{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2E3RCJDWUTOBD3DQDUKEYI5HLF","short_pith_number":"pith:2E3RCJDW","schema_version":"1.0","canonical_sha256":"d137112476a4dc11ec701d144c23a7594a45081596684663b457cb27b557d419","source":{"kind":"arxiv","id":"2505.11936","version":3},"attestation_state":"computed","paper":{"title":"CCD: Continual Consistency Diffusion for Lifelong Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingren Liu, Shuning Xu, Xiangyu Chen, Yun Wang, Zhong Ji","submitted_at":"2025-05-17T09:49:25Z","abstract_excerpt":"While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constrained by Generative Catastrophic Forgetting (GCF). We observe that even with a rehearsal buffer, new generative skills often overwrite previous ones, degrading performance on earlier tasks. Although some initial efforts have explored this space, most rely on heuristics borrowed from continual classification methods or use trained diffusion models as ad hoc replay generators, lacking a principled, unified solution to miti"},"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":"2505.11936","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T09:49:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cef4438f3046aef7aa49dfa5a36bc1ec044adc3321259816e7e016f23792f16b","abstract_canon_sha256":"f6f098b7a217a9bd58fcfc61da6f0de28e6707bbbd172c0ca35c89864aaaa2d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:36.770276Z","signature_b64":"YOSB87I4cAwqsSlkQLRovtBjn9NIojtbNwzH3OwWO2hny70V4D/Gf35ec04acYtUPx00vIKtp3Lcw9DX76dlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d137112476a4dc11ec701d144c23a7594a45081596684663b457cb27b557d419","last_reissued_at":"2026-07-05T11:57:36.769800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:36.769800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCD: Continual Consistency Diffusion for Lifelong Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingren Liu, Shuning Xu, Xiangyu Chen, Yun Wang, Zhong Ji","submitted_at":"2025-05-17T09:49:25Z","abstract_excerpt":"While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constrained by Generative Catastrophic Forgetting (GCF). We observe that even with a rehearsal buffer, new generative skills often overwrite previous ones, degrading performance on earlier tasks. Although some initial efforts have explored this space, most rely on heuristics borrowed from continual classification methods or use trained diffusion models as ad hoc replay generators, lacking a principled, unified solution to miti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11936","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/2505.11936/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":"2505.11936","created_at":"2026-07-05T11:57:36.769858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11936v3","created_at":"2026-07-05T11:57:36.769858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11936","created_at":"2026-07-05T11:57:36.769858+00:00"},{"alias_kind":"pith_short_12","alias_value":"2E3RCJDWUTOB","created_at":"2026-07-05T11:57:36.769858+00:00"},{"alias_kind":"pith_short_16","alias_value":"2E3RCJDWUTOBD3DQ","created_at":"2026-07-05T11:57:36.769858+00:00"},{"alias_kind":"pith_short_8","alias_value":"2E3RCJDW","created_at":"2026-07-05T11:57:36.769858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF","json":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF.json","graph_json":"https://pith.science/api/pith-number/2E3RCJDWUTOBD3DQDUKEYI5HLF/graph.json","events_json":"https://pith.science/api/pith-number/2E3RCJDWUTOBD3DQDUKEYI5HLF/events.json","paper":"https://pith.science/paper/2E3RCJDW"},"agent_actions":{"view_html":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF","download_json":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF.json","view_paper":"https://pith.science/paper/2E3RCJDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11936&json=true","fetch_graph":"https://pith.science/api/pith-number/2E3RCJDWUTOBD3DQDUKEYI5HLF/graph.json","fetch_events":"https://pith.science/api/pith-number/2E3RCJDWUTOBD3DQDUKEYI5HLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF/action/storage_attestation","attest_author":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF/action/author_attestation","sign_citation":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF/action/citation_signature","submit_replication":"https://pith.science/pith/2E3RCJDWUTOBD3DQDUKEYI5HLF/action/replication_record"}},"created_at":"2026-07-05T11:57:36.769858+00:00","updated_at":"2026-07-05T11:57:36.769858+00:00"}