{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MMLQUVCXA32J35G5AJ2JE6TDDK","short_pith_number":"pith:MMLQUVCX","canonical_record":{"source":{"id":"2512.12083","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-12T23:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"0645f829babe1a72977dd2b28277921e7c0b124ae6a1f07e5ef5f173b8f2c218","abstract_canon_sha256":"4d115b9aff5639ffffaf7dc8c8ebe275a1cbdc58caec78d0b510bfb5c891269e"},"schema_version":"1.0"},"canonical_sha256":"63170a545706f49df4dd0274927a631abed14e8fa86ae28ac5628f4917a3dc5e","source":{"kind":"arxiv","id":"2512.12083","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.12083","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2512.12083v3","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.12083","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"MMLQUVCXA32J","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MMLQUVCXA32J35G5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MMLQUVCX","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MMLQUVCXA32J35G5AJ2JE6TDDK","target":"record","payload":{"canonical_record":{"source":{"id":"2512.12083","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-12T23:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"0645f829babe1a72977dd2b28277921e7c0b124ae6a1f07e5ef5f173b8f2c218","abstract_canon_sha256":"4d115b9aff5639ffffaf7dc8c8ebe275a1cbdc58caec78d0b510bfb5c891269e"},"schema_version":"1.0"},"canonical_sha256":"63170a545706f49df4dd0274927a631abed14e8fa86ae28ac5628f4917a3dc5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.862643Z","signature_b64":"i/EJy278y8M4PAAuSGfiQEhWZnG3/21V34Y0vAhGmBVtQQTRTtRryQLPBQtRt+7JR/6SttG17NLnxd8nE+IzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63170a545706f49df4dd0274927a631abed14e8fa86ae28ac5628f4917a3dc5e","last_reissued_at":"2026-05-17T23:39:16.861851Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.861851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.12083","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFnixQumAFZRbluOB/R1Acc7hBQW2qjxp+n+RY9Uw38Vm+R4rfz2rnSIRa4534zD9fcwC9Bm+dNJ9PnL5qwmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:35:08.115538Z"},"content_sha256":"a0a2d6752fd9282d280d4b439e72df1267eebc2aaee70b75dddaaaa7cd565954","schema_version":"1.0","event_id":"sha256:a0a2d6752fd9282d280d4b439e72df1267eebc2aaee70b75dddaaaa7cd565954"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MMLQUVCXA32J35G5AJ2JE6TDDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"Compressing VFM features to a low-dimensional manifold lets DiTs reach FID 1.82 on ImageNet in 64 epochs, then a refiner improves it to 1.65.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Gao, Guanfang Dong, Luke Schultz, Negar Hassanpour","submitted_at":"2025-12-12T23:17:41Z","abstract_excerpt":"Semantic-rich features from Vision Foundation Models (VFMs) have been leveraged to enhance Latent Diffusion Models (LDMs). However, raw VFM features are typically high-dimensional and redundant, increasing the difficulty of learning and reducing training efficiency for Diffusion Transformers (DiTs). In this paper, we propose Repack then Refine, a three-stage framework that brings the semantic-rich VFM features to DiT while further accelerating learning efficiency. Specifically, the RePack module projects the high-dimensional features onto a compact, low-dimensional manifold. This filters out t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On ImageNet-1K, RePack-DiT-XL/1 achieves an FID of 1.82 in only 64 training epochs. With the Refiner module, performance further improves to an FID of 1.65, significantly surpassing latest LDMs in terms of convergence efficiency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the RePack projection to a compact manifold preserves essential structural information from VFM features such that the subsequent Latent-Guided Refiner can reliably restore high-frequency details without introducing artifacts or requiring extensive additional training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RePack projects VFM features to a low-dimensional manifold for efficient DiT training, followed by a Latent-Guided Refiner that improves FID to 1.65 on ImageNet-1K after 64 epochs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Compressing VFM features to a low-dimensional manifold lets DiTs reach FID 1.82 on ImageNet in 64 epochs, then a refiner improves it to 1.65.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"18ba4bf4a1f7a81e3dde713dc573dc6cd9ab4fe2735b5fcca9bce1787b133575"},"source":{"id":"2512.12083","kind":"arxiv","version":3},"verdict":{"id":"cee890c6-068b-46f0-a782-5518fc59320a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T22:21:53.674778Z","strongest_claim":"On ImageNet-1K, RePack-DiT-XL/1 achieves an FID of 1.82 in only 64 training epochs. With the Refiner module, performance further improves to an FID of 1.65, significantly surpassing latest LDMs in terms of convergence efficiency.","one_line_summary":"RePack projects VFM features to a low-dimensional manifold for efficient DiT training, followed by a Latent-Guided Refiner that improves FID to 1.65 on ImageNet-1K after 64 epochs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the RePack projection to a compact manifold preserves essential structural information from VFM features such that the subsequent Latent-Guided Refiner can reliably restore high-frequency details without introducing artifacts or requiring extensive additional training.","pith_extraction_headline":"Compressing VFM features to a low-dimensional manifold lets DiTs reach FID 1.82 on ImageNet in 64 epochs, then a refiner improves it to 1.65."