{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KLPQSYFTTAOMX3NQD4P5HIUFOY","short_pith_number":"pith:KLPQSYFT","canonical_record":{"source":{"id":"2603.12901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-13T11:07:01Z","cross_cats_sorted":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"1e96804b1adcd5afc71a4a382bc4289c9e1040d6dd44a992d17a0615d01d3940","abstract_canon_sha256":"8148d4f2d20641b0afa4526c6f507da2bd55cbfa3df61af5b9e54e520885feba"},"schema_version":"1.0"},"canonical_sha256":"52df0960b3981ccbedb01f1fd3a2857626797fbf4c887b29a5ff3145ae1ddfe7","source":{"kind":"arxiv","id":"2603.12901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.12901","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2603.12901v1","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12901","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"KLPQSYFTTAOM","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"KLPQSYFTTAOMX3NQ","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"KLPQSYFT","created_at":"2026-05-21T02:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KLPQSYFTTAOMX3NQD4P5HIUFOY","target":"record","payload":{"canonical_record":{"source":{"id":"2603.12901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-13T11:07:01Z","cross_cats_sorted":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"1e96804b1adcd5afc71a4a382bc4289c9e1040d6dd44a992d17a0615d01d3940","abstract_canon_sha256":"8148d4f2d20641b0afa4526c6f507da2bd55cbfa3df61af5b9e54e520885feba"},"schema_version":"1.0"},"canonical_sha256":"52df0960b3981ccbedb01f1fd3a2857626797fbf4c887b29a5ff3145ae1ddfe7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:00.972041Z","signature_b64":"Ckg7UwvY/KrKbEi5uWwf4Xn6zBNxpdnIf44GIswPf/o+NV7wN8YgPsy9vYPEBCkWjz7MUfzrlAOBjSg8eUWtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52df0960b3981ccbedb01f1fd3a2857626797fbf4c887b29a5ff3145ae1ddfe7","last_reissued_at":"2026-05-21T02:05:00.971207Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:00.971207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.12901","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"igkyQhSke67+K3mLJQePnxhKUwKqW+Fh3TfDW2EkOom+4BOQBbOT6Rkgpamz2IMUStHLcPoApHzmAZo/NJBsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:52:44.763224Z"},"content_sha256":"e5dd35dadc761b9fa9edee8d717e8d21754d7326b1d0074f151ad537114289c9","schema_version":"1.0","event_id":"sha256:e5dd35dadc761b9fa9edee8d717e8d21754d7326b1d0074f151ad537114289c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KLPQSYFTTAOMX3NQD4P5HIUFOY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A theory of learning data statistics in diffusion models, from easy to hard","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Claudia Merger, Lorenzo Bardone, Sebastian Goldt","submitted_at":"2026-03-13T11:07:01Z","abstract_excerpt":"While diffusion models have emerged as a powerful class of generative models, their learning dynamics remain poorly understood. We address this issue first by empirically showing that standard diffusion models trained on natural images exhibit a distributional simplicity bias, learning simple, pair-wise input statistics before specializing to higher-order correlations. We reproduce this behaviour in simple denoisers trained on a minimal data model, the mixed cumulant model, where we precisely control both pair-wise and higher-order correlations of the inputs. We identify a scalar invariant of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.12901","kind":"arxiv","version":1},"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/2603.12901/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":"2026-05-21T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jD+PXki5Vj4LmzwT0nDeUk59QS811hUy56RD21gH/91epVwAkOVZAr4daJAbFiYDnIJ92EXLn54KcSQtPbBEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:52:44.763928Z"},"content_sha256":"2682daaa112e72cedae8d5151e86383d25fa6a4f20ea93387838bb9766ba14e2","schema_version":"1.0","event_id":"sha256:2682daaa112e72cedae8d5151e86383d25fa6a4f20ea93387838bb9766ba14e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLPQSYFTTAOMX3NQD4P5HIUFOY/bundle.json","state_url":"https://pith.science/pith/KLPQSYFTTAOMX3NQD4P5HIUFOY