{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OCQQDA5G6DXGHBTH367AZ7EMD4","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":"3204c8443b2c72f03425199168275cb9df4e65a1d479fe466e8491a824f3daaa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-19T06:26:32Z","title_canon_sha256":"e35d5b95ccfa4b87a367c200490fc800c351704ae8788968d5eef2f43159168f"},"schema_version":"1.0","source":{"id":"2606.21140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21140","created_at":"2026-06-23T01:12:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21140v1","created_at":"2026-06-23T01:12:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21140","created_at":"2026-06-23T01:12:31Z"},{"alias_kind":"pith_short_12","alias_value":"OCQQDA5G6DXG","created_at":"2026-06-23T01:12:31Z"},{"alias_kind":"pith_short_16","alias_value":"OCQQDA5G6DXGHBTH","created_at":"2026-06-23T01:12:31Z"},{"alias_kind":"pith_short_8","alias_value":"OCQQDA5G","created_at":"2026-06-23T01:12:31Z"}],"graph_snapshots":[{"event_id":"sha256:37263ba3504e088b60090aef8820de34f1120905fdcdbdfc1be3f880b566dafd","target":"graph","created_at":"2026-06-23T01:12:31Z","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/2606.21140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents increasingly solve local tasks through command-line and CLI-based harness interfaces, including code editing, repository inspection, data analysis, and file workflows. Existing evaluations often emphasize task success, but deployed local agents are not models alone: the CLI mediates prompts, context replay, tool outputs, file access, terminal observations, and stopping behavior. As a result, the same model can produce different success, token, and cost profiles under different CLIs. We introduce AGENTMETER, a benchmark for evaluating model-CLI matching in CLI-mediated local task-sol","authors_text":"Baisheng Lai, Han Chi, Jianqiang Huang, Jiaxin Qi, Yan Cui","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-19T06:26:32Z","title":"AgentMeter: Evaluating Model-CLI Matching for CLI-Based Local Task-Solving Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21140","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":"sha256:08e246dfb19fca89b984aa705ace6f2d4117d139caff86d34c029c755ae29e79","target":"record","created_at":"2026-06-23T01:12:31Z","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":"3204c8443b2c72f03425199168275cb9df4e65a1d479fe466e8491a824f3daaa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-19T06:26:32Z","title_canon_sha256":"e35d5b95ccfa4b87a367c200490fc800c351704ae8788968d5eef2f43159168f"},"schema_version":"1.0","source":{"id":"2606.21140","kind":"arxiv","version":1}},"canonical_sha256":"70a10183a6f0ee638667dfbe0cfc8c1f352e855888b1bdcd0e89fd40ca263072","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70a10183a6f0ee638667dfbe0cfc8c1f352e855888b1bdcd0e89fd40ca263072","first_computed_at":"2026-06-23T01:12:31.175743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:31.175743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TWYRVHidWUtbH+NFLb0AFcKGG7HqQsKGlJv8BtUXOqxZ5Api+TyZJ8ZXb2t7Gmyz5wUjpiM+rMjpNsb+IQWbDg==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:31.176234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08e246dfb19fca89b984aa705ace6f2d4117d139caff86d34c029c755ae29e79","sha256:37263ba3504e088b60090aef8820de34f1120905fdcdbdfc1be3f880b566dafd"],"state_sha256":"f6e8810a165ba76567213357db4fa2bf287dbb0b3676ac9cd0096acb5bd4c48d"}