},"references":{"count":8,"sample":[{"doi":"10.1007/bf02288367","year":2023,"title":"1936 , month = sep, publisher =","work_id":"ed6e5de1-4aab-414b-9f04-f63d218a88df","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"In specific restoration domains such as blind face restoration, methods often leverage strong external priors","work_id":"92fe6f76-edd3-4049-b91e-096bc80ca13a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"II (Compression):We follow the common view that compressing the latent manifold helps simplify the modeling task","work_id":"a72b4b6d-ab81-4588-bf35-1d23f9fb60c9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"III (Semantic Fidelity):We observe that directly utilizing signals from frozen VFMs preserves higher semantic puritycompared to distilling them into a complex learnable encoder","work_id":"3779686d-77b1-437c-b028-3cfe047b213b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1936,"title":"IV (Decoupling):We follow a frequency-decoupled design","work_id":"52f5ea82-b265-4d12-b071-ffd772c000fb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":8,"snapshot_sha256":"7e26f215c9464816a9fea5d841d3792a5b3df0ff2494ea1de182be1f6d79f80a","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ee805359c7bc472eb00fba0b2a2821bd9288134c4af9c54dcc3928d0fe41493a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"cee890c6-068b-46f0-a782-5518fc59320a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"giDBlVRxdg+xWAapa2CtkdqKqIuXe1VE243tWZxnXP/Fr/7luR6DSVusZ/+OXzYpjqWPr96ls7yRS80zE7IQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:35:08.116160Z"},"content_sha256":"5c4ab8234c527be6c554b9e2388babe84e493ba3eff00fcd9ef5ebae12e4e87d","schema_version":"1.0","event_id":"sha256:5c4ab8234c527be6c554b9e2388babe84e493ba3eff00fcd9ef5ebae12e4e87d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMLQUVCXA32J35G5AJ2JE6TDDK/bundle.json","state_url":"https://pith.science/pith/MMLQUVCXA32J35G5AJ2JE6TDDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMLQUVCXA32J35G5AJ2JE6TDDK/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":"2026-05-31T23:35:08Z","links":{"resolver":"https://pith.science/pith/MMLQUVCXA32J35G5AJ2JE6TDDK","bundle":"https://pith.science/pith/MMLQUVCXA32J35G5AJ2JE6TDDK/bundle.json","state":"https://pith.science/pith/MMLQUVCXA32J35G5AJ2JE6TDDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMLQUVCXA32J35G5AJ2JE6TDDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MMLQUVCXA32J35G5AJ2JE6TDDK","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":"4d115b9aff5639ffffaf7dc8c8ebe275a1cbdc58caec78d0b510bfb5c891269e","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-12T23:17:41Z","title_canon_sha256":"0645f829babe1a72977dd2b28277921e7c0b124ae6a1f07e5ef5f173b8f2c218"},"schema_version":"1.0","source":{"id":"2512.12083","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.12083","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2512.12083v3","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.12083","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"MMLQUVCXA32J","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MMLQUVCXA32J35G5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MMLQUVCX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5c4ab8234c527be6c554b9e2388babe84e493ba3eff00fcd9ef5ebae12e4e87d","target":"graph","created_at":"2026-05-17T23:39:16Z","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":"On ImageNet-1K, RePack-DiT-XL/1 achieves an FID of 1.82 in only 64 training epochs. With the Refiner module, performance further improves to an FID of 1.65, significantly surpassing latest LDMs in terms of convergence efficiency."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the RePack projection to a compact manifold preserves essential structural information from VFM features such that the subsequent Latent-Guided Refiner can reliably restore high-frequency details without introducing artifacts or requiring extensive additional training."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RePack projects VFM features to a low-dimensional manifold for efficient DiT training, followed by a Latent-Guided Refiner that improves FID to 1.65 on ImageNet-1K after 64 epochs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Compressing VFM features to a low-dimensional manifold lets DiTs reach FID 1.82 on ImageNet in 64 epochs, then a refiner improves it to 1.65."