{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PXIN7O3K6X2TFMFU7P6A5JGEYA","short_pith_number":"pith:PXIN7O3K","schema_version":"1.0","canonical_sha256":"7dd0dfbb6af5f532b0b4fbfc0ea4c4c031e9f3604e725fd005e9b2eb00d417c3","source":{"kind":"arxiv","id":"2210.16844","version":2},"attestation_state":"computed","paper":{"title":"Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ke Li, Kiarash Zahirnia, Oliver Schulte, Parmis Naddaf","submitted_at":"2022-10-30T13:45:21Z","abstract_excerpt":"Generative models for graph data are an important research topic in machine learning. Graph data comprise two levels that are typically analyzed separately: node-level properties such as the existence of a link between a pair of nodes, and global aggregate graph-level statistics, such as motif counts. This paper proposes a new multi-level framework that jointly models node-level properties and graph-level statistics, as mutually reinforcing sources of information. We introduce a new micro-macro training objective for graph generation that combines node-level and graph-level losses. We utilize "},"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":"2210.16844","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-30T13:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"e31233205cab751afecff8cbdee0a03e9f9b94c2a31364c60978f21fb2ecdfc1","abstract_canon_sha256":"37367abf3ea936ed50c76ea3b4c1c06e50f21b3e047b6e42bb1b09e7dbf278ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:56.793999Z","signature_b64":"MNe3fSa3kvzG7+RMU98PsJ8QXjvuOaDcYz9f7nYwZGL2osHVmSkPEzFaanZkVIBhs0lhT+VGuvNxPcbrRoZmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dd0dfbb6af5f532b0b4fbfc0ea4c4c031e9f3604e725fd005e9b2eb00d417c3","last_reissued_at":"2026-07-05T05:32:56.793528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:56.793528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ke Li, Kiarash Zahirnia, Oliver Schulte, Parmis Naddaf","submitted_at":"2022-10-30T13:45:21Z","abstract_excerpt":"Generative models for graph data are an important research topic in machine learning. Graph data comprise two levels that are typically analyzed separately: node-level properties such as the existence of a link between a pair of nodes, and global aggregate graph-level statistics, such as motif counts. This paper proposes a new multi-level framework that jointly models node-level properties and graph-level statistics, as mutually reinforcing sources of information. We introduce a new micro-macro training objective for graph generation that combines node-level and graph-level losses. We utilize "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16844","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/2210.16844/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":"2210.16844","created_at":"2026-07-05T05:32:56.793586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16844v2","created_at":"2026-07-05T05:32:56.793586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16844","created_at":"2026-07-05T05:32:56.793586+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXIN7O3K6X2T","created_at":"2026-07-05T05:32:56.793586+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXIN7O3K6X2TFMFU","created_at":"2026-07-05T05:32:56.793586+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXIN7O3K","created_at":"2026-07-05T05:32:56.793586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA","json":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA.json","graph_json":"https://pith.science/api/pith-number/PXIN7O3K6X2TFMFU7P6A5JGEYA/graph.json","events_json":"https://pith.science/api/pith-number/PXIN7O3K6X2TFMFU7P6A5JGEYA/events.json","paper":"https://pith.science/paper/PXIN7O3K"},"agent_actions":{"view_html":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA","download_json":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA.json","view_paper":"https://pith.science/paper/PXIN7O3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16844&json=true","fetch_graph":"https://pith.science/api/pith-number/PXIN7O3K6X2TFMFU7P6A5JGEYA/graph.json","fetch_events":"https://pith.science/api/pith-number/PXIN7O3K6X2TFMFU7P6A5JGEYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA/action/storage_attestation","attest_author":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA/action/author_attestation","sign_citation":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA/action/citation_signature","submit_replication":"https://pith.science/pith/PXIN7O3K6X2TFMFU7P6A5JGEYA/action/replication_record"}},"created_at":"2026-07-05T05:32:56.793586+00:00","updated_at":"2026-07-05T05:32:56.793586+00:00"}