{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6JJ6BLBROSC5IO6TDA65HDTFV7","short_pith_number":"pith:6JJ6BLBR","canonical_record":{"source":{"id":"2605.16757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:11:34Z","cross_cats_sorted":["cs.MA","stat.ME","stat.ML"],"title_canon_sha256":"903b34c92712de8a7e3bd374f31b1280d3f4d883a03afece7c5d5cb021d05c77","abstract_canon_sha256":"2f16af74cac9eb2e36dde6092b851db144c9ef1187308552b9d95f87a59ba1fc"},"schema_version":"1.0"},"canonical_sha256":"f253e0ac317485d43bd3183dd38e65afc355b66926e127967d552a779e505625","source":{"kind":"arxiv","id":"2605.16757","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16757","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16757v1","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16757","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"6JJ6BLBROSC5","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"6JJ6BLBROSC5IO6T","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"6JJ6BLBR","created_at":"2026-05-20T00:03:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6JJ6BLBROSC5IO6TDA65HDTFV7","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:11:34Z","cross_cats_sorted":["cs.MA","stat.ME","stat.ML"],"title_canon_sha256":"903b34c92712de8a7e3bd374f31b1280d3f4d883a03afece7c5d5cb021d05c77","abstract_canon_sha256":"2f16af74cac9eb2e36dde6092b851db144c9ef1187308552b9d95f87a59ba1fc"},"schema_version":"1.0"},"canonical_sha256":"f253e0ac317485d43bd3183dd38e65afc355b66926e127967d552a779e505625","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:20.177286Z","signature_b64":"kBbzxhbRbd1asbc4T5xWEJ+vv0V22C23hQT/8LW8EpKTop9KE0Uw54HdwVwavjtP0yUW+QG77S+zKYskOUoPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f253e0ac317485d43bd3183dd38e65afc355b66926e127967d552a779e505625","last_reissued_at":"2026-05-20T00:03:20.176264Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:20.176264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16757","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":"2026-05-20T00:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EG0txVxHs+VvYy2g/MhUoSLiAKm4W/OvHbRlHrjDRc2nVyqjM8wMRuR5NXE/NYgHCUOrfbV7oi0Llwfg4z+yAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:08:05.106621Z"},"content_sha256":"4ab292b2e540dcd3e2ac328542eefeda710ed865065b3fb85e4cda0772555a70","schema_version":"1.0","event_id":"sha256:4ab292b2e540dcd3e2ac328542eefeda710ed865065b3fb85e4cda0772555a70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6JJ6BLBROSC5IO6TDA65HDTFV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multi-agent language systems modeled as neural networks allow reinforcement learning to induce specialization and coordination among role-free agents.","cross_cats":["cs.MA","stat.ME","stat.ML"],"primary_cat":"cs.AI","authors_text":"Haoran Lu, Luyang Fang, Ping Ma, Wenxuan Zhong","submitted_at":"2026-05-16T02:11:34Z","abstract_excerpt":"Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language system as a trainable and scalable neural-network-like architecture with LLM agents as nodes and intermediate textual signals as edges. In NeuroMAS, agent nodes are role-free but structure-aware: the topology only determines how information can flow in general, while reinforcement learning training determines how nodes communicate, specialize, and coordinate."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That reinforcement learning training on the network topology can reliably induce effective specialization, communication protocols, and coordination among role-free agents without additional hand-designed constraints or semantic role assignments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NeuroMAS reframes multi-agent language systems as neural architectures where LLM agents learn coordination via reinforcement learning rather than predefined roles.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-agent language systems modeled as neural networks allow reinforcement learning to induce specialization and coordination among role-free agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a306712a24135de6daf1b6d09fb6db3b76609cb35cc86c1c0a43857ca014b446"},"source":{"id":"2605.16757","kind":"arxiv","version":1},"verdict":{"id":"d120e690-3c72-4fab-86f5-9e3120b9b84a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:13:59.760581Z","strongest_claim":"Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems.","one_line_summary":"NeuroMAS reframes multi-agent language systems as neural architectures where LLM agents learn coordination via reinforcement learning rather than predefined roles.