{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T4LA46LZ2QE5HRY7XHT2NT246R","short_pith_number":"pith:T4LA46LZ","schema_version":"1.0","canonical_sha256":"9f160e7979d409d3c71fb9e7a6cf5cf454cefda8bf63269a136c2aa628289b13","source":{"kind":"arxiv","id":"2001.09621","version":1},"attestation_state":"computed","paper":{"title":"Deep Graph Matching Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Morris, Jan E. Lenssen, Jonathan Masci, Matthias Fey, Nils M. Kriege","submitted_at":"2020-01-27T08:05:57Z","abstract_excerpt":"This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes. Secondly, we employ synchronous message passing networks to iteratively re-rank the soft correspondences to reach a matching consensus in local neighborhoods between graphs. We show, theoretically and empirically, that our message passing scheme computes a well-founded measure of consensus for corresponding neighborhoods, which is then"},"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":"2001.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-27T08:05:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ea58b277da8e24d0a340fc9269647ab06ab76701e53eb4d15fee00c392b016dd","abstract_canon_sha256":"d165bda58cb6eae1dabef0ee83ade37c1301a8602ed5c18f5ca73212b1cae84f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:36:01.386127Z","signature_b64":"10WxMXVAFsYCPJ8c96tNFbzGUFSvG6N0yyQ27mme5/DsgpT4ynTzczm6R+215UjiRwugW9ZOs82d3QvZT7ZQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f160e7979d409d3c71fb9e7a6cf5cf454cefda8bf63269a136c2aa628289b13","last_reissued_at":"2026-07-05T00:36:01.385675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:36:01.385675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Graph Matching Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Morris, Jan E. Lenssen, Jonathan Masci, Matthias Fey, Nils M. Kriege","submitted_at":"2020-01-27T08:05:57Z","abstract_excerpt":"This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes. Secondly, we employ synchronous message passing networks to iteratively re-rank the soft correspondences to reach a matching consensus in local neighborhoods between graphs. We show, theoretically and empirically, that our message passing scheme computes a well-founded measure of consensus for corresponding neighborhoods, which is then"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09621","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/2001.09621/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":"2001.09621","created_at":"2026-07-05T00:36:01.385733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.09621v1","created_at":"2026-07-05T00:36:01.385733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09621","created_at":"2026-07-05T00:36:01.385733+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4LA46LZ2QE5","created_at":"2026-07-05T00:36:01.385733+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4LA46LZ2QE5HRY7","created_at":"2026-07-05T00:36:01.385733+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4LA46LZ","created_at":"2026-07-05T00:36:01.385733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.17715","citing_title":"Normalized Matching Transformer","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18255","citing_title":"RCTEA: Richness-guided Co-training for Temporal Entity Alignment","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R","json":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R.json","graph_json":"https://pith.science/api/pith-number/T4LA46LZ2QE5HRY7XHT2NT246R/graph.json","events_json":"https://pith.science/api/pith-number/T4LA46LZ2QE5HRY7XHT2NT246R/events.json","paper":"https://pith.science/paper/T4LA46LZ"},"agent_actions":{"view_html":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R","download_json":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R.json","view_paper":"https://pith.science/paper/T4LA46LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.09621&json=true","fetch_graph":"https://pith.science/api/pith-number/T4LA46LZ2QE5HRY7XHT2NT246R/graph.json","fetch_events":"https://pith.science/api/pith-number/T4LA46LZ2QE5HRY7XHT2NT246R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R/action/storage_attestation","attest_author":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R/action/author_attestation","sign_citation":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R/action/citation_signature","submit_replication":"https://pith.science/pith/T4LA46LZ2QE5HRY7XHT2NT246R/action/replication_record"}},"created_at":"2026-07-05T00:36:01.385733+00:00","updated_at":"2026-07-05T00:36:01.385733+00:00"}