{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BN7A34FEA4LBVGBFVQVEUOACYK","short_pith_number":"pith:BN7A34FE","schema_version":"1.0","canonical_sha256":"0b7e0df0a407161a9825ac2a4a3802c2a63abc132120414907d8a20a810c62ec","source":{"kind":"arxiv","id":"2405.18127","version":1},"attestation_state":"computed","paper":{"title":"Graph Coarsening with Message-Passing Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonin Joly, Nicolas Keriven","submitted_at":"2024-05-28T12:39:24Z","abstract_excerpt":"Graph coarsening aims to reduce the size of a large graph while preserving some of its key properties, which has been used in many applications to reduce computational load and memory footprint. For instance, in graph machine learning, training Graph Neural Networks (GNNs) on coarsened graphs leads to drastic savings in time and memory. However, GNNs rely on the Message-Passing (MP) paradigm, and classical spectral preservation guarantees for graph coarsening do not directly lead to theoretical guarantees when performing naive message-passing on the coarsened graph. In this work, we propose a "},"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":"2405.18127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:39:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fa063583dd33f288c95fe8596c9c9d0932eacdecc8c281f47414cc00cf8b449c","abstract_canon_sha256":"42abc114b2198438edef5acd26d93549fdefc0efb3cdaddb398883d9d94e540f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:15.973030Z","signature_b64":"Dst2mopa3KvEeytwOnRcWd+qGNKYTmjTKbbAFxTF/m3mXJNqYn5QTHn+usIKgp0BiuIKXUe2p1NjXOLUJoIjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b7e0df0a407161a9825ac2a4a3802c2a63abc132120414907d8a20a810c62ec","last_reissued_at":"2026-07-05T08:24:15.972548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:15.972548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Coarsening with Message-Passing Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonin Joly, Nicolas Keriven","submitted_at":"2024-05-28T12:39:24Z","abstract_excerpt":"Graph coarsening aims to reduce the size of a large graph while preserving some of its key properties, which has been used in many applications to reduce computational load and memory footprint. For instance, in graph machine learning, training Graph Neural Networks (GNNs) on coarsened graphs leads to drastic savings in time and memory. However, GNNs rely on the Message-Passing (MP) paradigm, and classical spectral preservation guarantees for graph coarsening do not directly lead to theoretical guarantees when performing naive message-passing on the coarsened graph. In this work, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18127","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/2405.18127/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":"2405.18127","created_at":"2026-07-05T08:24:15.972612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18127v1","created_at":"2026-07-05T08:24:15.972612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18127","created_at":"2026-07-05T08:24:15.972612+00:00"},{"alias_kind":"pith_short_12","alias_value":"BN7A34FEA4LB","created_at":"2026-07-05T08:24:15.972612+00:00"},{"alias_kind":"pith_short_16","alias_value":"BN7A34FEA4LBVGBF","created_at":"2026-07-05T08:24:15.972612+00:00"},{"alias_kind":"pith_short_8","alias_value":"BN7A34FE","created_at":"2026-07-05T08:24:15.972612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14033","citing_title":"Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK","json":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK.json","graph_json":"https://pith.science/api/pith-number/BN7A34FEA4LBVGBFVQVEUOACYK/graph.json","events_json":"https://pith.science/api/pith-number/BN7A34FEA4LBVGBFVQVEUOACYK/events.json","paper":"https://pith.science/paper/BN7A34FE"},"agent_actions":{"view_html":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK","download_json":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK.json","view_paper":"https://pith.science/paper/BN7A34FE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18127&json=true","fetch_graph":"https://pith.science/api/pith-number/BN7A34FEA4LBVGBFVQVEUOACYK/graph.json","fetch_events":"https://pith.science/api/pith-number/BN7A34FEA4LBVGBFVQVEUOACYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK/action/storage_attestation","attest_author":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK/action/author_attestation","sign_citation":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK/action/citation_signature","submit_replication":"https://pith.science/pith/BN7A34FEA4LBVGBFVQVEUOACYK/action/replication_record"}},"created_at":"2026-07-05T08:24:15.972612+00:00","updated_at":"2026-07-05T08:24:15.972612+00:00"}