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLPQSYFTTAOMX3NQD4P5HIUFOY/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":"2026-05-25T21:52:44Z","links":{"resolver":"https://pith.science/pith/KLPQSYFTTAOMX3NQD4P5HIUFOY","bundle":"https://pith.science/pith/KLPQSYFTTAOMX3NQD4P5HIUFOY/bundle.json","state":"https://pith.science/pith/KLPQSYFTTAOMX3NQD4P5HIUFOY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLPQSYFTTAOMX3NQD4P5HIUFOY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KLPQSYFTTAOMX3NQD4P5HIUFOY","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":"8148d4f2d20641b0afa4526c6f507da2bd55cbfa3df61af5b9e54e520885feba","cross_cats_sorted":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-13T11:07:01Z","title_canon_sha256":"1e96804b1adcd5afc71a4a382bc4289c9e1040d6dd44a992d17a0615d01d3940"},"schema_version":"1.0","source":{"id":"2603.12901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.12901","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2603.12901v1","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12901","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"KLPQSYFTTAOM","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"KLPQSYFTTAOMX3NQ","created_at":"2026-05-21T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"KLPQSYFT","created_at":"2026-05-21T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:2682daaa112e72cedae8d5151e86383d25fa6a4f20ea93387838bb9766ba14e2","target":"graph","created_at":"2026-05-21T02:05:00Z","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/2603.12901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While diffusion models have emerged as a powerful class of generative models, their learning dynamics remain poorly understood. We address this issue first by empirically showing that standard diffusion models trained on natural images exhibit a distributional simplicity bias, learning simple, pair-wise input statistics before specializing to higher-order correlations. We reproduce this behaviour in simple denoisers trained on a minimal data model, the mixed cumulant model, where we precisely control both pair-wise and higher-order correlations of the inputs. We identify a scalar invariant of ","authors_text":"Claudia Merger, Lorenzo Bardone, Sebastian Goldt","cross_cats":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-13T11:07:01Z","title":"A theory of learning data statistics in diffusion models, from easy to hard"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.12901","kind":"arxiv","version":1},"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:e5dd35dadc761b9fa9edee8d717e8d21754d7326b1d0074f151ad537114289c9","target":"record","created_at":"2026-05-21T02:05:00Z","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":"8148d4f2d20641b0afa4526c6f507da2bd55cbfa3df61af5b9e54e520885feba","cross_cats_sorted":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-13T11:07:01Z","title_canon_sha256":"1e96804b1adcd5afc71a4a382bc4289c9e1040d6dd44a992d17a0615d01d3940"},"schema_version":"1.0","source":{"id":"2603.12901","kind":"arxiv","version":1}},"canonical_sha256":"52df0960b3981ccbedb01f1fd3a2857626797fbf4c887b29a5ff3145ae1ddfe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52df0960b3981ccbedb01f1fd3a2857626797fbf4c887b29a5ff3145ae1ddfe7","first_computed_at":"2026-05-21T02:05:00.971207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:00.971207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ckg7UwvY/KrKbEi5uWwf4Xn6zBNxpdnIf44GIswPf/o+NV7wN8YgPsy9vYPEBCkWjz7MUfzrlAOBjSg8eUWtAw==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:00.972041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.12901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5dd35dadc761b9fa9edee8d717e8d21754d7326b1d0074f151ad537114289c9","sha256:2682daaa112e72cedae8d5151e86383d25fa6a4f20ea93387838bb9766ba14e2"],"state_sha256":"54407690dd9d0395d18ab799b3ea8893a1ecb46b5b4b04dcec33c6b79e7ae300"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xI3MAi09O1Zjfi4vV/JwFnozZBhoNghlZWdaSsMuvY1z/X0W+g7lbvBRHEtWyJUprbyFT7c9/GIF5Y9jvI3AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:52:44.767565Z","bundle_sha256":"50bc274470ab0a6608212692e4aca61a24bc61cb816bec89b2e457ed186484f2"}}