{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XTBB3PJ7HXE2UUI6MYTAAZ6KZF","short_pith_number":"pith:XTBB3PJ7","schema_version":"1.0","canonical_sha256":"bcc21dbd3f3dc9aa511e66260067cac976d2f9dcea39caee68e369435ee7d5d8","source":{"kind":"arxiv","id":"2212.10777","version":4},"attestation_state":"computed","paper":{"title":"Hierarchically branched diffusion models leverage dataset structure for class-conditional generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex M. Tseng, Gabriele Scalia, Max Shen, Tommaso Biancalani","submitted_at":"2022-12-21T05:27:23Z","abstract_excerpt":"Class-labeled datasets, particularly those common in scientific domains, are rife with internal structure, yet current class-conditional diffusion models ignore these relationships and implicitly diffuse on all classes in a flat fashion. To leverage this structure, we propose hierarchically branched diffusion models as a novel framework for class-conditional generation. Branched diffusion models rely on the same diffusion process as traditional models, but learn reverse diffusion separately for each branch of a hierarchy. We highlight several advantages of branched diffusion models over the cu"},"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":"2212.10777","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-21T05:27:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa371d1a39ec6b9c7c4c2620ba365214ddf4c39c743e474b351f5f7c57d8e0c5","abstract_canon_sha256":"5aa574f62199fc0ee33fc2c9600f2b36288fce705010a4858a9e6033978975f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:20.232563Z","signature_b64":"GH+Yuy25+TGW9rZwIon+6uAlBVamAUtLL8Dpa8DR515ocPFlGI378H0j+HsR0tgC/Y61I1b6OH0icA2OzCCBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcc21dbd3f3dc9aa511e66260067cac976d2f9dcea39caee68e369435ee7d5d8","last_reissued_at":"2026-07-05T07:40:20.232153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:20.232153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchically branched diffusion models leverage dataset structure for class-conditional generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex M. Tseng, Gabriele Scalia, Max Shen, Tommaso Biancalani","submitted_at":"2022-12-21T05:27:23Z","abstract_excerpt":"Class-labeled datasets, particularly those common in scientific domains, are rife with internal structure, yet current class-conditional diffusion models ignore these relationships and implicitly diffuse on all classes in a flat fashion. To leverage this structure, we propose hierarchically branched diffusion models as a novel framework for class-conditional generation. Branched diffusion models rely on the same diffusion process as traditional models, but learn reverse diffusion separately for each branch of a hierarchy. We highlight several advantages of branched diffusion models over the cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10777","kind":"arxiv","version":4},"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/2212.10777/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":"2212.10777","created_at":"2026-07-05T07:40:20.232218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10777v4","created_at":"2026-07-05T07:40:20.232218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10777","created_at":"2026-07-05T07:40:20.232218+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTBB3PJ7HXE2","created_at":"2026-07-05T07:40:20.232218+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTBB3PJ7HXE2UUI6","created_at":"2026-07-05T07:40:20.232218+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTBB3PJ7","created_at":"2026-07-05T07:40:20.232218+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/XTBB3PJ7HXE2UUI6MYTAAZ6KZF","json":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF.json","graph_json":"https://pith.science/api/pith-number/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/graph.json","events_json":"https://pith.science/api/pith-number/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/events.json","paper":"https://pith.science/paper/XTBB3PJ7"},"agent_actions":{"view_html":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF","download_json":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF.json","view_paper":"https://pith.science/paper/XTBB3PJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10777&json=true","fetch_graph":"https://pith.science/api/pith-number/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/graph.json","fetch_events":"https://pith.science/api/pith-number/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/action/storage_attestation","attest_author":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/action/author_attestation","sign_citation":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/action/citation_signature","submit_replication":"https://pith.science/pith/XTBB3PJ7HXE2UUI6MYTAAZ6KZF/action/replication_record"}},"created_at":"2026-07-05T07:40:20.232218+00:00","updated_at":"2026-07-05T07:40:20.232218+00:00"}