{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NW2JIABWECZIXLWRNUBA7ZRBCW","short_pith_number":"pith:NW2JIABW","schema_version":"1.0","canonical_sha256":"6db494003620b28baed16d020fe62115a38b68dd19c193a8e4b438d9da82ceb2","source":{"kind":"arxiv","id":"2309.10438","version":2},"attestation_state":"computed","paper":{"title":"AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Chao, Huixia Li, Jie Wu, Lijiang Li, Min Zheng, Rongrong Ji, Rui Wang, Xiawu Zheng, Xin Pan, Xuefeng Xiao","submitted_at":"2023-09-19T08:57:24Z","abstract_excerpt":"Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an undisputed principle of diffusion models. We consider that such a uniform assumption is not the optimal solution in practice; i.e., we can find different optimal time steps for different models. Therefore, we propose to search the optimal time steps sequence and compressed model architecture in a unified framework to achieve effective image generation for 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":"2309.10438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-19T08:57:24Z","cross_cats_sorted":[],"title_canon_sha256":"9d91d3c08dca8dbd26ede7e705bb8b613b5d9726b20c08c58e8a0ddc29d66fb6","abstract_canon_sha256":"a2b959a94477137dc555bee559c62c535628078d6558067373e9d4a9fa065dd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:45.061650Z","signature_b64":"S5ssPx7RYzVfhkdQ7e546aRbx3AxnvTHfBIvfVLX7AVivz63/+9MZdbn3oN3Uhct1FPPL1h1BRzjpcwzfg03AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6db494003620b28baed16d020fe62115a38b68dd19c193a8e4b438d9da82ceb2","last_reissued_at":"2026-07-05T06:53:45.061216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:45.061216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Chao, Huixia Li, Jie Wu, Lijiang Li, Min Zheng, Rongrong Ji, Rui Wang, Xiawu Zheng, Xin Pan, Xuefeng Xiao","submitted_at":"2023-09-19T08:57:24Z","abstract_excerpt":"Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an undisputed principle of diffusion models. We consider that such a uniform assumption is not the optimal solution in practice; i.e., we can find different optimal time steps for different models. Therefore, we propose to search the optimal time steps sequence and compressed model architecture in a unified framework to achieve effective image generation for d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10438","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/2309.10438/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":"2309.10438","created_at":"2026-07-05T06:53:45.061277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10438v2","created_at":"2026-07-05T06:53:45.061277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10438","created_at":"2026-07-05T06:53:45.061277+00:00"},{"alias_kind":"pith_short_12","alias_value":"NW2JIABWECZI","created_at":"2026-07-05T06:53:45.061277+00:00"},{"alias_kind":"pith_short_16","alias_value":"NW2JIABWECZIXLWR","created_at":"2026-07-05T06:53:45.061277+00:00"},{"alias_kind":"pith_short_8","alias_value":"NW2JIABW","created_at":"2026-07-05T06:53:45.061277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00382","citing_title":"Masked Generative Nested Transformers with Decode Time Scaling","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW","json":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW.json","graph_json":"https://pith.science/api/pith-number/NW2JIABWECZIXLWRNUBA7ZRBCW/graph.json","events_json":"https://pith.science/api/pith-number/NW2JIABWECZIXLWRNUBA7ZRBCW/events.json","paper":"https://pith.science/paper/NW2JIABW"},"agent_actions":{"view_html":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW","download_json":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW.json","view_paper":"https://pith.science/paper/NW2JIABW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10438&json=true","fetch_graph":"https://pith.science/api/pith-number/NW2JIABWECZIXLWRNUBA7ZRBCW/graph.json","fetch_events":"https://pith.science/api/pith-number/NW2JIABWECZIXLWRNUBA7ZRBCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW/action/storage_attestation","attest_author":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW/action/author_attestation","sign_citation":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW/action/citation_signature","submit_replication":"https://pith.science/pith/NW2JIABWECZIXLWRNUBA7ZRBCW/action/replication_record"}},"created_at":"2026-07-05T06:53:45.061277+00:00","updated_at":"2026-07-05T06:53:45.061277+00:00"}