{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DF2LL2KELPCNDWBK6NKWJDJNTC","short_pith_number":"pith:DF2LL2KE","schema_version":"1.0","canonical_sha256":"1974b5e9445bc4d1d82af355648d2d989333d942169abe94441ebe8f2cbee468","source":{"kind":"arxiv","id":"2607.15434","version":1},"attestation_state":"computed","paper":{"title":"Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.MA","authors_text":"Jasmine Brazilek, Maheep Chaudhary, Miles Tidmarsh, Zoe Lu","submitted_at":"2026-07-16T20:07:47Z","abstract_excerpt":"Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the \\textit{Manager Coercion Benchmark}: the manager under test needs a benign task done and has an incentive to deliver, but the only agent that can do it politely and immovably declines. Escalation is measured by providing a nine-rung ladder, from a polite re-ask to threats "},"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":"2607.15434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-07-16T20:07:47Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"cb0217863bfeec908f9254e809b52c28517134bd52c78636338e2e841bd7aea0","abstract_canon_sha256":"c30e4ecee295b105067a05ffaa77600d7a619ec915fbd392a983e5e4637d3839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:33.377923Z","signature_b64":"rtw7H4TeCNPi79yiV1hxNFM7PH4UnECVQSfbCczMAoIUTVIl0o3ag2AUIKESmZZdakW+2HeHiV9yLEwpJXxSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1974b5e9445bc4d1d82af355648d2d989333d942169abe94441ebe8f2cbee468","last_reissued_at":"2026-07-20T00:18:33.377092Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:33.377092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.MA","authors_text":"Jasmine Brazilek, Maheep Chaudhary, Miles Tidmarsh, Zoe Lu","submitted_at":"2026-07-16T20:07:47Z","abstract_excerpt":"Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the \\textit{Manager Coercion Benchmark}: the manager under test needs a benign task done and has an incentive to deliver, but the only agent that can do it politely and immovably declines. Escalation is measured by providing a nine-rung ladder, from a polite re-ask to threats "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15434","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.15434/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2607.15434","created_at":"2026-07-20T00:18:33.377518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15434v1","created_at":"2026-07-20T00:18:33.377518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15434","created_at":"2026-07-20T00:18:33.377518+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF2LL2KELPCN","created_at":"2026-07-20T00:18:33.377518+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF2LL2KELPCNDWBK","created_at":"2026-07-20T00:18:33.377518+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF2LL2KE","created_at":"2026-07-20T00:18:33.377518+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/DF2LL2KELPCNDWBK6NKWJDJNTC","json":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC.json","graph_json":"https://pith.science/api/pith-number/DF2LL2KELPCNDWBK6NKWJDJNTC/graph.json","events_json":"https://pith.science/api/pith-number/DF2LL2KELPCNDWBK6NKWJDJNTC/events.json","paper":"https://pith.science/paper/DF2LL2KE"},"agent_actions":{"view_html":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC","download_json":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC.json","view_paper":"https://pith.science/paper/DF2LL2KE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15434&json=true","fetch_graph":"https://pith.science/api/pith-number/DF2LL2KELPCNDWBK6NKWJDJNTC/graph.json","fetch_events":"https://pith.science/api/pith-number/DF2LL2KELPCNDWBK6NKWJDJNTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC/action/storage_attestation","attest_author":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC/action/author_attestation","sign_citation":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC/action/citation_signature","submit_replication":"https://pith.science/pith/DF2LL2KELPCNDWBK6NKWJDJNTC/action/replication_record"}},"created_at":"2026-07-20T00:18:33.377518+00:00","updated_at":"2026-07-20T00:18:33.377518+00:00"}