{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:25A7YFIL7RJTRGVCHVQIWUSQJR","short_pith_number":"pith:25A7YFIL","canonical_record":{"source":{"id":"2605.03675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T12:14:10Z","cross_cats_sorted":[],"title_canon_sha256":"0927aec2da9b2e91501eaaeea5d28d19e8daea8c46ef3a3e2d7dbc0c0338b479","abstract_canon_sha256":"6cf84fd207a612baab20bce9e794db623067caf660684c62a29921c34d51c440"},"schema_version":"1.0"},"canonical_sha256":"d741fc150bfc53389aa23d608b52504c498ca583f9bbaa284713e4cec7d25979","source":{"kind":"arxiv","id":"2605.03675","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03675","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03675v2","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03675","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"25A7YFIL7RJT","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"25A7YFIL7RJTRGVC","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"25A7YFIL","created_at":"2026-05-21T01:05:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:25A7YFIL7RJTRGVCHVQIWUSQJR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.03675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T12:14:10Z","cross_cats_sorted":[],"title_canon_sha256":"0927aec2da9b2e91501eaaeea5d28d19e8daea8c46ef3a3e2d7dbc0c0338b479","abstract_canon_sha256":"6cf84fd207a612baab20bce9e794db623067caf660684c62a29921c34d51c440"},"schema_version":"1.0"},"canonical_sha256":"d741fc150bfc53389aa23d608b52504c498ca583f9bbaa284713e4cec7d25979","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:19.861357Z","signature_b64":"mKxGtNAZ8jPeVvkltaV16nLuuU7sTDg44W0TJACBfuZow4AF4NGGMtkBD3DxbCoyEMY3HeBP80ewhRGMN5wbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d741fc150bfc53389aa23d608b52504c498ca583f9bbaa284713e4cec7d25979","last_reissued_at":"2026-05-21T01:05:19.860576Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:19.860576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.03675","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":"2026-05-21T01:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AwAkZYX7HZFn0uZUdQ4W7r/l0QVu8vxRc5fCfgBOxTvBtrkV5eT2m8quGydei108SbB84o7CCQoWvl3qalD3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T23:46:53.190049Z"},"content_sha256":"c3072817209f36e5685814ef5dd01374f9fb9606cc7b106336fe0bf4a504ea0e","schema_version":"1.0","event_id":"sha256:c3072817209f36e5685814ef5dd01374f9fb9606cc7b106336fe0bf4a504ea0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:25A7YFIL7RJTRGVCHVQIWUSQJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MEMTIER's tiered memory architecture improves long-running AI agent accuracy from 5% to 38% on the LongMemEval-S benchmark using only a 6GB consumer GPU.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bronislav Sidik, Lior Rokach","submitted_at":"2026-05-05T12:14:10Z","abstract_excerpt":"Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file memory systems. We present MEMTIER, a tripartite memory architecture for the OpenClaw agent runtime that introduces a structured episodic JSONL store, a five-signal weighted retrieval engine, an attention-attributed cognitive weight update loop, an asynchronous consolidation daemon promoting episodic facts to a semantic tier, and a PPO-based policy framework "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the full 500-question LongMemEval-S benchmark, MEMTIER achieves Acc=0.382, F1=0.412 with Qwen2.5-7B on a consumer 6GB GPU - a +33 percentage point improvement over the full-context baseline (0.050 -> 0.382). With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG BM25 GPT-4o baseline (0.560).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed accuracy and recall lifts are caused by the tripartite architecture, five-signal engine, consolidation daemon, and PPO weight adaptation rather than by benchmark-specific choices, model selection, or the external DeepSeek pre-population step, and that the infrastructure-validated components will deliver the stated performance gains once the camera-ready version is complete.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MEMTIER delivers 38% accuracy on the 500-question LongMemEval-S benchmark with a 7B model on 6GB GPU, a 33-point gain over full-context baselines, via structured episodic memory, five-signal retrieval, and semantic consolidation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MEMTIER's tiered memory architecture improves long-running AI agent accuracy from 5% to 38% on the LongMemEval-S benchmark using only a 6GB consumer GPU.