{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PMDLUX65ZHD4C7YWLK66WSSYCA","short_pith_number":"pith:PMDLUX65","schema_version":"1.0","canonical_sha256":"7b06ba5fddc9c7c17f165abdeb4a581028e95a521b85aa4e24a32fcf4bbbe13e","source":{"kind":"arxiv","id":"2509.01381","version":1},"attestation_state":"computed","paper":{"title":"Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Federico Errica, Jo\\\"el Mathys","submitted_at":"2025-09-01T11:27:53Z","abstract_excerpt":"Message-passing architectures struggle to sufficiently model long-range dependencies in node and graph prediction tasks. We propose a novel approach exploiting hierarchical graph structures and adaptive random walks to address this challenge. Our method introduces learnable transition probabilities that decide whether the walk should prefer the original graph or travel across hierarchical shortcuts. On a synthetic long-range task, we demonstrate that our approach can exceed the theoretical bound that constrains traditional approaches operating solely on the original topology. Specifically, wal"},"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":"2509.01381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-01T11:27:53Z","cross_cats_sorted":[],"title_canon_sha256":"cc92e4e04657ac47746d6c018f57d0068a8ddf38d3eaab91f44aeb784430e404","abstract_canon_sha256":"ce3724318b7e6e5a0aa5bf2f571f48431229f40249a59921d1f85caf5f529255"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:59.536473Z","signature_b64":"3GAT8lbz/u7C4vuCh4VN3oH73XLrypha0+gk2wjYQ+jaE36kvyf246KWkhgqB5qHW73N2W0PRmrxFJYtM7enCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b06ba5fddc9c7c17f165abdeb4a581028e95a521b85aa4e24a32fcf4bbbe13e","last_reissued_at":"2026-07-05T12:02:59.535722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:59.535722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Federico Errica, Jo\\\"el Mathys","submitted_at":"2025-09-01T11:27:53Z","abstract_excerpt":"Message-passing architectures struggle to sufficiently model long-range dependencies in node and graph prediction tasks. We propose a novel approach exploiting hierarchical graph structures and adaptive random walks to address this challenge. Our method introduces learnable transition probabilities that decide whether the walk should prefer the original graph or travel across hierarchical shortcuts. On a synthetic long-range task, we demonstrate that our approach can exceed the theoretical bound that constrains traditional approaches operating solely on the original topology. Specifically, wal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01381","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/2509.01381/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":"2509.01381","created_at":"2026-07-05T12:02:59.535831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01381v1","created_at":"2026-07-05T12:02:59.535831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01381","created_at":"2026-07-05T12:02:59.535831+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMDLUX65ZHD4","created_at":"2026-07-05T12:02:59.535831+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMDLUX65ZHD4C7YW","created_at":"2026-07-05T12:02:59.535831+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMDLUX65","created_at":"2026-07-05T12:02:59.535831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":136,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA","json":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA.json","graph_json":"https://pith.science/api/pith-number/PMDLUX65ZHD4C7YWLK66WSSYCA/graph.json","events_json":"https://pith.science/api/pith-number/PMDLUX65ZHD4C7YWLK66WSSYCA/events.json","paper":"https://pith.science/paper/PMDLUX65"},"agent_actions":{"view_html":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA","download_json":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA.json","view_paper":"https://pith.science/paper/PMDLUX65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01381&json=true","fetch_graph":"https://pith.science/api/pith-number/PMDLUX65ZHD4C7YWLK66WSSYCA/graph.json","fetch_events":"https://pith.science/api/pith-number/PMDLUX65ZHD4C7YWLK66WSSYCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA/action/storage_attestation","attest_author":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA/action/author_attestation","sign_citation":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA/action/citation_signature","submit_replication":"https://pith.science/pith/PMDLUX65ZHD4C7YWLK66WSSYCA/action/replication_record"}},"created_at":"2026-07-05T12:02:59.535831+00:00","updated_at":"2026-07-05T12:02:59.535831+00:00"}