{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BRXWPVLTXEI3ACV4MUWJ2Y36FI","short_pith_number":"pith:BRXWPVLT","schema_version":"1.0","canonical_sha256":"0c6f67d573b911b00abc652c9d637e2a2d710596f3a5cae9f8a7b00843232677","source":{"kind":"arxiv","id":"2507.17135","version":1},"attestation_state":"computed","paper":{"title":"SADA: Stability-guided Adaptive Diffusion Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hai Li, Hancheng Ye, Jianyi Zhang, Jingwei Sun, Jingyang Zhang, Ting Jiang, Yiran Chen, Yixiao Wang, Zekai Chen, Zishan Shao","submitted_at":"2025-07-23T02:15:45Z","abstract_excerpt":"Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce per-step computation cost, while effectively reducing sampling time, demonstrate low faithfulness compared to the original baseline. We hypothesize that this fidelity gap arises because (a) different prompts correspond to varying denoising trajectory, and (b) such methods do not consider the underlying ODE formulation and its numerical solution. In this pap"},"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":"2507.17135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T02:15:45Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"9e5f5c6a190a7e05fbfc6ebdb1de7118a503a4934ac61af5f4a9eb2a79735282","abstract_canon_sha256":"9df782242b1162c23035e96bf40413bd56b99478ae5c7257f10dec60476d5a71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:01.864986Z","signature_b64":"2O54wC3/7uljKWsHOwwlYrU8nwHxF0M6IOH3TBjcECOipsr+WOKhTXp98NHl8wdg2ZONc1m9SfRdBqWwvN2cBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c6f67d573b911b00abc652c9d637e2a2d710596f3a5cae9f8a7b00843232677","last_reissued_at":"2026-07-05T11:42:01.864499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:01.864499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SADA: Stability-guided Adaptive Diffusion Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hai Li, Hancheng Ye, Jianyi Zhang, Jingwei Sun, Jingyang Zhang, Ting Jiang, Yiran Chen, Yixiao Wang, Zekai Chen, Zishan Shao","submitted_at":"2025-07-23T02:15:45Z","abstract_excerpt":"Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce per-step computation cost, while effectively reducing sampling time, demonstrate low faithfulness compared to the original baseline. We hypothesize that this fidelity gap arises because (a) different prompts correspond to varying denoising trajectory, and (b) such methods do not consider the underlying ODE formulation and its numerical solution. In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17135","kind":"arxiv","version":1},"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/2507.17135/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":"2507.17135","created_at":"2026-07-05T11:42:01.864560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17135v1","created_at":"2026-07-05T11:42:01.864560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17135","created_at":"2026-07-05T11:42:01.864560+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRXWPVLTXEI3","created_at":"2026-07-05T11:42:01.864560+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRXWPVLTXEI3ACV4","created_at":"2026-07-05T11:42:01.864560+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRXWPVLT","created_at":"2026-07-05T11:42:01.864560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17378","citing_title":"RISE: Relay Inference and Online Scheduling for Efficient Edge-Device Collaborative Diffusion Model Services","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15397","citing_title":"ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest","ref_index":128,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI","json":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI.json","graph_json":"https://pith.science/api/pith-number/BRXWPVLTXEI3ACV4MUWJ2Y36FI/graph.json","events_json":"https://pith.science/api/pith-number/BRXWPVLTXEI3ACV4MUWJ2Y36FI/events.json","paper":"https://pith.science/paper/BRXWPVLT"},"agent_actions":{"view_html":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI","download_json":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI.json","view_paper":"https://pith.science/paper/BRXWPVLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17135&json=true","fetch_graph":"https://pith.science/api/pith-number/BRXWPVLTXEI3ACV4MUWJ2Y36FI/graph.json","fetch_events":"https://pith.science/api/pith-number/BRXWPVLTXEI3ACV4MUWJ2Y36FI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI/action/storage_attestation","attest_author":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI/action/author_attestation","sign_citation":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI/action/citation_signature","submit_replication":"https://pith.science/pith/BRXWPVLTXEI3ACV4MUWJ2Y36FI/action/replication_record"}},"created_at":"2026-07-05T11:42:01.864560+00:00","updated_at":"2026-07-05T11:42:01.864560+00:00"}