{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2XM5CQTV2CAP65WI4OHY4IRXYJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"766a3a8d5c285da4726732de0461164764b193fed63f032abd94d4a013a77bac","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","cs.LG","physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-05-12T18:00:02Z","title_canon_sha256":"c0f6406917aebddba081a0761924fa17c9f4e9bd5c12bffc813f279c6bb2b535"},"schema_version":"1.0","source":{"id":"2605.12597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12597","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12597v1","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12597","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"2XM5CQTV2CAP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2XM5CQTV2CAP65WI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2XM5CQTV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:40934e6e3e61ebb0397be1ef62e1ea8fb1607408afa7c2ea06edfc80534033c4","target":"graph","created_at":"2026-05-18T03:10:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Using a two-layer architecture drastically reduces the critical slowing down, with the training time scaling logarithmically rather than quadratically with system size. By introducing a local score approximation we show that this acceleration in training time can be achieved without increasing the number of neural network parameters."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Gaussian limit n→∞ of the O(n) model and the one-layer network exactly matching its score function are representative of the critical slowing down that occurs in practical diffusion models trained on finite-n or non-Gaussian systems."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Diffusion models on the Gaussian O(n) model exhibit critical slowing down with shallow networks that deeper local score approximations can reduce to logarithmic training-time scaling."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Two-layer networks with local score approximation reduce critical slowing down in diffusion models to logarithmic scaling."}],"snapshot_sha256":"eca8e5f6475974899fc805810158feb2730e8961f735c8d038ee5012113f2e15"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"28cdbbc5a67b0181ef897c353969a1b221d878d9665d6815367a873122a97ab4"},"paper":{"abstract_excerpt":"Computational sampling has been central to the sciences since the mid-20th century. While machine-learning-based approaches have recently enabled major advances, their behavior remains poorly understood, with limited theoretical control over when and why they succeed. Here we provide such insight for diffusion models-a class of generative schemes highly effective in practice-by analyzing their application to the $O(n)$ model of statistical field theory in the Gaussian limit $n \\to \\infty$. In this analytically tractable setting, we show that training a score model with a one-layer network arch","authors_text":"Giulio Biroli, Luca Maria Del Bono, Marylou Gabri\\'e, Patrick Charbonneau","cross_cats":["cond-mat.stat-mech","cs.AI","cs.LG","physics.comp-ph"],"headline":"Two-layer networks with local score approximation reduce critical slowing down in diffusion models to logarithmic scaling.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-05-12T18:00:02Z","title":"The critical slowing down in diffusion models"},"references":{"count":103,"internal_anchors":1,"resolved_work":103,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"(14) with the Fourier space kernel in Eq","work_id":"571ae045-fc3d-4825-b871-b32e3e243733","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"(22)—the generation dynamics Eq","work_id":"02d93bd8-e575-436b-9940-8634c344ab8a","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"MUR PON Ricerca e Innovazione 2014-2020","work_id":"0948c2cc-3eb4-43b1-a8c9-18b42faf7b23","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"G.Battimelli, G.Ciccotti, P.Greco,andG.Giobbi,Com- puter Meets Theoretical Physics: The New Frontier of Molecular Simulation(Springer, 2020)","work_id":"48304f98-11fa-4ee6-a2d2-991a32303c28","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi, Optimiza- tion by simulated annealing, Science220, 671 (1983)","work_id":"ea890f0e-9948-4b57-b753-a2a2901fe660","year":1983}],"snapshot_sha256":"67e84c09a32c729eda40f42f6f125559590ca7328912d538469d607299ce4738"},"source":{"id":"2605.12597","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:26:53.131007Z","id":"b46391af-3144-4687-bc59-462a9e20b203","model_set":{"reader":"grok-4.3"},"one_line_summary":"Diffusion models on the Gaussian O(n) model exhibit critical slowing down with shallow networks that deeper local score approximations can reduce to logarithmic training-time scaling.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Two-layer networks with local score approximation reduce critical slowing down in diffusion models to logarithmic scaling.","strongest_claim":"Using a two-layer architecture drastically reduces the critical slowing down, with the training time scaling logarithmically rather than quadratically with system size. By introducing a local score approximation we show that this acceleration in training time can be achieved without increasing the number of neural network parameters.","weakest_assumption":"That the Gaussian limit n→∞ of the O(n) model and the one-layer network exactly matching its score function are representative of the critical slowing down that occurs in practical diffusion models trained on finite-n or non-Gaussian systems."}},"verdict_id":"b46391af-3144-4687-bc59-462a9e20b203"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:923197f18360c94470f2a6557d37b40af900a703ce9c53d8fea9d5f6a3abfc36","target":"record","created_at":"2026-05-18T03:10:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"766a3a8d5c285da4726732de0461164764b193fed63f032abd94d4a013a77bac","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","cs.LG","physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-05-12T18:00:02Z","title_canon_sha256":"c0f6406917aebddba081a0761924fa17c9f4e9bd5c12bffc813f279c6bb2b535"},"schema_version":"1.0","source":{"id":"2605.12597","kind":"arxiv","version":1}},"canonical_sha256":"d5d9d14275d080ff76c8e38f8e2237c27f0c457d3f01ecc9ef4dd40fd8a0fa81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5d9d14275d080ff76c8e38f8e2237c27f0c457d3f01ecc9ef4dd40fd8a0fa81","first_computed_at":"2026-05-18T03:10:01.171182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:01.171182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OX9AQ3ICQk3/PwdzFGs1QkIIDRRb0dxf1rZB0Ht0nyup4vg3oWaTCJJRJJD3FE+4E5UL1mDtGzJeHm1jDQ8wCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:01.171682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:923197f18360c94470f2a6557d37b40af900a703ce9c53d8fea9d5f6a3abfc36","sha256:40934e6e3e61ebb0397be1ef62e1ea8fb1607408afa7c2ea06edfc80534033c4"],"state_sha256":"715051cd501173cf0a47ec68f773c8edf229311aaccb4311a632d30a1768d057"}