{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CPERPJ27GBSWXW5O7PUPOKGTY5","short_pith_number":"pith:CPERPJ27","schema_version":"1.0","canonical_sha256":"13c917a75f30656bdbaefbe8f728d3c77a0513f4df3d82ff58a29dc17cfaa8ed","source":{"kind":"arxiv","id":"2605.20530","version":1},"attestation_state":"computed","paper":{"title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Kasra Mazaheri, Parsa Mazaheri","submitted_at":"2026-05-19T22:05:12Z","abstract_excerpt":"Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evaluate them are fragmented: each emphasizes a different unit of measurement (final task success, tool-call validity, repeated-pass consistency, trajectory safety, or attack robustness). A line of 2024-2025 work has converged on the diagnosis that a single accuracy column is no longer the right unit of comparison for deployable agents. AgentAtlas extends this line of work with four components: (i) a six-state control-decision taxonomy (Act / Ask / Re"},"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":"2605.20530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T22:05:12Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"title_canon_sha256":"36ed191a43cd5662c1a37aa4da3a87f2cc7e278aa2105ecfa0ba43a69bd02a7b","abstract_canon_sha256":"4bd992aea8ea4ab82caac0adbbe92f14d08e1a249d5c0fcc8b38c52fdb7b3949"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:41.219210Z","signature_b64":"iHYyRc5hVSRarot6d8R0VMI/zdfxXhEWlgK5Mf1cti3nYOaK2db+WRpolHppxNsZqVHJMj0NSiLwnZJIdc8wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13c917a75f30656bdbaefbe8f728d3c77a0513f4df3d82ff58a29dc17cfaa8ed","last_reissued_at":"2026-05-21T01:04:41.218748Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:41.218748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Kasra Mazaheri, Parsa Mazaheri","submitted_at":"2026-05-19T22:05:12Z","abstract_excerpt":"Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evaluate them are fragmented: each emphasizes a different unit of measurement (final task success, tool-call validity, repeated-pass consistency, trajectory safety, or attack robustness). A line of 2024-2025 work has converged on the diagnosis that a single accuracy column is no longer the right unit of comparison for deployable agents. AgentAtlas extends this line of work with four components: (i) a six-state control-decision taxonomy (Act / Ask / Re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20530","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/2605.20530/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":"2605.20530","created_at":"2026-05-21T01:04:41.218822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20530v1","created_at":"2026-05-21T01:04:41.218822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20530","created_at":"2026-05-21T01:04:41.218822+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPERPJ27GBSW","created_at":"2026-05-21T01:04:41.218822+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPERPJ27GBSWXW5O","created_at":"2026-05-21T01:04:41.218822+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPERPJ27","created_at":"2026-05-21T01:04:41.218822+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/CPERPJ27GBSWXW5O7PUPOKGTY5","json":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5.json","graph_json":"https://pith.science/api/pith-number/CPERPJ27GBSWXW5O7PUPOKGTY5/graph.json","events_json":"https://pith.science/api/pith-number/CPERPJ27GBSWXW5O7PUPOKGTY5/events.json","paper":"https://pith.science/paper/CPERPJ27"},"agent_actions":{"view_html":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5","download_json":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5.json","view_paper":"https://pith.science/paper/CPERPJ27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20530&json=true","fetch_graph":"https://pith.science/api/pith-number/CPERPJ27GBSWXW5O7PUPOKGTY5/graph.json","fetch_events":"https://pith.science/api/pith-number/CPERPJ27GBSWXW5O7PUPOKGTY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5/action/storage_attestation","attest_author":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5/action/author_attestation","sign_citation":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5/action/citation_signature","submit_replication":"https://pith.science/pith/CPERPJ27GBSWXW5O7PUPOKGTY5/action/replication_record"}},"created_at":"2026-05-21T01:04:41.218822+00:00","updated_at":"2026-05-21T01:04:41.218822+00:00"}