{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IYWWMQQCCIQFLQVD2O5SPOGKIK","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":"a9753cd943ac800cbe20ea85b03457fc940473cd0df2618883fe95e853a890b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T17:27:27Z","title_canon_sha256":"211f87e2d4b14e8f4505829290e5786cdedbf3765988d88f91931e1a1b001e85"},"schema_version":"1.0","source":{"id":"2608.12282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12282","created_at":"2026-08-13T01:30:42Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12282v1","created_at":"2026-08-13T01:30:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12282","created_at":"2026-08-13T01:30:42Z"},{"alias_kind":"pith_short_12","alias_value":"IYWWMQQCCIQF","created_at":"2026-08-13T01:30:42Z"},{"alias_kind":"pith_short_16","alias_value":"IYWWMQQCCIQFLQVD","created_at":"2026-08-13T01:30:42Z"},{"alias_kind":"pith_short_8","alias_value":"IYWWMQQC","created_at":"2026-08-13T01:30:42Z"}],"graph_snapshots":[{"event_id":"sha256:ed6734abe84e0026067a1ebab7c906adee35331b8841b21c45b1b8c444ec0234","target":"graph","created_at":"2026-08-13T01:30:42Z","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/2608.12282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\\textbf{V}aluating \\textbf{A}PI and \\textbf{K}nowledge \\textbf{R}etrieval \\textbf{A}gents), a benchmark of over $8{,}000$ executable APIs across $62$ domains with tasks spanning three settings of increasing difficulty: diverse API interaction styles, multi-hop reasoning over structured APIs, and multi-source reasoning with natural-language tool-use policy constraints. Correctness is verified by re-executing pr","authors_text":"Abdulhamid Adebayo, Abhinav Jain, Ankita Rajaram Naik, Anupama Murthi, Benjamin Elder, Danish Contractor, Praveen Venkateswaran, Raavi Gupta, Siyu Huo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T17:27:27Z","title":"VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12282","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":"sha256:0325ca17d0763365302e29e11d57be25b9f416bc9c5925b8ff08f52807754654","target":"record","created_at":"2026-08-13T01:30:42Z","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":"a9753cd943ac800cbe20ea85b03457fc940473cd0df2618883fe95e853a890b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T17:27:27Z","title_canon_sha256":"211f87e2d4b14e8f4505829290e5786cdedbf3765988d88f91931e1a1b001e85"},"schema_version":"1.0","source":{"id":"2608.12282","kind":"arxiv","version":1}},"canonical_sha256":"462d664202122055c2a3d3bb27b8ca42a0c115ac883f4481e7cad996baa1720d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"462d664202122055c2a3d3bb27b8ca42a0c115ac883f4481e7cad996baa1720d","first_computed_at":"2026-08-13T01:30:42.733560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:30:42.733560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oUplQk7sOLrXaTeFSkgqTKnrxAY9Iegv/9iRR0i+OJTsiF7JQCJTqRrmwiokSwGPmWPPg309rbc4g4k+acXPAw==","signature_status":"signed_v1","signed_at":"2026-08-13T01:30:42.735918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0325ca17d0763365302e29e11d57be25b9f416bc9c5925b8ff08f52807754654","sha256:ed6734abe84e0026067a1ebab7c906adee35331b8841b21c45b1b8c444ec0234"],"state_sha256":"9384fc20494a1b88cafcab2b995fd9e5bbb2237be751f3b74ddb24db51416d3a"}