{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ASXOA3TJAHGFOZNF224GTGVAAF","short_pith_number":"pith:ASXOA3TJ","schema_version":"1.0","canonical_sha256":"04aee06e6901cc5765a5d6b8699aa0017ca92c308a110158ffeadc8c788de547","source":{"kind":"arxiv","id":"2605.09823","version":2},"attestation_state":"computed","paper":{"title":"CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CalBench is a benchmark where agents with private calendars must coordinate meeting schedules without sharing data.","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Chelsea Zou, Noah Goodman, Robert D. Hawkins, Selena She, Yiheng Yao","submitted_at":"2026-05-10T23:56:02Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.09823","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-10T23:56:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"214f42161ca674233252c399d91ab1c6ec1ed69ea4382b3c5446016f3e95a365","abstract_canon_sha256":"006f631bf071ea1f8d05f3f15f3161477b73bf1099fcb93456a088b983ab5dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:46.344524Z","signature_b64":"mgzZ21HK/4AgQRsfo5Kc4lttuRFc2Gp5DHmIBDE+6YHJ4sYPKVEhbxsPKO82J+oSWXooy/jxsgiSfKiOJc5GAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04aee06e6901cc5765a5d6b8699aa0017ca92c308a110158ffeadc8c788de547","last_reissued_at":"2026-05-29T02:05:46.343754Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:46.343754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CalBench is a benchmark where agents with private calendars must coordinate meeting schedules without sharing data.","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Chelsea Zou, Noah Goodman, Robert D. Hawkins, Selena She, Yiheng Yao","submitted_at":"2026-05-10T23:56:02Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CalBench is a benchmark where agents with private calendars must coordinate meeting schedules without sharing data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f2338722e2f3d872f9a3ede27eb8410c0f9b6869b2af6dd4e9da7d3568ef7ac3"},"source":{"id":"2605.09823","kind":"arxiv","version":2},"verdict":{"id":"db45bd4b-e345-48a3-865d-82027e5a1ff9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:59:53.883962Z","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.","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","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.","pith_extraction_headline":"CalBench is a benchmark where agents with private calendars must coordinate meeting schedules without sharing data."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.09823/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"6be5f186f5a1607108e81c467ff622b4e4a25bb8d9bc38cd22b9ff1c78649415"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.09823","created_at":"2026-05-29T02:05:46.343862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.09823v2","created_at":"2026-05-29T02:05:46.343862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09823","created_at":"2026-05-29T02:05:46.343862+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASXOA3TJAHGF","created_at":"2026-05-29T02:05:46.343862+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASXOA3TJAHGFOZNF","created_at":"2026-05-29T02:05:46.343862+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASXOA3TJ","created_at":"2026-05-29T02:05:46.343862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF","json":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF.json","graph_json":"https://pith.science/api/pith-number/ASXOA3TJAHGFOZNF224GTGVAAF/graph.json","events_json":"https://pith.science/api/pith-number/ASXOA3TJAHGFOZNF224GTGVAAF/events.json","paper":"https://pith.science/paper/ASXOA3TJ"},"agent_actions":{"view_html":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF","download_json":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF.json","view_paper":"https://pith.science/paper/ASXOA3TJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.09823&json=true","fetch_graph":"https://pith.science/api/pith-number/ASXOA3TJAHGFOZNF224GTGVAAF/graph.json","fetch_events":"https://pith.science/api/pith-number/ASXOA3TJAHGFOZNF224GTGVAAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF/action/storage_attestation","attest_author":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF/action/author_attestation","sign_citation":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF/action/citation_signature","submit_replication":"https://pith.science/pith/ASXOA3TJAHGFOZNF224GTGVAAF/action/replication_record"}},"created_at":"2026-05-29T02:05:46.343862+00:00","updated_at":"2026-05-29T02:05:46.343862+00:00"}