{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AIZ2HJPLJZ4JY5OLASZELUPVQA","short_pith_number":"pith:AIZ2HJPL","canonical_record":{"source":{"id":"1809.02709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T23:18:59Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"2f4bf6bf171ba9ab8e2bacb1d6940c00945764e543d94a9e64000bc91be3a4b7","abstract_canon_sha256":"b667b17d7c6a4929ab4b5cb6dd600fc992408255d7db4e9b71e7706bb89ac677"},"schema_version":"1.0"},"canonical_sha256":"0233a3a5eb4e789c75cb04b245d1f5802dd21b22f79dd391811164fecd861390","source":{"kind":"arxiv","id":"1809.02709","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02709","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02709v2","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02709","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"AIZ2HJPLJZ4J","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AIZ2HJPLJZ4JY5OL","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AIZ2HJPL","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AIZ2HJPLJZ4JY5OLASZELUPVQA","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T23:18:59Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"2f4bf6bf171ba9ab8e2bacb1d6940c00945764e543d94a9e64000bc91be3a4b7","abstract_canon_sha256":"b667b17d7c6a4929ab4b5cb6dd600fc992408255d7db4e9b71e7706bb89ac677"},"schema_version":"1.0"},"canonical_sha256":"0233a3a5eb4e789c75cb04b245d1f5802dd21b22f79dd391811164fecd861390","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:28.989940Z","signature_b64":"qXuRCRYzsYrsjnc0ISMNzhOTvOKd/U0KLZBXIom5iNcj4xyZegDjpKwXb2nqF/OuT3sqbS2h5bWGYtXWqZ0uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0233a3a5eb4e789c75cb04b245d1f5802dd21b22f79dd391811164fecd861390","last_reissued_at":"2026-05-17T23:55:28.989496Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:28.989496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02709","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohd9KYf0v5a5edVjHsQ2g0ISQrMGb238M9h16YUicKnnqWPhXAzz93jVVGUhL3XTG9lFqFkUJlEVMNYy6cGeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:01:39.036776Z"},"content_sha256":"9e321164a3a9f913c3f026716d4607dd2350ebd4e3b6ce2b7207f8e11c40b629","schema_version":"1.0","event_id":"sha256:9e321164a3a9f913c3f026716d4607dd2350ebd4e3b6ce2b7207f8e11c40b629"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AIZ2HJPLJZ4JY5OLASZELUPVQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Edge Features in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Liyu Gong, Qiang Cheng","submitted_at":"2018-09-07T23:18:59Z","abstract_excerpt":"Edge features contain important information about graphs. However, current state-of-the-art neural network models designed for graph learning, e.g. graph convolutional networks (GCN) and graph attention networks (GAT), adequately utilize edge features, especially multi-dimensional edge features. In this paper, we build a new framework for a family of new graph neural network models that can more sufficiently exploit edge features, including those of undirected or multi-dimensional edges. The proposed framework can consolidate current graph neural network models; e.g. graph convolutional networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02709","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V40BS5A42BhEi2FratzOKRgVx2bKZQ+pETJn6gT3uWE/b0i16gpFNfTet82zKn0PJLkn0l50AB4LNpQCMrXRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:01:39.037125Z"},"content_sha256":"c2f710737060513aa84e30b3a2f0a30604d8f732c3b80674ff652e464497dbdf","schema_version":"1.0","event_id":"sha256:c2f710737060513aa84e30b3a2f0a30604d8f732c3b80674ff652e464497dbdf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AIZ2HJPLJZ4JY5OLASZELUPVQA/bundle.json","state_url":"https://pith.science/pith/AIZ2HJPLJZ4JY5OLASZELUPVQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AIZ2HJPLJZ4JY5OLASZELUPVQA/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":"2026-06-09T16:01:39Z","links":{"resolver":"https://pith.science/pith/AIZ2HJPLJZ4JY5OLASZELUPVQA","bundle":"https://pith.science/pith/AIZ2HJPLJZ4JY5OLASZELUPVQA/bundle.json","state":"https://pith.science/pith/AIZ2HJPLJZ4JY5OLASZELUPVQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AIZ2HJPLJZ4JY5OLASZELUPVQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AIZ2HJPLJZ4JY5OLASZELUPVQA","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":"b667b17d7c6a4929ab4b5cb6dd600fc992408255d7db4e9b71e7706bb89ac677","cross_cats_sorted":["cs.SI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T23:18:59Z","title_canon_sha256":"2f4bf6bf171ba9ab8e2bacb1d6940c00945764e543d94a9e64000bc91be3a4b7"},"schema_version":"1.0","source":{"id":"1809.02709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02709","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02709v2","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02709","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"AIZ2HJPLJZ4J","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AIZ2HJPLJZ4JY5OL","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AIZ2HJPL","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:c2f710737060513aa84e30b3a2f0a30604d8f732c3b80674ff652e464497dbdf","target":"graph","created_at":"2026-05-17T23:55:28Z","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"},"paper":{"abstract_excerpt":"Edge features contain important information about graphs. However, current state-of-the-art neural network models designed for graph learning, e.g. graph convolutional networks (GCN) and graph attention networks (GAT), adequately utilize edge features, especially multi-dimensional edge features. In this paper, we build a new framework for a family of new graph neural network models that can more sufficiently exploit edge features, including those of undirected or multi-dimensional edges. The proposed framework can consolidate current graph neural network models; e.g. graph convolutional networ","authors_text":"Liyu Gong, Qiang Cheng","cross_cats":["cs.SI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T23:18:59Z","title":"Exploiting Edge Features in Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02709","kind":"arxiv","version":2},"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":"sha256:9e321164a3a9f913c3f026716d4607dd2350ebd4e3b6ce2b7207f8e11c40b629","target":"record","created_at":"2026-05-17T23:55:28Z","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":"b667b17d7c6a4929ab4b5cb6dd600fc992408255d7db4e9b71e7706bb89ac677","cross_cats_sorted":["cs.SI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T23:18:59Z","title_canon_sha256":"2f4bf6bf171ba9ab8e2bacb1d6940c00945764e543d94a9e64000bc91be3a4b7"},"schema_version":"1.0","source":{"id":"1809.02709","kind":"arxiv","version":2}},"canonical_sha256":"0233a3a5eb4e789c75cb04b245d1f5802dd21b22f79dd391811164fecd861390","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0233a3a5eb4e789c75cb04b245d1f5802dd21b22f79dd391811164fecd861390","first_computed_at":"2026-05-17T23:55:28.989496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:28.989496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qXuRCRYzsYrsjnc0ISMNzhOTvOKd/U0KLZBXIom5iNcj4xyZegDjpKwXb2nqF/OuT3sqbS2h5bWGYtXWqZ0uAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:28.989940Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e321164a3a9f913c3f026716d4607dd2350ebd4e3b6ce2b7207f8e11c40b629","sha256:c2f710737060513aa84e30b3a2f0a30604d8f732c3b80674ff652e464497dbdf"],"state_sha256":"e38fa8a33b3108142cc6d04f071b612fd0d2dcca67c1c48c56b3b689b32ef9ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/bX4P7rF5T0Ys5ri5XJudPANLyeVGCrRKtw4bxd4qwDAtv5QkoE2bteUByGFeKgnOqoqv0sfqBTvC7bR6WYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T16:01:39.039116Z","bundle_sha256":"8c01c3c1217d4aa1eccbe44dc68d6e0868753dd76bf16b2261dc7a545240f5e5"}}