{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LQN7OZYFQ3J6EEXQVKMBKWA3UB","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":"9947783645084c657fd23bf53f393c287915e656c5361aeaad796672d76a10cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T11:38:33Z","title_canon_sha256":"30856efd3df7f0a82977db49a22c352202e8bb1d6d26fbee25cfc3ef7a531b67"},"schema_version":"1.0","source":{"id":"2608.04719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04719","created_at":"2026-08-06T01:46:35Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04719v1","created_at":"2026-08-06T01:46:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04719","created_at":"2026-08-06T01:46:35Z"},{"alias_kind":"pith_short_12","alias_value":"LQN7OZYFQ3J6","created_at":"2026-08-06T01:46:35Z"},{"alias_kind":"pith_short_16","alias_value":"LQN7OZYFQ3J6EEXQ","created_at":"2026-08-06T01:46:35Z"},{"alias_kind":"pith_short_8","alias_value":"LQN7OZYF","created_at":"2026-08-06T01:46:35Z"}],"graph_snapshots":[{"event_id":"sha256:6c1389a658f32ed89c526688bd5e370eb9e13fb69f1386a8af182e052b1c6787","target":"graph","created_at":"2026-08-06T01:46:35Z","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/2608.04719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Model Context Protocol (MCP) tool set, each engineered to probe one specific tool-selection weakness. A six-type taxonomy (semantic decoys, parameter traps, capability mirages, prerequisite blindness, temporal decoys, and granularity traps) turns a single \"wrong tool\" outcome into a multi-dimensional profile of how a model reasons about tools. We evaluate eight models -- six hosted and two 8B open-weight -- spanning three capability tiers, on 120","authors_text":"Atul Anand, Sourav Chattaraj","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T11:38:33Z","title":"Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04719","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:e1a89d0daf434cc1b4051f80d3b3466cb4189fdbf38d2883fce43546604b0b28","target":"record","created_at":"2026-08-06T01:46:35Z","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":"9947783645084c657fd23bf53f393c287915e656c5361aeaad796672d76a10cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T11:38:33Z","title_canon_sha256":"30856efd3df7f0a82977db49a22c352202e8bb1d6d26fbee25cfc3ef7a531b67"},"schema_version":"1.0","source":{"id":"2608.04719","kind":"arxiv","version":1}},"canonical_sha256":"5c1bf7670586d3e212f0aa9815581ba04d87d3895b9b467ac07320de2f29e80e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c1bf7670586d3e212f0aa9815581ba04d87d3895b9b467ac07320de2f29e80e","first_computed_at":"2026-08-06T01:46:35.963079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:46:35.963079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQbqdtk245lEvtwtkQNebAV+Qj5xBCmJFARNA6Jqe2xTiZfwJy5xSE6xY5hXAoUvPtXa7VncN6L5ifk9K+DZBg==","signature_status":"signed_v1","signed_at":"2026-08-06T01:46:35.964752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1a89d0daf434cc1b4051f80d3b3466cb4189fdbf38d2883fce43546604b0b28","sha256:6c1389a658f32ed89c526688bd5e370eb9e13fb69f1386a8af182e052b1c6787"],"state_sha256":"517db305a0f616890dda899d4a5477f0dc46035da0f3caa83321baea18c77905"}