{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QQ5XNQA4LPNZASGZQK4X5OWZOG","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":"ecf2cea38a9a2ebee65bb2b871289d6f8f3746a198859d533481f99e7196d59f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-26T16:28:10Z","title_canon_sha256":"ce020bac9b96ca5cc8b5a26b6e28c1747e43811ed2e3be066585c7c3a978725b"},"schema_version":"1.0","source":{"id":"2605.27492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27492","created_at":"2026-05-28T00:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27492v1","created_at":"2026-05-28T00:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27492","created_at":"2026-05-28T00:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"QQ5XNQA4LPNZ","created_at":"2026-05-28T00:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"QQ5XNQA4LPNZASGZ","created_at":"2026-05-28T00:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"QQ5XNQA4","created_at":"2026-05-28T00:05:21Z"}],"graph_snapshots":[{"event_id":"sha256:438e3f59482c1f6c00356ef58dd1fb3bc3390f56bfc60ca004846298e202cc53","target":"graph","created_at":"2026-05-28T00:05:21Z","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/2605.27492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture the dynamic complexity of real-world production workflows. As a result, benchmark performance may poorly reflect practical capability under realistic runtime environments involving long execution chains, tool interactions, dependency management, and iterative feedback loops. We thus present RAMP, a production-grounded infrastructure for assessing long-horizon","authors_text":"Bingjie Liu, Xianwei Zhang, Xin Huang, Yipeng Ouyang, Yuhao Gu, Zhongchun Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-26T16:28:10Z","title":"Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27492","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:be713208b33ed76038f15d781017ab174b9480056c00c1e52d42336a24705e57","target":"record","created_at":"2026-05-28T00:05:21Z","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":"ecf2cea38a9a2ebee65bb2b871289d6f8f3746a198859d533481f99e7196d59f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-26T16:28:10Z","title_canon_sha256":"ce020bac9b96ca5cc8b5a26b6e28c1747e43811ed2e3be066585c7c3a978725b"},"schema_version":"1.0","source":{"id":"2605.27492","kind":"arxiv","version":1}},"canonical_sha256":"843b76c01c5bdb9048d982b97ebad9718564328147b350637e0f5caa8ae6547c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"843b76c01c5bdb9048d982b97ebad9718564328147b350637e0f5caa8ae6547c","first_computed_at":"2026-05-28T00:05:21.162536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T00:05:21.162536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kuBNYmW5hBOBtTwqrZ2XT2vQrwlDeVQFC16qjbwY31Gt19fImwr3HNPQtJ7/bJ6is6apgNWoUYEPUoPLcfnwCw==","signature_status":"signed_v1","signed_at":"2026-05-28T00:05:21.163113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be713208b33ed76038f15d781017ab174b9480056c00c1e52d42336a24705e57","sha256:438e3f59482c1f6c00356ef58dd1fb3bc3390f56bfc60ca004846298e202cc53"],"state_sha256":"ce072d27330c73accce695a9e6a94173d09c457784b05dee438365cf09257199"}