{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ASXOA3TJAHGFOZNF224GTGVAAF","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":"006f631bf071ea1f8d05f3f15f3161477b73bf1099fcb93456a088b983ab5dba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-10T23:56:02Z","title_canon_sha256":"214f42161ca674233252c399d91ab1c6ec1ed69ea4382b3c5446016f3e95a365"},"schema_version":"1.0","source":{"id":"2605.09823","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09823","created_at":"2026-05-29T02:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09823v2","created_at":"2026-05-29T02:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09823","created_at":"2026-05-29T02:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"ASXOA3TJAHGF","created_at":"2026-05-29T02:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"ASXOA3TJAHGFOZNF","created_at":"2026-05-29T02:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"ASXOA3TJ","created_at":"2026-05-29T02:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:18c9a0e405371e76de38439d981b424536152f58fdecb6f012509b227c5c3a8f","target":"graph","created_at":"2026-05-29T02:05:46Z","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":"CalBench is inherently decentralized: no agent has access to another agent's private calendar, yet agents must still reach mutually consistent decisions over shared meeting scheduling, enabling precise verification of task success, communication efficiency, and fairness."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the specific mechanics of private-calendar scheduling with oracle optima and semantic privacy tags form a representative and controllable proxy for general coordination-privacy trade-offs across multi-agent LLM applications."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CalBench introduces a decentralized multi-agent benchmark for calendar scheduling that measures coordination quality against an oracle optimum and privacy leakage under private information constraints."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CalBench is a benchmark where agents with private calendars must coordinate meeting schedules without sharing data."}],"snapshot_sha256":"f2338722e2f3d872f9a3ede27eb8410c0f9b6869b2af6dd4e9da7d3568ef7ac3"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T07:02:01.365544Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T16:35:15.579659Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T12:31:17.637007Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:54:16.808891Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.09823/integrity.json","findings":[],"snapshot_sha256":"6be5f186f5a1607108e81c467ff622b4e4a25bb8d9bc38cd22b9ff1c78649415","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences. Calendar scheduling makes the trust problem concrete: an assistant must coordinate with other assistants while deciding what to reveal about the person it represents. We introduce CalBench, a controlled benchmark for multi-agent calendar scheduling under private information. In each task, $N$ agents manage separate private calendars and schedule a stream of $M$ incoming meetings while minimizing disruption costs. Because no agent can inspect another agent's calendar, success requir","authors_text":"Chelsea Zou, Noah Goodman, Robert D. Hawkins, Selena She, Yiheng Yao","cross_cats":["cs.AI"],"headline":"CalBench is a benchmark where agents with private calendars must coordinate meeting schedules without sharing data.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-10T23:56:02Z","title":"CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.09823","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T01:59:53.883962Z","id":"db45bd4b-e345-48a3-865d-82027e5a1ff9","model_set":{"reader":"grok-4.3"},"one_line_summary":"CalBench introduces a decentralized multi-agent benchmark for calendar scheduling that measures coordination quality against an oracle optimum and privacy leakage under private information constraints.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CalBench is a benchmark where agents with private calendars must coordinate meeting schedules without sharing data.","strongest_claim":"CalBench is inherently decentralized: no agent has access to another agent's private calendar, yet agents must still reach mutually consistent decisions over shared meeting scheduling, enabling precise verification of task success, communication efficiency, and fairness.","weakest_assumption":"That the specific mechanics of private-calendar scheduling with oracle optima and semantic privacy tags form a representative and controllable proxy for general coordination-privacy trade-offs across multi-agent LLM applications."}},"verdict_id":"db45bd4b-e345-48a3-865d-82027e5a1ff9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b62e1732d1ab23fe2959a715dc4e466cb4e68787e70774d1e8a21ad52b87b1d5","target":"record","created_at":"2026-05-29T02:05:46Z","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":"006f631bf071ea1f8d05f3f15f3161477b73bf1099fcb93456a088b983ab5dba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-10T23:56:02Z","title_canon_sha256":"214f42161ca674233252c399d91ab1c6ec1ed69ea4382b3c5446016f3e95a365"},"schema_version":"1.0","source":{"id":"2605.09823","kind":"arxiv","version":2}},"canonical_sha256":"04aee06e6901cc5765a5d6b8699aa0017ca92c308a110158ffeadc8c788de547","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04aee06e6901cc5765a5d6b8699aa0017ca92c308a110158ffeadc8c788de547","first_computed_at":"2026-05-29T02:05:46.343754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:46.343754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mgzZ21HK/4AgQRsfo5Kc4lttuRFc2Gp5DHmIBDE+6YHJ4sYPKVEhbxsPKO82J+oSWXooy/jxsgiSfKiOJc5GAQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:46.344524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.09823","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b62e1732d1ab23fe2959a715dc4e466cb4e68787e70774d1e8a21ad52b87b1d5","sha256:18c9a0e405371e76de38439d981b424536152f58fdecb6f012509b227c5c3a8f"],"state_sha256":"1a79a53c88bfe7b1711c7cbf297e6084acda8d0de6e66e116d1ffb8e494b7f5c"}