{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BOLR37ZKRVR2XXZQZD44HGFVZZ","short_pith_number":"pith:BOLR37ZK","canonical_record":{"source":{"id":"2602.13483","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T21:41:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86d076f178dc5ed41fb42c4f95499884d4ed051998d7844be5f96d493f8bee6b","abstract_canon_sha256":"29dc341a63e705f5542be6f9b1beb90f833899d66d98bae03ca3acaa88ddf930"},"schema_version":"1.0"},"canonical_sha256":"0b971dff2a8d63abdf30c8f9c398b5ce5a61795ae7e3d5587651a8476c0f9a29","source":{"kind":"arxiv","id":"2602.13483","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.13483","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.13483v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13483","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"BOLR37ZKRVR2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BOLR37ZKRVR2XXZQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BOLR37ZK","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BOLR37ZKRVR2XXZQZD44HGFVZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2602.13483","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T21:41:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86d076f178dc5ed41fb42c4f95499884d4ed051998d7844be5f96d493f8bee6b","abstract_canon_sha256":"29dc341a63e705f5542be6f9b1beb90f833899d66d98bae03ca3acaa88ddf930"},"schema_version":"1.0"},"canonical_sha256":"0b971dff2a8d63abdf30c8f9c398b5ce5a61795ae7e3d5587651a8476c0f9a29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.172241Z","signature_b64":"w3NNWt0lg/4akZ5O7c5eOYeOMr/Rh7wzKR5d6lZOktCkaPn/+OXyPL20zA5vmC+fa3r9YOJ0zI9F5Z/NGuOBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b971dff2a8d63abdf30c8f9c398b5ce5a61795ae7e3d5587651a8476c0f9a29","last_reissued_at":"2026-05-17T23:39:16.171443Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.171443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.13483","source_version":2,"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":"rX2dkp/PTcdwPGKSebfs1sKekLTkdujKhdpO+9p7+7zSQdAwoeOOxPafM6u1U07yxJQQOqlGvNK4S1uyNK6xBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:31:37.435212Z"},"content_sha256":"e706b77b44080341f9636630d04450c108d3025e931a20fbf9a3787b2af568ab","schema_version":"1.0","event_id":"sha256:e706b77b44080341f9636630d04450c108d3025e931a20fbf9a3787b2af568ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BOLR37ZKRVR2XXZQZD44HGFVZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finding Interpretable Prompt-Specific Circuits in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ACC++ extracts causal attention signals from language models in a single forward pass, revealing many are interpretable via natural language.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Azalea Rohr, Gabriel Franco, Lucas M. Tassis, Mark Crovella","submitted_at":"2026-02-13T21:41:17Z","abstract_excerpt":"Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To this end, we introduce ACC++, an improved circuit-tracing method based on the principle of attention-causal communication (ACC) [1], which identifies signals, i.e., contents of low dimensional subspaces that cause attention on a token pair. ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++ consist of components that are causal for the model's attention decisions, together with the low-dimensional signals used to communicate between them. Across multiple models, a substantial portion of ACC++ signals are interpretable: many signals admit a short natural-language description.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the low-dimensional subspaces identified by the attention-causal communication principle are in fact the causal signals driving attention decisions, and that the natural-language descriptions assigned to them reflect genuine model mechanisms rather than post-hoc interpretations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ACC++ traces prompt-specific circuits in language models from one forward pass by extracting interpretable low-dimensional causal signals, revealing clustered mechanisms for indirect object identification and language-specific signals in multilingual settings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ACC++ extracts causal attention signals from language models in a single forward pass, revealing many are interpretable via natural language.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"064ee08e1b484f1ebf162daa1bb73c89d5d5707a45d4e68f401420850e404808"},"source":{"id":"2602.13483","kind":"arxiv","version":2},"verdict":{"id":"348b5f11-9cd1-4430-813f-b5680bd5f004","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T22:03:52.950991Z","strongest_claim":"ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++ consist of components that are causal for the model's attention decisions, together with the low-dimensional signals used to communicate between them. Across multiple models, a substantial portion of ACC++ signals are interpretable: many signals admit a short natural-language description.","one_line_summary":"ACC++ traces prompt-specific circuits in language models from one forward pass by extracting interpretable low-dimensional causal signals, revealing clustered mechanisms for indirect object identification and language-specific signals in multilingual settings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the low-dimensional subspaces identified by the attention-causal communication principle are in fact the causal signals driving attention decisions, and that the natural-language descriptions assigned to them reflect genuine model mechanisms rather than post-hoc interpretations.","pith_extraction_headline":"ACC++ extracts causal attention signals from language models in a single forward pass, revealing many are interpretable via natural language."