{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5T4SBXURLPJWFZOI7YQC4NS4SI","short_pith_number":"pith:5T4SBXUR","schema_version":"1.0","canonical_sha256":"ecf920de915bd362e5c8fe202e365c9205d274c94fa85c92dc7969a0bd248f5e","source":{"kind":"arxiv","id":"2309.17074","version":3},"attestation_state":"computed","paper":{"title":"AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caiwen Ding, Dongkuan Xu, Shengkun Tang, Yao Li, Yaqing Wang, Yi Liang","submitted_at":"2023-09-29T09:10:04Z","abstract_excerpt":"Diffusion models achieve great success in generating diverse and high-fidelity images, yet their widespread application, especially in real-time scenarios, is hampered by their inherently slow generation speed. The slow generation stems from the necessity of multi-step network inference. While some certain predictions benefit from the full computation of the model in each sampling iteration, not every iteration requires the same amount of computation, potentially leading to inefficient computation. Unlike typical adaptive computation challenges that deal with single-step generation problems, d"},"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":"2309.17074","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T09:10:04Z","cross_cats_sorted":[],"title_canon_sha256":"778a6594de69a2e0008289e3fe6330ef1ccd510bc1a91f01eae275a46fe197e9","abstract_canon_sha256":"a93ad201e549090ee42c7b620229d91a59d0cf8bc7924e1b5cb949b4158947f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:48.901271Z","signature_b64":"HKpJWkUvixddE590JOTrHvNnnDnfYhV30FJyeZEzx/N4kAlNeo3OeaBN1IVOsIOtxb24ZLX+m1LVnKU3mj0kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf920de915bd362e5c8fe202e365c9205d274c94fa85c92dc7969a0bd248f5e","last_reissued_at":"2026-07-05T08:55:48.900798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:48.900798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caiwen Ding, Dongkuan Xu, Shengkun Tang, Yao Li, Yaqing Wang, Yi Liang","submitted_at":"2023-09-29T09:10:04Z","abstract_excerpt":"Diffusion models achieve great success in generating diverse and high-fidelity images, yet their widespread application, especially in real-time scenarios, is hampered by their inherently slow generation speed. The slow generation stems from the necessity of multi-step network inference. While some certain predictions benefit from the full computation of the model in each sampling iteration, not every iteration requires the same amount of computation, potentially leading to inefficient computation. Unlike typical adaptive computation challenges that deal with single-step generation problems, d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17074","kind":"arxiv","version":3},"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/2309.17074/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":"2309.17074","created_at":"2026-07-05T08:55:48.900857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17074v3","created_at":"2026-07-05T08:55:48.900857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17074","created_at":"2026-07-05T08:55:48.900857+00:00"},{"alias_kind":"pith_short_12","alias_value":"5T4SBXURLPJW","created_at":"2026-07-05T08:55:48.900857+00:00"},{"alias_kind":"pith_short_16","alias_value":"5T4SBXURLPJWFZOI","created_at":"2026-07-05T08:55:48.900857+00:00"},{"alias_kind":"pith_short_8","alias_value":"5T4SBXUR","created_at":"2026-07-05T08:55:48.900857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02340","citing_title":"Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI","json":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI.json","graph_json":"https://pith.science/api/pith-number/5T4SBXURLPJWFZOI7YQC4NS4SI/graph.json","events_json":"https://pith.science/api/pith-number/5T4SBXURLPJWFZOI7YQC4NS4SI/events.json","paper":"https://pith.science/paper/5T4SBXUR"},"agent_actions":{"view_html":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI","download_json":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI.json","view_paper":"https://pith.science/paper/5T4SBXUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17074&json=true","fetch_graph":"https://pith.science/api/pith-number/5T4SBXURLPJWFZOI7YQC4NS4SI/graph.json","fetch_events":"https://pith.science/api/pith-number/5T4SBXURLPJWFZOI7YQC4NS4SI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI/action/storage_attestation","attest_author":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI/action/author_attestation","sign_citation":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI/action/citation_signature","submit_replication":"https://pith.science/pith/5T4SBXURLPJWFZOI7YQC4NS4SI/action/replication_record"}},"created_at":"2026-07-05T08:55:48.900857+00:00","updated_at":"2026-07-05T08:55:48.900857+00:00"}