{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UWWHJCJHNRSPG4S5DBS72INPPS","short_pith_number":"pith:UWWHJCJH","schema_version":"1.0","canonical_sha256":"a5ac7489276c64f3725d1865fd21af7cbc15fb9d2268714d1fac6cfe0d0200ce","source":{"kind":"arxiv","id":"2307.01646","version":4},"attestation_state":"computed","paper":{"title":"SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lele Wang, Qi Yan, Renjie Liao, Yang Song, Zhengyang Liang","submitted_at":"2023-07-04T10:58:42Z","abstract_excerpt":"Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data. However, in comparison to their non-invariant counterparts, we have found that these invariant models encounter greater learning challenges since 1) their effective target distributions exhibit more modes; 2) their optimal one-step denoising scores are the score functions of Gaussian mixtures with more components. Motivated by this analysis, we propose a non-invariant diffusion model, called $\\textit{SwinGNN}$, which employs an efficient edge-to-edge 2-WL message passing net"},"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":"2307.01646","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T10:58:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd781d0540441d3641c45fa946f677f8ff0e3c0a1e4438b5fcf1c4798ff13e6a","abstract_canon_sha256":"36919784a0760df134c8e26356f5b7277c6c6806db3a54da9ae0e96a656f7885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:04.141472Z","signature_b64":"IdBgHcM6QEWwKaYOKLxTBFfXdxzrA8aZqK6Tmx0A8eHT9T7KdqxQ9rPaj0UIzeokvoYvF3VW+kAFLq5k/lvFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5ac7489276c64f3725d1865fd21af7cbc15fb9d2268714d1fac6cfe0d0200ce","last_reissued_at":"2026-07-05T08:34:04.140936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:04.140936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lele Wang, Qi Yan, Renjie Liao, Yang Song, Zhengyang Liang","submitted_at":"2023-07-04T10:58:42Z","abstract_excerpt":"Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data. However, in comparison to their non-invariant counterparts, we have found that these invariant models encounter greater learning challenges since 1) their effective target distributions exhibit more modes; 2) their optimal one-step denoising scores are the score functions of Gaussian mixtures with more components. Motivated by this analysis, we propose a non-invariant diffusion model, called $\\textit{SwinGNN}$, which employs an efficient edge-to-edge 2-WL message passing net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01646","kind":"arxiv","version":4},"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/2307.01646/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":"2307.01646","created_at":"2026-07-05T08:34:04.140995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01646v4","created_at":"2026-07-05T08:34:04.140995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01646","created_at":"2026-07-05T08:34:04.140995+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWWHJCJHNRSP","created_at":"2026-07-05T08:34:04.140995+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWWHJCJHNRSPG4S5","created_at":"2026-07-05T08:34:04.140995+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWWHJCJH","created_at":"2026-07-05T08:34:04.140995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22702","citing_title":"Modular Diffusion Models for Structured Visual Recognition","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS","json":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS.json","graph_json":"https://pith.science/api/pith-number/UWWHJCJHNRSPG4S5DBS72INPPS/graph.json","events_json":"https://pith.science/api/pith-number/UWWHJCJHNRSPG4S5DBS72INPPS/events.json","paper":"https://pith.science/paper/UWWHJCJH"},"agent_actions":{"view_html":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS","download_json":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS.json","view_paper":"https://pith.science/paper/UWWHJCJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01646&json=true","fetch_graph":"https://pith.science/api/pith-number/UWWHJCJHNRSPG4S5DBS72INPPS/graph.json","fetch_events":"https://pith.science/api/pith-number/UWWHJCJHNRSPG4S5DBS72INPPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS/action/storage_attestation","attest_author":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS/action/author_attestation","sign_citation":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS/action/citation_signature","submit_replication":"https://pith.science/pith/UWWHJCJHNRSPG4S5DBS72INPPS/action/replication_record"}},"created_at":"2026-07-05T08:34:04.140995+00:00","updated_at":"2026-07-05T08:34:04.140995+00:00"}