{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KBL4AVIN3WWQVMU6INJCP4AY2V","short_pith_number":"pith:KBL4AVIN","schema_version":"1.0","canonical_sha256":"5057c0550dddad0ab29e435227f018d57699d480b45b173b8ccd4c86df726ffc","source":{"kind":"arxiv","id":"2306.04542","version":4},"attestation_state":"computed","paper":{"title":"On the Design Fundamentals of Diffusion Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"George Alex Koulieris, Hubert P. H. Shum, Hyung Jin Chang, Ziyi Chang","submitted_at":"2023-06-07T15:46:47Z","abstract_excerpt":"Diffusion models are learning pattern-learning systems to model and sample from data distributions with three functional components namely the forward process, the reverse process, and the sampling process. The components of diffusion models have gained significant attention with many design factors being considered in common practice. Existing reviews have primarily focused on higher-level solutions, covering less on the design fundamentals of components. This study seeks to address this gap by providing a comprehensive and coherent review of seminal designable factors within each functional "},"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":"2306.04542","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T15:46:47Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"32d776ad6ef0556149985087b583e6a29fbd0b44c6ef556af75c053332225ea4","abstract_canon_sha256":"64cd6bba808248e8b915156ceea8002eb1566b698a14f7ed9aef7e464b0e9c2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:15.283378Z","signature_b64":"/jBSrdAKzmpOWep3yg+R1CQ4mKGggFzI/zNKxqWg+yBD5scO65rNU/lL7egDfhiR+A4sQl/5UdvHIzklyo91AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5057c0550dddad0ab29e435227f018d57699d480b45b173b8ccd4c86df726ffc","last_reissued_at":"2026-07-05T11:12:15.282919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:15.282919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Design Fundamentals of Diffusion Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"George Alex Koulieris, Hubert P. H. Shum, Hyung Jin Chang, Ziyi Chang","submitted_at":"2023-06-07T15:46:47Z","abstract_excerpt":"Diffusion models are learning pattern-learning systems to model and sample from data distributions with three functional components namely the forward process, the reverse process, and the sampling process. The components of diffusion models have gained significant attention with many design factors being considered in common practice. Existing reviews have primarily focused on higher-level solutions, covering less on the design fundamentals of components. This study seeks to address this gap by providing a comprehensive and coherent review of seminal designable factors within each functional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04542","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/2306.04542/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":"2306.04542","created_at":"2026-07-05T11:12:15.282975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04542v4","created_at":"2026-07-05T11:12:15.282975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04542","created_at":"2026-07-05T11:12:15.282975+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBL4AVIN3WWQ","created_at":"2026-07-05T11:12:15.282975+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBL4AVIN3WWQVMU6","created_at":"2026-07-05T11:12:15.282975+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBL4AVIN","created_at":"2026-07-05T11:12:15.282975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18058","citing_title":"Multiscale reconstruction of protein conformations from cryo-EM images","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13022","citing_title":"Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04470","citing_title":"A Diffusion-based Generative Machine Learning Paradigm for Dynamic Contingency Screening","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V","json":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V.json","graph_json":"https://pith.science/api/pith-number/KBL4AVIN3WWQVMU6INJCP4AY2V/graph.json","events_json":"https://pith.science/api/pith-number/KBL4AVIN3WWQVMU6INJCP4AY2V/events.json","paper":"https://pith.science/paper/KBL4AVIN"},"agent_actions":{"view_html":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V","download_json":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V.json","view_paper":"https://pith.science/paper/KBL4AVIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04542&json=true","fetch_graph":"https://pith.science/api/pith-number/KBL4AVIN3WWQVMU6INJCP4AY2V/graph.json","fetch_events":"https://pith.science/api/pith-number/KBL4AVIN3WWQVMU6INJCP4AY2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V/action/storage_attestation","attest_author":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V/action/author_attestation","sign_citation":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V/action/citation_signature","submit_replication":"https://pith.science/pith/KBL4AVIN3WWQVMU6INJCP4AY2V/action/replication_record"}},"created_at":"2026-07-05T11:12:15.282975+00:00","updated_at":"2026-07-05T11:12:15.282975+00:00"}