{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OHT6LHTPQMD5EICVSVAMEDHFGA","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":"ca8d51413a37ad4d98762ff9e8f07be68dd5c40148aa0c5d9c4306e427f86e55","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T18:16:51Z","title_canon_sha256":"7d0cb65c3d291d84155a15fc8de85311f1349199a4d931ea6d6fea178c97c54f"},"schema_version":"1.0","source":{"id":"2608.11323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11323","created_at":"2026-08-13T00:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11323v1","created_at":"2026-08-13T00:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11323","created_at":"2026-08-13T00:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"OHT6LHTPQMD5","created_at":"2026-08-13T00:21:35Z"},{"alias_kind":"pith_short_16","alias_value":"OHT6LHTPQMD5EICV","created_at":"2026-08-13T00:21:35Z"},{"alias_kind":"pith_short_8","alias_value":"OHT6LHTP","created_at":"2026-08-13T00:21:35Z"}],"graph_snapshots":[{"event_id":"sha256:a41a2a41d41ad321be45b11f280c82657dc7df57a522296ad7296e40fbf13540","target":"graph","created_at":"2026-08-13T00:21:35Z","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/2608.11323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enterprise practitioners read agent leaderboards as if they ranked agent capability. We show, across three open agent-trace benchmarks (TheAgentCompany, $\\tau^2$-bench, and AppWorld), that the agent main effect accounts for less than 3% of total variance in every dataset and check type, while the agent-by-task interaction accounts for 7-23%. Leaderboards rank specialization, not capability. We arrive at this through a four-facet Generalizability Theory variance decomposition, fit with three estimators (Henderson Method-I, REML via lme4, and a Bayesian binomial GLMM) that agree to three decimal","authors_text":"Vasundra Srinivasan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T18:16:51Z","title":"Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11323","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":"sha256:665e09482d5e0693a69d9a631065d1d8fa3ae062e1d083b9a256e2c9a19bc384","target":"record","created_at":"2026-08-13T00:21:35Z","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":"ca8d51413a37ad4d98762ff9e8f07be68dd5c40148aa0c5d9c4306e427f86e55","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T18:16:51Z","title_canon_sha256":"7d0cb65c3d291d84155a15fc8de85311f1349199a4d931ea6d6fea178c97c54f"},"schema_version":"1.0","source":{"id":"2608.11323","kind":"arxiv","version":1}},"canonical_sha256":"71e7e59e6f8307d220559540c20ce5303a508f1978e94dee1d2887b7f1907e79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71e7e59e6f8307d220559540c20ce5303a508f1978e94dee1d2887b7f1907e79","first_computed_at":"2026-08-13T00:21:35.569699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:21:35.569699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4QJoKoeY+54BviaiVrKW2ib0R/gkk+JW/99cv9uUwLtUZdKqs5eUqlK4msXu1DUtBjINuvbxoN8LIV62y1I4AQ==","signature_status":"signed_v1","signed_at":"2026-08-13T00:21:35.571484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:665e09482d5e0693a69d9a631065d1d8fa3ae062e1d083b9a256e2c9a19bc384","sha256:a41a2a41d41ad321be45b11f280c82657dc7df57a522296ad7296e40fbf13540"],"state_sha256":"88238c1ffd29796162ac749b5ba748d60400177cc877663ca38d1a85524f0a94"}