{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SWT4PVDGFF7Z6PNG3U6GF7FGXN","short_pith_number":"pith:SWT4PVDG","schema_version":"1.0","canonical_sha256":"95a7c7d466297f9f3da6dd3c62fca6bb4a3748e638311f7dc5d59cc1ccafba43","source":{"kind":"arxiv","id":"2402.18974","version":2},"attestation_state":"computed","paper":{"title":"Generating Graphs via Spectral Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Bicciato, Andrea Torsello, Giorgia Minello, Luca Cosmo, Luca Rossi","submitted_at":"2024-02-29T09:26:46Z","abstract_excerpt":"In this paper, we present GGSD, a novel graph generative model based on 1) the spectral decomposition of the graph Laplacian matrix and 2) a diffusion process. Specifically, we propose to use a denoising model to sample eigenvectors and eigenvalues from which we can reconstruct the graph Laplacian and adjacency matrix. Using the Laplacian spectrum allows us to naturally capture the structural characteristics of the graph and work directly in the node space while avoiding the quadratic complexity bottleneck that limits the applicability of other diffusion-based methods. This, in turn, is accomp"},"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":"2402.18974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T09:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"e39a9d5c60b982500c5325e76c9a93155e944ead65121b5cf6a0166d696c6ee9","abstract_canon_sha256":"9b5892626a756aecc7a42051c712de4ec56424ff8ede198fdb59d58074b870d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:52.210631Z","signature_b64":"UbLVdTKOlydBVXu1CtiDKbSDvJ8bsdi3Voknz96t+atZR8yERlPUQKpHmrtAqzfk5VowdhK9UKEP7aCz6OdaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a7c7d466297f9f3da6dd3c62fca6bb4a3748e638311f7dc5d59cc1ccafba43","last_reissued_at":"2026-07-05T10:23:52.209997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:52.209997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Graphs via Spectral Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Bicciato, Andrea Torsello, Giorgia Minello, Luca Cosmo, Luca Rossi","submitted_at":"2024-02-29T09:26:46Z","abstract_excerpt":"In this paper, we present GGSD, a novel graph generative model based on 1) the spectral decomposition of the graph Laplacian matrix and 2) a diffusion process. Specifically, we propose to use a denoising model to sample eigenvectors and eigenvalues from which we can reconstruct the graph Laplacian and adjacency matrix. Using the Laplacian spectrum allows us to naturally capture the structural characteristics of the graph and work directly in the node space while avoiding the quadratic complexity bottleneck that limits the applicability of other diffusion-based methods. This, in turn, is accomp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18974","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/2402.18974/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":"2402.18974","created_at":"2026-07-05T10:23:52.210087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18974v2","created_at":"2026-07-05T10:23:52.210087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18974","created_at":"2026-07-05T10:23:52.210087+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWT4PVDGFF7Z","created_at":"2026-07-05T10:23:52.210087+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWT4PVDGFF7Z6PNG","created_at":"2026-07-05T10:23:52.210087+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWT4PVDG","created_at":"2026-07-05T10:23:52.210087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.17291","citing_title":"GraphWeave: Interpretable and Robust Graph Generation via Random Walk Trajectories","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN","json":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN.json","graph_json":"https://pith.science/api/pith-number/SWT4PVDGFF7Z6PNG3U6GF7FGXN/graph.json","events_json":"https://pith.science/api/pith-number/SWT4PVDGFF7Z6PNG3U6GF7FGXN/events.json","paper":"https://pith.science/paper/SWT4PVDG"},"agent_actions":{"view_html":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN","download_json":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN.json","view_paper":"https://pith.science/paper/SWT4PVDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18974&json=true","fetch_graph":"https://pith.science/api/pith-number/SWT4PVDGFF7Z6PNG3U6GF7FGXN/graph.json","fetch_events":"https://pith.science/api/pith-number/SWT4PVDGFF7Z6PNG3U6GF7FGXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN/action/storage_attestation","attest_author":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN/action/author_attestation","sign_citation":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN/action/citation_signature","submit_replication":"https://pith.science/pith/SWT4PVDGFF7Z6PNG3U6GF7FGXN/action/replication_record"}},"created_at":"2026-07-05T10:23:52.210087+00:00","updated_at":"2026-07-05T10:23:52.210087+00:00"}