{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QQNPLGOE7GRCOHD5UEMF4KGLNO","short_pith_number":"pith:QQNPLGOE","schema_version":"1.0","canonical_sha256":"841af599c4f9a2271c7da1185e28cb6badb1517f3af1ebaaf4ccdff27bbfafbb","source":{"kind":"arxiv","id":"2307.16092","version":2},"attestation_state":"computed","paper":{"title":"Feature Transportation Improves Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eldad Haber, Eran Treister, Moshe Eliasof","submitted_at":"2023-07-29T23:31:18Z","abstract_excerpt":"Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data. However, GNNs still face challenges in modeling complex phenomena that involve feature transportation. In this paper, we propose a novel GNN architecture inspired by Advection-Diffusion-Reaction systems, called ADR-GNN. Advection models feature transportation, while diffusion captures the local smoothing of features, and reaction represents the non-linear transformation between feature channels. We provide an analysis of the qualitative behavior of ADR-GNN, that shows the benefit o"},"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":"2307.16092","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T23:31:18Z","cross_cats_sorted":[],"title_canon_sha256":"663507ad54fb44a6f8cfec6f862492327fbf3ed8d8912ed561eeeb78ad9333ee","abstract_canon_sha256":"35bc664cce2d4e78198f1865434b0e049103aeac76a16ddc49a49e79c90a3890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:16.072306Z","signature_b64":"PWowhHNsKNSZ9QqL7f6b08XuQpS7+AGgkuZMg7WbOsc9Cmd9bK265+WymnWoSQnW7vAyhoOlR0x7hWYqSnTMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"841af599c4f9a2271c7da1185e28cb6badb1517f3af1ebaaf4ccdff27bbfafbb","last_reissued_at":"2026-07-05T07:26:16.071845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:16.071845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Transportation Improves Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eldad Haber, Eran Treister, Moshe Eliasof","submitted_at":"2023-07-29T23:31:18Z","abstract_excerpt":"Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data. However, GNNs still face challenges in modeling complex phenomena that involve feature transportation. In this paper, we propose a novel GNN architecture inspired by Advection-Diffusion-Reaction systems, called ADR-GNN. Advection models feature transportation, while diffusion captures the local smoothing of features, and reaction represents the non-linear transformation between feature channels. We provide an analysis of the qualitative behavior of ADR-GNN, that shows the benefit o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16092","kind":"arxiv","version":2},"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/2307.16092/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":"2307.16092","created_at":"2026-07-05T07:26:16.071904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16092v2","created_at":"2026-07-05T07:26:16.071904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16092","created_at":"2026-07-05T07:26:16.071904+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQNPLGOE7GRC","created_at":"2026-07-05T07:26:16.071904+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQNPLGOE7GRCOHD5","created_at":"2026-07-05T07:26:16.071904+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQNPLGOE","created_at":"2026-07-05T07:26:16.071904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23708","citing_title":"Learning Dynamic Stability Landscapes in Synchronization Networks","ref_index":183,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO","json":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO.json","graph_json":"https://pith.science/api/pith-number/QQNPLGOE7GRCOHD5UEMF4KGLNO/graph.json","events_json":"https://pith.science/api/pith-number/QQNPLGOE7GRCOHD5UEMF4KGLNO/events.json","paper":"https://pith.science/paper/QQNPLGOE"},"agent_actions":{"view_html":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO","download_json":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO.json","view_paper":"https://pith.science/paper/QQNPLGOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16092&json=true","fetch_graph":"https://pith.science/api/pith-number/QQNPLGOE7GRCOHD5UEMF4KGLNO/graph.json","fetch_events":"https://pith.science/api/pith-number/QQNPLGOE7GRCOHD5UEMF4KGLNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO/action/storage_attestation","attest_author":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO/action/author_attestation","sign_citation":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO/action/citation_signature","submit_replication":"https://pith.science/pith/QQNPLGOE7GRCOHD5UEMF4KGLNO/action/replication_record"}},"created_at":"2026-07-05T07:26:16.071904+00:00","updated_at":"2026-07-05T07:26:16.071904+00:00"}