{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TNY6MG6JB7XU5PDFFTE7KL3KKN","short_pith_number":"pith:TNY6MG6J","schema_version":"1.0","canonical_sha256":"9b71e61bc90fef4ebc652cc9f52f6a5352e4064694b9280f4a4f6000f51d940e","source":{"kind":"arxiv","id":"2205.15463","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Didrik Nielsen, Giorgio Giannone, Ole Winther","submitted_at":"2022-05-30T23:20:33Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable models with remarkable sample generation quality and training stability. These properties can be attributed to parameter sharing in the generative hierarchy, as well as a parameter-free diffusion-based inference procedure. In this paper, we present Few-Shot Diffusion Models (FSDM), a framework for few-shot generation leveraging conditional DDPMs. FSDMs are trained to adapt the generative process conditioned on a small set of images from a given class by aggregating image patch information using a set-base"},"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":"2205.15463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T23:20:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f0060d253523440ff7a0abdded8d550b1b0f9ced78a258f2cf60c4fe046552c3","abstract_canon_sha256":"e41aaef5b2fe6ff377dd92f8dc8b9c9030a7bcd33d0a0bfca8cbfd12d27536a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:33.076122Z","signature_b64":"7F7g8CMdiH2YQ9EM3lHGGNJhDDNUSEmH3kcIhWnoHomgwFzQZXEuXdSjbilQ+0Mzon707BRCfGVUkwYn8YLwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b71e61bc90fef4ebc652cc9f52f6a5352e4064694b9280f4a4f6000f51d940e","last_reissued_at":"2026-07-05T04:27:33.075675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:33.075675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Didrik Nielsen, Giorgio Giannone, Ole Winther","submitted_at":"2022-05-30T23:20:33Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable models with remarkable sample generation quality and training stability. These properties can be attributed to parameter sharing in the generative hierarchy, as well as a parameter-free diffusion-based inference procedure. In this paper, we present Few-Shot Diffusion Models (FSDM), a framework for few-shot generation leveraging conditional DDPMs. FSDMs are trained to adapt the generative process conditioned on a small set of images from a given class by aggregating image patch information using a set-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15463","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/2205.15463/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":"2205.15463","created_at":"2026-07-05T04:27:33.075741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15463v1","created_at":"2026-07-05T04:27:33.075741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15463","created_at":"2026-07-05T04:27:33.075741+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNY6MG6JB7XU","created_at":"2026-07-05T04:27:33.075741+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNY6MG6JB7XU5PDF","created_at":"2026-07-05T04:27:33.075741+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNY6MG6J","created_at":"2026-07-05T04:27:33.075741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13386","citing_title":"Support-Conditioned Flow Matching Is Kernel Smoothing","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN","json":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN.json","graph_json":"https://pith.science/api/pith-number/TNY6MG6JB7XU5PDFFTE7KL3KKN/graph.json","events_json":"https://pith.science/api/pith-number/TNY6MG6JB7XU5PDFFTE7KL3KKN/events.json","paper":"https://pith.science/paper/TNY6MG6J"},"agent_actions":{"view_html":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN","download_json":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN.json","view_paper":"https://pith.science/paper/TNY6MG6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15463&json=true","fetch_graph":"https://pith.science/api/pith-number/TNY6MG6JB7XU5PDFFTE7KL3KKN/graph.json","fetch_events":"https://pith.science/api/pith-number/TNY6MG6JB7XU5PDFFTE7KL3KKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN/action/storage_attestation","attest_author":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN/action/author_attestation","sign_citation":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN/action/citation_signature","submit_replication":"https://pith.science/pith/TNY6MG6JB7XU5PDFFTE7KL3KKN/action/replication_record"}},"created_at":"2026-07-05T04:27:33.075741+00:00","updated_at":"2026-07-05T04:27:33.075741+00:00"}