{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TEJITKKDLFVJMPMGXM53TBEBAW","short_pith_number":"pith:TEJITKKD","schema_version":"1.0","canonical_sha256":"991289a943596a963d86bb3bb98481058e4498289c916efb8ce920ee1b91dc3e","source":{"kind":"arxiv","id":"2605.15684","version":1},"attestation_state":"computed","paper":{"title":"ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binglei Bao, Chuntao Liu, Haizhen Xie, Hao Wu, Heyuan Gao, Huaao Tang, Jie Hu, Kunpeng Du, Lei Yu, Sen Lu, Xinghao Chen, Yang Zhao, Zhicai Huang, Zhijun Tu","submitted_at":"2026-05-15T07:13:27Z","abstract_excerpt":"The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices entails prohibitive computational and memory overhead. While efficiency-driven approaches like Linear-DiT and static pruning alleviate bottlenecks, they often incur quality degradation. Unlike cloud environments, mobile constraints require a single-model paradigm that dynamically balances fidelity and latency. We introduce ElasticDiT, which achieves this dy"},"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":"2605.15684","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T07:13:27Z","cross_cats_sorted":[],"title_canon_sha256":"c6c050f9e40f8e3cf5338e51b9e534277826d66850351421f2e5ef2e0f52e28d","abstract_canon_sha256":"17e8b4028677d7c9b3b3692b11b1128c8da1b283f4cca65baf3c63fc2d9c71ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:12.314569Z","signature_b64":"O/z6nG2LRoPF1hacOd/n0nnFVkgF/BYIDFo4gCeLctsxQuAvW2BtQLFXzXNhADweGldhB3VfpkFJKqMdx138BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"991289a943596a963d86bb3bb98481058e4498289c916efb8ce920ee1b91dc3e","last_reissued_at":"2026-05-20T00:01:12.313727Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:12.313727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binglei Bao, Chuntao Liu, Haizhen Xie, Hao Wu, Heyuan Gao, Huaao Tang, Jie Hu, Kunpeng Du, Lei Yu, Sen Lu, Xinghao Chen, Yang Zhao, Zhicai Huang, Zhijun Tu","submitted_at":"2026-05-15T07:13:27Z","abstract_excerpt":"The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices entails prohibitive computational and memory overhead. While efficiency-driven approaches like Linear-DiT and static pruning alleviate bottlenecks, they often incur quality degradation. Unlike cloud environments, mobile constraints require a single-model paradigm that dynamically balances fidelity and latency. We introduce ElasticDiT, which achieves this dy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15684","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/2605.15684/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:29.227276Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.049678Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ba45d64a87b8b1a9a7836823f8343bbaba80e6def67190038c17b35a74dbb71c"},"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":"2605.15684","created_at":"2026-05-20T00:01:12.313861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15684v1","created_at":"2026-05-20T00:01:12.313861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15684","created_at":"2026-05-20T00:01:12.313861+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEJITKKDLFVJ","created_at":"2026-05-20T00:01:12.313861+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEJITKKDLFVJMPMG","created_at":"2026-05-20T00:01:12.313861+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEJITKKD","created_at":"2026-05-20T00:01:12.313861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW","json":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW.json","graph_json":"https://pith.science/api/pith-number/TEJITKKDLFVJMPMGXM53TBEBAW/graph.json","events_json":"https://pith.science/api/pith-number/TEJITKKDLFVJMPMGXM53TBEBAW/events.json","paper":"https://pith.science/paper/TEJITKKD"},"agent_actions":{"view_html":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW","download_json":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW.json","view_paper":"https://pith.science/paper/TEJITKKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15684&json=true","fetch_graph":"https://pith.science/api/pith-number/TEJITKKDLFVJMPMGXM53TBEBAW/graph.json","fetch_events":"https://pith.science/api/pith-number/TEJITKKDLFVJMPMGXM53TBEBAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW/action/storage_attestation","attest_author":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW/action/author_attestation","sign_citation":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW/action/citation_signature","submit_replication":"https://pith.science/pith/TEJITKKDLFVJMPMGXM53TBEBAW/action/replication_record"}},"created_at":"2026-05-20T00:01:12.313861+00:00","updated_at":"2026-05-20T00:01:12.313861+00:00"}