{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KJBVNFK6SZGVVP6CQABYTKKHHP","short_pith_number":"pith:KJBVNFK6","canonical_record":{"source":{"id":"2202.10720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T08:16:58Z","cross_cats_sorted":[],"title_canon_sha256":"626be6b95330e5c059cd51fd619ef72b2c4f3d3d4db970f3cc14c73a121c0517","abstract_canon_sha256":"65065440899b665ecee75239e52f96b0083f95d03105a8cea8bc464146f5ce39"},"schema_version":"1.0"},"canonical_sha256":"524356955e964d5abfc2800389a9473bd605287ad226ab8115bdb84a18182bee","source":{"kind":"arxiv","id":"2202.10720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.10720","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"arxiv_version","alias_value":"2202.10720v1","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10720","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_12","alias_value":"KJBVNFK6SZGV","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_16","alias_value":"KJBVNFK6SZGVVP6C","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_8","alias_value":"KJBVNFK6","created_at":"2026-07-05T03:59:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KJBVNFK6SZGVVP6CQABYTKKHHP","target":"record","payload":{"canonical_record":{"source":{"id":"2202.10720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T08:16:58Z","cross_cats_sorted":[],"title_canon_sha256":"626be6b95330e5c059cd51fd619ef72b2c4f3d3d4db970f3cc14c73a121c0517","abstract_canon_sha256":"65065440899b665ecee75239e52f96b0083f95d03105a8cea8bc464146f5ce39"},"schema_version":"1.0"},"canonical_sha256":"524356955e964d5abfc2800389a9473bd605287ad226ab8115bdb84a18182bee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:07.700137Z","signature_b64":"kZKbBqkNpQ9PwJZ2RtE5EK1VobMAtraJug7Teul/oABU7cuO1FHQybF31RXe1epZIEZGMa719psm5f4eAmCUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"524356955e964d5abfc2800389a9473bd605287ad226ab8115bdb84a18182bee","last_reissued_at":"2026-07-05T03:59:07.699683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:07.699683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.10720","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":"2026-07-05T03:59:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f9GpnhYaT7bhz34EFN03D9TP064kaWMO5MxK49HlGCp/Wr/sx9WqdtdI1hec4Y8Qp4ow7V3xCHkCR3/Gy6KXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:22:56.309639Z"},"content_sha256":"e9ddd4e5f8965ff92c1a426ad5031a1569bc42689525613b68b4f026d272b9a6","schema_version":"1.0","event_id":"sha256:e9ddd4e5f8965ff92c1a426ad5031a1569bc42689525613b68b4f026d272b9a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KJBVNFK6SZGVVP6CQABYTKKHHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EIGNN: Efficient Infinite-Depth Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bryan Hooi, Juncheng Liu, Kenji Kawaguchi, Xiaokui Xiao, Yiwei Wang","submitted_at":"2022-02-22T08:16:58Z","abstract_excerpt":"Graph neural networks (GNNs) are widely used for modelling graph-structured data in numerous applications. However, with their inherently finite aggregation layers, existing GNN models may not be able to effectively capture long-range dependencies in the underlying graphs. Motivated by this limitation, we propose a GNN model with infinite depth, which we call Efficient Infinite-Depth Graph Neural Networks (EIGNN), to efficiently capture very long-range dependencies. We theoretically derive a closed-form solution of EIGNN which makes training an infinite-depth GNN model tractable. We then furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10720","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/2202.10720/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":"2026-07-05T03:59:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUu3cZBHFgBNkKVNF7WKEgLmhbJgciZIHGsE5beo3S/xLObEUHlZaCPbskkomAwwZTXqQEIauXXFY8LhLtRGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:22:56.310001Z"},"content_sha256":"6c075955476d2741ed6fc1e153849ffeee7fdcd72275818eef0a792219e994b6","schema_version":"1.0","event_id":"sha256:6c075955476d2741ed6fc1e153849ffeee7fdcd72275818eef0a792219e994b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJBVNFK6SZGVVP6CQABYTKKHHP/bundle.json","state_url":