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That reinforcement learning training on the network topology can reliably induce effective specialization, communication protocols, and coordination among role-free agents without additional hand-designed constraints or semantic role assignments.","pith_extraction_headline":"Multi-agent language systems modeled as neural networks allow reinforcement learning to induce specialization and coordination among role-free agents."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16757/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.372595Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:21:24.005595Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.321919Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.453462Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"463c3e8127d9bb22da1622119e3f3e290fc251aa623b4f29b79f03bc06930d47"},"references":{"count":65,"sample":[{"doi":"","year":1992,"title":"Machine Learning , volume =","work_id":"3f4206f6-1e77-48fd-b656-cc7c4a027789","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Parameter-Efficient Transfer Learning for","work_id":"ec25a416-e4a9-47ba-9a72-b1c99c11efbf","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , booktitle =","work_id":"55c0e00e-cd66-4668-b59e-52cd4c7986ab","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Learning Decentralized","work_id":"30535028-eda1-4dc0-9f74-7c2e71802c10","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Yang, An and Li, Anfeng and Yang, Baosong and Zhang, Beichen and Hui, Binyuan and Zheng, Bo and others , journal =","work_id":"8582e112-cf97-4829-b163-eafc030129a4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":65,"snapshot_sha256":"06dc5df4f487d1c5673d1f44b4a2742b30917b6c177e0fc7430532eda9db7667","internal_anchors":7},"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":"d120e690-3c72-4fab-86f5-9e3120b9b84a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4T/JjCH6/TrvZ6i/FWHj6EGBGCVzASjUQIMgP0ghWw7Tfh3krjARk5x5eVNz2TOgoFVKeXJOoll13yYOHmx1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:08:05.107231Z"},"content_sha256":"8cf5522481a2df11a9dc4eb644ef2cd95951cc222b28991d10e90c4a749b8e58","schema_version":"1.0","event_id":"sha256:8cf5522481a2df11a9dc4eb644ef2cd95951cc222b28991d10e90c4a749b8e58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JJ6BLBROSC5IO6TDA65HDTFV7/bundle.json","state_url":"https://pith.science/pith/6JJ6BLBROSC5IO6TDA65HDTFV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JJ6BLBROSC5IO6TDA65HDTFV7/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":"2026-05-30T05:08:05Z","links":{"resolver":"https://pith.science/pith/6JJ6BLBROSC5IO6TDA65HDTFV7","bundle":"https://pith.science/pith/6JJ6BLBROSC5IO6TDA65HDTFV7/bundle.json","state":"https://pith.science/pith/6JJ6BLBROSC5IO6TDA65HDTFV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JJ6BLBROSC5IO6TDA65HDTFV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6JJ6BLBROSC5IO6TDA65HDTFV7","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":"2f16af74cac9eb2e36dde6092b851db144c9ef1187308552b9d95f87a59ba1fc","cross_cats_sorted":["cs.MA","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:11:34Z","title_canon_sha256":"903b34c92712de8a7e3bd374f31b1280d3f4d883a03afece7c5d5cb021d05c77"},"schema_version":"1.0","source":{"id":"2605.16757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16757","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16757v1","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16757","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"6JJ6BLBROSC5","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"6JJ6BLBROSC5IO6T","created_at":"2026-05-20T00:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"6JJ6BLBR","created_at":"2026-05-20T00:03:20Z"}],"graph_snapshots":[{"event_id":"sha256:8cf5522481a2df11a9dc4eb644ef2cd95951cc222b28991d10e90c4a749b8e58","target":"graph","created_at":"2026-05-20T00:03:20Z","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":"Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That reinforcement learning training on the network topology can reliably induce effective specialization, communication protocols, and coordination among role-free agents without additional hand-designed constraints or semantic role assignments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"NeuroMAS reframes multi-agent language systems as neural architectures where LLM agents learn coordination via reinforcement learning rather than predefined roles."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multi-agent language systems modeled as neural networks allow reinforcement learning to induce specialization and coordination among role-free agents."