{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YFOMROQWM3347EG2OPAIDFQADJ","short_pith_number":"pith:YFOMROQW","canonical_record":{"source":{"id":"2603.09921","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T17:18:53Z","cross_cats_sorted":[],"title_canon_sha256":"cda13c5300ca32b649746b9d9ab668a1ad3bb4121b5caee3abe72c86483879ee","abstract_canon_sha256":"dc3aec675a8b18c858459f81e936f858bc8662129adfc9aaa2e8510bed3a343f"},"schema_version":"1.0"},"canonical_sha256":"c15cc8ba1666f7cf90da73c08196001a7820e7b907a90061aa6d03ee9149eb07","source":{"kind":"arxiv","id":"2603.09921","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.09921","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2603.09921v3","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09921","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"YFOMROQWM334","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YFOMROQWM3347EG2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YFOMROQW","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YFOMROQWM3347EG2OPAIDFQADJ","target":"record","payload":{"canonical_record":{"source":{"id":"2603.09921","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T17:18:53Z","cross_cats_sorted":[],"title_canon_sha256":"cda13c5300ca32b649746b9d9ab668a1ad3bb4121b5caee3abe72c86483879ee","abstract_canon_sha256":"dc3aec675a8b18c858459f81e936f858bc8662129adfc9aaa2e8510bed3a343f"},"schema_version":"1.0"},"canonical_sha256":"c15cc8ba1666f7cf90da73c08196001a7820e7b907a90061aa6d03ee9149eb07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:59.671827Z","signature_b64":"+hFZNU3artmPPNA5d4OVhpmiXYgQQFs/vI4eLeHYr0KTnNOmXPH2sTRjLc9jNXyyHVTtaHk8jK/R2E4ohebCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c15cc8ba1666f7cf90da73c08196001a7820e7b907a90061aa6d03ee9149eb07","last_reissued_at":"2026-05-17T23:38:59.671088Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:59.671088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.09921","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":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYI4PC7kMKrQuykLL1ptmQ+a8SBgQgcr1g9XXCESjpxSJtMOi8LVEnuU79zPK9bTf4bCtgqtwpfJiN3xtbCHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:10:49.644946Z"},"content_sha256":"313d2d04db6f7103ef5fd9ae575e6de480b87e31dc364f3084b2a64e0ad7d1aa","schema_version":"1.0","event_id":"sha256:313d2d04db6f7103ef5fd9ae575e6de480b87e31dc364f3084b2a64e0ad7d1aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YFOMROQWM3347EG2OPAIDFQADJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"WikiCLIP shows a contrastive model with LLM entity embeddings and patch-level adaptation can outperform generative methods on open-domain visual entity recognition while running nearly 100 times faster.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxuan Sun, Longtian Qiu, Shan Ning, Xuming He","submitted_at":"2026-03-10T17:18:53Z","abstract_excerpt":"Open-domain visual entity recognition (VER) seeks to associate images with entities in encyclopedic knowledge bases such as Wikipedia. Recent generative methods tailored for VER demonstrate strong performance but incur high computational costs, limiting their scalability and practical deployment. In this work, we revisit the contrastive paradigm for VER and introduce WikiCLIP, a simple yet effective framework that establishes a strong and efficient baseline for open-domain VER. WikiCLIP leverages large language model embeddings as knowledge-rich entity representations and enhances them with a "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"WikiCLIP achieves a 16% improvement on the challenging OVEN unseen set, while reducing inference latency by nearly 100 times compared with the leading generative model, AutoVER.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM-derived entity embeddings combined with the Vision-Guided Knowledge Adaptor and hard-negative synthesis can capture sufficient fine-grained visual-semantic alignment for open-domain entities without requiring generative modeling capacity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"WikiCLIP shows a contrastive model with LLM entity embeddings and patch-level adaptation can outperform generative methods on open-domain visual entity recognition while running nearly 100 times faster.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"06a0564b5c5b5caa71cc01d6446f56efaf2b9350b5dacde8e4fe3be5677edb6c"},"source":{"id":"2603.09921","kind":"arxiv","version":3},"verdict":{"id":"f2cbff46-72c2-48a2-a421-c47f7108d2a7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T13:08:23.785959Z","strongest_claim":"WikiCLIP achieves a 16% improvement on the challenging OVEN unseen set, while reducing inference latency by nearly 100 times compared with the leading generative model, AutoVER.","one_line_summary":"WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM-derived entity embeddings combined with the Vision-Guided Knowledge Adaptor and hard-negative synthesis can capture sufficient fine-grained visual-semantic alignment for open-domain entities without requiring generative modeling capacity.","pith_extraction_headline":"WikiCLIP shows a contrastive model with LLM entity embeddings and patch-level adaptation can outperform generative methods on open-domain visual entity recognition while running nearly 100 times faster."