{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KZDIAXPC6XUZ3LMYIRLIYYQMLS","short_pith_number":"pith:KZDIAXPC","canonical_record":{"source":{"id":"2605.12640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T18:30:49Z","cross_cats_sorted":[],"title_canon_sha256":"bc0e8492167e38dae6d27e8cf108daf4447ce5315cd1ed06e0bb8092964590a4","abstract_canon_sha256":"6d448bbcd8cbe23b6da141dd86d19f54b93eaf500b0afa95eb722f6cbb47b89e"},"schema_version":"1.0"},"canonical_sha256":"5646805de2f5e99dad9844568c620c5ca9ff0d85c085df02d034968796f0afce","source":{"kind":"arxiv","id":"2605.12640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12640","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12640v1","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12640","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"KZDIAXPC6XUZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KZDIAXPC6XUZ3LMY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KZDIAXPC","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KZDIAXPC6XUZ3LMYIRLIYYQMLS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T18:30:49Z","cross_cats_sorted":[],"title_canon_sha256":"bc0e8492167e38dae6d27e8cf108daf4447ce5315cd1ed06e0bb8092964590a4","abstract_canon_sha256":"6d448bbcd8cbe23b6da141dd86d19f54b93eaf500b0afa95eb722f6cbb47b89e"},"schema_version":"1.0"},"canonical_sha256":"5646805de2f5e99dad9844568c620c5ca9ff0d85c085df02d034968796f0afce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:00.012674Z","signature_b64":"Jz1btIyfxVP//0PpK1dVVLnEkpCYJOK031TvO1Jr8/qtA3wUcbdJkAmKpN+HYvVet42z//Pp/HgKH4Z6cxjAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5646805de2f5e99dad9844568c620c5ca9ff0d85c085df02d034968796f0afce","last_reissued_at":"2026-05-18T03:10:00.012201Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:00.012201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12640","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":"2026-05-18T03:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdX3ol6j8PvQYgeP+SD56wjv9tBYLpYKYey02dL9q2gAATBULVNpUTBHiLfzwni8wtPd/9oPln4N3mddSwUyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:54:05.726468Z"},"content_sha256":"fa8529055ba70bf32a88b8f2f6955b47b5d10587dd2f4f099b93b1e803487c01","schema_version":"1.0","event_id":"sha256:fa8529055ba70bf32a88b8f2f6955b47b5d10587dd2f4f099b93b1e803487c01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KZDIAXPC6XUZ3LMYIRLIYYQMLS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MambaPanoptic replaces transformers and convolutions with structured state space blocks to achieve competitive panoptic segmentation at linear complexity.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Damiano Bertolini, Daniel Cremers, Dong Wang, Niclas Zeller, Qing Cheng, Wei Zhang","submitted_at":"2026-05-12T18:30:49Z","abstract_excerpt":"Panoptic segmentation requires the simultaneous recognition of countable thing instances and amorphous stuff regions, placing joint demands on long-range context modelling, multi-scale feature representation, and efficient dense prediction. Existing convolutional and transformer-based methods struggle to satisfy all three requirements concurrently: convolutional architectures are limited in their capacity to model long-range dependencies, while transformer-based methods incur quadratic computational cost that is prohibitive at high resolutions. In this paper, we propose MambaPanoptic, a fully "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the Cityscapes and COCO panoptic segmentation benchmarks demonstrate that MambaPanoptic consistently outperforms PanopticDeepLab and PanopticFCN under comparable model sizes, and matches or surpasses Mask2Former on Cityscapes in PQ and AP while requiring fewer parameters.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That Mamba blocks can be directly substituted into a PanopticFCN-style kernel generator and top-down FPN while preserving the necessary multi-scale coherence and boundary accuracy for both thing and stuff classes without additional task-specific adaptations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MambaPanoptic replaces CNN and transformer components with Mamba blocks in a feature pyramid and kernel generator, achieving higher panoptic quality than PanopticDeepLab and PanopticFCN on Cityscapes and COCO while using fewer parameters than Mask2Former.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MambaPanoptic replaces transformers and convolutions with structured state space blocks to achieve competitive panoptic segmentation at linear complexity.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8bf622843bc275c357e25a3071fa84776d671009049f86c044120c2643179529"},"source":{"id":"2605.12640","kind":"arxiv","version":1},"verdict":{"id":"c4412eeb-4e58-476c-8d25-1b415f0ce1d7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:16:03.879058Z","strongest_claim":"Experiments on the Cityscapes and COCO panoptic segmentation benchmarks demonstrate that MambaPanoptic consistently outperforms PanopticDeepLab and PanopticFCN under comparable model sizes, and matches or surpasses Mask2Former on Cityscapes in PQ and AP while requiring fewer parameters.","one_line_summary":"MambaPanoptic replaces CNN and transformer components with Mamba blocks in a feature pyramid and kernel generator, achieving higher panoptic quality than PanopticDeepLab and PanopticFCN on Cityscapes and COCO while using fewer parameters than Mask2Former.