{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LS7VTBTJW5FXIJIGIVLGZCV4RA","short_pith_number":"pith:LS7VTBTJ","canonical_record":{"source":{"id":"2605.27975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T05:12:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4144d21b9cdf32ebeb452e28a717d21abb02d40e69058ec321a0cebf024f0f8a","abstract_canon_sha256":"c7a4ac2015272dce25404d5de0f160061062bbe7ef9cd85d953f68c5364f0a61"},"schema_version":"1.0"},"canonical_sha256":"5cbf598669b74b74250645566c8abc8835ac7bb1a4d638c3067bdf64aaa6e3c2","source":{"kind":"arxiv","id":"2605.27975","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27975","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27975v1","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27975","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"LS7VTBTJW5FX","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"LS7VTBTJW5FXIJIG","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"LS7VTBTJ","created_at":"2026-05-28T01:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LS7VTBTJW5FXIJIGIVLGZCV4RA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T05:12:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4144d21b9cdf32ebeb452e28a717d21abb02d40e69058ec321a0cebf024f0f8a","abstract_canon_sha256":"c7a4ac2015272dce25404d5de0f160061062bbe7ef9cd85d953f68c5364f0a61"},"schema_version":"1.0"},"canonical_sha256":"5cbf598669b74b74250645566c8abc8835ac7bb1a4d638c3067bdf64aaa6e3c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:54.998799Z","signature_b64":"XJMCmYFSTGk4+txsSI6Lv9SZXF0RRSO9tLcy1c1JjThruja14S6SiVvgrH3H2ztymN5mWwdEFB/AEl6xZGkwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cbf598669b74b74250645566c8abc8835ac7bb1a4d638c3067bdf64aaa6e3c2","last_reissued_at":"2026-05-28T01:04:54.998383Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:54.998383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27975","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":"2026-05-28T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1UmIdkElnvvxukoslynWQKigXGdzrCqc3LRHmwXJHCeEQqfr6DCzV5ryueVexlzp6FwC0hBfFCbv0IaYe+JmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:24:34.581977Z"},"content_sha256":"94db191b02d2a7f59de351d847d9869fe8671db5ddde0e0f89a94ff8dd3f2d6c","schema_version":"1.0","event_id":"sha256:94db191b02d2a7f59de351d847d9869fe8671db5ddde0e0f89a94ff8dd3f2d6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LS7VTBTJW5FXIJIGIVLGZCV4RA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ken Takeda, Masafumi Oizumi, Ryo Karakida","submitted_at":"2026-05-27T05:12:41Z","abstract_excerpt":"Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem setting. However, continual learning in such generative models remains poorly understood: after a task change, what aspects of the learned distribution are most easily lost, and what replay samples should be prioritized? We address these questions through the modern Hopfield energy. Recent links between modern Hopfield networks (MHNs) and diffusion models allow analyses in MHNs to be transferred to diffusion models."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27975","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/2605.27975/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":"2026-05-28T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tgAnix1tNk1xgjxQ15bd9XhMr0jIn0YwHG6jCQBOA08sVr8MJVJOom8u+ZQAaeyjOFOeblbJ/KdRplM4qI7UAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:24:34.582366Z"},"content_sha256":"1f4b99a74ed35c0959c9cbd28322102c06a0f691ed7d592cdfeab3f64909416f","schema_version":"1.0","event_id":"sha256:1f4b99a74ed35c0959c9cbd28322102c06a0f691ed7d592cdfeab3f64909416f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LS7VTBTJW5FXIJIGIVLGZCV4RA/bundle.json","state_url":"https://pith.science/pith/LS7VTBTJW5FXIJIGIVLGZCV4RA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LS7VTBTJW5FXIJIGIVLGZCV4RA/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":"2026-06-01T11:24:34Z","links":{"resolver":"https://pith.science/pith/LS7VTBTJW5FXIJIGIVLGZCV4RA","bundle":"https://pith.science/pith/LS7VTBTJW5FXIJIGIVLGZCV4RA/bundle.json","state":"https://pith.science/pith/LS7VTBTJW5FXIJIGIVLGZCV4RA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LS7VTBTJW5FXIJIGIVLGZCV4RA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LS7VTBTJW5FXIJIGIVLGZCV4RA","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":"c7a4ac2015272dce25404d5de0f160061062bbe7ef9cd85d953f68c5364f0a61","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T05:12:41Z","title_canon_sha256":"4144d21b9cdf32ebeb452e28a717d21abb02d40e69058ec321a0cebf024f0f8a"},"schema_version":"1.0","source":{"id":"2605.27975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27975","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27975v1","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27975","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"LS7VTBTJW5FX","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"LS7VTBTJW5FXIJIG","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"LS7VTBTJ","created_at":"2026-05-28T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:1f4b99a74ed35c0959c9cbd28322102c06a0f691ed7d592cdfeab3f64909416f","target":"graph","created_at":"2026-05-28T01:04:54Z","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/2605.27975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem setting. However, continual learning in such generative models remains poorly understood: after a task change, what aspects of the learned distribution are most easily lost, and what replay samples should be prioritized? We address these questions through the modern Hopfield energy. Recent links between modern Hopfield networks (MHNs) and diffusion models allow analyses in MHNs to be transferred to diffusion models.","authors_text":"Ken Takeda, Masafumi Oizumi, Ryo Karakida","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T05:12:41Z","title":"Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27975","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":"sha256:94db191b02d2a7f59de351d847d9869fe8671db5ddde0e0f89a94ff8dd3f2d6c","target":"record","created_at":"2026-05-28T01:04:54Z","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":"c7a4ac2015272dce25404d5de0f160061062bbe7ef9cd85d953f68c5364f0a61","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T05:12:41Z","title_canon_sha256":"4144d21b9cdf32ebeb452e28a717d21abb02d40e69058ec321a0cebf024f0f8a"},"schema_version":"1.0","source":{"id":"2605.27975","kind":"arxiv","version":1}},"canonical_sha256":"5cbf598669b74b74250645566c8abc8835ac7bb1a4d638c3067bdf64aaa6e3c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cbf598669b74b74250645566c8abc8835ac7bb1a4d638c3067bdf64aaa6e3c2","first_computed_at":"2026-05-28T01:04:54.998383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:54.998383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJMCmYFSTGk4+txsSI6Lv9SZXF0RRSO9tLcy1c1JjThruja14S6SiVvgrH3H2ztymN5mWwdEFB/AEl6xZGkwAA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:54.998799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94db191b02d2a7f59de351d847d9869fe8671db5ddde0e0f89a94ff8dd3f2d6c","sha256:1f4b99a74ed35c0959c9cbd28322102c06a0f691ed7d592cdfeab3f64909416f"],"state_sha256":"18dda64f561b7be760cf378b9d286d1f78940a129922bcfca5c5c3fa301b6fef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FlTGhT6EFmMy/3j47rqgxOJHq1Kk64D/kMcdP8+J/PtMIibiZZ9ix1kpvs6zqfBN21U7fyXXQs+BbsUzibNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T11:24:34.584339Z","bundle_sha256":"1e40b5622f1d50f94f821db0173302e376eda66d855b1f0e9d63c967752f093f"}}