{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:J7DZSRRHZSUK4DDTYEUNXC7YTX","short_pith_number":"pith:J7DZSRRH","canonical_record":{"source":{"id":"2605.10180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:31:57Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"5bd83ebcd5a390aaa8f1b15e30b8a1f02c964df625bd043cfdba626a1c5caca1","abstract_canon_sha256":"7962f16007da89688f376f618fc6b8e422059591c07a1bc3255eb1f9bffea8c9"},"schema_version":"1.0"},"canonical_sha256":"4fc7994627cca8ae0c73c128db8bf89dd91e96ae013bf9d66196e948314b5872","source":{"kind":"arxiv","id":"2605.10180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10180","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10180v1","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10180","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"J7DZSRRHZSUK","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"J7DZSRRHZSUK4DDT","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"J7DZSRRH","created_at":"2026-05-20T17:03:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:J7DZSRRHZSUK4DDTYEUNXC7YTX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.10180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:31:57Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"5bd83ebcd5a390aaa8f1b15e30b8a1f02c964df625bd043cfdba626a1c5caca1","abstract_canon_sha256":"7962f16007da89688f376f618fc6b8e422059591c07a1bc3255eb1f9bffea8c9"},"schema_version":"1.0"},"canonical_sha256":"4fc7994627cca8ae0c73c128db8bf89dd91e96ae013bf9d66196e948314b5872","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T17:03:46.341501Z","signature_b64":"LRD3n42iHVMpOd8ea2EzV417TMe0B6vYSgYCMCLgRDfbvF75UiLEdSo5F2yHumHwN/Y3NuzcgU56MuzHDxx0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fc7994627cca8ae0c73c128db8bf89dd91e96ae013bf9d66196e948314b5872","last_reissued_at":"2026-05-20T17:03:46.339984Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T17:03:46.339984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.10180","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":"2026-05-20T17:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jFcEAhHdiqA8d0T1aj6Xv8BSzibYteYqPzkwiQk2WAYkaJyHlpUsFqca+MtuEDkTLxXLPp3JOeN3g3hZLqKjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:43:32.180124Z"},"content_sha256":"61c81587dd2a7930e55a2a5e1c1368a93bab3696b97445489a4876a050b0d4fa","schema_version":"1.0","event_id":"sha256:61c81587dd2a7930e55a2a5e1c1368a93bab3696b97445489a4876a050b0d4fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:J7DZSRRHZSUK4DDTYEUNXC7YTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Attention heads in diffusion transformers show concept-specific sensitivity that lets risky content be detected and suppressed at inference time.","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"An-An Liu, Chenyu Zhang, Lanjun Wang, Ruidong Chen, Wenhui Li, Yueyang Cheng","submitted_at":"2026-05-11T08:31:57Z","abstract_excerpt":"The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyright-protected images, highlighting the need for effective safeguards within the models themselves. Although existing methods have been proposed to eliminate risky concepts from T2I models, they are primarily developed for earlier U-Net architectures, leaving the state-of-the-art Diffusion-Transformer-based T2I models inadequately protected. This gap stems from a fundamental architectural shift: Diffusion Transformers (DiTs) entangle semantic inje"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"attention heads exhibit concept-specific sensitivity. This property enables both the detection and suppression of risky content.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that concept-specific sensitivity in attention heads is stable enough across prompts and models to allow reliable detection and suppression of risky tokens without degrading overall image quality or being easily circumvented.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Attention heads in diffusion transformers show concept-specific sensitivity that lets risky content be detected and suppressed at inference time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e44bcf953a71c6a9d8580a55bda40371cbe1f59578773e7a67e8a1f392dd919c"},"source":{"id":"2605.10180","kind":"arxiv","version":1},"verdict":{"id":"97611447-afe7-4c92-b19a-b393f3075579","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T04:32:10.137925Z","strongest_claim":"attention heads exhibit concept-specific sensitivity. This property enables both the detection and suppression of risky content.","one_line_summary":"A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that concept-specific sensitivity in attention heads is stable enough across prompts and models to allow reliable detection and suppression of risky tokens without degrading overall image quality or being easily circumvented.","pith_extraction_headline":"Attention heads in diffusion transformers show concept-specific sensitivity that lets risky content be detected and suppressed at inference time."