}],"snapshot_sha256":"a306712a24135de6daf1b6d09fb6db3b76609cb35cc86c1c0a43857ca014b446"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.372595Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:21:24.005595Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.321919Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.453462Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16757/integrity.json","findings":[],"snapshot_sha256":"463c3e8127d9bb22da1622119e3f3e290fc251aa623b4f29b79f03bc06930d47","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language system as a trainable and scalable neural-network-like architecture with LLM agents as nodes and intermediate textual signals as edges. In NeuroMAS, agent nodes are role-free but structure-aware: the topology only determines how information can flow in general, while reinforcement learning training determines how nodes communicate, specialize, and coordinate.","authors_text":"Haoran Lu, Luyang Fang, Ping Ma, Wenxuan Zhong","cross_cats":["cs.MA","stat.ME","stat.ML"],"headline":"Multi-agent language systems modeled as neural networks allow reinforcement learning to induce specialization and coordination among role-free agents.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:11:34Z","title":"NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning"},"references":{"count":65,"internal_anchors":7,"resolved_work":65,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Machine Learning , volume =","work_id":"3f4206f6-1e77-48fd-b656-cc7c4a027789","year":1992},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Parameter-Efficient Transfer Learning for","work_id":"ec25a416-e4a9-47ba-9a72-b1c99c11efbf","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , booktitle =","work_id":"55c0e00e-cd66-4668-b59e-52cd4c7986ab","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Learning Decentralized","work_id":"30535028-eda1-4dc0-9f74-7c2e71802c10","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Yang, An and Li, Anfeng and Yang, Baosong and Zhang, Beichen and Hui, Binyuan and Zheng, Bo and others , journal =","work_id":"8582e112-cf97-4829-b163-eafc030129a4","year":null}],"snapshot_sha256":"06dc5df4f487d1c5673d1f44b4a2742b30917b6c177e0fc7430532eda9db7667"},"source":{"id":"2605.16757","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:13:59.760581Z","id":"d120e690-3c72-4fab-86f5-9e3120b9b84a","model_set":{"reader":"grok-4.3"},"one_line_summary":"NeuroMAS reframes multi-agent language systems as neural architectures where LLM agents learn coordination via reinforcement learning rather than predefined roles.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multi-agent language systems modeled as neural networks allow reinforcement learning to induce specialization and coordination among role-free agents.","strongest_claim":"Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems.","weakest_assumption":"That reinforcement learning training on the network topology can reliably induce effective specialization, communication protocols, and coordination among role-free agents without additional hand-designed constraints or semantic role assignments."}},"verdict_id":"d120e690-3c72-4fab-86f5-9e3120b9b84a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ab292b2e540dcd3e2ac328542eefeda710ed865065b3fb85e4cda0772555a70","target":"record","created_at":"2026-05-20T00:03:20Z","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":"2f16af74cac9eb2e36dde6092b851db144c9ef1187308552b9d95f87a59ba1fc","cross_cats_sorted":["cs.MA","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:11:34Z","title_canon_sha256":"903b34c92712de8a7e3bd374f31b1280d3f4d883a03afece7c5d5cb021d05c77"},"schema_version":"1.0","source":{"id":"2605.16757","kind":"arxiv","version":1}},"canonical_sha256":"f253e0ac317485d43bd3183dd38e65afc355b66926e127967d552a779e505625","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f253e0ac317485d43bd3183dd38e65afc355b66926e127967d552a779e505625","first_computed_at":"2026-05-20T00:03:20.176264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:20.176264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kBbzxhbRbd1asbc4T5xWEJ+vv0V22C23hQT/8LW8EpKTop9KE0Uw54HdwVwavjtP0yUW+QG77S+zKYskOUoPDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:20.177286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ab292b2e540dcd3e2ac328542eefeda710ed865065b3fb85e4cda0772555a70","sha256:8cf5522481a2df11a9dc4eb644ef2cd95951cc222b28991d10e90c4a749b8e58"],"state_sha256":"b9b3833d31302d36a4e10d8dfbd38b2b418bef8dabf9f54caf6a592b624b09cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lSYO6j2GKHt/ZjuOZVKXJswOcwvJ4zA2twYnFJVmczDCPr0VlOgJHTdRHBjPhdLsW5i4Hy0ZRTUj1vt6n3QuCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:08:05.110337Z","bundle_sha256":"074b823d9825f36f79825805088bafa244de806f619044f8d1550394e972f812"}}