{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MMOO4SXUNLQLBGDW57FPADT72P","short_pith_number":"pith:MMOO4SXU","schema_version":"1.0","canonical_sha256":"631cee4af46ae0b09876efcaf00e7fd3f1c1dba00be2b2373d9b153654dbe691","source":{"kind":"arxiv","id":"2404.17099","version":1},"attestation_state":"computed","paper":{"title":"Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Feng Ji, Kai Zhao, Qinxu Ding, Qiyu Kang, Wee Peng Tay, Wenfei Liang, Xuhao Li, Yang Song","submitted_at":"2024-04-26T01:20:45Z","abstract_excerpt":"We introduce the FRactional-Order graph Neural Dynamical network (FROND), a new continuous graph neural network (GNN) framework. Unlike traditional continuous GNNs that rely on integer-order differential equations, FROND employs the Caputo fractional derivative to leverage the non-local properties of fractional calculus. This approach enables the capture of long-term dependencies in feature updates, moving beyond the Markovian update mechanisms in conventional integer-order models and offering enhanced capabilities in graph representation learning. We offer an interpretation of the node featur"},"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":"2404.17099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-26T01:20:45Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"102b49809d269d2d0886a2a703671ef143193a4078eccfa364c15e20e2cb4b31","abstract_canon_sha256":"079a85d587fc43230fc35e2878b2e13107ac7e854f79ea35eef3559474bd9777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:19.661848Z","signature_b64":"IribJCODzEsfyRKN2ngOFYFsNTJeN1LaGmUMNsx6qxrONuFpo8yDpK7eSMgSXdcQEWA8N9QaA3uikQ0+VFdmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631cee4af46ae0b09876efcaf00e7fd3f1c1dba00be2b2373d9b153654dbe691","last_reissued_at":"2026-07-05T08:12:19.661432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:19.661432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Feng Ji, Kai Zhao, Qinxu Ding, Qiyu Kang, Wee Peng Tay, Wenfei Liang, Xuhao Li, Yang Song","submitted_at":"2024-04-26T01:20:45Z","abstract_excerpt":"We introduce the FRactional-Order graph Neural Dynamical network (FROND), a new continuous graph neural network (GNN) framework. Unlike traditional continuous GNNs that rely on integer-order differential equations, FROND employs the Caputo fractional derivative to leverage the non-local properties of fractional calculus. This approach enables the capture of long-term dependencies in feature updates, moving beyond the Markovian update mechanisms in conventional integer-order models and offering enhanced capabilities in graph representation learning. We offer an interpretation of the node featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17099","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/2404.17099/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":"2404.17099","created_at":"2026-07-05T08:12:19.661488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17099v1","created_at":"2026-07-05T08:12:19.661488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17099","created_at":"2026-07-05T08:12:19.661488+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMOO4SXUNLQL","created_at":"2026-07-05T08:12:19.661488+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMOO4SXUNLQLBGDW","created_at":"2026-07-05T08:12:19.661488+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMOO4SXU","created_at":"2026-07-05T08:12:19.661488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P","json":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P.json","graph_json":"https://pith.science/api/pith-number/MMOO4SXUNLQLBGDW57FPADT72P/graph.json","events_json":"https://pith.science/api/pith-number/MMOO4SXUNLQLBGDW57FPADT72P/events.json","paper":"https://pith.science/paper/MMOO4SXU"},"agent_actions":{"view_html":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P","download_json":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P.json","view_paper":"https://pith.science/paper/MMOO4SXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17099&json=true","fetch_graph":"https://pith.science/api/pith-number/MMOO4SXUNLQLBGDW57FPADT72P/graph.json","fetch_events":"https://pith.science/api/pith-number/MMOO4SXUNLQLBGDW57FPADT72P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P/action/storage_attestation","attest_author":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P/action/author_attestation","sign_citation":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P/action/citation_signature","submit_replication":"https://pith.science/pith/MMOO4SXUNLQLBGDW57FPADT72P/action/replication_record"}},"created_at":"2026-07-05T08:12:19.661488+00:00","updated_at":"2026-07-05T08:12:19.661488+00:00"}