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a5e5a513d98df722cd73bec43eee1b78e19830c93120abb57971f2142be57ed8"},"source":{"id":"2605.03675","kind":"arxiv","version":2},"verdict":{"id":"9fadb931-20d1-41b6-a851-4e7569a400e7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T04:09:29.186448Z","strongest_claim":"On the full 500-question LongMemEval-S benchmark, MEMTIER achieves Acc=0.382, F1=0.412 with Qwen2.5-7B on a consumer 6GB GPU - a +33 percentage point improvement over the full-context baseline (0.050 -> 0.382). With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG BM25 GPT-4o baseline (0.560).","one_line_summary":"MEMTIER delivers 38% accuracy on the 500-question LongMemEval-S benchmark with a 7B model on 6GB GPU, a 33-point gain over full-context baselines, via structured episodic memory, five-signal retrieval, and semantic consolidation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed accuracy and recall lifts are caused by the tripartite architecture, five-signal engine, consolidation daemon, and PPO weight adaptation rather than by benchmark-specific choices, model selection, or the external DeepSeek pre-population step, and that the infrastructure-validated components will deliver the stated performance gains once the camera-ready version is complete.","pith_extraction_headline":"MEMTIER's tiered memory architecture improves long-running AI agent accuracy from 5% to 38% on the LongMemEval-S benchmark using only a 6GB consumer GPU."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03675/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T13:36:31.370937Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T00:31:21.602262Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:06:15.583763Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"db0cecd5c591a117ede0a6fef72eab3ace0338a22e009a96bc11416adec816bd"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","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":"9fadb931-20d1-41b6-a851-4e7569a400e7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJkyT2XpdyX1W+o0B1ucxBdJcCrHCQ5hY18dIZczNVoBSIe3rPO/ue+9TFcnuIqCixrM3qKwdvtoe524J0vsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T23:46:53.190932Z"},"content_sha256":"3a456f6cc38d9e1e54ed779683e6e199f322f4c69a152695909f551e986f3255","schema_version":"1.0","event_id":"sha256:3a456f6cc38d9e1e54ed779683e6e199f322f4c69a152695909f551e986f3255"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25A7YFIL7RJTRGVCHVQIWUSQJR/bundle.json","state_url":"https://pith.science/pith/25A7YFIL7RJTRGVCHVQIWUSQJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25A7YFIL7RJTRGVCHVQIWUSQJR/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":"2026-06-06T23:46:53Z","links":{"resolver":"https://pith.science/pith/25A7YFIL7RJTRGVCHVQIWUSQJR","bundle":"https://pith.science/pith/25A7YFIL7RJTRGVCHVQIWUSQJR/bundle.json","state":"https://pith.science/pith/25A7YFIL7RJTRGVCHVQIWUSQJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25A7YFIL7RJTRGVCHVQIWUSQJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:25A7YFIL7RJTRGVCHVQIWUSQJR","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":"6cf84fd207a612baab20bce9e794db623067caf660684c62a29921c34d51c440","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T12:14:10Z","title_canon_sha256":"0927aec2da9b2e91501eaaeea5d28d19e8daea8c46ef3a3e2d7dbc0c0338b479"},"schema_version":"1.0","source":{"id":"2605.03675","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03675","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03675v2","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03675","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"25A7YFIL7RJT","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"25A7YFIL7RJTRGVC","created_at":"2026-05-21T01:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"25A7YFIL","created_at":"2026-05-21T01:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:3a456f6cc38d9e1e54ed779683e6e199f322f4c69a152695909f551e986f3255","target":"graph","created_at":"2026-05-21T01:05:19Z","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":"On the full 500-question LongMemEval-S benchmark, MEMTIER achieves Acc=0.382, F1=0.412 with Qwen2.5-7B on a consumer 6GB GPU - a +33 percentage point improvement over the full-context baseline (0.050 -> 0.382). With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG BM25 GPT-4o baseline (0.560)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed accuracy and recall lifts are caused by the tripartite architecture, five-signal engine, consolidation daemon, and PPO weight adaptation rather than by benchmark-specific choices, model selection, or the external DeepSeek pre-population step, and that the infrastructure-validated components will deliver the stated performance gains once the camera-ready version is complete."