{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RIPJLQD42T5K3SDKHMIFPWXD5Z","short_pith_number":"pith:RIPJLQD4","schema_version":"1.0","canonical_sha256":"8a1e95c07cd4faadc86a3b1057dae3ee714dc067d02e2996b5b3dd7cbef0e752","source":{"kind":"arxiv","id":"2411.17786","version":1},"attestation_state":"computed","paper":{"title":"DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Diego Valsesia, Emanuele Aiello, Enrico Magli, Mete Ozay, Umberto Michieli","submitted_at":"2024-11-26T15:03:14Z","abstract_excerpt":"Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts. Existing methods face challenges due to complex training requirements, high inference costs, limited flexibility, or a combination of these issues. In this paper, we introduce DreamCache, a scalable approach for efficient and high-quality personalized image generation. By caching a small number of reference image features from a subset of layers and a single timestep of the pretrained diffusion denoiser, Dream"},"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":"2411.17786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T15:03:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"94948e0a87e41382f6d44cf92a56962baf4f7ea98e59c9ee24c1b970ed5ae315","abstract_canon_sha256":"b46b6157785cd48faefed308d9619853286d1ee5d9e360eddb5608db9da6963e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:06.825754Z","signature_b64":"Ncb594S2UCxwJ2zovNmdCLuMjZtEYCvoW4/ImMw+GO/OESWb9gcbQR5y5ikjSwV+N3GWauFhsq4uYcCjhA/PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a1e95c07cd4faadc86a3b1057dae3ee714dc067d02e2996b5b3dd7cbef0e752","last_reissued_at":"2026-07-05T09:41:06.825332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:06.825332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Diego Valsesia, Emanuele Aiello, Enrico Magli, Mete Ozay, Umberto Michieli","submitted_at":"2024-11-26T15:03:14Z","abstract_excerpt":"Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts. Existing methods face challenges due to complex training requirements, high inference costs, limited flexibility, or a combination of these issues. In this paper, we introduce DreamCache, a scalable approach for efficient and high-quality personalized image generation. By caching a small number of reference image features from a subset of layers and a single timestep of the pretrained diffusion denoiser, Dream"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17786","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/2411.17786/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":"2411.17786","created_at":"2026-07-05T09:41:06.825382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17786v1","created_at":"2026-07-05T09:41:06.825382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17786","created_at":"2026-07-05T09:41:06.825382+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIPJLQD42T5K","created_at":"2026-07-05T09:41:06.825382+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIPJLQD42T5K3SDK","created_at":"2026-07-05T09:41:06.825382+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIPJLQD4","created_at":"2026-07-05T09:41:06.825382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.19519","citing_title":"Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z","json":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z.json","graph_json":"https://pith.science/api/pith-number/RIPJLQD42T5K3SDKHMIFPWXD5Z/graph.json","events_json":"https://pith.science/api/pith-number/RIPJLQD42T5K3SDKHMIFPWXD5Z/events.json","paper":"https://pith.science/paper/RIPJLQD4"},"agent_actions":{"view_html":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z","download_json":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z.json","view_paper":"https://pith.science/paper/RIPJLQD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17786&json=true","fetch_graph":"https://pith.science/api/pith-number/RIPJLQD42T5K3SDKHMIFPWXD5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/RIPJLQD42T5K3SDKHMIFPWXD5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z/action/storage_attestation","attest_author":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z/action/author_attestation","sign_citation":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z/action/citation_signature","submit_replication":"https://pith.science/pith/RIPJLQD42T5K3SDKHMIFPWXD5Z/action/replication_record"}},"created_at":"2026-07-05T09:41:06.825382+00:00","updated_at":"2026-07-05T09:41:06.825382+00:00"}