{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KTJAHLZJRND2IPE5FSKBTM7ZCC","short_pith_number":"pith:KTJAHLZJ","schema_version":"1.0","canonical_sha256":"54d203af298b47a43c9d2c9419b3f910bfb32ca01050bc5ab5c2ba1bfb7cc116","source":{"kind":"arxiv","id":"2602.23566","version":3},"attestation_state":"computed","paper":{"title":"Flowette: Flow Matching with Graphette Priors for Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Asiri Wijesinghe, Cheng Soon Ong, Daniel M. Steinberg, Sevvandi Kandanaarachchi","submitted_at":"2026-02-27T00:22:21Z","abstract_excerpt":"We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework that employs a graph neural network-based transformer to learn a velocity field over graph representations with node and edge attributes. Our model promotes topology-aware alignment through optimal transport-based coupling and encourages global structural coherence through regularisation. To incorporate domain-driven structural priors, we introduce graphettes, a new probabilistic family of graph structure models that generalize graphons via controlled structural edit"},"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":"2602.23566","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-27T00:22:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a74ccaea0533bd6910e1189a4a9275e51730b708e2223774badb6dd15e10c3f4","abstract_canon_sha256":"cd62a1c4f5e5820746e240e34b2aad275e596421f9b7b0390143396bedb8731d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:26.772626Z","signature_b64":"L1Kbaw2orURaO8vAa3fWEA+pWXPqku/K/XFYESJ3f7sO74Wx/swFqpWAuuEtHSmSph18xAMV0nE6SozhoYilDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d203af298b47a43c9d2c9419b3f910bfb32ca01050bc5ab5c2ba1bfb7cc116","last_reissued_at":"2026-05-20T00:04:26.771858Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:26.771858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flowette: Flow Matching with Graphette Priors for Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Asiri Wijesinghe, Cheng Soon Ong, Daniel M. Steinberg, Sevvandi Kandanaarachchi","submitted_at":"2026-02-27T00:22:21Z","abstract_excerpt":"We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework that employs a graph neural network-based transformer to learn a velocity field over graph representations with node and edge attributes. Our model promotes topology-aware alignment through optimal transport-based coupling and encourages global structural coherence through regularisation. To incorporate domain-driven structural priors, we introduce graphettes, a new probabilistic family of graph structure models that generalize graphons via controlled structural edit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23566","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/2602.23566/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":"2602.23566","created_at":"2026-05-20T00:04:26.771987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23566v3","created_at":"2026-05-20T00:04:26.771987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23566","created_at":"2026-05-20T00:04:26.771987+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTJAHLZJRND2","created_at":"2026-05-20T00:04:26.771987+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTJAHLZJRND2IPE5","created_at":"2026-05-20T00:04:26.771987+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTJAHLZJ","created_at":"2026-05-20T00:04:26.771987+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/KTJAHLZJRND2IPE5FSKBTM7ZCC","json":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC.json","graph_json":"https://pith.science/api/pith-number/KTJAHLZJRND2IPE5FSKBTM7ZCC/graph.json","events_json":"https://pith.science/api/pith-number/KTJAHLZJRND2IPE5FSKBTM7ZCC/events.json","paper":"https://pith.science/paper/KTJAHLZJ"},"agent_actions":{"view_html":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC","download_json":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC.json","view_paper":"https://pith.science/paper/KTJAHLZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23566&json=true","fetch_graph":"https://pith.science/api/pith-number/KTJAHLZJRND2IPE5FSKBTM7ZCC/graph.json","fetch_events":"https://pith.science/api/pith-number/KTJAHLZJRND2IPE5FSKBTM7ZCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC/action/storage_attestation","attest_author":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC/action/author_attestation","sign_citation":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC/action/citation_signature","submit_replication":"https://pith.science/pith/KTJAHLZJRND2IPE5FSKBTM7ZCC/action/replication_record"}},"created_at":"2026-05-20T00:04:26.771987+00:00","updated_at":"2026-05-20T00:04:26.771987+00:00"}