{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PZ666CUP3ZEWGJH422W2SZ2CZA","short_pith_number":"pith:PZ666CUP","schema_version":"1.0","canonical_sha256":"7e7def0a8fde496324fcd6ada96742c82ebbba2ee5bc14d16bc059d62e7979ac","source":{"kind":"arxiv","id":"2410.21212","version":2},"attestation_state":"computed","paper":{"title":"On learning higher-order cumulants in diffusion models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"hep-lat","authors_text":"Diaa E. Habibi, Gert Aarts, Kai Zhou, Lingxiao Wang","submitted_at":"2024-10-28T16:57:02Z","abstract_excerpt":"To analyse how diffusion models learn correlations beyond Gaussian ones, we study the behaviour of higher-order cumulants, or connected n-point functions, under both the forward and backward process. We derive explicit expressions for the moment- and cumulant-generating functionals, in terms of the distribution of the initial data and properties of forward process. It is shown analytically that during the forward process higher-order cumulants are conserved in models without a drift, such as the variance-expanding scheme, and that therefore the endpoint of the forward process maintains nontriv"},"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":"2410.21212","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-lat","submitted_at":"2024-10-28T16:57:02Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"eab7cc97f266dede71acd7c3e126354d8fbe2e40c6999fb0083f3a2a61cfda54","abstract_canon_sha256":"c314a6ec4457d0c939f7ea5f46e8dfeee3fb9c62f84786124628e4e57d312377"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:19.048997Z","signature_b64":"qvxp54n7P4nzkOegDc+zMYUDSXQxCC5T/bjkGTXvhJ7oMD4F8VyK4PMEiJPt2oACUcx6HFwakRWrpk7+4c8GCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e7def0a8fde496324fcd6ada96742c82ebbba2ee5bc14d16bc059d62e7979ac","last_reissued_at":"2026-07-05T10:44:19.048490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:19.048490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On learning higher-order cumulants in diffusion models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"hep-lat","authors_text":"Diaa E. Habibi, Gert Aarts, Kai Zhou, Lingxiao Wang","submitted_at":"2024-10-28T16:57:02Z","abstract_excerpt":"To analyse how diffusion models learn correlations beyond Gaussian ones, we study the behaviour of higher-order cumulants, or connected n-point functions, under both the forward and backward process. We derive explicit expressions for the moment- and cumulant-generating functionals, in terms of the distribution of the initial data and properties of forward process. It is shown analytically that during the forward process higher-order cumulants are conserved in models without a drift, such as the variance-expanding scheme, and that therefore the endpoint of the forward process maintains nontriv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21212","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/2410.21212/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":"2410.21212","created_at":"2026-07-05T10:44:19.048556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21212v2","created_at":"2026-07-05T10:44:19.048556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21212","created_at":"2026-07-05T10:44:19.048556+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZ666CUP3ZEW","created_at":"2026-07-05T10:44:19.048556+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZ666CUP3ZEWGJH4","created_at":"2026-07-05T10:44:19.048556+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZ666CUP","created_at":"2026-07-05T10:44:19.048556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08505","citing_title":"Diffusion Models for Sampling Near Criticality in Lattice Field Theories","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2510.25704","citing_title":"Scaling flow-based approaches for topology sampling in $\\mathrm{SU}(3)$ gauge theory","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA","json":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA.json","graph_json":"https://pith.science/api/pith-number/PZ666CUP3ZEWGJH422W2SZ2CZA/graph.json","events_json":"https://pith.science/api/pith-number/PZ666CUP3ZEWGJH422W2SZ2CZA/events.json","paper":"https://pith.science/paper/PZ666CUP"},"agent_actions":{"view_html":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA","download_json":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA.json","view_paper":"https://pith.science/paper/PZ666CUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21212&json=true","fetch_graph":"https://pith.science/api/pith-number/PZ666CUP3ZEWGJH422W2SZ2CZA/graph.json","fetch_events":"https://pith.science/api/pith-number/PZ666CUP3ZEWGJH422W2SZ2CZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA/action/storage_attestation","attest_author":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA/action/author_attestation","sign_citation":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA/action/citation_signature","submit_replication":"https://pith.science/pith/PZ666CUP3ZEWGJH422W2SZ2CZA/action/replication_record"}},"created_at":"2026-07-05T10:44:19.048556+00:00","updated_at":"2026-07-05T10:44:19.048556+00:00"}