{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GNX4TTMF2ZIO7SEO3IIFDZGHO6","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":"194c9f5c235e197560a9ffe7d911881c02d522443a2f08fcc68fb13b37a31302","cross_cats_sorted":["cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T14:02:50Z","title_canon_sha256":"7620abf29fc6168a75ff28bf854269f1bc6329596b2818f03d6f3814227fe689"},"schema_version":"1.0","source":{"id":"2607.12790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12790","created_at":"2026-07-15T01:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12790v1","created_at":"2026-07-15T01:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12790","created_at":"2026-07-15T01:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"GNX4TTMF2ZIO","created_at":"2026-07-15T01:22:18Z"},{"alias_kind":"pith_short_16","alias_value":"GNX4TTMF2ZIO7SEO","created_at":"2026-07-15T01:22:18Z"},{"alias_kind":"pith_short_8","alias_value":"GNX4TTMF","created_at":"2026-07-15T01:22:18Z"}],"graph_snapshots":[{"event_id":"sha256:72a3ef04ee04bab1ebd9e4efc41533d1363887751bb7ff0d87e11d1deb47e825","target":"graph","created_at":"2026-07-15T01:22:18Z","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/2607.12790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists. In many real applications it does not. We make three claims. First, metrics can be \\emph{evolved}: our metric loop searches compositions of small drawback detectors under a full evolutionary lifecycle, trained to agree with a ten-item anchored reference set, regularized by consensus over unlabeled outputs, and audited against a held-out anchor it never reads, yielding a transparent, inspectable metric rather tha","authors_text":"Bing Zhu, Guanghui Wang, Peiyang He, Wei Qiu, Xing Zhang, Yanwei Cui, Ziyuan Li","cross_cats":["cs.CL","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T14:02:50Z","title":"Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12790","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:a85b5e564eee035f6b0dca75dd66a1cf2e3e6440beefbfd0234c97762a6a817d","target":"record","created_at":"2026-07-15T01:22:18Z","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":"194c9f5c235e197560a9ffe7d911881c02d522443a2f08fcc68fb13b37a31302","cross_cats_sorted":["cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T14:02:50Z","title_canon_sha256":"7620abf29fc6168a75ff28bf854269f1bc6329596b2818f03d6f3814227fe689"},"schema_version":"1.0","source":{"id":"2607.12790","kind":"arxiv","version":1}},"canonical_sha256":"336fc9cd85d650efc88eda1051e4c777bf144f60c65c3b350c9618ffca3dbfd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"336fc9cd85d650efc88eda1051e4c777bf144f60c65c3b350c9618ffca3dbfd9","first_computed_at":"2026-07-15T01:22:18.122408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:22:18.122408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V0GTL9L4aNgCvfFfWyAms+koRJGUx6qus+GE+q6FfJUp4Hh3H8wGXwL5jPmmmG9MWuQu5xh2k8Qg6Ueq22vnDA==","signature_status":"signed_v1","signed_at":"2026-07-15T01:22:18.123210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a85b5e564eee035f6b0dca75dd66a1cf2e3e6440beefbfd0234c97762a6a817d","sha256:72a3ef04ee04bab1ebd9e4efc41533d1363887751bb7ff0d87e11d1deb47e825"],"state_sha256":"e441e588ae34fef91e95018f6b4c6cf88b51a2c57eeaaa4bfe5e8ec63bd7d708"}