{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OCQQDA5G6DXGHBTH367AZ7EMD4","short_pith_number":"pith:OCQQDA5G","schema_version":"1.0","canonical_sha256":"70a10183a6f0ee638667dfbe0cfc8c1f352e855888b1bdcd0e89fd40ca263072","source":{"kind":"arxiv","id":"2606.21140","version":1},"attestation_state":"computed","paper":{"title":"AgentMeter: Evaluating Model-CLI Matching for CLI-Based Local Task-Solving Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Baisheng Lai, Han Chi, Jianqiang Huang, Jiaxin Qi, Yan Cui","submitted_at":"2026-06-19T06:26:32Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.21140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-19T06:26:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e35d5b95ccfa4b87a367c200490fc800c351704ae8788968d5eef2f43159168f","abstract_canon_sha256":"3204c8443b2c72f03425199168275cb9df4e65a1d479fe466e8491a824f3daaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:31.176234Z","signature_b64":"TWYRVHidWUtbH+NFLb0AFcKGG7HqQsKGlJv8BtUXOqxZ5Api+TyZJ8ZXb2t7Gmyz5wUjpiM+rMjpNsb+IQWbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a10183a6f0ee638667dfbe0cfc8c1f352e855888b1bdcd0e89fd40ca263072","last_reissued_at":"2026-06-23T01:12:31.175743Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:31.175743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentMeter: Evaluating Model-CLI Matching for CLI-Based Local Task-Solving Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Baisheng Lai, Han Chi, Jianqiang Huang, Jiaxin Qi, Yan Cui","submitted_at":"2026-06-19T06:26:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21140","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.21140/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.21140","created_at":"2026-06-23T01:12:31.175813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21140v1","created_at":"2026-06-23T01:12:31.175813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21140","created_at":"2026-06-23T01:12:31.175813+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCQQDA5G6DXG","created_at":"2026-06-23T01:12:31.175813+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCQQDA5G6DXGHBTH","created_at":"2026-06-23T01:12:31.175813+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCQQDA5G","created_at":"2026-06-23T01:12:31.175813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4","json":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4.json","graph_json":"https://pith.science/api/pith-number/OCQQDA5G6DXGHBTH367AZ7EMD4/graph.json","events_json":"https://pith.science/api/pith-number/OCQQDA5G6DXGHBTH367AZ7EMD4/events.json","paper":"https://pith.science/paper/OCQQDA5G"},"agent_actions":{"view_html":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4","download_json":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4.json","view_paper":"https://pith.science/paper/OCQQDA5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21140&json=true","fetch_graph":"https://pith.science/api/pith-number/OCQQDA5G6DXGHBTH367AZ7EMD4/graph.json","fetch_events":"https://pith.science/api/pith-number/OCQQDA5G6DXGHBTH367AZ7EMD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4/action/storage_attestation","attest_author":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4/action/author_attestation","sign_citation":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4/action/citation_signature","submit_replication":"https://pith.science/pith/OCQQDA5G6DXGHBTH367AZ7EMD4/action/replication_record"}},"created_at":"2026-06-23T01:12:31.175813+00:00","updated_at":"2026-06-23T01:12:31.175813+00:00"}