{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BOVYFUXRPEGMZCOI22DN4CQVBB","short_pith_number":"pith:BOVYFUXR","canonical_record":{"source":{"id":"2605.14191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T23:13:29Z","cross_cats_sorted":[],"title_canon_sha256":"5f3f341b8d95770267ac541fa599d623099a1bfc01bbbc1bed784f96d6c05e82","abstract_canon_sha256":"d636a1122738d4a1e98a66b91ae9bd1f4347dc86445d0a5f89793b45c77691d3"},"schema_version":"1.0"},"canonical_sha256":"0bab82d2f1790ccc89c8d686de0a15087affee2a7a4c89d224d2f297efb2f2c6","source":{"kind":"arxiv","id":"2605.14191","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14191","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14191v1","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14191","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"BOVYFUXRPEGM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BOVYFUXRPEGMZCOI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BOVYFUXR","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BOVYFUXRPEGMZCOI22DN4CQVBB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T23:13:29Z","cross_cats_sorted":[],"title_canon_sha256":"5f3f341b8d95770267ac541fa599d623099a1bfc01bbbc1bed784f96d6c05e82","abstract_canon_sha256":"d636a1122738d4a1e98a66b91ae9bd1f4347dc86445d0a5f89793b45c77691d3"},"schema_version":"1.0"},"canonical_sha256":"0bab82d2f1790ccc89c8d686de0a15087affee2a7a4c89d224d2f297efb2f2c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:11.140718Z","signature_b64":"Q2CtQ8w1twG4N6SeaCpXuTncbEXx+VKgBhVCbba3sC8Pg+wLal8izzXpW+tEwE0iBvzD4K5rKd+ZISAqvbe5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bab82d2f1790ccc89c8d686de0a15087affee2a7a4c89d224d2f297efb2f2c6","last_reissued_at":"2026-05-17T23:39:11.140095Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:11.140095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14191","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vl0JBg6oSKFP0mzPCu20yUcErc6jAqDwz9YpzClS7exvyTJ5f7sPupv1qg5043cXbQzCasa7SvUkoq45IneFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T17:21:14.316014Z"},"content_sha256":"ee70838dda67129b8a9389d8d19a7b1435ef2486630711b978d903a5ad2f901f","schema_version":"1.0","event_id":"sha256:ee70838dda67129b8a9389d8d19a7b1435ef2486630711b978d903a5ad2f901f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BOVYFUXRPEGMZCOI22DN4CQVBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CoReDiT prunes redundant tokens in diffusion transformers via spatial coherence scores and reconstructs their outputs from neighbors to cut computation while preserving quality.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hong Cai, Hsin-Pai Cheng, Shizhong Han, Zhuojin Li","submitted_at":"2026-05-13T23:13:29Z","abstract_excerpt":"Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across vision tasks. CoReDiT uses a linear-time spatial coherence score to estimate local redundancy in the latent token lattice and skips high coherence (redundant) tokens in self-attention. To maintain a dense representation and avoid visual discontinuities, we reconstruct skipped attention outputs via coherence-guided aggregation of spatially neighboring retain"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across state-of-the-art diffusion backbones including PixArt-α and MagicDrive-V2, CoReDiT achieves up to 55% self-attention FLOPs reduction and inference speedups of 1.33x on cloud GPUs and 1.72x on mobile NPUs, while maintaining high visual quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the linear-time spatial coherence score reliably identifies redundant tokens whose removal and subsequent neighbor-based reconstruction will not introduce perceptible visual artifacts or degrade generation quality across diverse prompts and resolutions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CoReDiT reduces self-attention FLOPs in DiTs by up to 55% via linear-time spatial coherence pruning and neighbor-based reconstruction, delivering 1.33x-1.72x speedups with maintained quality.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CoReDiT prunes redundant tokens in diffusion transformers via spatial coherence scores and reconstructs their outputs from neighbors to cut computation while preserving quality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d02da5d9d3feeecb90cbfcce96a112fab47ba5eef61efca4e5fce3b142e4e26f"},"source":{"id":"2605.14191","kind":"arxiv","version":1},"verdict":{"id":"75a9ac45-b170-4228-a88b-2acb23233bed","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T04:44:28.788273Z","strongest_claim":"Across state-of-the-art diffusion backbones including PixArt-α and MagicDrive-V2, CoReDiT achieves up to 55% self-attention FLOPs reduction and inference speedups of 1.33x on cloud GPUs and 1.72x on mobile NPUs, while maintaining high visual quality.","one_line_summary":"CoReDiT reduces self-attention FLOPs in DiTs by up to 55% via linear-time spatial coherence pruning and neighbor-based reconstruction, delivering 1.33x-1.72x speedups with maintained quality.