{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3Z4BSKVRWGBSWV4EG7U6U7ZBDA","short_pith_number":"pith:3Z4BSKVR","schema_version":"1.0","canonical_sha256":"de78192ab1b1832b578437e9ea7f21182dfe80d35d843af0f756ec98d7994e53","source":{"kind":"arxiv","id":"2202.10643","version":2},"attestation_state":"computed","paper":{"title":"Equivariant Graph Hierarchy-Based Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Han, Tingyang Xu, Wenbing Huang, Yu Rong","submitted_at":"2022-02-22T03:11:47Z","abstract_excerpt":"Equivariant Graph neural Networks (EGNs) are powerful in characterizing the dynamics of multi-body physical systems. Existing EGNs conduct flat message passing, which, yet, is unable to capture the spatial/dynamical hierarchy for complex systems particularly, limiting substructure discovery and global information fusion. In this paper, we propose Equivariant Hierarchy-based Graph Networks (EGHNs) which consist of the three key components: generalized Equivariant Matrix Message Passing (EMMP) , E-Pool and E-UpPool. In particular, EMMP is able to improve the expressivity of conventional equivari"},"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":"2202.10643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T03:11:47Z","cross_cats_sorted":[],"title_canon_sha256":"dcf604038bd915f473852979f616b72058e85ed7a174bfef0285bb05c542be77","abstract_canon_sha256":"a699d0f2f01623642bece0e4bed330fa1a4f940751a370215fa1bfb2cc8bf38d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:55.076390Z","signature_b64":"5w8h2KNMKosEOqQzgieipJyg6Clmg8pUg7acaZGNmLTbVbCagajUFVQd5SlIUXFuwcvRMmYHADfShnf+CYr+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de78192ab1b1832b578437e9ea7f21182dfe80d35d843af0f756ec98d7994e53","last_reissued_at":"2026-07-05T05:06:55.075918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:55.075918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivariant Graph Hierarchy-Based Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Han, Tingyang Xu, Wenbing Huang, Yu Rong","submitted_at":"2022-02-22T03:11:47Z","abstract_excerpt":"Equivariant Graph neural Networks (EGNs) are powerful in characterizing the dynamics of multi-body physical systems. Existing EGNs conduct flat message passing, which, yet, is unable to capture the spatial/dynamical hierarchy for complex systems particularly, limiting substructure discovery and global information fusion. In this paper, we propose Equivariant Hierarchy-based Graph Networks (EGHNs) which consist of the three key components: generalized Equivariant Matrix Message Passing (EMMP) , E-Pool and E-UpPool. In particular, EMMP is able to improve the expressivity of conventional equivari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10643","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/2202.10643/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":"2202.10643","created_at":"2026-07-05T05:06:55.075977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.10643v2","created_at":"2026-07-05T05:06:55.075977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10643","created_at":"2026-07-05T05:06:55.075977+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Z4BSKVRWGBS","created_at":"2026-07-05T05:06:55.075977+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Z4BSKVRWGBSWV4E","created_at":"2026-07-05T05:06:55.075977+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Z4BSKVR","created_at":"2026-07-05T05:06:55.075977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22429","citing_title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","ref_index":162,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA","json":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA.json","graph_json":"https://pith.science/api/pith-number/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/graph.json","events_json":"https://pith.science/api/pith-number/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/events.json","paper":"https://pith.science/paper/3Z4BSKVR"},"agent_actions":{"view_html":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA","download_json":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA.json","view_paper":"https://pith.science/paper/3Z4BSKVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.10643&json=true","fetch_graph":"https://pith.science/api/pith-number/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/graph.json","fetch_events":"https://pith.science/api/pith-number/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/action/storage_attestation","attest_author":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/action/author_attestation","sign_citation":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/action/citation_signature","submit_replication":"https://pith.science/pith/3Z4BSKVRWGBSWV4EG7U6U7ZBDA/action/replication_record"}},"created_at":"2026-07-05T05:06:55.075977+00:00","updated_at":"2026-07-05T05:06:55.075977+00:00"}