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10180/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.936784Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:39:02.398987Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T12:01:17.240386Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:37:44.434715Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d04589fb9943b6f585cf35f0a023f71baa14c5f061d03ff4f49491e9813fa483"},"references":{"count":51,"sample":[{"doi":"","year":2019,"title":"Praneeth Bedapudi. 2019. NudeNet: Neural Nets for Nudity Detection and Cen- soring. https://github.com/bedapudi6788/NudeNet. Python package, version 1.1.0","work_id":"05429815-c391-487d-9c42-9f477dd80878","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Black Forest Labs. 2025. FLUX.1 [dev] — Model Card. https://huggingface.co/ black-forest-labs/FLUX.1-dev","work_id":"743b8ee9-fd06-420a-869c-b0ea17efba28","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","work_id":"f1080a62-48e1-4255-b023-7556be57370d","ref_index":3,"cited_arxiv_id":"2511.22699","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qi Cai, Yehao Li, Yingwei Pan, Ting Yao, and Tao Mei. 2025. HiDream-I1: An Open-Source High-Efficient Image Generative Foundation Model. InProceedings of the 33rd ACM International Conference on Multi","work_id":"bc364007-0952-4e44-bc27-da8838fc0d89","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","work_id":"77157568-e4be-4041-bb20-388177fc59d0","ref_index":5,"cited_arxiv_id":"2310.00426","is_internal_anchor":true}],"resolved_work":51,"snapshot_sha256":"3e2add9f9dbd6f1f5896e2a5400e8f171f979efab57a4fc3670c049b91c39d19","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ea68a205f558a39adf58d56a0c5479a34351664edab4f1c3d850d7589e8ba486"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"97611447-afe7-4c92-b19a-b393f3075579"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T17:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wyiEGJ6FLyynArAEchcdpcbkZisrwRsEPg/7OUQxGSs8bmYwa9kkkgB17V5sDHX6J66BT9BKUtmamBXRHQRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:43:32.180777Z"},"content_sha256":"5c58995292c5a47d1a1176bfa8932cffed4cf98bdc87b91fa4f0f0e4964f7ec0","schema_version":"1.0","event_id":"sha256:5c58995292c5a47d1a1176bfa8932cffed4cf98bdc87b91fa4f0f0e4964f7ec0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J7DZSRRHZSUK4DDTYEUNXC7YTX/bundle.json","state_url":"https://pith.science/pith/J7DZSRRHZSUK4DDTYEUNXC7YTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J7DZSRRHZSUK4DDTYEUNXC7YTX/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":"2026-05-30T15:43:32Z","links":{"resolver":"https://pith.science/pith/J7DZSRRHZSUK4DDTYEUNXC7YTX","bundle":"https://pith.science/pith/J7DZSRRHZSUK4DDTYEUNXC7YTX/bundle.json","state":"https://pith.science/pith/J7DZSRRHZSUK4DDTYEUNXC7YTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J7DZSRRHZSUK4DDTYEUNXC7YTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:J7DZSRRHZSUK4DDTYEUNXC7YTX","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":"7962f16007da89688f376f618fc6b8e422059591c07a1bc3255eb1f9bffea8c9","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:31:57Z","title_canon_sha256":"5bd83ebcd5a390aaa8f1b15e30b8a1f02c964df625bd043cfdba626a1c5caca1"},"schema_version":"1.0","source":{"id":"2605.10180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10180","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10180v1","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10180","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"J7DZSRRHZSUK","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"J7DZSRRHZSUK4DDT","created_at":"2026-05-20T17:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"J7DZSRRH","created_at":"2026-05-20T17:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:5c58995292c5a47d1a1176bfa8932cffed4cf98bdc87b91fa4f0f0e4964f7ec0","target":"graph","created_at":"2026-05-20T17:03:46Z","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":"attention heads exhibit concept-specific sensitivity. This property enables both the detection and suppression of risky content."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that concept-specific sensitivity in attention heads is stable enough across prompts and models to allow reliable detection and suppression of risky tokens without degrading overall image quality or being easily circumvented."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Attention heads in diffusion transformers show concept-specific sensitivity that lets risky content be detected and suppressed at inference time."