{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TKHNAPVGM2KSJQSAU5MBBHCUIZ","short_pith_number":"pith:TKHNAPVG","schema_version":"1.0","canonical_sha256":"9a8ed03ea6669524c240a758109c54465b8f7be64e9317167eb280f485e8ce43","source":{"kind":"arxiv","id":"2410.04263","version":3},"attestation_state":"computed","paper":{"title":"DeFoG: Discrete Flow Matching for Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dorina Thanou, Manuel Madeira, Pascal Frossard, Yiming Qin","submitted_at":"2024-10-05T18:52:54Z","abstract_excerpt":"Graph generative models are essential across diverse scientific domains by capturing complex distributions over relational data. Among them, graph diffusion models achieve superior performance but face inefficient sampling and limited flexibility due to the tight coupling between training and sampling stages. We introduce DeFoG, a novel graph generative framework that disentangles sampling from training, enabling a broader design space for more effective and efficient model optimization. DeFoG employs a discrete flow-matching formulation that respects the inherent symmetries of graphs. We theo"},"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":"2410.04263","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T18:52:54Z","cross_cats_sorted":[],"title_canon_sha256":"016d33ff5724a7e2c56810266b0294be97c059ecd5585c66aff8a8a5a45e166f","abstract_canon_sha256":"9b1d6b2d2557abc4bcb1ed8224fa32c8dff1d03e5b6007c92c035d502ce307da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:36.552145Z","signature_b64":"2FWDAYF+MBsVpxc2yA0YF2erBVvYDGLorgXSbu5tJgbYUz8S4MLAmnNXWohOd9Af8E0PJCVApQ6pzoP3DMibCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a8ed03ea6669524c240a758109c54465b8f7be64e9317167eb280f485e8ce43","last_reissued_at":"2026-07-05T11:21:36.551613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:36.551613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeFoG: Discrete Flow Matching for Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dorina Thanou, Manuel Madeira, Pascal Frossard, Yiming Qin","submitted_at":"2024-10-05T18:52:54Z","abstract_excerpt":"Graph generative models are essential across diverse scientific domains by capturing complex distributions over relational data. Among them, graph diffusion models achieve superior performance but face inefficient sampling and limited flexibility due to the tight coupling between training and sampling stages. We introduce DeFoG, a novel graph generative framework that disentangles sampling from training, enabling a broader design space for more effective and efficient model optimization. DeFoG employs a discrete flow-matching formulation that respects the inherent symmetries of graphs. We theo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04263","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/2410.04263/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":"2410.04263","created_at":"2026-07-05T11:21:36.551674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04263v3","created_at":"2026-07-05T11:21:36.551674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04263","created_at":"2026-07-05T11:21:36.551674+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKHNAPVGM2KS","created_at":"2026-07-05T11:21:36.551674+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKHNAPVGM2KSJQSA","created_at":"2026-07-05T11:21:36.551674+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKHNAPVG","created_at":"2026-07-05T11:21:36.551674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06546","citing_title":"Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02133","citing_title":"Variational Learning for Insertion-based Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15354","citing_title":"Controllable Molecular Generative Foundation Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18472","citing_title":"Flowing with Confidence","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03015","citing_title":"Discrete Bayesian Sample Inference for Graph Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07020","citing_title":"FlashMol: High-Quality Molecule Generation in as Few as Four Steps","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17310","citing_title":"Interpolating Discrete Diffusion Models with Controllable Resampling","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ","json":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ.json","graph_json":"https://pith.science/api/pith-number/TKHNAPVGM2KSJQSAU5MBBHCUIZ/graph.json","events_json":"https://pith.science/api/pith-number/TKHNAPVGM2KSJQSAU5MBBHCUIZ/events.json","paper":"https://pith.science/paper/TKHNAPVG"},"agent_actions":{"view_html":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ","download_json":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ.json","view_paper":"https://pith.science/paper/TKHNAPVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04263&json=true","fetch_graph":"https://pith.science/api/pith-number/TKHNAPVGM2KSJQSAU5MBBHCUIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TKHNAPVGM2KSJQSAU5MBBHCUIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ/action/storage_attestation","attest_author":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ/action/author_attestation","sign_citation":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ/action/citation_signature","submit_replication":"https://pith.science/pith/TKHNAPVGM2KSJQSAU5MBBHCUIZ/action/replication_record"}},"created_at":"2026-07-05T11:21:36.551674+00:00","updated_at":"2026-07-05T11:21:36.551674+00:00"}