{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GBHKPFUNNYD3ZNKJI3RPU4QZML","short_pith_number":"pith:GBHKPFUN","schema_version":"1.0","canonical_sha256":"304ea7968d6e07bcb54946e2fa721962dd3802d8ae3baebf0c23b93cfee11c6b","source":{"kind":"arxiv","id":"2605.18387","version":1},"attestation_state":"computed","paper":{"title":"Graph Hierarchical Recurrence for Long-Range Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessio Gravina, Bruno Lepri, Davide Bacciu, Marco Pacini, Sebastiano Bontorin, Stefano Carotti","submitted_at":"2026-05-18T13:31:21Z","abstract_excerpt":"Graph Neural Networks (GNNs) and Graph Transformers (GTs) are now a fundamental paradigm for graph learning, combining the representation-learning capabilities of deep models with the sample efficiency induced by their inductive biases. Despite their effectiveness, a large body of work has shown that these models still face fundamental limitations in tasks that require capturing correlations between distant regions of a graph. To address this issue, we introduce Graph Hierarchical Recurrence (GHR), a novel framework that operates jointly on the input graph and on a hierarchical abstraction obt"},"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":"2605.18387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T13:31:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d3fd4d86bdea3779afd258fb3643692ff9d5d69756300410f5cc97e1e6245e98","abstract_canon_sha256":"9ef91e0e3cc598381cae82a8e9c1461c56f5e6aac89d9cd65174d10abfa41042"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:58.329417Z","signature_b64":"zCmGWz2aGdyAAeTnm1PsA7C3XZL+lVDOymUOdpVfL4krManQt76/JXaKM7b8vUACKOKSm/tpNaVsDqayjbzMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"304ea7968d6e07bcb54946e2fa721962dd3802d8ae3baebf0c23b93cfee11c6b","last_reissued_at":"2026-05-20T00:05:58.328515Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:58.328515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Hierarchical Recurrence for Long-Range Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessio Gravina, Bruno Lepri, Davide Bacciu, Marco Pacini, Sebastiano Bontorin, Stefano Carotti","submitted_at":"2026-05-18T13:31:21Z","abstract_excerpt":"Graph Neural Networks (GNNs) and Graph Transformers (GTs) are now a fundamental paradigm for graph learning, combining the representation-learning capabilities of deep models with the sample efficiency induced by their inductive biases. Despite their effectiveness, a large body of work has shown that these models still face fundamental limitations in tasks that require capturing correlations between distant regions of a graph. To address this issue, we introduce Graph Hierarchical Recurrence (GHR), a novel framework that operates jointly on the input graph and on a hierarchical abstraction obt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18387","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/2605.18387/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T23:52:11.701677Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T23:50:03.612034Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:29.761528Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T23:31:45.342642Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.748840Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1d3f6908b4525a78f26c6d111ea398cd8d442038a0d3a0b0fc0dfb6b9dba83e2"},"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":"2605.18387","created_at":"2026-05-20T00:05:58.328645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18387v1","created_at":"2026-05-20T00:05:58.328645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18387","created_at":"2026-05-20T00:05:58.328645+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBHKPFUNNYD3","created_at":"2026-05-20T00:05:58.328645+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBHKPFUNNYD3ZNKJ","created_at":"2026-05-20T00:05:58.328645+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBHKPFUN","created_at":"2026-05-20T00:05:58.328645+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/GBHKPFUNNYD3ZNKJI3RPU4QZML","json":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML.json","graph_json":"https://pith.science/api/pith-number/GBHKPFUNNYD3ZNKJI3RPU4QZML/graph.json","events_json":"https://pith.science/api/pith-number/GBHKPFUNNYD3ZNKJI3RPU4QZML/events.json","paper":"https://pith.science/paper/GBHKPFUN"},"agent_actions":{"view_html":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML","download_json":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML.json","view_paper":"https://pith.science/paper/GBHKPFUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18387&json=true","fetch_graph":"https://pith.science/api/pith-number/GBHKPFUNNYD3ZNKJI3RPU4QZML/graph.json","fetch_events":"https://pith.science/api/pith-number/GBHKPFUNNYD3ZNKJI3RPU4QZML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML/action/storage_attestation","attest_author":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML/action/author_attestation","sign_citation":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML/action/citation_signature","submit_replication":"https://pith.science/pith/GBHKPFUNNYD3ZNKJI3RPU4QZML/action/replication_record"}},"created_at":"2026-05-20T00:05:58.328645+00:00","updated_at":"2026-05-20T00:05:58.328645+00:00"}