}],"snapshot_sha256":"e44bcf953a71c6a9d8580a55bda40371cbe1f59578773e7a67e8a1f392dd919c"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ea68a205f558a39adf58d56a0c5479a34351664edab4f1c3d850d7589e8ba486"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.936784Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:39:02.398987Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T12:01:17.240386Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:37:44.434715Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10180/integrity.json","findings":[],"snapshot_sha256":"d04589fb9943b6f585cf35f0a023f71baa14c5f061d03ff4f49491e9813fa483","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyright-protected images, highlighting the need for effective safeguards within the models themselves. Although existing methods have been proposed to eliminate risky concepts from T2I models, they are primarily developed for earlier U-Net architectures, leaving the state-of-the-art Diffusion-Transformer-based T2I models inadequately protected. This gap stems from a fundamental architectural shift: Diffusion Transformers (DiTs) entangle semantic inje","authors_text":"An-An Liu, Chenyu Zhang, Lanjun Wang, Ruidong Chen, Wenhui Li, Yueyang Cheng","cross_cats":["cs.CR"],"headline":"Attention heads in diffusion transformers show concept-specific sensitivity that lets risky content be detected and suppressed at inference time.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:31:57Z","title":"What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers"},"references":{"count":51,"internal_anchors":6,"resolved_work":51,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Praneeth Bedapudi. 2019. NudeNet: Neural Nets for Nudity Detection and Cen- soring. https://github.com/bedapudi6788/NudeNet. Python package, version 1.1.0","work_id":"05429815-c391-487d-9c42-9f477dd80878","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Black Forest Labs. 2025. FLUX.1 [dev] — Model Card. https://huggingface.co/ black-forest-labs/FLUX.1-dev","work_id":"743b8ee9-fd06-420a-869c-b0ea17efba28","year":2025},{"cited_arxiv_id":"2511.22699","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","work_id":"f1080a62-48e1-4255-b023-7556be57370d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Qi Cai, Yehao Li, Yingwei Pan, Ting Yao, and Tao Mei. 2025. HiDream-I1: An Open-Source High-Efficient Image Generative Foundation Model. InProceedings of the 33rd ACM International Conference on Multi","work_id":"bc364007-0952-4e44-bc27-da8838fc0d89","year":2025},{"cited_arxiv_id":"2310.00426","doi":"","is_internal_anchor":true,"ref_index":5,"title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","work_id":"77157568-e4be-4041-bb20-388177fc59d0","year":2023}],"snapshot_sha256":"3e2add9f9dbd6f1f5896e2a5400e8f171f979efab57a4fc3670c049b91c39d19"},"source":{"id":"2605.10180","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-12T04:32:10.137925Z","id":"97611447-afe7-4c92-b19a-b393f3075579","model_set":{"reader":"grok-4.3"},"one_line_summary":"A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Attention heads in diffusion transformers show concept-specific sensitivity that lets risky content be detected and suppressed at inference time.","strongest_claim":"attention heads exhibit concept-specific sensitivity. This property enables both the detection and suppression of risky content.","weakest_assumption":"The assumption that concept-specific sensitivity in attention heads is stable enough across prompts and models to allow reliable detection and suppression of risky tokens without degrading overall image quality or being easily circumvented."}},"verdict_id":"97611447-afe7-4c92-b19a-b393f3075579"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:61c81587dd2a7930e55a2a5e1c1368a93bab3696b97445489a4876a050b0d4fa","target":"record","created_at":"2026-05-20T17:03:46Z","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":"7962f16007da89688f376f618fc6b8e422059591c07a1bc3255eb1f9bffea8c9","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:31:57Z","title_canon_sha256":"5bd83ebcd5a390aaa8f1b15e30b8a1f02c964df625bd043cfdba626a1c5caca1"},"schema_version":"1.0","source":{"id":"2605.10180","kind":"arxiv","version":1}},"canonical_sha256":"4fc7994627cca8ae0c73c128db8bf89dd91e96ae013bf9d66196e948314b5872","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fc7994627cca8ae0c73c128db8bf89dd91e96ae013bf9d66196e948314b5872","first_computed_at":"2026-05-20T17:03:46.339984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T17:03:46.339984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRD3n42iHVMpOd8ea2EzV417TMe0B6vYSgYCMCLgRDfbvF75UiLEdSo5F2yHumHwN/Y3NuzcgU56MuzHDxx0DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T17:03:46.341501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61c81587dd2a7930e55a2a5e1c1368a93bab3696b97445489a4876a050b0d4fa","sha256:5c58995292c5a47d1a1176bfa8932cffed4cf98bdc87b91fa4f0f0e4964f7ec0"],"state_sha256":"3348a94daa480edd5ab65b9689ec0fc39a98e1dd19ee2274f2d227693b06489a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHqkkoFvgRMmLsjHN3mYL1I2hVF6mQXNzHTH33LlUU35pKFMPHMBjEhABwSlMQx36J5wG7O5n7nfkie6/LpJBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:43:32.183423Z","bundle_sha256":"daa3a46f45e6b77e4f04ec6561bcdbd23e39c093f75c0def3a215caae3aa0109"}}