{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I4ZTPQDU45RNANETQRGHX3Q4O4","short_pith_number":"pith:I4ZTPQDU","schema_version":"1.0","canonical_sha256":"473337c074e762d03493844c7bee1c773ed4898b35dbd27875251ad53a44457f","source":{"kind":"arxiv","id":"2608.02670","version":1},"attestation_state":"computed","paper":{"title":"Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dotan Davidovich, Hai Rozencwajg, Or Hiltch, Yair Amar","submitted_at":"2026-08-02T14:26:12Z","abstract_excerpt":"Coding agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root execution) constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is unknown how performance changes when policy is enforced. In this work, we evaluate 12 coding agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions. Hardening is never free but far from uniform: under the strictest policy, success losse"},"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":"2608.02670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-08-02T14:26:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a4d9f8109fe4ef6baac6eb518ad02d5ad2d069bc08f32cc83acd435ccc3d992","abstract_canon_sha256":"8a0c8ebdb60af07a94abf16c2f2aaf61f197e6fe5c98d9d356027345d398ca99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:38:38.913292Z","signature_b64":"vZb5WU3sPyJPraXdo+E7y/pvFlS7fqp0vuPBkoxj78TRhoCSXx6xWxNEzH4HHlN5m1XGMY9VjfE2EvvxnGhiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"473337c074e762d03493844c7bee1c773ed4898b35dbd27875251ad53a44457f","last_reissued_at":"2026-08-05T00:38:38.910796Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:38:38.910796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dotan Davidovich, Hai Rozencwajg, Or Hiltch, Yair Amar","submitted_at":"2026-08-02T14:26:12Z","abstract_excerpt":"Coding agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root execution) constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is unknown how performance changes when policy is enforced. In this work, we evaluate 12 coding agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions. Hardening is never free but far from uniform: under the strictest policy, success losse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02670","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/2608.02670/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":"2608.02670","created_at":"2026-08-05T00:38:38.911719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02670v1","created_at":"2026-08-05T00:38:38.911719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02670","created_at":"2026-08-05T00:38:38.911719+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4ZTPQDU45RN","created_at":"2026-08-05T00:38:38.911719+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4ZTPQDU45RNANET","created_at":"2026-08-05T00:38:38.911719+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4ZTPQDU","created_at":"2026-08-05T00:38:38.911719+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/I4ZTPQDU45RNANETQRGHX3Q4O4","json":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4.json","graph_json":"https://pith.science/api/pith-number/I4ZTPQDU45RNANETQRGHX3Q4O4/graph.json","events_json":"https://pith.science/api/pith-number/I4ZTPQDU45RNANETQRGHX3Q4O4/events.json","paper":"https://pith.science/paper/I4ZTPQDU"},"agent_actions":{"view_html":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4","download_json":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4.json","view_paper":"https://pith.science/paper/I4ZTPQDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02670&json=true","fetch_graph":"https://pith.science/api/pith-number/I4ZTPQDU45RNANETQRGHX3Q4O4/graph.json","fetch_events":"https://pith.science/api/pith-number/I4ZTPQDU45RNANETQRGHX3Q4O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4/action/storage_attestation","attest_author":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4/action/author_attestation","sign_citation":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4/action/citation_signature","submit_replication":"https://pith.science/pith/I4ZTPQDU45RNANETQRGHX3Q4O4/action/replication_record"}},"created_at":"2026-08-05T00:38:38.911719+00:00","updated_at":"2026-08-05T00:38:38.911719+00:00"}