{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ARV33IV7CJN3OJTPVJQ243QPQX","short_pith_number":"pith:ARV33IV7","schema_version":"1.0","canonical_sha256":"046bbda2bf125bb7266faa61ae6e0f85f4cb8871ca7cf206761d1aa9cce9775e","source":{"kind":"arxiv","id":"2210.12100","version":2},"attestation_state":"computed","paper":{"title":"Boomerang: Local sampling on image manifolds using diffusion models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ali Siahkoohi, Josue Casco-Rodriguez, Lorenzo Luzi, Paul M Mayer, Richard G. Baraniuk","submitted_at":"2022-10-21T16:52:16Z","abstract_excerpt":"The inference stage of diffusion models can be seen as running a reverse-time diffusion stochastic differential equation, where samples from a Gaussian latent distribution are transformed into samples from a target distribution that usually reside on a low-dimensional manifold, e.g., an image manifold. The intermediate values between the initial latent space and the image manifold can be interpreted as noisy images, with the amount of noise determined by the forward diffusion process noise schedule. We utilize this interpretation to present Boomerang, an approach for local sampling of image ma"},"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":"2210.12100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-21T16:52:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"8db45ba83d792dad4ac813a18d55620e50b457bb1b95c78e311bee656ef9d550","abstract_canon_sha256":"4eda0bc478828f181942589f1145859970ee0cbe9a43be8115adccbcfb0d062b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:11.415376Z","signature_b64":"XbTt1tVOZ1w2Pzm8BDu0egkAS9fMYWXnOPn9SQ4fPIz+iyt+6PsLbXT/THjDJr0lH4Sm2s70rWtO4j1M2GLoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"046bbda2bf125bb7266faa61ae6e0f85f4cb8871ca7cf206761d1aa9cce9775e","last_reissued_at":"2026-07-05T08:09:11.414884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:11.414884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boomerang: Local sampling on image manifolds using diffusion models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ali Siahkoohi, Josue Casco-Rodriguez, Lorenzo Luzi, Paul M Mayer, Richard G. Baraniuk","submitted_at":"2022-10-21T16:52:16Z","abstract_excerpt":"The inference stage of diffusion models can be seen as running a reverse-time diffusion stochastic differential equation, where samples from a Gaussian latent distribution are transformed into samples from a target distribution that usually reside on a low-dimensional manifold, e.g., an image manifold. The intermediate values between the initial latent space and the image manifold can be interpreted as noisy images, with the amount of noise determined by the forward diffusion process noise schedule. We utilize this interpretation to present Boomerang, an approach for local sampling of image ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12100","kind":"arxiv","version":2},"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/2210.12100/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":"2210.12100","created_at":"2026-07-05T08:09:11.414942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12100v2","created_at":"2026-07-05T08:09:11.414942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12100","created_at":"2026-07-05T08:09:11.414942+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARV33IV7CJN3","created_at":"2026-07-05T08:09:11.414942+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARV33IV7CJN3OJTP","created_at":"2026-07-05T08:09:11.414942+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARV33IV7","created_at":"2026-07-05T08:09:11.414942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24238","citing_title":"GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX","json":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX.json","graph_json":"https://pith.science/api/pith-number/ARV33IV7CJN3OJTPVJQ243QPQX/graph.json","events_json":"https://pith.science/api/pith-number/ARV33IV7CJN3OJTPVJQ243QPQX/events.json","paper":"https://pith.science/paper/ARV33IV7"},"agent_actions":{"view_html":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX","download_json":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX.json","view_paper":"https://pith.science/paper/ARV33IV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12100&json=true","fetch_graph":"https://pith.science/api/pith-number/ARV33IV7CJN3OJTPVJQ243QPQX/graph.json","fetch_events":"https://pith.science/api/pith-number/ARV33IV7CJN3OJTPVJQ243QPQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX/action/storage_attestation","attest_author":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX/action/author_attestation","sign_citation":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX/action/citation_signature","submit_replication":"https://pith.science/pith/ARV33IV7CJN3OJTPVJQ243QPQX/action/replication_record"}},"created_at":"2026-07-05T08:09:11.414942+00:00","updated_at":"2026-07-05T08:09:11.414942+00:00"}