{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U7IRHESR4ZRZBCV4Q6EMMCG3AP","short_pith_number":"pith:U7IRHESR","schema_version":"1.0","canonical_sha256":"a7d1139251e663908abc8788c608db03cf87b6d161ef4da26524a698bb2991dc","source":{"kind":"arxiv","id":"2412.17762","version":2},"attestation_state":"computed","paper":{"title":"The Superposition of Diffusion Models Using the It\\^o Density Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Tong, Avishek Joey Bose, Kirill Neklyudov, Lazar Atanackovic, Marta Skreta","submitted_at":"2024-12-23T18:18:07Z","abstract_excerpt":"The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant computational burden of re-training a larger combined model. In this paper, we cast the problem of combining multiple pre-trained diffusion models at the generation stage under a novel proposed framework termed superposition. Theoretically, we derive superposition from rigorous first principles stemming from the celebrated continuity equation and design two novel algorithms tailor-made for combining"},"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":"2412.17762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T18:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"d295cdcea4089c068868b58d76ab503b9f467727fb9e0c671eba3d1b22685337","abstract_canon_sha256":"5e0988676e764e9078be51217fd8fd745b32dee3cc88d409bb0fc2b2c1904a4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:11.351445Z","signature_b64":"XcKAqk0wiJTCdyzppZ3OTJtFRPpNWmmEYOv7u7HjCQ/GJVW2J7lmBLwcwfdx9UW206YYLtzeamMPp70i8M2bDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7d1139251e663908abc8788c608db03cf87b6d161ef4da26524a698bb2991dc","last_reissued_at":"2026-07-05T10:22:11.350817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:11.350817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Superposition of Diffusion Models Using the It\\^o Density Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Tong, Avishek Joey Bose, Kirill Neklyudov, Lazar Atanackovic, Marta Skreta","submitted_at":"2024-12-23T18:18:07Z","abstract_excerpt":"The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant computational burden of re-training a larger combined model. In this paper, we cast the problem of combining multiple pre-trained diffusion models at the generation stage under a novel proposed framework termed superposition. Theoretically, we derive superposition from rigorous first principles stemming from the celebrated continuity equation and design two novel algorithms tailor-made for combining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17762","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/2412.17762/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":"2412.17762","created_at":"2026-07-05T10:22:11.350879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17762v2","created_at":"2026-07-05T10:22:11.350879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17762","created_at":"2026-07-05T10:22:11.350879+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7IRHESR4ZRZ","created_at":"2026-07-05T10:22:11.350879+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7IRHESR4ZRZBCV4","created_at":"2026-07-05T10:22:11.350879+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7IRHESR","created_at":"2026-07-05T10:22:11.350879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.20549","citing_title":"Sample-efficient evidence estimation of score based priors for model selection","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21066","citing_title":"Optimizing Diffusion Priors in Image Reconstruction from a Single Observation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP","json":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP.json","graph_json":"https://pith.science/api/pith-number/U7IRHESR4ZRZBCV4Q6EMMCG3AP/graph.json","events_json":"https://pith.science/api/pith-number/U7IRHESR4ZRZBCV4Q6EMMCG3AP/events.json","paper":"https://pith.science/paper/U7IRHESR"},"agent_actions":{"view_html":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP","download_json":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP.json","view_paper":"https://pith.science/paper/U7IRHESR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17762&json=true","fetch_graph":"https://pith.science/api/pith-number/U7IRHESR4ZRZBCV4Q6EMMCG3AP/graph.json","fetch_events":"https://pith.science/api/pith-number/U7IRHESR4ZRZBCV4Q6EMMCG3AP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP/action/storage_attestation","attest_author":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP/action/author_attestation","sign_citation":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP/action/citation_signature","submit_replication":"https://pith.science/pith/U7IRHESR4ZRZBCV4Q6EMMCG3AP/action/replication_record"}},"created_at":"2026-07-05T10:22:11.350879+00:00","updated_at":"2026-07-05T10:22:11.350879+00:00"}