{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NVGKXTXREIMAJXEDZMBZTSAJJW","short_pith_number":"pith:NVGKXTXR","schema_version":"1.0","canonical_sha256":"6d4cabcef1221804dc83cb0399c8094dac317717228a872bb1c5f8ba7b80557a","source":{"kind":"arxiv","id":"2202.09671","version":4},"attestation_state":"computed","paper":{"title":"Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Huangjie Zheng, Mingyuan Zhou, Pengcheng He, Weizhu Chen","submitted_at":"2022-02-19T20:18:49Z","abstract_excerpt":"Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly because it needs many forward and reverse steps. We propose a faster and cheaper approach that adds noise not until the data become pure random noise, but until they reach a hidden noisy data distribution that we can confidently learn. Then, we use fewer reverse steps to generate data by starting from this hidden distribution that is made similar to the noisy data"},"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":"2202.09671","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-02-19T20:18:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aa1c83a8eac6cc9785abe783d36987a5b9b5d79f8d3ee09bc33a17f1a6631807","abstract_canon_sha256":"3052b2f70d35209c7aa7de8bb77099c618f0517665bbdcf1512c884edaa8984d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:30.106700Z","signature_b64":"77R6INbMlM9JSZRz1gvC/My5uzD2YB0yWIj3thuRT/lFWU9BXuM40Uuxc4K7l0tBIOxnZ642XmKJ0Oa+zyEMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d4cabcef1221804dc83cb0399c8094dac317717228a872bb1c5f8ba7b80557a","last_reissued_at":"2026-07-05T06:48:30.106214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:30.106214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Huangjie Zheng, Mingyuan Zhou, Pengcheng He, Weizhu Chen","submitted_at":"2022-02-19T20:18:49Z","abstract_excerpt":"Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly because it needs many forward and reverse steps. We propose a faster and cheaper approach that adds noise not until the data become pure random noise, but until they reach a hidden noisy data distribution that we can confidently learn. Then, we use fewer reverse steps to generate data by starting from this hidden distribution that is made similar to the noisy data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09671","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/2202.09671/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":"2202.09671","created_at":"2026-07-05T06:48:30.106268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09671v4","created_at":"2026-07-05T06:48:30.106268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09671","created_at":"2026-07-05T06:48:30.106268+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVGKXTXREIMA","created_at":"2026-07-05T06:48:30.106268+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVGKXTXREIMAJXED","created_at":"2026-07-05T06:48:30.106268+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVGKXTXR","created_at":"2026-07-05T06:48:30.106268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2209.14577","citing_title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2208.06193","citing_title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW","json":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW.json","graph_json":"https://pith.science/api/pith-number/NVGKXTXREIMAJXEDZMBZTSAJJW/graph.json","events_json":"https://pith.science/api/pith-number/NVGKXTXREIMAJXEDZMBZTSAJJW/events.json","paper":"https://pith.science/paper/NVGKXTXR"},"agent_actions":{"view_html":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW","download_json":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW.json","view_paper":"https://pith.science/paper/NVGKXTXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09671&json=true","fetch_graph":"https://pith.science/api/pith-number/NVGKXTXREIMAJXEDZMBZTSAJJW/graph.json","fetch_events":"https://pith.science/api/pith-number/NVGKXTXREIMAJXEDZMBZTSAJJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW/action/storage_attestation","attest_author":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW/action/author_attestation","sign_citation":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW/action/citation_signature","submit_replication":"https://pith.science/pith/NVGKXTXREIMAJXEDZMBZTSAJJW/action/replication_record"}},"created_at":"2026-07-05T06:48:30.106268+00:00","updated_at":"2026-07-05T06:48:30.106268+00:00"}