{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q3QWTFIPAKN5RPNEZHTR7SCXS6","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":"4731426017ef2f7458b7ef99887950b8e340a52704e16d33680a5cc2e165a584","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-15T18:48:49Z","title_canon_sha256":"7385ed195eedaedc34c4c0806bfbcc70e89a5efa57817a942a402dea6150b6ab"},"schema_version":"1.0","source":{"id":"2607.14285","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14285","created_at":"2026-07-17T00:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14285v1","created_at":"2026-07-17T00:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14285","created_at":"2026-07-17T00:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"Q3QWTFIPAKN5","created_at":"2026-07-17T00:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"Q3QWTFIPAKN5RPNE","created_at":"2026-07-17T00:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"Q3QWTFIP","created_at":"2026-07-17T00:21:03Z"}],"graph_snapshots":[{"event_id":"sha256:f13ddec77fc22098129d1ca449478caa4f6f9b89b99830b75838ac96d878ea5d","target":"graph","created_at":"2026-07-17T00:21:03Z","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/2607.14285/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety alignment in LLMs aims to align models with human values, but which values take precedence when they conflict? We investigate this question in the context of tool-calling LLM agents deployed in regulated industries, where agents processing confidential documents may encounter content that triggers safety-trained values (e.g., public welfare) that conflict with deployment-context instructions (e.g., internal logging). To empirically verify this phenomenon, we build a benchmark of 128 scenarios across 16 domains. We find that safety-aligned open-source models override their deployment ins","authors_text":"Amrita Bhattacharjee, Aryan Keluskar, Huan Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-15T18:48:49Z","title":"ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14285","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":"sha256:072e3b5436a5eff890922f7d5631c478231f9e97b0eac9aa8daad4bd2a14ddf2","target":"record","created_at":"2026-07-17T00:21:03Z","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":"4731426017ef2f7458b7ef99887950b8e340a52704e16d33680a5cc2e165a584","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-15T18:48:49Z","title_canon_sha256":"7385ed195eedaedc34c4c0806bfbcc70e89a5efa57817a942a402dea6150b6ab"},"schema_version":"1.0","source":{"id":"2607.14285","kind":"arxiv","version":1}},"canonical_sha256":"86e169950f029bd8bda4c9e71fc85797beab9e3cd39f629ccbd51098c11ba246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86e169950f029bd8bda4c9e71fc85797beab9e3cd39f629ccbd51098c11ba246","first_computed_at":"2026-07-17T00:21:03.278048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:21:03.278048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M37lR+O4UwuhqatYhzL63T/X/m7au4LSOebSBARt8bq95ewIV8wNr0C3AUBfpgX/+gFJQ6mfa9/C2gIfu2K9Cg==","signature_status":"signed_v1","signed_at":"2026-07-17T00:21:03.278855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14285","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:072e3b5436a5eff890922f7d5631c478231f9e97b0eac9aa8daad4bd2a14ddf2","sha256:f13ddec77fc22098129d1ca449478caa4f6f9b89b99830b75838ac96d878ea5d"],"state_sha256":"31cc0446caed8475740857475ee6428ae09821b12e7cc535eea47483c63f2028"}