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the linear-time spatial coherence score reliably identifies redundant tokens whose removal and subsequent neighbor-based reconstruction will not introduce perceptible visual artifacts or degrade generation quality across diverse prompts and resolutions.","pith_extraction_headline":"CoReDiT prunes redundant tokens in diffusion transformers via spatial coherence scores and reconstructs their outputs from neighbors to cut computation while preserving quality."},"references":{"count":39,"sample":[{"doi":"","year":null,"title":"Token merging for fast sta- ble diffusion","work_id":"c2a6db5b-1e5d-46b2-bd17-02ef709ec2b4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Token Merging: Your ViT But Faster","work_id":"528509bc-2611-4e7f-a772-ea14d25b6dae","ref_index":2,"cited_arxiv_id":"2210.09461","is_internal_anchor":true},{"doi":"","year":2020,"title":"nuscenes: A multi- modal dataset for autonomous driving","work_id":"1a9f2e91-86e4-47cd-ad1d-adad75cf9987","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Exploring diffusion transformer designs via grafting","work_id":"53d6cabb-10d6-4ec8-94c8-f4eda9eac668","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Flexdit: Dynamic token density control for diffusion transformer, 2024","work_id":"51d825d6-e2e3-43cb-bfb5-1a09206b7b54","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"a9bc256b7337589452d0f4bcb96b12a8f1f4a3bf32fbbc106b57656c8cd6c68b","internal_anchors":3},"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":"75a9ac45-b170-4228-a88b-2acb23233bed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9N/NgoUJjOGpYkB1kdAMAqb5xE+rCn/n0c4brMLLiBebzEDkawnlUSqZy3O3zqHMSgiKx+IaFL5r3FgXS7kTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T17:21:14.316690Z"},"content_sha256":"dd8b26dd929dd493ec9854fd5640297d7c538b415bbd68020f38d27d98f26c21","schema_version":"1.0","event_id":"sha256:dd8b26dd929dd493ec9854fd5640297d7c538b415bbd68020f38d27d98f26c21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOVYFUXRPEGMZCOI22DN4CQVBB/bundle.json","state_url":"https://pith.science/pith/BOVYFUXRPEGMZCOI22DN4CQVBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOVYFUXRPEGMZCOI22DN4CQVBB/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":"2026-06-03T17:21:14Z","links":{"resolver":"https://pith.science/pith/BOVYFUXRPEGMZCOI22DN4CQVBB","bundle":"https://pith.science/pith/BOVYFUXRPEGMZCOI22DN4CQVBB/bundle.json","state":"https://pith.science/pith/BOVYFUXRPEGMZCOI22DN4CQVBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOVYFUXRPEGMZCOI22DN4CQVBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BOVYFUXRPEGMZCOI22DN4CQVBB","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":"d636a1122738d4a1e98a66b91ae9bd1f4347dc86445d0a5f89793b45c77691d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T23:13:29Z","title_canon_sha256":"5f3f341b8d95770267ac541fa599d623099a1bfc01bbbc1bed784f96d6c05e82"},"schema_version":"1.0","source":{"id":"2605.14191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14191","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14191v1","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14191","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"BOVYFUXRPEGM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BOVYFUXRPEGMZCOI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BOVYFUXR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:dd8b26dd929dd493ec9854fd5640297d7c538b415bbd68020f38d27d98f26c21","target":"graph","created_at":"2026-05-17T23:39:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across state-of-the-art diffusion backbones including PixArt-α and MagicDrive-V2, CoReDiT achieves up to 55% self-attention FLOPs reduction and inference speedups of 1.33x on cloud GPUs and 1.72x on mobile NPUs, while maintaining high visual quality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the linear-time spatial coherence score reliably identifies redundant tokens whose removal and subsequent neighbor-based reconstruction will not introduce perceptible visual artifacts or degrade generation quality across diverse prompts and resolutions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CoReDiT reduces self-attention FLOPs in DiTs by up to 55% via linear-time spatial coherence pruning and neighbor-based reconstruction, delivering 1.33x-1.72x speedups with maintained quality."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CoReDiT prunes redundant tokens in diffusion transformers via spatial coherence scores and reconstructs their outputs from neighbors to cut computation while preserving quality."