{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HWI7UAYCKNPVJABKJ7IFIGE6UX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"babf70aace65b6d8ec648e726a0bb407f9a1599f0093d5248ad0c0e5ba1a8def","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:59:59Z","title_canon_sha256":"3a3d0db060b58468897936be0ee2a2f18e16a563c3960562b953f0f792eddc0a"},"schema_version":"1.0","source":{"id":"2505.14687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14687","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14687v1","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14687","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"HWI7UAYCKNPV","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"HWI7UAYCKNPVJABK","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"HWI7UAYC","created_at":"2026-07-05T11:06:17Z"}],"graph_snapshots":[{"event_id":"sha256:d5186dbf5f8cbdee728dbdf0864de2dc3808c1827a6fd65c522520d668f58bf9","target":"graph","created_at":"2026-07-05T11:06:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.14687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based Transformers have demonstrated impressive generative capabilities, but their high computational costs hinder practical deployment, for example, generating an $8192\\times 8192$ image can take over an hour on an A100 GPU. In this work, we propose GRAT (\\textbf{GR}ouping first, \\textbf{AT}tending smartly), a training-free attention acceleration strategy for fast image and video generation without compromising output quality. The key insight is to exploit the inherent sparsity in learned attention maps (which tend to be locally focused) in pretrained Diffusion Transformers and leve","authors_text":"Alan Yuille, Ju He, Liang-Chieh Chen, Qihang Yu, Sucheng Ren","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:59:59Z","title":"Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14687","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2f24bee656a7b3cbe59547b7fdf6f1d9d5869fb64efd7685b8ee7f58f988180b","target":"record","created_at":"2026-07-05T11:06:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"babf70aace65b6d8ec648e726a0bb407f9a1599f0093d5248ad0c0e5ba1a8def","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:59:59Z","title_canon_sha256":"3a3d0db060b58468897936be0ee2a2f18e16a563c3960562b953f0f792eddc0a"},"schema_version":"1.0","source":{"id":"2505.14687","kind":"arxiv","version":1}},"canonical_sha256":"3d91fa0302535f54802a4fd054189ea5f4743c06945be5c9b0cf17d6f8ae5b7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d91fa0302535f54802a4fd054189ea5f4743c06945be5c9b0cf17d6f8ae5b7e","first_computed_at":"2026-07-05T11:06:17.653331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:17.653331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fLeSH/wFibmvFwnTG3Kv7bta89C7lla41Aa7nflqoCOTgvkA9327828utOwvDY+Kdl2EWuhxGHLy7999v/F4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:17.653842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f24bee656a7b3cbe59547b7fdf6f1d9d5869fb64efd7685b8ee7f58f988180b","sha256:d5186dbf5f8cbdee728dbdf0864de2dc3808c1827a6fd65c522520d668f58bf9"],"state_sha256":"ce75d259fa02087fbded9255a9c4b5ab3205f7641ec87f19802a8e7f8a7c1f26"}