{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DLDBIUYJPCVEAC6XRUR6XLN53F","short_pith_number":"pith:DLDBIUYJ","schema_version":"1.0","canonical_sha256":"1ac614530978aa400bd78d23ebadbdd9522870d655f0e4b6b249634c1c8f415a","source":{"kind":"arxiv","id":"2110.00577","version":4},"attestation_state":"computed","paper":{"title":"Reconstruction for Powerful Graph Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM"],"primary_cat":"cs.LG","authors_text":"Bruno Ribeiro, Christopher Morris, Leonardo Cotta","submitted_at":"2021-10-01T17:59:24Z","abstract_excerpt":"Graph neural networks (GNNs) have limited expressive power, failing to represent many graph classes correctly. While more expressive graph representation learning (GRL) alternatives can distinguish some of these classes, they are significantly harder to implement, may not scale well, and have not been shown to outperform well-tuned GNNs in real-world tasks. Thus, devising simple, scalable, and expressive GRL architectures that also achieve real-world improvements remains an open challenge. In this work, we show the extent to which graph reconstruction -- reconstructing a graph from its subgrap"},"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":"2110.00577","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T17:59:24Z","cross_cats_sorted":["cs.AI","cs.DM"],"title_canon_sha256":"a0ab7dbed6687d598d07d642e8ebe2d9f71966ee62725ef6f8b6766ce20ac127","abstract_canon_sha256":"dca60b79da97a6d2cb667fe321d42e92238702a288bd1b78aa37106e7705683f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:36.470569Z","signature_b64":"98VzM/CXN1yQgp0bQ5/ATNTrTlaUi0HqWmx3Vbsjyosn1KI7XdNPUWKW/V6ZKNjxSpib06QIV7wK7euVYCMaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ac614530978aa400bd78d23ebadbdd9522870d655f0e4b6b249634c1c8f415a","last_reissued_at":"2026-07-05T03:38:36.470181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:36.470181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconstruction for Powerful Graph Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM"],"primary_cat":"cs.LG","authors_text":"Bruno Ribeiro, Christopher Morris, Leonardo Cotta","submitted_at":"2021-10-01T17:59:24Z","abstract_excerpt":"Graph neural networks (GNNs) have limited expressive power, failing to represent many graph classes correctly. While more expressive graph representation learning (GRL) alternatives can distinguish some of these classes, they are significantly harder to implement, may not scale well, and have not been shown to outperform well-tuned GNNs in real-world tasks. Thus, devising simple, scalable, and expressive GRL architectures that also achieve real-world improvements remains an open challenge. In this work, we show the extent to which graph reconstruction -- reconstructing a graph from its subgrap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00577","kind":"arxiv","version":4},"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/2110.00577/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":"2110.00577","created_at":"2026-07-05T03:38:36.470232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.00577v4","created_at":"2026-07-05T03:38:36.470232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00577","created_at":"2026-07-05T03:38:36.470232+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLDBIUYJPCVE","created_at":"2026-07-05T03:38:36.470232+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLDBIUYJPCVEAC6X","created_at":"2026-07-05T03:38:36.470232+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLDBIUYJ","created_at":"2026-07-05T03:38:36.470232+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/DLDBIUYJPCVEAC6XRUR6XLN53F","json":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F.json","graph_json":"https://pith.science/api/pith-number/DLDBIUYJPCVEAC6XRUR6XLN53F/graph.json","events_json":"https://pith.science/api/pith-number/DLDBIUYJPCVEAC6XRUR6XLN53F/events.json","paper":"https://pith.science/paper/DLDBIUYJ"},"agent_actions":{"view_html":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F","download_json":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F.json","view_paper":"https://pith.science/paper/DLDBIUYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.00577&json=true","fetch_graph":"https://pith.science/api/pith-number/DLDBIUYJPCVEAC6XRUR6XLN53F/graph.json","fetch_events":"https://pith.science/api/pith-number/DLDBIUYJPCVEAC6XRUR6XLN53F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F/action/storage_attestation","attest_author":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F/action/author_attestation","sign_citation":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F/action/citation_signature","submit_replication":"https://pith.science/pith/DLDBIUYJPCVEAC6XRUR6XLN53F/action/replication_record"}},"created_at":"2026-07-05T03:38:36.470232+00:00","updated_at":"2026-07-05T03:38:36.470232+00:00"}