{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BOAG7S3RR6SZ6A4L2R2MVBOVKI","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":"f6105e1c0e213415e6e9fe2b68f331687970409bee6c01c3072ee2e28e5892bd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T07:58:07Z","title_canon_sha256":"e563261819373ec232cc635fb635964405c0f359de57a2c00afc6783bf61d4f2"},"schema_version":"1.0","source":{"id":"2607.25398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25398","created_at":"2026-07-29T01:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25398v1","created_at":"2026-07-29T01:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25398","created_at":"2026-07-29T01:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"BOAG7S3RR6SZ","created_at":"2026-07-29T01:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"BOAG7S3RR6SZ6A4L","created_at":"2026-07-29T01:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"BOAG7S3R","created_at":"2026-07-29T01:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:0eef2fa1528aa9db3d03fd0248788e55ea7f909a01ee9692302412d2ed0bb9f8","target":"graph","created_at":"2026-07-29T01:25:13Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.25398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context, and the agent is trusted to let it govern every action that follows. Existing benchmarks rarely test this deployment pattern directly; they measure whether an agent can complete a task, not whether a long, binding policy document actually constrains its behavior over an extended tool-use horizon. We present HANDBOOK.md, a benchmark of 65 agentic tasks modeled on how enterprise employees follow company handbooks. Each task places an agent in a s","authors_text":"Bradley Monton, Derek Ray, Edwin Chen, Liudas Panavas, Sebastian Minus, Suhaas Garre, Sushant Mehta","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T07:58:07Z","title":"HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25398","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4fcea0b83d03058fb043eac735e65b2629e317baea4674754ba6e30fa05761c1","target":"record","created_at":"2026-07-29T01:25:13Z","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":"f6105e1c0e213415e6e9fe2b68f331687970409bee6c01c3072ee2e28e5892bd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T07:58:07Z","title_canon_sha256":"e563261819373ec232cc635fb635964405c0f359de57a2c00afc6783bf61d4f2"},"schema_version":"1.0","source":{"id":"2607.25398","kind":"arxiv","version":1}},"canonical_sha256":"0b806fcb718fa59f038bd474ca85d5523d57bde2057c33f7fd70177f29b06290","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b806fcb718fa59f038bd474ca85d5523d57bde2057c33f7fd70177f29b06290","first_computed_at":"2026-07-29T01:25:13.629200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:25:13.629200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hvikQhX9thffa4mx0rmNtUJgrDEcxbtotNZblIH7UYO5djzriElugy76QPhnEp4VN0bqFxgnwZ9Kl3aGJ2sDCg==","signature_status":"signed_v1","signed_at":"2026-07-29T01:25:13.630054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fcea0b83d03058fb043eac735e65b2629e317baea4674754ba6e30fa05761c1","sha256:0eef2fa1528aa9db3d03fd0248788e55ea7f909a01ee9692302412d2ed0bb9f8"],"state_sha256":"0584c193183bde8dc775d626ab28e52d61b62b9bb97a48b3988c0a74edff7eaf"}