{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BOXUGESZXHOOBB2S63O7JXK47H","short_pith_number":"pith:BOXUGESZ","schema_version":"1.0","canonical_sha256":"0baf431259b9dce08752f6ddf4dd5cf9c1d7539ae9f2afb969cb3c1d7d520a67","source":{"kind":"arxiv","id":"2503.23612","version":2},"attestation_state":"computed","paper":{"title":"Diffusion-Free Graph Generation with Next-Scale Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charles Harris, Marian Chen, Miruna Cretu, Pietro Lio, Samuel Belkadi, Steve Hong","submitted_at":"2025-03-30T22:30:34Z","abstract_excerpt":"Autoregressive models excel in efficiency and plug directly into the transformer ecosystem, delivering robust generalization, predictable scalability, and seamless workflows such as fine-tuning and parallelized training. However, they require an explicit sequence order, which contradicts the unordered nature of graphs. In contrast, diffusion models maintain permutation invariance and enable one-shot generation but require up to thousands of denoising steps and additional features for expressivity, leading to high computational costs. Inspired by recent breakthroughs in image generation, especi"},"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":"2503.23612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-30T22:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"0bbf17b5c6b660af3fb1f0eb089cb1e5ac54caec60d12b6923de15419671cb21","abstract_canon_sha256":"1b03932897ae087cdf815ad4ca268c1eff9d2ff3c642a39e452676bcb2ae313d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:11.018469Z","signature_b64":"DGhx86bLdFCKTG/2Rdb0+M97uTaZ4cOOEVSub7mKE7Ir6rgkPoCInqrhT9YZQOCtCuE6JoLJUbyU5LbXvnFiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0baf431259b9dce08752f6ddf4dd5cf9c1d7539ae9f2afb969cb3c1d7d520a67","last_reissued_at":"2026-07-05T11:20:11.017852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:11.017852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Free Graph Generation with Next-Scale Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charles Harris, Marian Chen, Miruna Cretu, Pietro Lio, Samuel Belkadi, Steve Hong","submitted_at":"2025-03-30T22:30:34Z","abstract_excerpt":"Autoregressive models excel in efficiency and plug directly into the transformer ecosystem, delivering robust generalization, predictable scalability, and seamless workflows such as fine-tuning and parallelized training. However, they require an explicit sequence order, which contradicts the unordered nature of graphs. In contrast, diffusion models maintain permutation invariance and enable one-shot generation but require up to thousands of denoising steps and additional features for expressivity, leading to high computational costs. Inspired by recent breakthroughs in image generation, especi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23612","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/2503.23612/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":"2503.23612","created_at":"2026-07-05T11:20:11.017924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23612v2","created_at":"2026-07-05T11:20:11.017924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23612","created_at":"2026-07-05T11:20:11.017924+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOXUGESZXHOO","created_at":"2026-07-05T11:20:11.017924+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOXUGESZXHOOBB2S","created_at":"2026-07-05T11:20:11.017924+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOXUGESZ","created_at":"2026-07-05T11:20:11.017924+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/BOXUGESZXHOOBB2S63O7JXK47H","json":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H.json","graph_json":"https://pith.science/api/pith-number/BOXUGESZXHOOBB2S63O7JXK47H/graph.json","events_json":"https://pith.science/api/pith-number/BOXUGESZXHOOBB2S63O7JXK47H/events.json","paper":"https://pith.science/paper/BOXUGESZ"},"agent_actions":{"view_html":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H","download_json":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H.json","view_paper":"https://pith.science/paper/BOXUGESZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23612&json=true","fetch_graph":"https://pith.science/api/pith-number/BOXUGESZXHOOBB2S63O7JXK47H/graph.json","fetch_events":"https://pith.science/api/pith-number/BOXUGESZXHOOBB2S63O7JXK47H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H/action/storage_attestation","attest_author":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H/action/author_attestation","sign_citation":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H/action/citation_signature","submit_replication":"https://pith.science/pith/BOXUGESZXHOOBB2S63O7JXK47H/action/replication_record"}},"created_at":"2026-07-05T11:20:11.017924+00:00","updated_at":"2026-07-05T11:20:11.017924+00:00"}