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That Mamba blocks can be directly substituted into a PanopticFCN-style kernel generator and top-down FPN while preserving the necessary multi-scale coherence and boundary accuracy for both thing and stuff classes without additional task-specific adaptations.","pith_extraction_headline":"MambaPanoptic replaces transformers and convolutions with structured state space blocks to achieve competitive panoptic segmentation at linear complexity."},"references":{"count":39,"sample":[{"doi":"","year":2020,"title":"End-to-end object detection with transformers","work_id":"f42b8d22-6c7d-4997-8e33-b8b1c05af74c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"D., Zhu, Y., Liu, T., Huang, T","work_id":"1419eb74-7dfb-4e17-b13c-5a14038bbbdb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"G., Kirillov, A., Girdhar, R., 2022","work_id":"cd535965-1df5-458d-862a-eeeecec56017","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Per-pixel classification is not all you need for semantic segmentation","work_id":"479e0334-3a35-4293-acec-10791a34c10f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"The cityscapes dataset for semantic urban scene understanding","work_id":"d57df302-d2ed-47be-9d1a-9ffbcc66e366","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"6afe5ca3735b2648ce8fde78860f6f8574544da2bbe2a47fde0e970d02c53306","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"951e9de2c038fbd9e5c386b54b7223bdd4f3f018e28119834038058c402fb946"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c4412eeb-4e58-476c-8d25-1b415f0ce1d7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1WRwA5JQ7qld1s77vz2e70cbGtPAvIOKEp+n44+WatOJOaqpFT/CEzTV81NrJzTc63FeuK8dDFeh/JEcpLF4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:54:05.727003Z"},"content_sha256":"231bc2428dfa93e5e286b6c2f3bae8b940bf30dcfbabe198cb1585b1bd81b841","schema_version":"1.0","event_id":"sha256:231bc2428dfa93e5e286b6c2f3bae8b940bf30dcfbabe198cb1585b1bd81b841"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZDIAXPC6XUZ3LMYIRLIYYQMLS/bundle.json","state_url":"https://pith.science/pith/KZDIAXPC6XUZ3LMYIRLIYYQMLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZDIAXPC6XUZ3LMYIRLIYYQMLS/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":"2026-05-26T17:54:05Z","links":{"resolver":"https://pith.science/pith/KZDIAXPC6XUZ3LMYIRLIYYQMLS","bundle":"https://pith.science/pith/KZDIAXPC6XUZ3LMYIRLIYYQMLS/bundle.json","state":"https://pith.science/pith/KZDIAXPC6XUZ3LMYIRLIYYQMLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZDIAXPC6XUZ3LMYIRLIYYQMLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KZDIAXPC6XUZ3LMYIRLIYYQMLS","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":"6d448bbcd8cbe23b6da141dd86d19f54b93eaf500b0afa95eb722f6cbb47b89e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T18:30:49Z","title_canon_sha256":"bc0e8492167e38dae6d27e8cf108daf4447ce5315cd1ed06e0bb8092964590a4"},"schema_version":"1.0","source":{"id":"2605.12640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12640","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12640v1","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12640","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"KZDIAXPC6XUZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KZDIAXPC6XUZ3LMY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KZDIAXPC","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:231bc2428dfa93e5e286b6c2f3bae8b940bf30dcfbabe198cb1585b1bd81b841","target":"graph","created_at":"2026-05-18T03:10:00Z","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":"Experiments on the Cityscapes and COCO panoptic segmentation benchmarks demonstrate that MambaPanoptic consistently outperforms PanopticDeepLab and PanopticFCN under comparable model sizes, and matches or surpasses Mask2Former on Cityscapes in PQ and AP while requiring fewer parameters."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That Mamba blocks can be directly substituted into a PanopticFCN-style kernel generator and top-down FPN while preserving the necessary multi-scale coherence and boundary accuracy for both thing and stuff classes without additional task-specific adaptations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MambaPanoptic replaces CNN and transformer components with Mamba blocks in a feature pyramid and kernel generator, achieving higher panoptic quality than PanopticDeepLab and PanopticFCN on Cityscapes and COCO while using fewer parameters than Mask2Former."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MambaPanoptic replaces transformers and convolutions with structured state space blocks to achieve competitive panoptic segmentation at linear complexity."