},"references":{"count":47,"sample":[{"doi":"","year":null,"title":"Flamingo: a visual language model for few-shot learning.Advances in Neural Information Processing Systems, 35:23716–23736,","work_id":"bb8f1e74-4594-4917-9ca6-659e49ced632","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Good news, everyone! context driven entity-aware captioning for news images","work_id":"7e60f8b5-4339-4afb-b1fc-a8320ec0c45d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Web-scale visual entity recognition: An llm-driven data approach.ArXiv, abs/2410.23676, 2024","work_id":"c5457418-5a8e-4591-bd89-f0ae7c614656","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A generative approach for wikipedia-scale visual entity recognition.2024 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR), pages 17313– 17322, 2024","work_id":"3eb0a83e-2c9e-4997-addb-6060be16df31","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","work_id":"29921cff-29c1-4aad-a27d-adac346027ec","ref_index":5,"cited_arxiv_id":"2209.06794","is_internal_anchor":true}],"resolved_work":47,"snapshot_sha256":"7f0b1f1649ebe0fb07b1d5e4e82f341deb4a10165027498b7290c8dbd8aa54ca","internal_anchors":12},"formal_canon":{"evidence_count":1,"snapshot_sha256":"7e66b8e0fb1eefff1429e64fb08d6488bcd9130c9bcd40c3f7c67a5d784e4b43"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f2cbff46-72c2-48a2-a421-c47f7108d2a7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"za3GPnDcZA+AepvO8EEW5O9ULB/ctEDMBt+pUXnN7P+EDlmml05igXcTUKMqzbUwHTKF+B9DpqU06rxYbV6vAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:10:49.646165Z"},"content_sha256":"42f730d98179839aae2f3a3d4c1603b152a6531fb60b3e5677092335a7f1fef0","schema_version":"1.0","event_id":"sha256:42f730d98179839aae2f3a3d4c1603b152a6531fb60b3e5677092335a7f1fef0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFOMROQWM3347EG2OPAIDFQADJ/bundle.json","state_url":"https://pith.science/pith/YFOMROQWM3347EG2OPAIDFQADJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFOMROQWM3347EG2OPAIDFQADJ/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":"2026-05-27T21:10:49Z","links":{"resolver":"https://pith.science/pith/YFOMROQWM3347EG2OPAIDFQADJ","bundle":"https://pith.science/pith/YFOMROQWM3347EG2OPAIDFQADJ/bundle.json","state":"https://pith.science/pith/YFOMROQWM3347EG2OPAIDFQADJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFOMROQWM3347EG2OPAIDFQADJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YFOMROQWM3347EG2OPAIDFQADJ","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":"dc3aec675a8b18c858459f81e936f858bc8662129adfc9aaa2e8510bed3a343f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T17:18:53Z","title_canon_sha256":"cda13c5300ca32b649746b9d9ab668a1ad3bb4121b5caee3abe72c86483879ee"},"schema_version":"1.0","source":{"id":"2603.09921","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.09921","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2603.09921v3","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09921","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"YFOMROQWM334","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YFOMROQWM3347EG2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YFOMROQW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:42f730d98179839aae2f3a3d4c1603b152a6531fb60b3e5677092335a7f1fef0","target":"graph","created_at":"2026-05-17T23:38:59Z","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":"WikiCLIP achieves a 16% improvement on the challenging OVEN unseen set, while reducing inference latency by nearly 100 times compared with the leading generative model, AutoVER."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM-derived entity embeddings combined with the Vision-Guided Knowledge Adaptor and hard-negative synthesis can capture sufficient fine-grained visual-semantic alignment for open-domain entities without requiring generative modeling capacity."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"WikiCLIP shows a contrastive model with LLM entity embeddings and patch-level adaptation can outperform generative methods on open-domain visual entity recognition while running nearly 100 times faster."