{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6F5NIZGL4E2TVXFBTQ2DRE5V63","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":"5c15efcd71fad02d22c2cb3865e2dd36ad39f05a5cf0f9ab443d8b42362c2f03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:40:12Z","title_canon_sha256":"54d92965b4beb2342fdb461554dcdc1a59799cfac7916a178364cdb4d51bf63b"},"schema_version":"1.0","source":{"id":"2606.06546","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06546","created_at":"2026-06-08T00:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06546v1","created_at":"2026-06-08T00:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06546","created_at":"2026-06-08T00:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"6F5NIZGL4E2T","created_at":"2026-06-08T00:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"6F5NIZGL4E2TVXFB","created_at":"2026-06-08T00:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"6F5NIZGL","created_at":"2026-06-08T00:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:8743cd73908786b4a127ac52a024dfe535cb2cbbca3075591b41633765aa4022","target":"graph","created_at":"2026-06-08T00:03:41Z","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/2606.06546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) for education requires measuring how models teach, not only what they know. Existing benchmarks emphasize domain-general correctness or depend on manually designed rubrics that scale poorly to long-tail pedagogical scenarios. We introduce Elmes*, an end-to-end framework for constructing, refining, and applying fine-grained scenario-specific rubrics. Elmes* combines a declarative multi-agent engine for teacher--student--judge interactions with SceneGen, a self-evolving module that co-optimizes evaluation criteria and test data from expert-defined pedagogi","authors_text":"Aimin Zhou, Hao Hao, Ruohua Zhang, Siyu Song, Tao Liu, Wentao Liu, Ye Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:40:12Z","title":"Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06546","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":"sha256:2be5fed33c385dceb02fc4fd323174c3c9e01c0e733c63eb138e9f346ed83384","target":"record","created_at":"2026-06-08T00:03:41Z","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":"5c15efcd71fad02d22c2cb3865e2dd36ad39f05a5cf0f9ab443d8b42362c2f03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:40:12Z","title_canon_sha256":"54d92965b4beb2342fdb461554dcdc1a59799cfac7916a178364cdb4d51bf63b"},"schema_version":"1.0","source":{"id":"2606.06546","kind":"arxiv","version":1}},"canonical_sha256":"f17ad464cbe1353adca19c343893b5f6ed3190018ffc251f8f47c26b2516dc36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f17ad464cbe1353adca19c343893b5f6ed3190018ffc251f8f47c26b2516dc36","first_computed_at":"2026-06-08T00:03:41.879358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T00:03:41.879358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"In4KwiIuf5WW5I+StMJ42k88SRHIgQw4BsvPBFGxXHha6yy+4qYDdQuaLJuXHd1gDd0ALVAeHS3ghF8VHf7kAQ==","signature_status":"signed_v1","signed_at":"2026-06-08T00:03:41.880251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06546","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2be5fed33c385dceb02fc4fd323174c3c9e01c0e733c63eb138e9f346ed83384","sha256:8743cd73908786b4a127ac52a024dfe535cb2cbbca3075591b41633765aa4022"],"state_sha256":"cdf1dcea9a7d92efc684b799db316193251a37bb39cd144fb6d64a3f4488a4a7"}