}],"snapshot_sha256":"8bf622843bc275c357e25a3071fa84776d671009049f86c044120c2643179529"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"951e9de2c038fbd9e5c386b54b7223bdd4f3f018e28119834038058c402fb946"},"paper":{"abstract_excerpt":"Panoptic segmentation requires the simultaneous recognition of countable thing instances and amorphous stuff regions, placing joint demands on long-range context modelling, multi-scale feature representation, and efficient dense prediction. Existing convolutional and transformer-based methods struggle to satisfy all three requirements concurrently: convolutional architectures are limited in their capacity to model long-range dependencies, while transformer-based methods incur quadratic computational cost that is prohibitive at high resolutions. In this paper, we propose MambaPanoptic, a fully ","authors_text":"Damiano Bertolini, Daniel Cremers, Dong Wang, Niclas Zeller, Qing Cheng, Wei Zhang","cross_cats":[],"headline":"MambaPanoptic replaces transformers and convolutions with structured state space blocks to achieve competitive panoptic segmentation at linear complexity.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T18:30:49Z","title":"MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation"},"references":{"count":39,"internal_anchors":3,"resolved_work":39,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"End-to-end object detection with transformers","work_id":"f42b8d22-6c7d-4997-8e33-b8b1c05af74c","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"D., Zhu, Y., Liu, T., Huang, T","work_id":"1419eb74-7dfb-4e17-b13c-5a14038bbbdb","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"G., Kirillov, A., Girdhar, R., 2022","work_id":"cd535965-1df5-458d-862a-eeeecec56017","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Per-pixel classification is not all you need for semantic segmentation","work_id":"479e0334-3a35-4293-acec-10791a34c10f","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"The cityscapes dataset for semantic urban scene understanding","work_id":"d57df302-d2ed-47be-9d1a-9ffbcc66e366","year":2016}],"snapshot_sha256":"6afe5ca3735b2648ce8fde78860f6f8574544da2bbe2a47fde0e970d02c53306"},"source":{"id":"2605.12640","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T21:16:03.879058Z","id":"c4412eeb-4e58-476c-8d25-1b415f0ce1d7","model_set":{"reader":"grok-4.3"},"one_line_summary":"MambaPanoptic replaces CNN and transformer components with Mamba blocks in a feature pyramid and kernel generator, achieving higher panoptic quality than PanopticDeepLab and PanopticFCN on Cityscapes and COCO while using fewer parameters than Mask2Former.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MambaPanoptic replaces transformers and convolutions with structured state space blocks to achieve competitive panoptic segmentation at linear complexity.","strongest_claim":"Experiments on the Cityscapes and COCO panoptic segmentation benchmarks demonstrate that MambaPanoptic consistently outperforms PanopticDeepLab and PanopticFCN under comparable model sizes, and matches or surpasses Mask2Former on Cityscapes in PQ and AP while requiring fewer parameters.","weakest_assumption":"That Mamba blocks can be directly substituted into a PanopticFCN-style kernel generator and top-down FPN while preserving the necessary multi-scale coherence and boundary accuracy for both thing and stuff classes without additional task-specific adaptations."}},"verdict_id":"c4412eeb-4e58-476c-8d25-1b415f0ce1d7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fa8529055ba70bf32a88b8f2f6955b47b5d10587dd2f4f099b93b1e803487c01","target":"record","created_at":"2026-05-18T03:10:00Z","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":"6d448bbcd8cbe23b6da141dd86d19f54b93eaf500b0afa95eb722f6cbb47b89e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T18:30:49Z","title_canon_sha256":"bc0e8492167e38dae6d27e8cf108daf4447ce5315cd1ed06e0bb8092964590a4"},"schema_version":"1.0","source":{"id":"2605.12640","kind":"arxiv","version":1}},"canonical_sha256":"5646805de2f5e99dad9844568c620c5ca9ff0d85c085df02d034968796f0afce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5646805de2f5e99dad9844568c620c5ca9ff0d85c085df02d034968796f0afce","first_computed_at":"2026-05-18T03:10:00.012201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:00.012201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jz1btIyfxVP//0PpK1dVVLnEkpCYJOK031TvO1Jr8/qtA3wUcbdJkAmKpN+HYvVet42z//Pp/HgKH4Z6cxjAAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:00.012674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa8529055ba70bf32a88b8f2f6955b47b5d10587dd2f4f099b93b1e803487c01","sha256:231bc2428dfa93e5e286b6c2f3bae8b940bf30dcfbabe198cb1585b1bd81b841"],"state_sha256":"0875e4c5c7a46c708bc3e22039cc38bcd6f038e6f05eccb5e6184e6df239016a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qhkLft3W85D6KOlUensnqCtQfE5vRDD8gDyh7H9M9pUVU3jnLUW46wL790mca6j415cyfBdwoTlqWg2cUA/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:54:05.729931Z","bundle_sha256":"7e24b7500b66cac90b4f83aea71018b47f6f1ed5bbed3429778f6f9f90e63d54"}}