{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MOZIAAFRNC6UMADKS4UDCGKP4B","short_pith_number":"pith:MOZIAAFR","schema_version":"1.0","canonical_sha256":"63b28000b168bd46006a972831194fe04e81a5eff2ea42f4d1626e6a45a22f43","source":{"kind":"arxiv","id":"2405.14822","version":2},"attestation_state":"computed","paper":{"title":"PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Wei-Hsiang Liao, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2024-05-23T17:39:09Z","abstract_excerpt":"The diffusion model performs remarkable in generating high-dimensional content but is computationally intensive, especially during training. We propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a novel pipeline that reduces the training costs through three stages: training diffusion on downsampled data, distilling the pretrained diffusion, and progressive super-resolution. With the proposed pipeline, PaGoDA achieves a $64\\times$ reduced cost in training its diffusion model on 8x downsampled data; while at the inference, with the single-step, it performs state-of-the-art on ImageNe"},"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":"2405.14822","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T17:39:09Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"30ed3ee902ee110af5630500a416ad5b4d48de37e2d679e4e8ee72bcc6134755","abstract_canon_sha256":"882216beee658c9d2a4042e5ea1fb698a75112b08d225cdcebdea7792585dd5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:54.462703Z","signature_b64":"SAyIvyuaNPKllPj16oLfKEe2ejMh8eLrGeSsKemf8LT3pEZ4wS4yd8v066rDNhgXNy7vPVUaZWxNay+un8teDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b28000b168bd46006a972831194fe04e81a5eff2ea42f4d1626e6a45a22f43","last_reissued_at":"2026-07-05T09:27:54.462177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:54.462177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Wei-Hsiang Liao, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2024-05-23T17:39:09Z","abstract_excerpt":"The diffusion model performs remarkable in generating high-dimensional content but is computationally intensive, especially during training. We propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a novel pipeline that reduces the training costs through three stages: training diffusion on downsampled data, distilling the pretrained diffusion, and progressive super-resolution. With the proposed pipeline, PaGoDA achieves a $64\\times$ reduced cost in training its diffusion model on 8x downsampled data; while at the inference, with the single-step, it performs state-of-the-art on ImageNe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14822","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/2405.14822/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":"2405.14822","created_at":"2026-07-05T09:27:54.462254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14822v2","created_at":"2026-07-05T09:27:54.462254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14822","created_at":"2026-07-05T09:27:54.462254+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOZIAAFRNC6U","created_at":"2026-07-05T09:27:54.462254+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOZIAAFRNC6UMADK","created_at":"2026-07-05T09:27:54.462254+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOZIAAFR","created_at":"2026-07-05T09:27:54.462254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.07514","citing_title":"A Unified View of Score-Based and Drifting Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B","json":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B.json","graph_json":"https://pith.science/api/pith-number/MOZIAAFRNC6UMADKS4UDCGKP4B/graph.json","events_json":"https://pith.science/api/pith-number/MOZIAAFRNC6UMADKS4UDCGKP4B/events.json","paper":"https://pith.science/paper/MOZIAAFR"},"agent_actions":{"view_html":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B","download_json":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B.json","view_paper":"https://pith.science/paper/MOZIAAFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14822&json=true","fetch_graph":"https://pith.science/api/pith-number/MOZIAAFRNC6UMADKS4UDCGKP4B/graph.json","fetch_events":"https://pith.science/api/pith-number/MOZIAAFRNC6UMADKS4UDCGKP4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B/action/storage_attestation","attest_author":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B/action/author_attestation","sign_citation":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B/action/citation_signature","submit_replication":"https://pith.science/pith/MOZIAAFRNC6UMADKS4UDCGKP4B/action/replication_record"}},"created_at":"2026-07-05T09:27:54.462254+00:00","updated_at":"2026-07-05T09:27:54.462254+00:00"}