{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H3H5HFP65P5WUHA5ERRTE6W4TH","short_pith_number":"pith:H3H5HFP6","canonical_record":{"source":{"id":"2312.14238","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"a1ac82f747e2a3587afe40679d605d0e334026956a02cd3c1db6c73412eb7a52","abstract_canon_sha256":"7a45ff5ab2ecc0bdc5ca8cf64ddcbda622701f0eef9e49594e9068a99f433a99"},"schema_version":"1.0"},"canonical_sha256":"3ecfd395feebfb6a1c1d2463327adc99ff4b060d707ccbf59f6e4e06d4dc0e4e","source":{"kind":"arxiv","id":"2312.14238","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14238","created_at":"2026-05-18T04:02:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14238v3","created_at":"2026-05-18T04:02:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14238","created_at":"2026-05-18T04:02:53Z"},{"alias_kind":"pith_short_12","alias_value":"H3H5HFP65P5W","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"H3H5HFP65P5WUHA5","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"H3H5HFP6","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H3H5HFP65P5WUHA5ERRTE6W4TH","target":"record","payload":{"canonical_record":{"source":{"id":"2312.14238","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"a1ac82f747e2a3587afe40679d605d0e334026956a02cd3c1db6c73412eb7a52","abstract_canon_sha256":"7a45ff5ab2ecc0bdc5ca8cf64ddcbda622701f0eef9e49594e9068a99f433a99"},"schema_version":"1.0"},"canonical_sha256":"3ecfd395feebfb6a1c1d2463327adc99ff4b060d707ccbf59f6e4e06d4dc0e4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:53.809955Z","signature_b64":"nCCnl6a0klzHpAErey9Ky91MOtvfrc50+NcOUoNMdVW06cbT2Q39bKxgGxtLSKuKsbGEy0HGYOJRMg05bvbSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ecfd395feebfb6a1c1d2463327adc99ff4b060d707ccbf59f6e4e06d4dc0e4e","last_reissued_at":"2026-05-18T04:02:53.809045Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:53.809045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.14238","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":"2026-05-18T04:02:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bs7DbNSaIs5Qxe44VW2QgmATOSRNRJ42n6Q8+9mggTgy+4uAws23Xh8WTj9+BU7ivAUm4XbeLzyfrfsvoW0EDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T08:53:50.764249Z"},"content_sha256":"3d85247b3992776ed5ef8377a1cbed7f449c4843751126793924477bd496156d","schema_version":"1.0","event_id":"sha256:3d85247b3992776ed5ef8377a1cbed7f449c4843751126793924477bd496156d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H3H5HFP65P5WUHA5ERRTE6W4TH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"InternVL scales a vision foundation model to 6 billion parameters and progressively aligns it with an LLM on web-scale image-text data to reach state-of-the-art performance on 32 visual-linguistic benchmarks.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Guo Chen, Jiannan Wu, Jifeng Dai, Lewei Lu, Muyan Zhong, Ping Luo, Qinglong Zhang, Sen Xing, Tong Lu, Weijie Su, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zhe Chen","submitted_at":"2023-12-21T18:59:31Z","abstract_excerpt":"The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That scaling the vision model to 6 billion parameters and aligning it progressively with web-scale image-text data from various sources will produce generalizable state-of-the-art performance across 32 diverse benchmarks without significant overfitting or data-source biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"InternVL scales a vision foundation model to 6 billion parameters and progressively aligns it with an LLM on web-scale image-text data to reach state-of-the-art performance on 32 visual-linguistic benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9dd1ca293bd7db08a072a922f3a7e5792e3c489632dd873e9c75dc557203fbbe"},"source":{"id":"2312.14238","kind":"arxiv","version":3},"verdict":{"id":"9dc11b10-afed-4f51-b3b7-6fed5542f104","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T22:42:55.432347Z","strongest_claim":"we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems.","one_line_summary":"InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That scaling the vision model to 6 billion parameters and aligning it progressively with web-scale image-text data from various sources will produce generalizable state-of-the-art performance across 32 diverse benchmarks without significant overfitting or data-source biases.","pith_extraction_headline":"InternVL scales a vision foundation model to 6 billion parameters and progressively aligns it with an LLM on web-scale image-text data to reach state-of-the-art performance on 32 visual-linguistic benchmarks."