{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XDDZ3STF7VSJ5P7QCJUYPVD2G6","short_pith_number":"pith:XDDZ3STF","schema_version":"1.0","canonical_sha256":"b8c79dca65fd649ebff0126987d47a37be539eee98ad30d0819ac88a2a3cdc50","source":{"kind":"arxiv","id":"1904.08745","version":2},"attestation_state":"computed","paper":{"title":"edGNN: a Simple and Powerful GNN for Directed Labeled Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"An-phi Nguyen, Guillaume Jaume, Jean-Philippe Thiran, Maria Gabrani, Mar\\'ia Rodr\\'iguez Mart\\'inez","submitted_at":"2019-04-18T13:04:56Z","abstract_excerpt":"The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled graphs, is as powerful as the Weisfeiler-Lehman algorithm for graph isomorphism. Our experiments support our theoretical findings, confirming that graph neural networks can be used effectively for inference problems on directed graphs with both node and edge labels. Code available at https://github.com/guillaumejaume/edGNN."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.08745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-18T13:04:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"29cff7975ac7535ffa9f0f3751a3ddec5a120dc86d06402c34b1c6956c8a5912","abstract_canon_sha256":"04ada9aa660b3a5bc27cebc9bd745ee6ad9c50c55a30b656d0171383078a7064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:49.149167Z","signature_b64":"35a3ApUiqnzFMiyctweFdZIBcEPp36sHkgOKVs4M6l/hW8zfGesJu4nvOdBKqF4GuZyRbEIXghUlR5+olAxqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8c79dca65fd649ebff0126987d47a37be539eee98ad30d0819ac88a2a3cdc50","last_reissued_at":"2026-07-05T00:23:49.148720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:49.148720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"edGNN: a Simple and Powerful GNN for Directed Labeled Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"An-phi Nguyen, Guillaume Jaume, Jean-Philippe Thiran, Maria Gabrani, Mar\\'ia Rodr\\'iguez Mart\\'inez","submitted_at":"2019-04-18T13:04:56Z","abstract_excerpt":"The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled graphs, is as powerful as the Weisfeiler-Lehman algorithm for graph isomorphism. Our experiments support our theoretical findings, confirming that graph neural networks can be used effectively for inference problems on directed graphs with both node and edge labels. Code available at https://github.com/guillaumejaume/edGNN."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08745","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1904.08745/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.08745","created_at":"2026-07-05T00:23:49.148778+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.08745v2","created_at":"2026-07-05T00:23:49.148778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08745","created_at":"2026-07-05T00:23:49.148778+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDDZ3STF7VSJ","created_at":"2026-07-05T00:23:49.148778+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDDZ3STF7VSJ5P7Q","created_at":"2026-07-05T00:23:49.148778+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDDZ3STF","created_at":"2026-07-05T00:23:49.148778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26243","citing_title":"Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02899","citing_title":"Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6","json":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6.json","graph_json":"https://pith.science/api/pith-number/XDDZ3STF7VSJ5P7QCJUYPVD2G6/graph.json","events_json":"https://pith.science/api/pith-number/XDDZ3STF7VSJ5P7QCJUYPVD2G6/events.json","paper":"https://pith.science/paper/XDDZ3STF"},"agent_actions":{"view_html":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6","download_json":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6.json","view_paper":"https://pith.science/paper/XDDZ3STF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.08745&json=true","fetch_graph":"https://pith.science/api/pith-number/XDDZ3STF7VSJ5P7QCJUYPVD2G6/graph.json","fetch_events":"https://pith.science/api/pith-number/XDDZ3STF7VSJ5P7QCJUYPVD2G6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6/action/storage_attestation","attest_author":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6/action/author_attestation","sign_citation":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6/action/citation_signature","submit_replication":"https://pith.science/pith/XDDZ3STF7VSJ5P7QCJUYPVD2G6/action/replication_record"}},"created_at":"2026-07-05T00:23:49.148778+00:00","updated_at":"2026-07-05T00:23:49.148778+00:00"}