}],"snapshot_sha256":"d02da5d9d3feeecb90cbfcce96a112fab47ba5eef61efca4e5fce3b142e4e26f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across vision tasks. CoReDiT uses a linear-time spatial coherence score to estimate local redundancy in the latent token lattice and skips high coherence (redundant) tokens in self-attention. To maintain a dense representation and avoid visual discontinuities, we reconstruct skipped attention outputs via coherence-guided aggregation of spatially neighboring retain","authors_text":"Fatih Porikli, Hong Cai, Hsin-Pai Cheng, Shizhong Han, Zhuojin Li","cross_cats":[],"headline":"CoReDiT prunes redundant tokens in diffusion transformers via spatial coherence scores and reconstructs their outputs from neighbors to cut computation while preserving quality.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T23:13:29Z","title":"CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers"},"references":{"count":39,"internal_anchors":3,"resolved_work":39,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Token merging for fast sta- ble diffusion","work_id":"c2a6db5b-1e5d-46b2-bd17-02ef709ec2b4","year":null},{"cited_arxiv_id":"2210.09461","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Token Merging: Your ViT But Faster","work_id":"528509bc-2611-4e7f-a772-ea14d25b6dae","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"nuscenes: A multi- modal dataset for autonomous driving","work_id":"1a9f2e91-86e4-47cd-ad1d-adad75cf9987","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Exploring diffusion transformer designs via grafting","work_id":"53d6cabb-10d6-4ec8-94c8-f4eda9eac668","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Flexdit: Dynamic token density control for diffusion transformer, 2024","work_id":"51d825d6-e2e3-43cb-bfb5-1a09206b7b54","year":2024}],"snapshot_sha256":"a9bc256b7337589452d0f4bcb96b12a8f1f4a3bf32fbbc106b57656c8cd6c68b"},"source":{"id":"2605.14191","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T04:44:28.788273Z","id":"75a9ac45-b170-4228-a88b-2acb23233bed","model_set":{"reader":"grok-4.3"},"one_line_summary":"CoReDiT reduces self-attention FLOPs in DiTs by up to 55% via linear-time spatial coherence pruning and neighbor-based reconstruction, delivering 1.33x-1.72x speedups with maintained quality.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CoReDiT prunes redundant tokens in diffusion transformers via spatial coherence scores and reconstructs their outputs from neighbors to cut computation while preserving quality.","strongest_claim":"Across state-of-the-art diffusion backbones including PixArt-α and MagicDrive-V2, CoReDiT achieves up to 55% self-attention FLOPs reduction and inference speedups of 1.33x on cloud GPUs and 1.72x on mobile NPUs, while maintaining high visual quality.","weakest_assumption":"That the linear-time spatial coherence score reliably identifies redundant tokens whose removal and subsequent neighbor-based reconstruction will not introduce perceptible visual artifacts or degrade generation quality across diverse prompts and resolutions."}},"verdict_id":"75a9ac45-b170-4228-a88b-2acb23233bed"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ee70838dda67129b8a9389d8d19a7b1435ef2486630711b978d903a5ad2f901f","target":"record","created_at":"2026-05-17T23:39:11Z","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":"d636a1122738d4a1e98a66b91ae9bd1f4347dc86445d0a5f89793b45c77691d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T23:13:29Z","title_canon_sha256":"5f3f341b8d95770267ac541fa599d623099a1bfc01bbbc1bed784f96d6c05e82"},"schema_version":"1.0","source":{"id":"2605.14191","kind":"arxiv","version":1}},"canonical_sha256":"0bab82d2f1790ccc89c8d686de0a15087affee2a7a4c89d224d2f297efb2f2c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bab82d2f1790ccc89c8d686de0a15087affee2a7a4c89d224d2f297efb2f2c6","first_computed_at":"2026-05-17T23:39:11.140095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:11.140095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q2CtQ8w1twG4N6SeaCpXuTncbEXx+VKgBhVCbba3sC8Pg+wLal8izzXpW+tEwE0iBvzD4K5rKd+ZISAqvbe5CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:11.140718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee70838dda67129b8a9389d8d19a7b1435ef2486630711b978d903a5ad2f901f","sha256:dd8b26dd929dd493ec9854fd5640297d7c538b415bbd68020f38d27d98f26c21"],"state_sha256":"159e0a88edd935fd20e60bedfbd1c1d33118bcaffb8a3102429f5053d8bbf33b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yV+x6JgUXmkNmC9T/DEG4reolXJ1G8FAcvphODmVeV9flIApRCJepGsHom7dZ07VVlCnVMMUFwOn7iJDXRvfDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T17:21:14.319525Z","bundle_sha256":"a7ebf64203d0dc65b6c98c34da3bad766c9afe2cab792f06d228c81013797050"}}