{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A72BYMQGNAB3ET5AQ77JAK2P2Q","short_pith_number":"pith:A72BYMQG","canonical_record":{"source":{"id":"2204.07697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-16T02:08:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"edef3896c9af75f0dc21fdb330b3d0b824102649911f350cbdc939a5f3ddeca1","abstract_canon_sha256":"4f7128456ef4a50f8d4fde24bcfa24a6b46da39b50edc18245891f53bfd4a17d"},"schema_version":"1.0"},"canonical_sha256":"07f41c32066803b24fa087fe902b4fd42cbd68d0206518f76a135261783766d4","source":{"kind":"arxiv","id":"2204.07697","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07697","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07697v1","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07697","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"pith_short_12","alias_value":"A72BYMQGNAB3","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"pith_short_16","alias_value":"A72BYMQGNAB3ET5A","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"pith_short_8","alias_value":"A72BYMQG","created_at":"2026-07-05T04:15:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A72BYMQGNAB3ET5AQ77JAK2P2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2204.07697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-16T02:08:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"edef3896c9af75f0dc21fdb330b3d0b824102649911f350cbdc939a5f3ddeca1","abstract_canon_sha256":"4f7128456ef4a50f8d4fde24bcfa24a6b46da39b50edc18245891f53bfd4a17d"},"schema_version":"1.0"},"canonical_sha256":"07f41c32066803b24fa087fe902b4fd42cbd68d0206518f76a135261783766d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:17.538944Z","signature_b64":"rFyhL237sl+HcYSfhbUqLxZDW855XX0YMPxNsw4dAYmcfZRrGjY+cr6NJdIa3yzMR7qz4X8MMp/CY2Gyl718Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07f41c32066803b24fa087fe902b4fd42cbd68d0206518f76a135261783766d4","last_reissued_at":"2026-07-05T04:15:17.538471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:17.538471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.07697","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":"2026-07-05T04:15:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xA61LrjYu6vXSwcAS/3qFD2suu1eC8RD2mPkHHp4gPStgz+z6HzxAokD7h1qHmZqFiSJJ3Nu+luO8mO8FudmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:10:39.732415Z"},"content_sha256":"a37b09d1bb915e3a5956cc7ebb81d997d94094b9f060e64871b10cf5fe220b5a","schema_version":"1.0","event_id":"sha256:a37b09d1bb915e3a5956cc7ebb81d997d94094b9f060e64871b10cf5fe220b5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A72BYMQGNAB3ET5AQ77JAK2P2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Theory of Graph Neural Networks: Representation and Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Stefanie Jegelka","submitted_at":"2022-04-16T02:08:50Z","abstract_excerpt":"Graph Neural Networks (GNNs), neural network architectures targeted to learning representations of graphs, have become a popular learning model for prediction tasks on nodes, graphs and configurations of points, with wide success in practice. This article summarizes a selection of the emerging theoretical results on approximation and learning properties of widely used message passing GNNs and higher-order GNNs, focusing on representation, generalization and extrapolation. Along the way, it summarizes mathematical connections."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07697","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/2204.07697/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":"2026-07-05T04:15:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wT7M9bU3YOBN/W3pbkSeACt1qK2kz6Jc9x1BTYeuogsSTHr9xkp27EgdatEHn/XXQ+cF8Khjz4Z68SnPPKNyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:10:39.732944Z"},"content_sha256":"11351854880b374ff63e731a37d8a4d917a757b611fbf6fe97b0c21ca2bcd102","schema_version":"1.0","event_id":"sha256:11351854880b374ff63e731a37d8a4d917a757b611fbf6fe97b0c21ca2bcd102"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A72BYMQGNAB3ET5AQ77JAK2P2Q/bundle.json","state_url":"https://pith.science/pith/A72BYMQGNAB3ET5AQ77JAK2P2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A72BYMQGNAB3ET5AQ77JAK2P2Q/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":"2026-08-22T22:10:39Z","links":{"resolver":"https://pith.science/pith/A72BYMQGNAB3ET5AQ77JAK2P2Q","bundle":"https://pith.science/pith/A72BYMQGNAB3ET5AQ77JAK2P2Q/bundle.json","state":"https://pith.science/pith/A72BYMQGNAB3ET5AQ77JAK2P2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A72BYMQGNAB3ET5AQ77JAK2P2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A72BYMQGNAB3ET5AQ77JAK2P2Q","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":"4f7128456ef4a50f8d4fde24bcfa24a6b46da39b50edc18245891f53bfd4a17d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-16T02:08:50Z","title_canon_sha256":"edef3896c9af75f0dc21fdb330b3d0b824102649911f350cbdc939a5f3ddeca1"},"schema_version":"1.0","source":{"id":"2204.07697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07697","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07697v1","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07697","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"pith_short_12","alias_value":"A72BYMQGNAB3","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"pith_short_16","alias_value":"A72BYMQGNAB3ET5A","created_at":"2026-07-05T04:15:17Z"},{"alias_kind":"pith_short_8","alias_value":"A72BYMQG","created_at":"2026-07-05T04:15:17Z"}],"graph_snapshots":[{"event_id":"sha256:11351854880b374ff63e731a37d8a4d917a757b611fbf6fe97b0c21ca2bcd102","target":"graph","created_at":"2026-07-05T04:15:17Z","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/2204.07697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs), neural network architectures targeted to learning representations of graphs, have become a popular learning model for prediction tasks on nodes, graphs and configurations of points, with wide success in practice. This article summarizes a selection of the emerging theoretical results on approximation and learning properties of widely used message passing GNNs and higher-order GNNs, focusing on representation, generalization and extrapolation. Along the way, it summarizes mathematical connections.","authors_text":"Stefanie Jegelka","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-16T02:08:50Z","title":"Theory of Graph Neural Networks: Representation and Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07697","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:a37b09d1bb915e3a5956cc7ebb81d997d94094b9f060e64871b10cf5fe220b5a","target":"record","created_at":"2026-07-05T04:15:17Z","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":"4f7128456ef4a50f8d4fde24bcfa24a6b46da39b50edc18245891f53bfd4a17d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-16T02:08:50Z","title_canon_sha256":"edef3896c9af75f0dc21fdb330b3d0b824102649911f350cbdc939a5f3ddeca1"},"schema_version":"1.0","source":{"id":"2204.07697","kind":"arxiv","version":1}},"canonical_sha256":"07f41c32066803b24fa087fe902b4fd42cbd68d0206518f76a135261783766d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07f41c32066803b24fa087fe902b4fd42cbd68d0206518f76a135261783766d4","first_computed_at":"2026-07-05T04:15:17.538471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:17.538471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rFyhL237sl+HcYSfhbUqLxZDW855XX0YMPxNsw4dAYmcfZRrGjY+cr6NJdIa3yzMR7qz4X8MMp/CY2Gyl718Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:17.538944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a37b09d1bb915e3a5956cc7ebb81d997d94094b9f060e64871b10cf5fe220b5a","sha256:11351854880b374ff63e731a37d8a4d917a757b611fbf6fe97b0c21ca2bcd102"],"state_sha256":"ae97d2f589beb96d97030f1dd8b54a9d30d495dbd9e9db518dd5b21016b20b1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rx5ku0pdlJzSbbjgWRy0ibLiF+rZb+aPIGWY5hWkKNtX0AtwCu10xln1Zz6WfQ5LzYnWXSZ/X3NHgf13sZRvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:10:39.736755Z","bundle_sha256":"26da52668a34cb8dac3124fa6bd48a3a9d7f276c98dfb37fe8bbac069e533b39"}}