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MEMTIER delivers 38% accuracy on the 500-question LongMemEval-S benchmark with a 7B model on 6GB GPU, a 33-point gain over full-context baselines, via structured episodic memory, five-signal retrieval, and semantic consolidation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MEMTIER's tiered memory architecture improves long-running AI agent accuracy from 5% to 38% on the LongMemEval-S benchmark using only a 6GB consumer GPU."}],"snapshot_sha256":"a5e5a513d98df722cd73bec43eee1b78e19830c93120abb57971f2142be57ed8"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T13:36:31.370937Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T00:31:21.602262Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:06:15.583763Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.03675/integrity.json","findings":[],"snapshot_sha256":"db0cecd5c591a117ede0a6fef72eab3ace0338a22e009a96bc11416adec816bd","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file memory systems. We present MEMTIER, a tripartite memory architecture for the OpenClaw agent runtime that introduces a structured episodic JSONL store, a five-signal weighted retrieval engine, an attention-attributed cognitive weight update loop, an asynchronous consolidation daemon promoting episodic facts to a semantic tier, and a PPO-based policy framework ","authors_text":"Bronislav Sidik, Lior Rokach","cross_cats":[],"headline":"MEMTIER's tiered memory architecture improves long-running AI agent accuracy from 5% to 38% on the LongMemEval-S benchmark using only a 6GB consumer GPU.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T12:14:10Z","title":"MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.03675","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T04:09:29.186448Z","id":"9fadb931-20d1-41b6-a851-4e7569a400e7","model_set":{"reader":"grok-4.3"},"one_line_summary":"MEMTIER delivers 38% accuracy on the 500-question LongMemEval-S benchmark with a 7B model on 6GB GPU, a 33-point gain over full-context baselines, via structured episodic memory, five-signal retrieval, and semantic consolidation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MEMTIER's tiered memory architecture improves long-running AI agent accuracy from 5% to 38% on the LongMemEval-S benchmark using only a 6GB consumer GPU.","strongest_claim":"On the full 500-question LongMemEval-S benchmark, MEMTIER achieves Acc=0.382, F1=0.412 with Qwen2.5-7B on a consumer 6GB GPU - a +33 percentage point improvement over the full-context baseline (0.050 -> 0.382). With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG BM25 GPT-4o baseline (0.560).","weakest_assumption":"That the observed accuracy and recall lifts are caused by the tripartite architecture, five-signal engine, consolidation daemon, and PPO weight adaptation rather than by benchmark-specific choices, model selection, or the external DeepSeek pre-population step, and that the infrastructure-validated components will deliver the stated performance gains once the camera-ready version is complete."}},"verdict_id":"9fadb931-20d1-41b6-a851-4e7569a400e7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c3072817209f36e5685814ef5dd01374f9fb9606cc7b106336fe0bf4a504ea0e","target":"record","created_at":"2026-05-21T01:05:19Z","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":"6cf84fd207a612baab20bce9e794db623067caf660684c62a29921c34d51c440","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T12:14:10Z","title_canon_sha256":"0927aec2da9b2e91501eaaeea5d28d19e8daea8c46ef3a3e2d7dbc0c0338b479"},"schema_version":"1.0","source":{"id":"2605.03675","kind":"arxiv","version":2}},"canonical_sha256":"d741fc150bfc53389aa23d608b52504c498ca583f9bbaa284713e4cec7d25979","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d741fc150bfc53389aa23d608b52504c498ca583f9bbaa284713e4cec7d25979","first_computed_at":"2026-05-21T01:05:19.860576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:19.860576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mKxGtNAZ8jPeVvkltaV16nLuuU7sTDg44W0TJACBfuZow4AF4NGGMtkBD3DxbCoyEMY3HeBP80ewhRGMN5wbCA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:19.861357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.03675","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3072817209f36e5685814ef5dd01374f9fb9606cc7b106336fe0bf4a504ea0e","sha256:3a456f6cc38d9e1e54ed779683e6e199f322f4c69a152695909f551e986f3255"],"state_sha256":"f506ff7fc1d9dadb8418ec47f5b6e519863cd472d781a3c8a608fa759e2df720"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ene7LjoWcJUlPgycdIv7wjuL9Xqeb0aIgsVqMN3ZPU6hjoIsGiMrmloh+9Q/VE/MuyjrKeT8hR0ZcRW694+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T23:46:53.194802Z","bundle_sha256":"b59b1fa7c01c1251b81badc3a23554248b3d939842b760b4ed3931911d052f4f"}}