},"references":{"count":18,"sample":[{"doi":"10.48550/arxiv.2307","year":2025,"title":"doi:10.48550/ARXIV.2307","work_id":"1b282611-e55d-4374-95d1-628b9e4bcd1f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Set up the counterfactual.Choose an attention head and a destination–source pair, then decide whether we are searching fordestinationsignals (in the destination token) orsourcesignals (distributed acr","work_id":"9c99932e-180e-4878-b788-7649650dc9e2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Enumerate candidate signals.Decompose the residual stream into outputs of upstream components, and project each component’s contribution onto the head’s singular-vector directions to form a set of can","work_id":"a44c09f5-d705-4486-b316-762de16fbff7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Build a contribution table.Convert candidates into a contribution matrix whose rows correspond to candidate signals and whose columns correspond to source positions in the destination row of attention","work_id":"7041f06b-dbf6-4eb7-a5c3-2e1d03472a41","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Score candidates with attribution.Use Integrated Gradients to assign each candidate a fixed importance score for the attention weight on the chosen source token, while accounting for Softmax competiti","work_id":"fac3f535-87d1-4015-aa55-400822f413b1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"ee4e0e0bb5dabc6b2aa4b7cbeaf7f41b3dfff7174bfbc1c49d5afd25f2688138","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"348b5f11-9cd1-4430-813f-b5680bd5f004"},"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":"RzjOqRSYQ3XnHtjd7a9uHtpoWghZWcl5B/m3uljdSl15DwKJRnWp+U1YXp/IFOOyiSWXx+GyYsQzO3ElMBkpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:31:37.435914Z"},"content_sha256":"5ea7333434894cc90051afa2e952238ff8adb7911a66956bcd2b2bb85de328d0","schema_version":"1.0","event_id":"sha256:5ea7333434894cc90051afa2e952238ff8adb7911a66956bcd2b2bb85de328d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOLR37ZKRVR2XXZQZD44HGFVZZ/bundle.json","state_url":"https://pith.science/pith/BOLR37ZKRVR2XXZQZD44HGFVZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOLR37ZKRVR2XXZQZD44HGFVZZ/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":"2026-06-04T01:31:37Z","links":{"resolver":"https://pith.science/pith/BOLR37ZKRVR2XXZQZD44HGFVZZ","bundle":"https://pith.science/pith/BOLR37ZKRVR2XXZQZD44HGFVZZ/bundle.json","state":"https://pith.science/pith/BOLR37ZKRVR2XXZQZD44HGFVZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOLR37ZKRVR2XXZQZD44HGFVZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BOLR37ZKRVR2XXZQZD44HGFVZZ","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":"29dc341a63e705f5542be6f9b1beb90f833899d66d98bae03ca3acaa88ddf930","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T21:41:17Z","title_canon_sha256":"86d076f178dc5ed41fb42c4f95499884d4ed051998d7844be5f96d493f8bee6b"},"schema_version":"1.0","source":{"id":"2602.13483","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.13483","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.13483v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13483","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"BOLR37ZKRVR2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BOLR37ZKRVR2XXZQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BOLR37ZK","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5ea7333434894cc90051afa2e952238ff8adb7911a66956bcd2b2bb85de328d0","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":"ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++ consist of components that are causal for the model's attention decisions, together with the low-dimensional signals used to communicate between them. Across multiple models, a substantial portion of ACC++ signals are interpretable: many signals admit a short natural-language description."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the low-dimensional subspaces identified by the attention-causal communication principle are in fact the causal signals driving attention decisions, and that the natural-language descriptions assigned to them reflect genuine model mechanisms rather than post-hoc interpretations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ACC++ traces prompt-specific circuits in language models from one forward pass by extracting interpretable low-dimensional causal signals, revealing clustered mechanisms for indirect object identification and language-specific signals in multilingual settings."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ACC++ extracts causal attention signals from language models in a single forward pass, revealing many are interpretable via natural language."