{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SIDTBTMOG2PXSAJNU5IJEZBLGV","short_pith_number":"pith:SIDTBTMO","schema_version":"1.0","canonical_sha256":"920730cd8e369f79012da75092642b356545eef90de93c99d5b566a8a35093e8","source":{"kind":"arxiv","id":"2410.23788","version":1},"attestation_state":"computed","paper":{"title":"EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feifei Feng, Jian Tang, Ning Liu, Xinwang Chen, Yichen Zhu","submitted_at":"2024-10-31T10:13:05Z","abstract_excerpt":"Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical applications. To reduce the computation budget of transformer-based DPMs, this work proposes the Efficient Diffusion Transformer (EDT) framework. The framework includes a lightweight-design diffusion model architecture, and a training-free Attention Modulation Matrix and its alternation arrangement in EDT inspired by human-like sketching. Additionally, we propose a token relation-enhanced masking training strategy tail"},"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":"2410.23788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T10:13:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9fdcb27b7f73f47180306f8a625831865375968a812721c3ea91fc80da3264cb","abstract_canon_sha256":"8a137d0e26b1322e2d15e2863fe3ae334b292104462fd1e50c6ebb15139ec365"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:05.192986Z","signature_b64":"ZhH7RTFqXiKYqjzIrOFtux49UO8dt/ixPkF115DRNhHGcTNKuG4N9yiTBYPlqtvJlwvGYEbmvp9Jzr+aFNpRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"920730cd8e369f79012da75092642b356545eef90de93c99d5b566a8a35093e8","last_reissued_at":"2026-07-05T09:29:05.192571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:05.192571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feifei Feng, Jian Tang, Ning Liu, Xinwang Chen, Yichen Zhu","submitted_at":"2024-10-31T10:13:05Z","abstract_excerpt":"Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical applications. To reduce the computation budget of transformer-based DPMs, this work proposes the Efficient Diffusion Transformer (EDT) framework. The framework includes a lightweight-design diffusion model architecture, and a training-free Attention Modulation Matrix and its alternation arrangement in EDT inspired by human-like sketching. Additionally, we propose a token relation-enhanced masking training strategy tail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23788","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/2410.23788/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":"2410.23788","created_at":"2026-07-05T09:29:05.192629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23788v1","created_at":"2026-07-05T09:29:05.192629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23788","created_at":"2026-07-05T09:29:05.192629+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIDTBTMOG2PX","created_at":"2026-07-05T09:29:05.192629+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIDTBTMOG2PXSAJN","created_at":"2026-07-05T09:29:05.192629+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIDTBTMO","created_at":"2026-07-05T09:29:05.192629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10494","citing_title":"SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV","json":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV.json","graph_json":"https://pith.science/api/pith-number/SIDTBTMOG2PXSAJNU5IJEZBLGV/graph.json","events_json":"https://pith.science/api/pith-number/SIDTBTMOG2PXSAJNU5IJEZBLGV/events.json","paper":"https://pith.science/paper/SIDTBTMO"},"agent_actions":{"view_html":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV","download_json":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV.json","view_paper":"https://pith.science/paper/SIDTBTMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23788&json=true","fetch_graph":"https://pith.science/api/pith-number/SIDTBTMOG2PXSAJNU5IJEZBLGV/graph.json","fetch_events":"https://pith.science/api/pith-number/SIDTBTMOG2PXSAJNU5IJEZBLGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV/action/storage_attestation","attest_author":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV/action/author_attestation","sign_citation":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV/action/citation_signature","submit_replication":"https://pith.science/pith/SIDTBTMOG2PXSAJNU5IJEZBLGV/action/replication_record"}},"created_at":"2026-07-05T09:29:05.192629+00:00","updated_at":"2026-07-05T09:29:05.192629+00:00"}