{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KVTMGSVN3SU7RKVAMTBSQCQCBV","short_pith_number":"pith:KVTMGSVN","schema_version":"1.0","canonical_sha256":"5566c34aaddca9f8aaa064c3280a020d60423eb6b4c06233cbb1be5bc6603ded","source":{"kind":"arxiv","id":"2106.00967","version":3},"attestation_state":"computed","paper":{"title":"Multiresolution Equivariant Graph Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Risi Kondor, Truong Son Hy","submitted_at":"2021-06-02T06:28:47Z","abstract_excerpt":"In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our propos"},"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":"2106.00967","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T06:28:47Z","cross_cats_sorted":["cs.SI","physics.chem-ph"],"title_canon_sha256":"1e54da9ea209ac716860e0011e21b2869a41a76748547f82a21f65918c85bea6","abstract_canon_sha256":"0765bebfda8569634dda6042c6daac4ea9cd444056a6ebddf9dc3bd42220d8aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:56.149943Z","signature_b64":"6GLCDb7vWHEzKlJbh09Ffohjx8ebkEf5EaOE8fkj8hKsB+pgmAm2vB1VtW1OjqZATrwzJdtv9Bant5RIabgABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5566c34aaddca9f8aaa064c3280a020d60423eb6b4c06233cbb1be5bc6603ded","last_reissued_at":"2026-07-05T04:35:56.149479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:56.149479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiresolution Equivariant Graph Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Risi Kondor, Truong Son Hy","submitted_at":"2021-06-02T06:28:47Z","abstract_excerpt":"In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00967","kind":"arxiv","version":3},"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/2106.00967/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":"2106.00967","created_at":"2026-07-05T04:35:56.149536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00967v3","created_at":"2026-07-05T04:35:56.149536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00967","created_at":"2026-07-05T04:35:56.149536+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVTMGSVN3SU7","created_at":"2026-07-05T04:35:56.149536+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVTMGSVN3SU7RKVA","created_at":"2026-07-05T04:35:56.149536+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVTMGSVN","created_at":"2026-07-05T04:35:56.149536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08850","citing_title":"Graph Counterfactual Explainable AI via Latent Space Traversal","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV","json":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV.json","graph_json":"https://pith.science/api/pith-number/KVTMGSVN3SU7RKVAMTBSQCQCBV/graph.json","events_json":"https://pith.science/api/pith-number/KVTMGSVN3SU7RKVAMTBSQCQCBV/events.json","paper":"https://pith.science/paper/KVTMGSVN"},"agent_actions":{"view_html":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV","download_json":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV.json","view_paper":"https://pith.science/paper/KVTMGSVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00967&json=true","fetch_graph":"https://pith.science/api/pith-number/KVTMGSVN3SU7RKVAMTBSQCQCBV/graph.json","fetch_events":"https://pith.science/api/pith-number/KVTMGSVN3SU7RKVAMTBSQCQCBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV/action/storage_attestation","attest_author":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV/action/author_attestation","sign_citation":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV/action/citation_signature","submit_replication":"https://pith.science/pith/KVTMGSVN3SU7RKVAMTBSQCQCBV/action/replication_record"}},"created_at":"2026-07-05T04:35:56.149536+00:00","updated_at":"2026-07-05T04:35:56.149536+00:00"}