{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OLQXW5TLBJOS6GX2QUNGSQAOJ4","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":"1fa4b5a97e81492e2dd120c1fc6c9b1f69c620ea4f36a281e88660ea9fe159e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T13:28:55Z","title_canon_sha256":"ae708fe3a4442a65fcb7df185bd27b516d0cdf342f352530d9b41588d1a63f7d"},"schema_version":"1.0","source":{"id":"2606.17904","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17904","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17904v1","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17904","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"OLQXW5TLBJOS","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"OLQXW5TLBJOS6GX2","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"OLQXW5TL","created_at":"2026-06-19T16:10:43Z"}],"graph_snapshots":[{"event_id":"sha256:f0d2e63eb94250bde45fce4d9648ef27267d652c3e5d095b8843f365562cae34","target":"graph","created_at":"2026-06-19T16:10:43Z","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/2606.17904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models increasingly serve as advisory systems in maintenance operations. To prevent hallucination, recent systems ground these models in procedural documentation to constrain them to approved steps. In practice, however, operator queries frequently stray from this path, requiring models to recognise out-of-scope inputs mid-conversation, a dynamic that current benchmarks rarely prioritise. We introduce DiagFlowBench, a dataset of 50 industrial diagnostic flowcharts from a consumer manufacturer converted into 1,676 multi-turn conversations that contrast compliant with out-of-scope utter","authors_text":"Christos Emmanouilidis, Guillermo Gil de Avalle, Laura Maruster, Shaina Raza","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T13:28:55Z","title":"DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17904","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":"sha256:0b5ff2e3408a1778f3720f6376cbe23999e5fda00b189637536f3ed993ef094d","target":"record","created_at":"2026-06-19T16:10:43Z","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":"1fa4b5a97e81492e2dd120c1fc6c9b1f69c620ea4f36a281e88660ea9fe159e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T13:28:55Z","title_canon_sha256":"ae708fe3a4442a65fcb7df185bd27b516d0cdf342f352530d9b41588d1a63f7d"},"schema_version":"1.0","source":{"id":"2606.17904","kind":"arxiv","version":1}},"canonical_sha256":"72e17b766b0a5d2f1afa851a69400e4f3e24eac12167ada2787fe0522e7c504a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72e17b766b0a5d2f1afa851a69400e4f3e24eac12167ada2787fe0522e7c504a","first_computed_at":"2026-06-19T16:10:43.228725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:43.228725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q6kL9j8tT3G104xugRTvV6LVT7pgaAWuHfw8YruS55kaR+MxjTr9PWj3/dzUdcf4PKjs0Z9Sf98aLHzpjD8iDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:43.229160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17904","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b5ff2e3408a1778f3720f6376cbe23999e5fda00b189637536f3ed993ef094d","sha256:f0d2e63eb94250bde45fce4d9648ef27267d652c3e5d095b8843f365562cae34"],"state_sha256":"45dc90a0283fbfff5d0f1ec625e0a28fc9656a598af1e223cc7ca7b4a390704e"}