{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:57RDJMXZ5UKC6FG4QQPLI66HD4","short_pith_number":"pith:57RDJMXZ","canonical_record":{"source":{"id":"2405.18428","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T17:59:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25b03eaf37be2b599d170a3d135558ba8a70ae97329e331f599b285a42a2a39f","abstract_canon_sha256":"d24e8f387b819c8589c37cb3b68b3db14eefcd5000bddb52b58c4f4447f48025"},"schema_version":"1.0"},"canonical_sha256":"efe234b2f9ed142f14dc841eb47bc71f1cffc858ab05b1ab8a8e90e8892f85fc","source":{"kind":"arxiv","id":"2405.18428","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18428","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18428v2","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18428","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"57RDJMXZ5UKC","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"57RDJMXZ5UKC6FG4","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"57RDJMXZ","created_at":"2026-07-05T09:40:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:57RDJMXZ5UKC6FG4QQPLI66HD4","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18428","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T17:59:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25b03eaf37be2b599d170a3d135558ba8a70ae97329e331f599b285a42a2a39f","abstract_canon_sha256":"d24e8f387b819c8589c37cb3b68b3db14eefcd5000bddb52b58c4f4447f48025"},"schema_version":"1.0"},"canonical_sha256":"efe234b2f9ed142f14dc841eb47bc71f1cffc858ab05b1ab8a8e90e8892f85fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:57.912452Z","signature_b64":"boncwSNvEoBiWwne5xcAXrqA/5YLl1x15TN6f+fE5cZO+HgDLe3kIRV2DFejYeH9+eXQJXEJynkin+cBFbhLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efe234b2f9ed142f14dc841eb47bc71f1cffc858ab05b1ab8a8e90e8892f85fc","last_reissued_at":"2026-07-05T09:40:57.911944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:57.911944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18428","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rzS2mkNtr1WQJ02WmvWokIRjj5wDlEBGw+p/+L6+P6S/obk0XU3ORSE+N5iKcfaQIsDiS9F5CKrXrS4VNjvrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:27:57.297680Z"},"content_sha256":"63d5a928a8db2fa5523ee6bcb96ca2383451fe04bc5a9abe0a209cc9de625029","schema_version":"1.0","event_id":"sha256:63d5a928a8db2fa5523ee6bcb96ca2383451fe04bc5a9abe0a209cc9de625029"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:57RDJMXZ5UKC6FG4QQPLI66HD4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bencheng Liao, Hanshu Yan, Jiashi Feng, Jun Hao Liew, Lianghui Zhu, Xinggang Wang, Zilong Huang","submitted_at":"2024-05-28T17:59:33Z","abstract_excerpt":"Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic complexity efficiency, especially when handling long sequences. In this paper, we aim to incorporate the sub-quadratic modeling capability of Gated Linear Attention (GLA) into the 2D diffusion backbone. Specifically, we introduce Diffusion Gated Linear Attention Transformers (DiG), a simple, adoptable solution with minimal parameter overhead. We offer two var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18428","kind":"arxiv","version":2},"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/2405.18428/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSRKuxXeJKAnfhmfsoG0m/oX9zEWAG/amhkItWOxCZI1HBxNVGn+mu/IWc9OV5RplAG8JzKyuAqiowwOLzaBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:27:57.298179Z"},"content_sha256":"4b1ce8d158a519b6dcd26c51c696257c2fb5ce3c14ff4b0b26667e1367e4300c","schema_version":"1.0","event_id":"sha256:4b1ce8d158a519b6dcd26c51c696257c2fb5ce3c14ff4b0b26667e1367e4300c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57RDJMXZ5UKC6FG4QQPLI66HD4/bundle.json","state_url":"https://pith.science/pith/57RDJMXZ5UKC6FG4QQPLI66HD4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57RDJMXZ5UKC6FG4QQPLI66HD4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T05:27:57Z","links":{"resolver":"https://pith.science/pith/57RDJMXZ5UKC6FG4QQPLI66HD4","bundle":"https://pith.science/pith/57RDJMXZ5UKC6FG4QQPLI66HD4/bundle.json","state":"https://pith.science/pith/57RDJMXZ5UKC6FG4QQPLI66HD4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57RDJMXZ5UKC6FG4QQPLI66HD4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:57RDJMXZ5UKC6FG4QQPLI66HD4","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":"d24e8f387b819c8589c37cb3b68b3db14eefcd5000bddb52b58c4f4447f48025","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T17:59:33Z","title_canon_sha256":"25b03eaf37be2b599d170a3d135558ba8a70ae97329e331f599b285a42a2a39f"},"schema_version":"1.0","source":{"id":"2405.18428","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18428","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18428v2","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18428","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"57RDJMXZ5UKC","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"57RDJMXZ5UKC6FG4","created_at":"2026-07-05T09:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"57RDJMXZ","created_at":"2026-07-05T09:40:57Z"}],"graph_snapshots":[{"event_id":"sha256:4b1ce8d158a519b6dcd26c51c696257c2fb5ce3c14ff4b0b26667e1367e4300c","target":"graph","created_at":"2026-07-05T09:40:57Z","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/2405.18428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic complexity efficiency, especially when handling long sequences. In this paper, we aim to incorporate the sub-quadratic modeling capability of Gated Linear Attention (GLA) into the 2D diffusion backbone. Specifically, we introduce Diffusion Gated Linear Attention Transformers (DiG), a simple, adoptable solution with minimal parameter overhead. We offer two var","authors_text":"Bencheng Liao, Hanshu Yan, Jiashi Feng, Jun Hao Liew, Lianghui Zhu, Xinggang Wang, Zilong Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T17:59:33Z","title":"DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18428","kind":"arxiv","version":2},"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":"sha256:63d5a928a8db2fa5523ee6bcb96ca2383451fe04bc5a9abe0a209cc9de625029","target":"record","created_at":"2026-07-05T09:40:57Z","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":"d24e8f387b819c8589c37cb3b68b3db14eefcd5000bddb52b58c4f4447f48025","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T17:59:33Z","title_canon_sha256":"25b03eaf37be2b599d170a3d135558ba8a70ae97329e331f599b285a42a2a39f"},"schema_version":"1.0","source":{"id":"2405.18428","kind":"arxiv","version":2}},"canonical_sha256":"efe234b2f9ed142f14dc841eb47bc71f1cffc858ab05b1ab8a8e90e8892f85fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efe234b2f9ed142f14dc841eb47bc71f1cffc858ab05b1ab8a8e90e8892f85fc","first_computed_at":"2026-07-05T09:40:57.911944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:57.911944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"boncwSNvEoBiWwne5xcAXrqA/5YLl1x15TN6f+fE5cZO+HgDLe3kIRV2DFejYeH9+eXQJXEJynkin+cBFbhLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:57.912452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18428","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63d5a928a8db2fa5523ee6bcb96ca2383451fe04bc5a9abe0a209cc9de625029","sha256:4b1ce8d158a519b6dcd26c51c696257c2fb5ce3c14ff4b0b26667e1367e4300c"],"state_sha256":"83fb3b79e4a6f7b80bd88dba4e642926691ccaa168be97c2cd8a4f4d3d6dc539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dS9wzVKDwdAcPvaRKqf95jPUyBsp6+lkvRl7Wt+cZrXrrcoptwgnnol2x7HkJjgRkV1e5dmrp3hMEt8U7OqTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:27:57.301737Z","bundle_sha256":"5de68b45a122bfd51dc26cfb259f097271bddd623be1d9640c8975b093fcee4c"}}