{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PFYF2GMXVLHSYLCXOS6I2KG5DQ","short_pith_number":"pith:PFYF2GMX","schema_version":"1.0","canonical_sha256":"79705d1997aacf2c2c5774bc8d28dd1c2e679ce8677d659336f0fb6247004f43","source":{"kind":"arxiv","id":"2306.06991","version":2},"attestation_state":"computed","paper":{"title":"Fast Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Kenji Kawaguchi, Pan Zhou, Zike Wu","submitted_at":"2023-06-12T09:38:04Z","abstract_excerpt":"Diffusion models (DMs) have been adopted across diverse fields with its remarkable abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a stochastic optimization perspective for both faster training and sampling. We first find that the diffusion process of DMs accords with the stochastic optimization process of stochastic gradient descent (SGD) on a stochastic time-variant problem. Then, inspired by momentum SGD that uses both gradient and an extra momentum to achieve faster and more stable convergence th"},"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":"2306.06991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T09:38:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a6890b8725bafd6222cee2d707b31e95172bcd033e2707581c0ec67052dae506","abstract_canon_sha256":"cf290b192822f0844e5745588dad419639999d80c8990f94983ac53af0766fbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:08.456358Z","signature_b64":"/e38klEuV14p/9rKp2e4at3V9wpady9eHAcLeG21n5Rfe6COoYQGesydtwjckDxBUNNoA96vMwCx2UkOOfNVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79705d1997aacf2c2c5774bc8d28dd1c2e679ce8677d659336f0fb6247004f43","last_reissued_at":"2026-07-05T06:57:08.455881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:08.455881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Kenji Kawaguchi, Pan Zhou, Zike Wu","submitted_at":"2023-06-12T09:38:04Z","abstract_excerpt":"Diffusion models (DMs) have been adopted across diverse fields with its remarkable abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a stochastic optimization perspective for both faster training and sampling. We first find that the diffusion process of DMs accords with the stochastic optimization process of stochastic gradient descent (SGD) on a stochastic time-variant problem. Then, inspired by momentum SGD that uses both gradient and an extra momentum to achieve faster and more stable convergence th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06991","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/2306.06991/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":"2306.06991","created_at":"2026-07-05T06:57:08.455938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06991v2","created_at":"2026-07-05T06:57:08.455938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06991","created_at":"2026-07-05T06:57:08.455938+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFYF2GMXVLHS","created_at":"2026-07-05T06:57:08.455938+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFYF2GMXVLHSYLCX","created_at":"2026-07-05T06:57:08.455938+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFYF2GMX","created_at":"2026-07-05T06:57:08.455938+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07350","citing_title":"MapBERT: Bitwise Masked Modeling for Real-Time Semantic Mapping Generation","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ","json":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ.json","graph_json":"https://pith.science/api/pith-number/PFYF2GMXVLHSYLCXOS6I2KG5DQ/graph.json","events_json":"https://pith.science/api/pith-number/PFYF2GMXVLHSYLCXOS6I2KG5DQ/events.json","paper":"https://pith.science/paper/PFYF2GMX"},"agent_actions":{"view_html":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ","download_json":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ.json","view_paper":"https://pith.science/paper/PFYF2GMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06991&json=true","fetch_graph":"https://pith.science/api/pith-number/PFYF2GMXVLHSYLCXOS6I2KG5DQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PFYF2GMXVLHSYLCXOS6I2KG5DQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ/action/storage_attestation","attest_author":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ/action/author_attestation","sign_citation":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ/action/citation_signature","submit_replication":"https://pith.science/pith/PFYF2GMXVLHSYLCXOS6I2KG5DQ/action/replication_record"}},"created_at":"2026-07-05T06:57:08.455938+00:00","updated_at":"2026-07-05T06:57:08.455938+00:00"}