a1756e41b3bd3bbda1521bad62bfeb01afa6ad3677b572da","abstract_canon_sha256":"bcb0638c16392c7f14475fd8879c46f297a7369c4557511e9d9b82e69a1b1817"},"schema_version":"1.0"},"canonical_sha256":"555dd4c7a2075547daa63dd9132af58a81a7852640bd2b509968239f9586af02","source":{"kind":"arxiv","id":"2209.14107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14107","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14107v1","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14107","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"KVO5JR5CA5KU","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"KVO5JR5CA5KUPWVG","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"KVO5JR5C","created_at":"2026-07-05T05:01:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KVO5JR5CA5KUPWVGHXMRGKXVRK","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T13:55:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"efa157957fa4df72a1756e41b3bd3bbda1521bad62bfeb01afa6ad3677b572da","abstract_canon_sha256":"bcb0638c16392c7f14475fd8879c46f297a7369c4557511e9d9b82e69a1b1817"},"schema_version":"1.0"},"canonical_sha256":"555dd4c7a2075547daa63dd9132af58a81a7852640bd2b509968239f9586af02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:47.983201Z","signature_b64":"eQ6ti6Uj3f9+7GkOHdXdiKGVhMIJQWzFmOPpuMXgZVVbcQ2hAT49IbGBrUIG0m2//ByjRdXEURCk230jNhw2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"555dd4c7a2075547daa63dd9132af58a81a7852640bd2b509968239f9586af02","last_reissued_at":"2026-07-05T05:01:47.982824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:47.982824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14107","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":"2026-07-05T05:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4xD7SqFyW4XnfKCQllKINQ9GUHKQcbNp+/EUp/ZgL5qgAu31ZGlIevAb8KlZJ4rTj1S6T29tab/bFGcyO5bBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:22:44.356127Z"},"content_sha256":"57099519ed346359993829faccb86858aebab537594f2232d886116c9e15816c","schema_version":"1.0","event_id":"sha256:57099519ed346359993829faccb86858aebab537594f2232d886116c9e15816c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KVO5JR5CA5KUPWVGHXMRGKXVRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Jian Tang, Shaohua Fan, Xiao Wang, Yanhu Mo","submitted_at":"2022-09-28T13:55:52Z","abstract_excerpt":"Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by learning the correlation between the input graphs and labels. However, by presenting a graph classification investigation on the training graphs with severe bias, surprisingly, we discover that GNNs always tend to explore the spurious correlations to make decision, even if the causal correlation always exists. This implies that existing GNNs trained on such biased datasets will suffer from poor generalization capability. By analyzing this problem in a causal view, we find that disentangling and decorrelating the causal an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14107","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/2209.14107/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":"2026-07-05T05:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2VPCwkLkaNMyg7QIl+f8yBaeiDIHOJkT4cXssBz+Nhij69/hEpai4GTquE3EQQsTYxWgQfrBbjaQmLodskfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:22:44.356711Z"},"content_sha256":"fc7333af026d4b7486f48ba0bb3d16f7475b404b4edd0a732671da0a08217dc7","schema_version":"1.0","event_id":"sha256:fc7333af026d4b7486f48ba0bb3d16f7475b404b4edd0a732671da0a08217dc7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KVO5JR5CA5KUPWVGHXMRGKXVRK/bundle.json","state_url":"https://pith.science/pith/KVO5JR5CA5KUPWVGHXMRGKXVRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KVO5JR5CA5KUPWVGHXMRGKXVRK/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":"2026-08-07T01:22:44Z","links":{"resolver":"https://pith.science/pith/KVO5JR5CA5KUPWVGHXMRGKXVRK","bundle":"https://pith.science/pith/KVO5JR5CA5KUPWVGHXMRGKXVRK/bundle.json","state":"https://pith.science/pith/KVO5JR5CA5KUPWVGHXMRGKXVRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KVO5JR5CA5KUPWVGHXMRGKXVRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KVO5JR5CA5KUPWVGHXMRGKXVRK","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":"bcb0638c16392c7f14475fd8879c46f297a7369c4557511e9d9b82e69a1b1817","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T13:55:52Z","title_canon_sha256":"efa157957fa4df72a1756e41b3bd3bbda1521bad62bfeb01afa6ad3677b572da"},"schema_version":"1.0","source":{"id":"2209.14107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14107","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14107v1","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14107","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"KVO5JR5CA5KU","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"KVO5JR5CA5KUPWVG","created_at":"2026-07-05T05:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"KVO5JR5C","created_at":"2026-07-05T05:01:47Z"}],"graph_snapshots":[{"event_id":"sha256:fc7333af026d4b7486f48ba0bb3d16f7475b404b4edd0a732671da0a08217dc7","target":"graph","created_at":"2026-07-05T05:01:47Z","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/2209.14107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by learning the correlation between the input graphs and labels. However, by presenting a graph classification investigation on the training graphs with severe bias, surprisingly, we discover that GNNs always tend to explore the spurious correlations to make decision, even if the causal correlation always exists. This implies that existing GNNs trained on such biased datasets will suffer from poor generalization capability. By analyzing this problem in a causal view, we find that disentangling and decorrelating the causal an","authors_text":"Chuan Shi, Jian Tang, Shaohua Fan, Xiao Wang, Yanhu Mo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T13:55:52Z","title":"Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14107","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":"sha256:57099519ed346359993829faccb86858aebab537594f2232d886116c9e15816c","target":"record","created_at":"2026-07-05T05:01:47Z","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":"bcb0638c16392c7f14475fd8879c46f297a7369c4557511e9d9b82e69a1b1817","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T13:55:52Z","title_canon_sha256":"efa157957fa4df72a1756e41b3bd3bbda1521bad62bfeb01afa6ad3677b572da"},"schema_version":"1.0","source":{"id":"2209.14107","kind":"arxiv","version":1}},"canonical_sha256":"555dd4c7a2075547daa63dd9132af58a81a7852640bd2b509968239f9586af02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"555dd4c7a2075547daa63dd9132af58a81a7852640bd2b509968239f9586af02","first_computed_at":"2026-07-05T05:01:47.982824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:01:47.982824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eQ6ti6Uj3f9+7GkOHdXdiKGVhMIJQWzFmOPpuMXgZVVbcQ2hAT49IbGBrUIG0m2//ByjRdXEURCk230jNhw2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:01:47.983201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57099519ed346359993829faccb86858aebab537594f2232d886116c9e15816c","sha256:fc7333af026d4b7486f48ba0bb3d16f7475b404b4edd0a732671da0a08217dc7"],"state_sha256":"8c8409ea62b3c2383732b68805d89b66cd1808a5096aa71da8c9e3191749ab35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cT87MacXva0t/qQvyeERqa/iufp8igyt+BNAJcD5aRHatyghC+vJ5BsrItkdQiQIjPsjUlirLgh91PwYpBCfCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:22:44.361273Z","bundle_sha256":"673f5c3429fa922b101b67f65d588eaefb358ba4bbe32af9ba08028a8f2bcada"}}