{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KPO4RVDWZ6KMYWWVTWW2ZFJ5A2","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":"cf0d023af2637e0f64399765521f3c4da04be06dd5ce5925b7ccd9e19510c679","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-19T03:20:33Z","title_canon_sha256":"499280a4ec5d0818fca7e82224a883507e9c8e703bb67af3cc1b7ed4b0002387"},"schema_version":"1.0","source":{"id":"2607.17044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17044","created_at":"2026-07-21T01:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17044v1","created_at":"2026-07-21T01:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17044","created_at":"2026-07-21T01:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"KPO4RVDWZ6KM","created_at":"2026-07-21T01:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"KPO4RVDWZ6KMYWWV","created_at":"2026-07-21T01:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"KPO4RVDW","created_at":"2026-07-21T01:21:12Z"}],"graph_snapshots":[{"event_id":"sha256:3282a5f00321ecaccad9c3d872fdc68ec2983f1c2d4957f190e7ada8b3f59eb1","target":"graph","created_at":"2026-07-21T01:21:12Z","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/2607.17044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it. We study one production system (Leni) whose architecture installs such checkpoints: verification loops (execute, observe, compare, correct) staffed by lightweight task-specialized post-trained models. We evaluate the unmodified production configuration on three public benchmarks stressing distinct failure modes: SpreadsheetBench Verified (silent computation error), BullshitBench v2 (premise confabulation), and the GAIA validation split (cascad","authors_text":"Arunabh Dastidar, the Leni Team","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-19T03:20:33Z","title":"Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17044","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":"sha256:8d5d0720b85618a0b563b8fe616ca694365eef7485b41e8a63be9b71637b8361","target":"record","created_at":"2026-07-21T01:21:12Z","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":"cf0d023af2637e0f64399765521f3c4da04be06dd5ce5925b7ccd9e19510c679","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-19T03:20:33Z","title_canon_sha256":"499280a4ec5d0818fca7e82224a883507e9c8e703bb67af3cc1b7ed4b0002387"},"schema_version":"1.0","source":{"id":"2607.17044","kind":"arxiv","version":1}},"canonical_sha256":"53ddc8d476cf94cc5ad59dadac953d06a50bb371bc4e7be89a22a7b2a24b0f74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53ddc8d476cf94cc5ad59dadac953d06a50bb371bc4e7be89a22a7b2a24b0f74","first_computed_at":"2026-07-21T01:21:12.053473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:12.053473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VVdaRL3dWpfefbr+VH4tnzO+fHmz/8AgHCb7/jC1aXlZI4m226+QSPZ69NIQ6TSLfcRu1t8GSMO34WRF3BZYBQ==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:12.054300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d5d0720b85618a0b563b8fe616ca694365eef7485b41e8a63be9b71637b8361","sha256:3282a5f00321ecaccad9c3d872fdc68ec2983f1c2d4957f190e7ada8b3f59eb1"],"state_sha256":"aabb681396610c8c6901a3dbe44ffcc310d68bde6ed4856ddcdf507d5f119378"}