{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AJ54QZ3RRMC57RFR4QHUW5T34F","short_pith_number":"pith:AJ54QZ3R","canonical_record":{"source":{"id":"2402.08082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-12T22:02:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"26050566682d2156c7763027934b899cf3fc256c74910eddaf1b7f1e09cc73ac","abstract_canon_sha256":"14e2467d23c577d7f5732b50871bd103cd0465f0e0edbb371ebd05302ac07d1e"},"schema_version":"1.0"},"canonical_sha256":"027bc867718b05dfc4b1e40f4b767be15934e40048646406466dfb7947642d9b","source":{"kind":"arxiv","id":"2402.08082","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08082","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08082v3","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08082","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"AJ54QZ3RRMC5","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"AJ54QZ3RRMC57RFR","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"AJ54QZ3R","created_at":"2026-07-05T07:48:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AJ54QZ3RRMC57RFR4QHUW5T34F","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-12T22:02:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"26050566682d2156c7763027934b899cf3fc256c74910eddaf1b7f1e09cc73ac","abstract_canon_sha256":"14e2467d23c577d7f5732b50871bd103cd0465f0e0edbb371ebd05302ac07d1e"},"schema_version":"1.0"},"canonical_sha256":"027bc867718b05dfc4b1e40f4b767be15934e40048646406466dfb7947642d9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:34.545677Z","signature_b64":"6N+xDp+j3d1kdah7aoL/sbxKVIZ4szZzaWSjoNvwXIWjLWuJjtudnf7FYvOMvwFKobbcVYisu5+WOz1/urOdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027bc867718b05dfc4b1e40f4b767be15934e40048646406466dfb7947642d9b","last_reissued_at":"2026-07-05T07:48:34.545102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:34.545102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08082","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nDOanCmgxrOCVuWKs9DZ4gFFNVj/Pc4BsNXRj0btR6JiZoK5BU807+BLIqx4vm86w3p2ghcFvdDwBllsPO0nBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:25:18.098342Z"},"content_sha256":"38f475226285088cec3ae8cdefc4d7d972c739b05ea35c15bd1d3d6515fb6573","schema_version":"1.0","event_id":"sha256:38f475226285088cec3ae8cdefc4d7d972c739b05ea35c15bd1d3d6515fb6573"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AJ54QZ3RRMC57RFR4QHUW5T34F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian probability distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Frank Cole, Yulong Lu","submitted_at":"2024-02-12T22:02:23Z","abstract_excerpt":"While score-based generative models (SGMs) have achieved remarkable success in enormous image generation tasks, their mathematical foundations are still limited. In this paper, we analyze the approximation and generalization of SGMs in learning a family of sub-Gaussian probability distributions. We introduce a notion of complexity for probability distributions in terms of their relative density with respect to the standard Gaussian measure. We prove that if the log-relative density can be locally approximated by a neural network whose parameters can be suitably bounded, then the distribution g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08082","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/2402.08082/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZJK9MWwcD5IUPuYpa0y1wE2AT6Rt+zP+swoGXcXSUwlYXCy5o6TL6ryrGR0zzG4d8OwimCXX66P2PY1ZYvk/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:25:18.099242Z"},"content_sha256":"ea0a7371674cef1f545aebd4df2d19027e423f49967f1856db5ca16936f44950","schema_version":"1.0","event_id":"sha256:ea0a7371674cef1f545aebd4df2d19027e423f49967f1856db5ca16936f44950"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJ54QZ3RRMC57RFR4QHUW5T34F/bundle.json","state_url":"https://pith.science/pith/AJ54QZ3RRMC57RFR4QHUW5T34F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJ54QZ3RRMC57RFR4QHUW5T34F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T18:25:18Z","links":{"resolver":"https://pith.science/pith/AJ54QZ3RRMC57RFR4QHUW5T34F","bundle":"https://pith.science/pith/AJ54QZ3RRMC57RFR4QHUW5T34F/bundle.json","state":"https://pith.science/pith/AJ54QZ3RRMC57RFR4QHUW5T34F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJ54QZ3RRMC57RFR4QHUW5T34F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AJ54QZ3RRMC57RFR4QHUW5T34F","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":"14e2467d23c577d7f5732b50871bd103cd0465f0e0edbb371ebd05302ac07d1e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-12T22:02:23Z","title_canon_sha256":"26050566682d2156c7763027934b899cf3fc256c74910eddaf1b7f1e09cc73ac"},"schema_version":"1.0","source":{"id":"2402.08082","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08082","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08082v3","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08082","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"AJ54QZ3RRMC5","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"AJ54QZ3RRMC57RFR","created_at":"2026-07-05T07:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"AJ54QZ3R","created_at":"2026-07-05T07:48:34Z"}],"graph_snapshots":[{"event_id":"sha256:ea0a7371674cef1f545aebd4df2d19027e423f49967f1856db5ca16936f44950","target":"graph","created_at":"2026-07-05T07:48:34Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.08082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While score-based generative models (SGMs) have achieved remarkable success in enormous image generation tasks, their mathematical foundations are still limited. In this paper, we analyze the approximation and generalization of SGMs in learning a family of sub-Gaussian probability distributions. We introduce a notion of complexity for probability distributions in terms of their relative density with respect to the standard Gaussian measure. We prove that if the log-relative density can be locally approximated by a neural network whose parameters can be suitably bounded, then the distribution g","authors_text":"Frank Cole, Yulong Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-12T22:02:23Z","title":"Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian probability distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08082","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:38f475226285088cec3ae8cdefc4d7d972c739b05ea35c15bd1d3d6515fb6573","target":"record","created_at":"2026-07-05T07:48:34Z","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":"14e2467d23c577d7f5732b50871bd103cd0465f0e0edbb371ebd05302ac07d1e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-12T22:02:23Z","title_canon_sha256":"26050566682d2156c7763027934b899cf3fc256c74910eddaf1b7f1e09cc73ac"},"schema_version":"1.0","source":{"id":"2402.08082","kind":"arxiv","version":3}},"canonical_sha256":"027bc867718b05dfc4b1e40f4b767be15934e40048646406466dfb7947642d9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"027bc867718b05dfc4b1e40f4b767be15934e40048646406466dfb7947642d9b","first_computed_at":"2026-07-05T07:48:34.545102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:34.545102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6N+xDp+j3d1kdah7aoL/sbxKVIZ4szZzaWSjoNvwXIWjLWuJjtudnf7FYvOMvwFKobbcVYisu5+WOz1/urOdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:34.545677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08082","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38f475226285088cec3ae8cdefc4d7d972c739b05ea35c15bd1d3d6515fb6573","sha256:ea0a7371674cef1f545aebd4df2d19027e423f49967f1856db5ca16936f44950"],"state_sha256":"333045dd1447d685e43fafe4bd955505a7f303524a797fd2096890ebaf07f1a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wq/t8Nd3L8sDL3CsgAHxxS9kZoArMhnzhQ+bX3ADrxaqCA9Kplk/JenABjTS9Wek2ciPtJjN2pU995f2TjhYCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:25:18.108295Z","bundle_sha256":"4839ac582c67e0c5eb7612042f2199c2dada64cf88ff4548c8554ba2f365e255"}}