{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STYUP2VPRWOKKBTWHUTATB22GI","short_pith_number":"pith:STYUP2VP","schema_version":"1.0","canonical_sha256":"94f147eaaf8d9ca506763d2609875a323ea57ab17aadb45dd46a796dc1261bbf","source":{"kind":"arxiv","id":"2403.04982","version":3},"attestation_state":"computed","paper":{"title":"A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image Generation with Patch Similarity-based Sparsity Augmentation and Text-based Mixed-Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Beomseok Kwon, Hoi-Jun Yoo, Jiwon Choi, Seongyon Hong, Wonhoon Park, Wooyoung Jo","submitted_at":"2024-03-08T01:41:02Z","abstract_excerpt":"This paper presents an energy-efficient stable diffusion processor for text-to-image generation. While stable diffusion attained attention for high-quality image synthesis results, its inherent characteristics hinder its deployment on mobile platforms. The proposed processor achieves high throughput and energy efficiency with three key features as solutions: 1) Patch similarity-based sparsity augmentation (PSSA) to reduce external memory access (EMA) energy of self-attention score by 60.3 %, leading to 37.8 % total EMA energy reduction. 2) Text-based important pixel spotting (TIPS) to allow 44"},"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":"2403.04982","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2024-03-08T01:41:02Z","cross_cats_sorted":[],"title_canon_sha256":"5fc16ff81914e959421ed1b061740823d8be43b763f72025e8e28825cb224885","abstract_canon_sha256":"2a9186cddd80f5e206c56de3de0d3d8630ffef072e70f47c95b0af257a3d8fed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:56.864334Z","signature_b64":"TOTkXrW1j6ntfAPB7E3xQG7YpIgbNBgThP5qgYVLcUXQeHJ2Elr/+wcuBH0BbNhkcLL/UvMGy8cFnNvUF7hyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94f147eaaf8d9ca506763d2609875a323ea57ab17aadb45dd46a796dc1261bbf","last_reissued_at":"2026-07-05T09:09:56.863842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:56.863842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image Generation with Patch Similarity-based Sparsity Augmentation and Text-based Mixed-Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Beomseok Kwon, Hoi-Jun Yoo, Jiwon Choi, Seongyon Hong, Wonhoon Park, Wooyoung Jo","submitted_at":"2024-03-08T01:41:02Z","abstract_excerpt":"This paper presents an energy-efficient stable diffusion processor for text-to-image generation. While stable diffusion attained attention for high-quality image synthesis results, its inherent characteristics hinder its deployment on mobile platforms. The proposed processor achieves high throughput and energy efficiency with three key features as solutions: 1) Patch similarity-based sparsity augmentation (PSSA) to reduce external memory access (EMA) energy of self-attention score by 60.3 %, leading to 37.8 % total EMA energy reduction. 2) Text-based important pixel spotting (TIPS) to allow 44"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04982","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/2403.04982/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":"2403.04982","created_at":"2026-07-05T09:09:56.863897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04982v3","created_at":"2026-07-05T09:09:56.863897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04982","created_at":"2026-07-05T09:09:56.863897+00:00"},{"alias_kind":"pith_short_12","alias_value":"STYUP2VPRWOK","created_at":"2026-07-05T09:09:56.863897+00:00"},{"alias_kind":"pith_short_16","alias_value":"STYUP2VPRWOKKBTW","created_at":"2026-07-05T09:09:56.863897+00:00"},{"alias_kind":"pith_short_8","alias_value":"STYUP2VP","created_at":"2026-07-05T09:09:56.863897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06805","citing_title":"Efficient Diffusion Models: A Survey","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI","json":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI.json","graph_json":"https://pith.science/api/pith-number/STYUP2VPRWOKKBTWHUTATB22GI/graph.json","events_json":"https://pith.science/api/pith-number/STYUP2VPRWOKKBTWHUTATB22GI/events.json","paper":"https://pith.science/paper/STYUP2VP"},"agent_actions":{"view_html":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI","download_json":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI.json","view_paper":"https://pith.science/paper/STYUP2VP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04982&json=true","fetch_graph":"https://pith.science/api/pith-number/STYUP2VPRWOKKBTWHUTATB22GI/graph.json","fetch_events":"https://pith.science/api/pith-number/STYUP2VPRWOKKBTWHUTATB22GI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI/action/storage_attestation","attest_author":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI/action/author_attestation","sign_citation":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI/action/citation_signature","submit_replication":"https://pith.science/pith/STYUP2VPRWOKKBTWHUTATB22GI/action/replication_record"}},"created_at":"2026-07-05T09:09:56.863897+00:00","updated_at":"2026-07-05T09:09:56.863897+00:00"}