{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q37736CHAKNHAPC3URM7YSQIFO","short_pith_number":"pith:Q37736CH","schema_version":"1.0","canonical_sha256":"86fffdf847029a703c5ba459fc4a082b9549cefda0a48b4b0f71e760e1240126","source":{"kind":"arxiv","id":"2510.03086","version":2},"attestation_state":"computed","paper":{"title":"Chaining 2-FWL GNNs for Combinatorial Graph Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marc Lelarge","submitted_at":"2025-10-03T15:17:00Z","abstract_excerpt":"For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly initialized FAQ remains a strong classical baseline, while existing GNN approaches struggle in the purely structural setting. We introduce a chaining procedure: a sequence of Folklore-type (2-FWL) GNNs in which each network is trained with cross-entropy after decoding the previous network's similarity matrix and ranking nodes by their current alignment quality. This non-differentiable ranking step injects discrete combin"},"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":"2510.03086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-03T15:17:00Z","cross_cats_sorted":[],"title_canon_sha256":"c881649be9ece2d1e2d0ce212c927a8bd90c3ecac0a4f813320cb6bf35f7fdd3","abstract_canon_sha256":"113103b8ff43ad19614341eecfb7ebe1cb7ce1d9753c0da38f1c83c283fa5959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:34.781533Z","signature_b64":"CDlmkS0gdCECT9uyYsTSkkLqvwfpSBFa89FZqQqntINxR/jxsyqIb7LvaZ8qs2AZlAQaB5wjeb/h6tCMV8vkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86fffdf847029a703c5ba459fc4a082b9549cefda0a48b4b0f71e760e1240126","last_reissued_at":"2026-06-02T03:04:34.781084Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:34.781084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chaining 2-FWL GNNs for Combinatorial Graph Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marc Lelarge","submitted_at":"2025-10-03T15:17:00Z","abstract_excerpt":"For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly initialized FAQ remains a strong classical baseline, while existing GNN approaches struggle in the purely structural setting. We introduce a chaining procedure: a sequence of Folklore-type (2-FWL) GNNs in which each network is trained with cross-entropy after decoding the previous network's similarity matrix and ranking nodes by their current alignment quality. This non-differentiable ranking step injects discrete combin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03086","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/2510.03086/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":"2510.03086","created_at":"2026-06-02T03:04:34.781147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03086v2","created_at":"2026-06-02T03:04:34.781147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03086","created_at":"2026-06-02T03:04:34.781147+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q37736CHAKNH","created_at":"2026-06-02T03:04:34.781147+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q37736CHAKNHAPC3","created_at":"2026-06-02T03:04:34.781147+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q37736CH","created_at":"2026-06-02T03:04:34.781147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO","json":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO.json","graph_json":"https://pith.science/api/pith-number/Q37736CHAKNHAPC3URM7YSQIFO/graph.json","events_json":"https://pith.science/api/pith-number/Q37736CHAKNHAPC3URM7YSQIFO/events.json","paper":"https://pith.science/paper/Q37736CH"},"agent_actions":{"view_html":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO","download_json":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO.json","view_paper":"https://pith.science/paper/Q37736CH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03086&json=true","fetch_graph":"https://pith.science/api/pith-number/Q37736CHAKNHAPC3URM7YSQIFO/graph.json","fetch_events":"https://pith.science/api/pith-number/Q37736CHAKNHAPC3URM7YSQIFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO/action/storage_attestation","attest_author":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO/action/author_attestation","sign_citation":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO/action/citation_signature","submit_replication":"https://pith.science/pith/Q37736CHAKNHAPC3URM7YSQIFO/action/replication_record"}},"created_at":"2026-06-02T03:04:34.781147+00:00","updated_at":"2026-06-02T03:04:34.781147+00:00"}