},"references":{"count":189,"sample":[{"doi":"","year":2012,"title":"Towards zero- shot cross-lingual image retrieval","work_id":"dceda28c-2ba0-4fd3-b121-ead8d5f338ab","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Nocaps: Novel object cap- tioning at scale","work_id":"f5941427-8e5e-4a5a-93c2-318cd6427d75","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning","work_id":"1623aeed-8003-46af-bbeb-d3c46c689404","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen Technical Report","work_id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","ref_index":4,"cited_arxiv_id":"2309.16609","is_internal_anchor":true},{"doi":"","year":null,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":5,"cited_arxiv_id":"2308.12966","is_internal_anchor":true}],"resolved_work":189,"snapshot_sha256":"943d9fc9aa7734f0084212eb383e305b6d4a4b30fc88b9279a460ceca1979908","internal_anchors":41},"formal_canon":{"evidence_count":2,"snapshot_sha256":"019be00942ea8ea10f7d86710feb6873d89eb14a6b30b44c02b030c40723836f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"9dc11b10-afed-4f51-b3b7-6fed5542f104"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:02:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QAemqhvvInbk0DGRBenzLvDcf9u+rIK8+W4P2LY8fvgszupfn2A+OpfdxyJHZJT8osW+RJaPjtTRvw9SMxUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T08:53:50.765150Z"},"content_sha256":"aaa48a97caff371d33d050ab45696d676c59d56eae86193d2c05a4fd7b3f93c5","schema_version":"1.0","event_id":"sha256:aaa48a97caff371d33d050ab45696d676c59d56eae86193d2c05a4fd7b3f93c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H3H5HFP65P5WUHA5ERRTE6W4TH/bundle.json","state_url":"https://pith.science/pith/H3H5HFP65P5WUHA5ERRTE6W4TH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H3H5HFP65P5WUHA5ERRTE6W4TH/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":"2026-06-04T08:53:50Z","links":{"resolver":"https://pith.science/pith/H3H5HFP65P5WUHA5ERRTE6W4TH","bundle":"https://pith.science/pith/H3H5HFP65P5WUHA5ERRTE6W4TH/bundle.json","state":"https://pith.science/pith/H3H5HFP65P5WUHA5ERRTE6W4TH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H3H5HFP65P5WUHA5ERRTE6W4TH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H3H5HFP65P5WUHA5ERRTE6W4TH","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":"7a45ff5ab2ecc0bdc5ca8cf64ddcbda622701f0eef9e49594e9068a99f433a99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:59:31Z","title_canon_sha256":"a1ac82f747e2a3587afe40679d605d0e334026956a02cd3c1db6c73412eb7a52"},"schema_version":"1.0","source":{"id":"2312.14238","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14238","created_at":"2026-05-18T04:02:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14238v3","created_at":"2026-05-18T04:02:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14238","created_at":"2026-05-18T04:02:53Z"},{"alias_kind":"pith_short_12","alias_value":"H3H5HFP65P5W","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"H3H5HFP65P5WUHA5","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"H3H5HFP6","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:aaa48a97caff371d33d050ab45696d676c59d56eae86193d2c05a4fd7b3f93c5","target":"graph","created_at":"2026-05-18T04:02:53Z","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":"we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That scaling the vision model to 6 billion parameters and aligning it progressively with web-scale image-text data from various sources will produce generalizable state-of-the-art performance across 32 diverse benchmarks without significant overfitting or data-source biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"InternVL scales a vision foundation model to 6 billion parameters and progressively aligns it with an LLM on web-scale image-text data to reach state-of-the-art performance on 32 visual-linguistic benchmarks."