{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RM3CKGKHBVEIUIDUPN6YE7V2LN","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":"3852338a62d516536245bc9a3b88c79f46a10b14bb50b889627aeaabbbfd4c36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-02T15:11:39Z","title_canon_sha256":"52203ee79402c088ad4a26ee1e80e37a0227261d213fe67f9a91bfb86cf354a1"},"schema_version":"1.0","source":{"id":"2607.02294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02294","created_at":"2026-07-03T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02294v1","created_at":"2026-07-03T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02294","created_at":"2026-07-03T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"RM3CKGKHBVEI","created_at":"2026-07-03T01:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"RM3CKGKHBVEIUIDU","created_at":"2026-07-03T01:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"RM3CKGKH","created_at":"2026-07-03T01:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:4fab45a6876dc16fc76d7031eb394dc078e26d2b83d40649d0b3a54303e328b3","target":"graph","created_at":"2026-07-03T01:17:47Z","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/2607.02294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM coding agents are increasingly deployed to act autonomously on real production infrastructure. They execute shell commands, modify repositories, and call operational APIs. However, completing a task is not sufficient for safety. A wrong action can cause severe consequences. Existing agent benchmarks largely emphasize task completion, leaving open how agents behave under benign but underspecified instructions.\n  We present UnderSpecBench, a benchmark for measuring action-boundary violations in coding agents (i.e., Claude Code, Codex, and OpenCode) on DevOps tasks. UnderSpecBench includes 69","authors_text":"Congying Xu, Shing-Chi Cheung, Shuai Wang, Yudong Gao, Zekai Zhang, Zimo Ji, Zongjie Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-02T15:11:39Z","title":"Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02294","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":"sha256:871d305d796f4585360e1710beac792e39ae7853d3cec9c3e4c17ccbcb9fe0de","target":"record","created_at":"2026-07-03T01:17:47Z","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":"3852338a62d516536245bc9a3b88c79f46a10b14bb50b889627aeaabbbfd4c36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-02T15:11:39Z","title_canon_sha256":"52203ee79402c088ad4a26ee1e80e37a0227261d213fe67f9a91bfb86cf354a1"},"schema_version":"1.0","source":{"id":"2607.02294","kind":"arxiv","version":1}},"canonical_sha256":"8b362519470d488a20747b7d827eba5b4e669993c42ee9af482450fefde3dc01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b362519470d488a20747b7d827eba5b4e669993c42ee9af482450fefde3dc01","first_computed_at":"2026-07-03T01:17:47.766343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:47.766343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DtHxm+KzonoKrePd0mBajgv98GxOqbCCjE5PQay+49ce6XEikcnc3ij3gy+2+IMZOTAyncpKN3rG476KncpaDw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:47.766775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:871d305d796f4585360e1710beac792e39ae7853d3cec9c3e4c17ccbcb9fe0de","sha256:4fab45a6876dc16fc76d7031eb394dc078e26d2b83d40649d0b3a54303e328b3"],"state_sha256":"2e62393c2348d9559f1c119cb3ca545550fbd08a4d543de0fa00f71cb921e8eb"}