"https://pith.science/pith/KJBVNFK6SZGVVP6CQABYTKKHHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJBVNFK6SZGVVP6CQABYTKKHHP/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":"2026-07-07T09:22:56Z","links":{"resolver":"https://pith.science/pith/KJBVNFK6SZGVVP6CQABYTKKHHP","bundle":"https://pith.science/pith/KJBVNFK6SZGVVP6CQABYTKKHHP/bundle.json","state":"https://pith.science/pith/KJBVNFK6SZGVVP6CQABYTKKHHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJBVNFK6SZGVVP6CQABYTKKHHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KJBVNFK6SZGVVP6CQABYTKKHHP","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":"65065440899b665ecee75239e52f96b0083f95d03105a8cea8bc464146f5ce39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T08:16:58Z","title_canon_sha256":"626be6b95330e5c059cd51fd619ef72b2c4f3d3d4db970f3cc14c73a121c0517"},"schema_version":"1.0","source":{"id":"2202.10720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.10720","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"arxiv_version","alias_value":"2202.10720v1","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10720","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_12","alias_value":"KJBVNFK6SZGV","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_16","alias_value":"KJBVNFK6SZGVVP6C","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_8","alias_value":"KJBVNFK6","created_at":"2026-07-05T03:59:07Z"}],"graph_snapshots":[{"event_id":"sha256:6c075955476d2741ed6fc1e153849ffeee7fdcd72275818eef0a792219e994b6","target":"graph","created_at":"2026-07-05T03:59:07Z","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/2202.10720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks (GNNs) are widely used for modelling graph-structured data in numerous applications. However, with their inherently finite aggregation layers, existing GNN models may not be able to effectively capture long-range dependencies in the underlying graphs. Motivated by this limitation, we propose a GNN model with infinite depth, which we call Efficient Infinite-Depth Graph Neural Networks (EIGNN), to efficiently capture very long-range dependencies. We theoretically derive a closed-form solution of EIGNN which makes training an infinite-depth GNN model tractable. We then furth","authors_text":"Bryan Hooi, Juncheng Liu, Kenji Kawaguchi, Xiaokui Xiao, Yiwei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T08:16:58Z","title":"EIGNN: Efficient Infinite-Depth Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10720","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:e9ddd4e5f8965ff92c1a426ad5031a1569bc42689525613b68b4f026d272b9a6","target":"record","created_at":"2026-07-05T03:59:07Z","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":"65065440899b665ecee75239e52f96b0083f95d03105a8cea8bc464146f5ce39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T08:16:58Z","title_canon_sha256":"626be6b95330e5c059cd51fd619ef72b2c4f3d3d4db970f3cc14c73a121c0517"},"schema_version":"1.0","source":{"id":"2202.10720","kind":"arxiv","version":1}},"canonical_sha256":"524356955e964d5abfc2800389a9473bd605287ad226ab8115bdb84a18182bee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"524356955e964d5abfc2800389a9473bd605287ad226ab8115bdb84a18182bee","first_computed_at":"2026-07-05T03:59:07.699683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:07.699683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kZKbBqkNpQ9PwJZ2RtE5EK1VobMAtraJug7Teul/oABU7cuO1FHQybF31RXe1epZIEZGMa719psm5f4eAmCUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:07.700137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.10720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9ddd4e5f8965ff92c1a426ad5031a1569bc42689525613b68b4f026d272b9a6","sha256:6c075955476d2741ed6fc1e153849ffeee7fdcd72275818eef0a792219e994b6"],"state_sha256":"3f0b6ed5f13d92fc882aa929084605f89b301c48089c857bb2647d2f5d1ad973"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MZg8J3qLRoLlgIMA7o6g4qrNBcRwgCqGMVnKRv1gPof3qm/z9hhQQvmwxDaGaAXOEXEd6Od67kAu+vFZho9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:22:56.311813Z","bundle_sha256":"1e49cfbe82f51cc7a8d93451be6f4f3795b6747f78bbfc3813a7e0361b8e3fa9"}}