{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BOAG7S3RR6SZ6A4L2R2MVBOVKI","short_pith_number":"pith:BOAG7S3R","schema_version":"1.0","canonical_sha256":"0b806fcb718fa59f038bd474ca85d5523d57bde2057c33f7fd70177f29b06290","source":{"kind":"arxiv","id":"2607.25398","version":1},"attestation_state":"computed","paper":{"title":"HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bradley Monton, Derek Ray, Edwin Chen, Liudas Panavas, Sebastian Minus, Suhaas Garre, Sushant Mehta","submitted_at":"2026-07-28T07:58:07Z","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"},"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":"2607.25398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T07:58:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e563261819373ec232cc635fb635964405c0f359de57a2c00afc6783bf61d4f2","abstract_canon_sha256":"f6105e1c0e213415e6e9fe2b68f331687970409bee6c01c3072ee2e28e5892bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:25:13.630054Z","signature_b64":"hvikQhX9thffa4mx0rmNtUJgrDEcxbtotNZblIH7UYO5djzriElugy76QPhnEp4VN0bqFxgnwZ9Kl3aGJ2sDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b806fcb718fa59f038bd474ca85d5523d57bde2057c33f7fd70177f29b06290","last_reissued_at":"2026-07-29T01:25:13.629200Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:25:13.629200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bradley Monton, Derek Ray, Edwin Chen, Liudas Panavas, Sebastian Minus, Suhaas Garre, Sushant Mehta","submitted_at":"2026-07-28T07:58:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25398","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/2607.25398/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":"2607.25398","created_at":"2026-07-29T01:25:13.629645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25398v1","created_at":"2026-07-29T01:25:13.629645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25398","created_at":"2026-07-29T01:25:13.629645+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOAG7S3RR6SZ","created_at":"2026-07-29T01:25:13.629645+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOAG7S3RR6SZ6A4L","created_at":"2026-07-29T01:25:13.629645+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOAG7S3R","created_at":"2026-07-29T01:25:13.629645+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/BOAG7S3RR6SZ6A4L2R2MVBOVKI","json":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI.json","graph_json":"https://pith.science/api/pith-number/BOAG7S3RR6SZ6A4L2R2MVBOVKI/graph.json","events_json":"https://pith.science/api/pith-number/BOAG7S3RR6SZ6A4L2R2MVBOVKI/events.json","paper":"https://pith.science/paper/BOAG7S3R"},"agent_actions":{"view_html":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI","download_json":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI.json","view_paper":"https://pith.science/paper/BOAG7S3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25398&json=true","fetch_graph":"https://pith.science/api/pith-number/BOAG7S3RR6SZ6A4L2R2MVBOVKI/graph.json","fetch_events":"https://pith.science/api/pith-number/BOAG7S3RR6SZ6A4L2R2MVBOVKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI/action/storage_attestation","attest_author":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI/action/author_attestation","sign_citation":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI/action/citation_signature","submit_replication":"https://pith.science/pith/BOAG7S3RR6SZ6A4L2R2MVBOVKI/action/replication_record"}},"created_at":"2026-07-29T01:25:13.629645+00:00","updated_at":"2026-07-29T01:25:13.629645+00:00"}