}],"snapshot_sha256":"9dd1ca293bd7db08a072a922f3a7e5792e3c489632dd873e9c75dc557203fbbe"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"019be00942ea8ea10f7d86710feb6873d89eb14a6b30b44c02b030c40723836f"},"paper":{"abstract_excerpt":"The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on","authors_text":"Bin Li, Guo Chen, Jiannan Wu, Jifeng Dai, Lewei Lu, Muyan Zhong, Ping Luo, Qinglong Zhang, Sen Xing, Tong Lu, Weijie Su, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zhe Chen","cross_cats":[],"headline":"InternVL scales a vision foundation model to 6 billion parameters and progressively aligns it with an LLM on web-scale image-text data to reach state-of-the-art performance on 32 visual-linguistic benchmarks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:59:31Z","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks"},"references":{"count":189,"internal_anchors":41,"resolved_work":189,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Towards zero- shot cross-lingual image retrieval","work_id":"dceda28c-2ba0-4fd3-b121-ead8d5f338ab","year":2012},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Nocaps: Novel object cap- tioning at scale","work_id":"f5941427-8e5e-4a5a-93c2-318cd6427d75","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Flamingo: a visual language model for few-shot learning","work_id":"1623aeed-8003-46af-bbeb-d3c46c689404","year":2022},{"cited_arxiv_id":"2309.16609","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Qwen Technical Report","work_id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","year":2023},{"cited_arxiv_id":"2308.12966","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","year":null}],"snapshot_sha256":"943d9fc9aa7734f0084212eb383e305b6d4a4b30fc88b9279a460ceca1979908"},"source":{"id":"2312.14238","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-13T22:42:55.432347Z","id":"9dc11b10-afed-4f51-b3b7-6fed5542f104","model_set":{"reader":"grok-4.3"},"one_line_summary":"InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"InternVL scales a vision foundation model to 6 billion parameters and progressively aligns it with an LLM on web-scale image-text data to reach state-of-the-art performance on 32 visual-linguistic benchmarks.","strongest_claim":"we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems.","weakest_assumption":"That scaling the vision model to 6 billion parameters and aligning it progressively with web-scale image-text data from various sources will produce generalizable state-of-the-art performance across 32 diverse benchmarks without significant overfitting or data-source biases."}},"verdict_id":"9dc11b10-afed-4f51-b3b7-6fed5542f104"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3d85247b3992776ed5ef8377a1cbed7f449c4843751126793924477bd496156d","target":"record","created_at":"2026-05-18T04:02:53Z","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":"7a45ff5ab2ecc0bdc5ca8cf64ddcbda622701f0eef9e49594e9068a99f433a99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:59:31Z","title_canon_sha256":"a1ac82f747e2a3587afe40679d605d0e334026956a02cd3c1db6c73412eb7a52"},"schema_version":"1.0","source":{"id":"2312.14238","kind":"arxiv","version":3}},"canonical_sha256":"3ecfd395feebfb6a1c1d2463327adc99ff4b060d707ccbf59f6e4e06d4dc0e4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ecfd395feebfb6a1c1d2463327adc99ff4b060d707ccbf59f6e4e06d4dc0e4e","first_computed_at":"2026-05-18T04:02:53.809045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:02:53.809045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCCnl6a0klzHpAErey9Ky91MOtvfrc50+NcOUoNMdVW06cbT2Q39bKxgGxtLSKuKsbGEy0HGYOJRMg05bvbSBw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:02:53.809955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14238","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d85247b3992776ed5ef8377a1cbed7f449c4843751126793924477bd496156d","sha256:aaa48a97caff371d33d050ab45696d676c59d56eae86193d2c05a4fd7b3f93c5"],"state_sha256":"c29fabaedcccc17d575051f39b518ec04c3950cd570ed0e62a49b5716b3baf6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLGNq2fYxVJC1JUCpkYTuxhRXq0SiYqCulDavV3ldYbbdv4SX3E6I/A0qZ9ZFLDG2ljz+FC87awDwIhhobkDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T08:53:50.768864Z","bundle_sha256":"36dd711f26055fa1bdd6c1dd595a090979df0124c18ca9c2117f336986bb171c"}}