}],"snapshot_sha256":"18ba4bf4a1f7a81e3dde713dc573dc6cd9ab4fe2735b5fcca9bce1787b133575"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ee805359c7bc472eb00fba0b2a2821bd9288134c4af9c54dcc3928d0fe41493a"},"paper":{"abstract_excerpt":"Semantic-rich features from Vision Foundation Models (VFMs) have been leveraged to enhance Latent Diffusion Models (LDMs). However, raw VFM features are typically high-dimensional and redundant, increasing the difficulty of learning and reducing training efficiency for Diffusion Transformers (DiTs). In this paper, we propose Repack then Refine, a three-stage framework that brings the semantic-rich VFM features to DiT while further accelerating learning efficiency. Specifically, the RePack module projects the high-dimensional features onto a compact, low-dimensional manifold. This filters out t","authors_text":"Chao Gao, Guanfang Dong, Luke Schultz, Negar Hassanpour","cross_cats":[],"headline":"Compressing VFM features to a low-dimensional manifold lets DiTs reach FID 1.82 on ImageNet in 64 epochs, then a refiner improves it to 1.65.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-12T23:17:41Z","title":"RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model"},"references":{"count":8,"internal_anchors":0,"resolved_work":8,"sample":[{"cited_arxiv_id":"","doi":"10.1007/bf02288367","is_internal_anchor":false,"ref_index":1,"title":"1936 , month = sep, publisher =","work_id":"ed6e5de1-4aab-414b-9f04-f63d218a88df","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"In specific restoration domains such as blind face restoration, methods often leverage strong external priors","work_id":"92fe6f76-edd3-4049-b91e-096bc80ca13a","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"II (Compression):We follow the common view that compressing the latent manifold helps simplify the modeling task","work_id":"a72b4b6d-ab81-4588-bf35-1d23f9fb60c9","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"III (Semantic Fidelity):We observe that directly utilizing signals from frozen VFMs preserves higher semantic puritycompared to distilling them into a complex learnable encoder","work_id":"3779686d-77b1-437c-b028-3cfe047b213b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"IV (Decoupling):We follow a frequency-decoupled design","work_id":"52f5ea82-b265-4d12-b071-ffd772c000fb","year":1936}],"snapshot_sha256":"7e26f215c9464816a9fea5d841d3792a5b3df0ff2494ea1de182be1f6d79f80a"},"source":{"id":"2512.12083","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T22:21:53.674778Z","id":"cee890c6-068b-46f0-a782-5518fc59320a","model_set":{"reader":"grok-4.3"},"one_line_summary":"RePack projects VFM features to a low-dimensional manifold for efficient DiT training, followed by a Latent-Guided Refiner that improves FID to 1.65 on ImageNet-1K after 64 epochs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Compressing VFM features to a low-dimensional manifold lets DiTs reach FID 1.82 on ImageNet in 64 epochs, then a refiner improves it to 1.65.","strongest_claim":"On ImageNet-1K, RePack-DiT-XL/1 achieves an FID of 1.82 in only 64 training epochs. With the Refiner module, performance further improves to an FID of 1.65, significantly surpassing latest LDMs in terms of convergence efficiency.","weakest_assumption":"That the RePack projection to a compact manifold preserves essential structural information from VFM features such that the subsequent Latent-Guided Refiner can reliably restore high-frequency details without introducing artifacts or requiring extensive additional training."}},"verdict_id":"cee890c6-068b-46f0-a782-5518fc59320a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a0a2d6752fd9282d280d4b439e72df1267eebc2aaee70b75dddaaaa7cd565954","target":"record","created_at":"2026-05-17T23:39:16Z","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":"4d115b9aff5639ffffaf7dc8c8ebe275a1cbdc58caec78d0b510bfb5c891269e","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-12T23:17:41Z","title_canon_sha256":"0645f829babe1a72977dd2b28277921e7c0b124ae6a1f07e5ef5f173b8f2c218"},"schema_version":"1.0","source":{"id":"2512.12083","kind":"arxiv","version":3}},"canonical_sha256":"63170a545706f49df4dd0274927a631abed14e8fa86ae28ac5628f4917a3dc5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63170a545706f49df4dd0274927a631abed14e8fa86ae28ac5628f4917a3dc5e","first_computed_at":"2026-05-17T23:39:16.861851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:16.861851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/EJy278y8M4PAAuSGfiQEhWZnG3/21V34Y0vAhGmBVtQQTRTtRryQLPBQtRt+7JR/6SttG17NLnxd8nE+IzCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:16.862643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.12083","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0a2d6752fd9282d280d4b439e72df1267eebc2aaee70b75dddaaaa7cd565954","sha256:5c4ab8234c527be6c554b9e2388babe84e493ba3eff00fcd9ef5ebae12e4e87d"],"state_sha256":"d9c8d01cf763c68e72aa61a7146814d94a2e05e2fa954e47172728b6128e0a0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQWOmuUgWaGBp6avUQQ5bcaeZEKAGeZs5w0CTdjtN5fal1vVob96dtHnHYj9Xn2EXMAP3c1t1Q+xHLsNz5QQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T23:35:08.119983Z","bundle_sha256":"5260d3738989cfb810f753bebba1fc9886c793b1cf599830d5c92175f4e22db8"}}