}],"snapshot_sha256":"064ee08e1b484f1ebf162daa1bb73c89d5d5707a45d4e68f401420850e404808"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To this end, we introduce ACC++, an improved circuit-tracing method based on the principle of attention-causal communication (ACC) [1], which identifies signals, i.e., contents of low dimensional subspaces that cause attention on a token pair. ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++","authors_text":"Azalea Rohr, Gabriel Franco, Lucas M. Tassis, Mark Crovella","cross_cats":["cs.AI"],"headline":"ACC++ extracts causal attention signals from language models in a single forward pass, revealing many are interpretable via natural language.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T21:41:17Z","title":"Finding Interpretable Prompt-Specific Circuits in Language Models"},"references":{"count":18,"internal_anchors":0,"resolved_work":18,"sample":[{"cited_arxiv_id":"","doi":"10.48550/arxiv.2307","is_internal_anchor":false,"ref_index":1,"title":"doi:10.48550/ARXIV.2307","work_id":"1b282611-e55d-4374-95d1-628b9e4bcd1f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Set up the counterfactual.Choose an attention head and a destination–source pair, then decide whether we are searching fordestinationsignals (in the destination token) orsourcesignals (distributed acr","work_id":"9c99932e-180e-4878-b788-7649650dc9e2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Enumerate candidate signals.Decompose the residual stream into outputs of upstream components, and project each component’s contribution onto the head’s singular-vector directions to form a set of can","work_id":"a44c09f5-d705-4486-b316-762de16fbff7","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Build a contribution table.Convert candidates into a contribution matrix whose rows correspond to candidate signals and whose columns correspond to source positions in the destination row of attention","work_id":"7041f06b-dbf6-4eb7-a5c3-2e1d03472a41","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Score candidates with attribution.Use Integrated Gradients to assign each candidate a fixed importance score for the attention weight on the chosen source token, while accounting for Softmax competiti","work_id":"fac3f535-87d1-4015-aa55-400822f413b1","year":null}],"snapshot_sha256":"ee4e0e0bb5dabc6b2aa4b7cbeaf7f41b3dfff7174bfbc1c49d5afd25f2688138"},"source":{"id":"2602.13483","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T22:03:52.950991Z","id":"348b5f11-9cd1-4430-813f-b5680bd5f004","model_set":{"reader":"grok-4.3"},"one_line_summary":"ACC++ traces prompt-specific circuits in language models from one forward pass by extracting interpretable low-dimensional causal signals, revealing clustered mechanisms for indirect object identification and language-specific signals in multilingual settings.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ACC++ extracts causal attention signals from language models in a single forward pass, revealing many are interpretable via natural language.","strongest_claim":"ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++ consist of components that are causal for the model's attention decisions, together with the low-dimensional signals used to communicate between them. Across multiple models, a substantial portion of ACC++ signals are interpretable: many signals admit a short natural-language description.","weakest_assumption":"That the low-dimensional subspaces identified by the attention-causal communication principle are in fact the causal signals driving attention decisions, and that the natural-language descriptions assigned to them reflect genuine model mechanisms rather than post-hoc interpretations."}},"verdict_id":"348b5f11-9cd1-4430-813f-b5680bd5f004"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e706b77b44080341f9636630d04450c108d3025e931a20fbf9a3787b2af568ab","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":"29dc341a63e705f5542be6f9b1beb90f833899d66d98bae03ca3acaa88ddf930","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T21:41:17Z","title_canon_sha256":"86d076f178dc5ed41fb42c4f95499884d4ed051998d7844be5f96d493f8bee6b"},"schema_version":"1.0","source":{"id":"2602.13483","kind":"arxiv","version":2}},"canonical_sha256":"0b971dff2a8d63abdf30c8f9c398b5ce5a61795ae7e3d5587651a8476c0f9a29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b971dff2a8d63abdf30c8f9c398b5ce5a61795ae7e3d5587651a8476c0f9a29","first_computed_at":"2026-05-17T23:39:16.171443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:16.171443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w3NNWt0lg/4akZ5O7c5eOYeOMr/Rh7wzKR5d6lZOktCkaPn/+OXyPL20zA5vmC+fa3r9YOJ0zI9F5Z/NGuOBDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:16.172241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.13483","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e706b77b44080341f9636630d04450c108d3025e931a20fbf9a3787b2af568ab","sha256:5ea7333434894cc90051afa2e952238ff8adb7911a66956bcd2b2bb85de328d0"],"state_sha256":"ce330496c6a8282e4aee0b6db00fe10ed9e51fd5de42c69129278814daa7899b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ShSZWxVl7dXVihq8BMcx848rfeoloffQOKosy6aXagFHtbgKYcKWAcdXep5yxasgRDmiwwoMS11gmBBgb0QVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T01:31:37.438649Z","bundle_sha256":"2d035454e7d1be0db8a7d593100735dc7cd2ef52a2b9393a5221aa8968b04660"}}