{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CPERPJ27GBSWXW5O7PUPOKGTY5","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":"4bd992aea8ea4ab82caac0adbbe92f14d08e1a249d5c0fcc8b38c52fdb7b3949","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T22:05:12Z","title_canon_sha256":"36ed191a43cd5662c1a37aa4da3a87f2cc7e278aa2105ecfa0ba43a69bd02a7b"},"schema_version":"1.0","source":{"id":"2605.20530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20530","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20530v1","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20530","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"CPERPJ27GBSW","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"CPERPJ27GBSWXW5O","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"CPERPJ27","created_at":"2026-05-21T01:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:111344381205aa9674956f32ed04c9127ec524b6d2129d0ae4a3c17ac631b1fc","target":"graph","created_at":"2026-05-21T01:04:41Z","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/2605.20530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kasra Mazaheri, Parsa Mazaheri","cross_cats":["cs.CL","cs.LG","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T22:05:12Z","title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20530","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":"sha256:4e637f6e581a00c98a0875536a68db4ffd3095cb624c1107b7f821c89596dfd3","target":"record","created_at":"2026-05-21T01:04:41Z","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":"4bd992aea8ea4ab82caac0adbbe92f14d08e1a249d5c0fcc8b38c52fdb7b3949","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T22:05:12Z","title_canon_sha256":"36ed191a43cd5662c1a37aa4da3a87f2cc7e278aa2105ecfa0ba43a69bd02a7b"},"schema_version":"1.0","source":{"id":"2605.20530","kind":"arxiv","version":1}},"canonical_sha256":"13c917a75f30656bdbaefbe8f728d3c77a0513f4df3d82ff58a29dc17cfaa8ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13c917a75f30656bdbaefbe8f728d3c77a0513f4df3d82ff58a29dc17cfaa8ed","first_computed_at":"2026-05-21T01:04:41.218748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:41.218748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iHYyRc5hVSRarot6d8R0VMI/zdfxXhEWlgK5Mf1cti3nYOaK2db+WRpolHppxNsZqVHJMj0NSiLwnZJIdc8wDw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:41.219210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e637f6e581a00c98a0875536a68db4ffd3095cb624c1107b7f821c89596dfd3","sha256:111344381205aa9674956f32ed04c9127ec524b6d2129d0ae4a3c17ac631b1fc"],"state_sha256":"255b75d3f7179228e3f269a4dac3408c6b07ca0548056297c9c62b8492833d04"}