}],"snapshot_sha256":"06a0564b5c5b5caa71cc01d6446f56efaf2b9350b5dacde8e4fe3be5677edb6c"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"7e66b8e0fb1eefff1429e64fb08d6488bcd9130c9bcd40c3f7c67a5d784e4b43"},"paper":{"abstract_excerpt":"Open-domain visual entity recognition (VER) seeks to associate images with entities in encyclopedic knowledge bases such as Wikipedia. Recent generative methods tailored for VER demonstrate strong performance but incur high computational costs, limiting their scalability and practical deployment. In this work, we revisit the contrastive paradigm for VER and introduce WikiCLIP, a simple yet effective framework that establishes a strong and efficient baseline for open-domain VER. WikiCLIP leverages large language model embeddings as knowledge-rich entity representations and enhances them with a ","authors_text":"Jiaxuan Sun, Longtian Qiu, Shan Ning, Xuming He","cross_cats":[],"headline":"WikiCLIP shows a contrastive model with LLM entity embeddings and patch-level adaptation can outperform generative methods on open-domain visual entity recognition while running nearly 100 times faster.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T17:18:53Z","title":"WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition"},"references":{"count":47,"internal_anchors":12,"resolved_work":47,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Flamingo: a visual language model for few-shot learning.Advances in Neural Information Processing Systems, 35:23716–23736,","work_id":"bb8f1e74-4594-4917-9ca6-659e49ced632","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Good news, everyone! context driven entity-aware captioning for news images","work_id":"7e60f8b5-4339-4afb-b1fc-a8320ec0c45d","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Web-scale visual entity recognition: An llm-driven data approach.ArXiv, abs/2410.23676, 2024","work_id":"c5457418-5a8e-4591-bd89-f0ae7c614656","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A generative approach for wikipedia-scale visual entity recognition.2024 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR), pages 17313– 17322, 2024","work_id":"3eb0a83e-2c9e-4997-addb-6060be16df31","year":2024},{"cited_arxiv_id":"2209.06794","doi":"","is_internal_anchor":true,"ref_index":5,"title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","work_id":"29921cff-29c1-4aad-a27d-adac346027ec","year":2022}],"snapshot_sha256":"7f0b1f1649ebe0fb07b1d5e4e82f341deb4a10165027498b7290c8dbd8aa54ca"},"source":{"id":"2603.09921","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T13:08:23.785959Z","id":"f2cbff46-72c2-48a2-a421-c47f7108d2a7","model_set":{"reader":"grok-4.3"},"one_line_summary":"WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"WikiCLIP shows a contrastive model with LLM entity embeddings and patch-level adaptation can outperform generative methods on open-domain visual entity recognition while running nearly 100 times faster.","strongest_claim":"WikiCLIP achieves a 16% improvement on the challenging OVEN unseen set, while reducing inference latency by nearly 100 times compared with the leading generative model, AutoVER.","weakest_assumption":"That LLM-derived entity embeddings combined with the Vision-Guided Knowledge Adaptor and hard-negative synthesis can capture sufficient fine-grained visual-semantic alignment for open-domain entities without requiring generative modeling capacity."}},"verdict_id":"f2cbff46-72c2-48a2-a421-c47f7108d2a7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:313d2d04db6f7103ef5fd9ae575e6de480b87e31dc364f3084b2a64e0ad7d1aa","target":"record","created_at":"2026-05-17T23:38:59Z","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":"dc3aec675a8b18c858459f81e936f858bc8662129adfc9aaa2e8510bed3a343f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T17:18:53Z","title_canon_sha256":"cda13c5300ca32b649746b9d9ab668a1ad3bb4121b5caee3abe72c86483879ee"},"schema_version":"1.0","source":{"id":"2603.09921","kind":"arxiv","version":3}},"canonical_sha256":"c15cc8ba1666f7cf90da73c08196001a7820e7b907a90061aa6d03ee9149eb07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c15cc8ba1666f7cf90da73c08196001a7820e7b907a90061aa6d03ee9149eb07","first_computed_at":"2026-05-17T23:38:59.671088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:59.671088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+hFZNU3artmPPNA5d4OVhpmiXYgQQFs/vI4eLeHYr0KTnNOmXPH2sTRjLc9jNXyyHVTtaHk8jK/R2E4ohebCBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:59.671827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.09921","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:313d2d04db6f7103ef5fd9ae575e6de480b87e31dc364f3084b2a64e0ad7d1aa","sha256:42f730d98179839aae2f3a3d4c1603b152a6531fb60b3e5677092335a7f1fef0"],"state_sha256":"aae98af9f55cd9c82ee6f153b641526bbbd2df42abf0bf318e78eed74f5df495"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AEaIuLdrdK2DLtaQTSG/WU9D17ZlLbzxirjQ1XwzDZqZXKQr6tXz27tje+mY8mpPE+m/NhTY8cv8pvnG1bWJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:10:49.651099Z","bundle_sha256":"5dd86efd22979deef63cd72b1796e968fe6480a0de1a61c98a1cd8d79c423dd5"}}