{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VACGU3RNEDVMB4KP5GPWKQECO6","short_pith_number":"pith:VACGU3RN","schema_version":"1.0","canonical_sha256":"a8046a6e2d20eac0f14fe99f65408277905727fef211184914789e54afbc275c","source":{"kind":"arxiv","id":"2503.01323","version":1},"attestation_state":"computed","paper":{"title":"CacheQuant: Comprehensively Accelerated Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2025-03-03T09:04:51Z","abstract_excerpt":"Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. Nevertheless, the slow inference and complex networks, resulting from redundancy at both temporal and structural levels, hinder their low-latency applications in real-world scenarios. Current acceleration methods for diffusion models focus separately on temporal and structural levels. However, independent optimization at each level to further push the acceleration limits results in significant performance degradation. On the other hand, integrating optimizations at "},"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":"2503.01323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T09:04:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3026765c8006e823fcb83b47fadc7ee9f6c1ad19dbc35a05340171150a532620","abstract_canon_sha256":"98a3f5bac2e2461f6bc13a931340bbeb308464b06e0a6a037d2e101729181853"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:04.636280Z","signature_b64":"pno1yujeKewO3F9tcGIrFKACGSFj21DOjwQqnVCMGt6Fa1NaAaPLDiaeIerh9O8KPTZWFIuvg5CLG9T8MqbfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8046a6e2d20eac0f14fe99f65408277905727fef211184914789e54afbc275c","last_reissued_at":"2026-07-05T10:23:04.635483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:04.635483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CacheQuant: Comprehensively Accelerated Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2025-03-03T09:04:51Z","abstract_excerpt":"Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. Nevertheless, the slow inference and complex networks, resulting from redundancy at both temporal and structural levels, hinder their low-latency applications in real-world scenarios. Current acceleration methods for diffusion models focus separately on temporal and structural levels. However, independent optimization at each level to further push the acceleration limits results in significant performance degradation. On the other hand, integrating optimizations at "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01323","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/2503.01323/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":"2503.01323","created_at":"2026-07-05T10:23:04.635587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01323v1","created_at":"2026-07-05T10:23:04.635587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01323","created_at":"2026-07-05T10:23:04.635587+00:00"},{"alias_kind":"pith_short_12","alias_value":"VACGU3RNEDVM","created_at":"2026-07-05T10:23:04.635587+00:00"},{"alias_kind":"pith_short_16","alias_value":"VACGU3RNEDVMB4KP","created_at":"2026-07-05T10:23:04.635587+00:00"},{"alias_kind":"pith_short_8","alias_value":"VACGU3RN","created_at":"2026-07-05T10:23:04.635587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14561","citing_title":"CoCoDiff: Optimizing Collective Communications for Distributed Diffusion Transformer Inference Under Ulysses Sequence Parallelism","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6","json":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6.json","graph_json":"https://pith.science/api/pith-number/VACGU3RNEDVMB4KP5GPWKQECO6/graph.json","events_json":"https://pith.science/api/pith-number/VACGU3RNEDVMB4KP5GPWKQECO6/events.json","paper":"https://pith.science/paper/VACGU3RN"},"agent_actions":{"view_html":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6","download_json":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6.json","view_paper":"https://pith.science/paper/VACGU3RN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01323&json=true","fetch_graph":"https://pith.science/api/pith-number/VACGU3RNEDVMB4KP5GPWKQECO6/graph.json","fetch_events":"https://pith.science/api/pith-number/VACGU3RNEDVMB4KP5GPWKQECO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6/action/storage_attestation","attest_author":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6/action/author_attestation","sign_citation":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6/action/citation_signature","submit_replication":"https://pith.science/pith/VACGU3RNEDVMB4KP5GPWKQECO6/action/replication_record"}},"created_at":"2026-07-05T10:23:04.635587+00:00","updated_at":"2026-07-05T10:23:04.635587+00:00"}