{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7OPC42PYLB4NHCW5JWZFXI34VX","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":"806917e859ca329a16057176631412184870bdc594edb7e4bd18ddc3bc05e5c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T00:08:59Z","title_canon_sha256":"e8a4f95d3ce9729bb80341a8573ddf6c33fe14bee2a322ba3cc944d21a38e11a"},"schema_version":"1.0","source":{"id":"2506.00319","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00319","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00319v1","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00319","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"7OPC42PYLB4N","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"7OPC42PYLB4NHCW5","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"7OPC42PY","created_at":"2026-07-05T11:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:bfaba212f42018bf10ab76345da64035db2d1b3ed6645301f2b01e3ab03df201","target":"graph","created_at":"2026-07-05T11:13:32Z","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/2506.00319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language models evolve to tackle complex, multifaceted tasks, their evaluation must adapt to capture this intricacy. A granular, skill-specific understanding of model capabilities can empower researchers to make informed model development plans. In this paper, we introduce SkillVerse, an unsupervised tree-structured diagnosis framework for understanding model proficiency in specific abilities. With LLM as a judge, SkillVerse first critiques the model responses, and then organizes them into a hierarchical structure termed dendrogram. Given proficiency at arbitrary levels of granularity, Skil","authors_text":"Jiao Sun, Nanyun Peng, Yufei Tian, Zizhao Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T00:08:59Z","title":"SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00319","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:af4f60f15b1e26302ad5ecfbde70aae1b3a8c986ddaf5a53d511d11baecd2ea8","target":"record","created_at":"2026-07-05T11:13:32Z","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":"806917e859ca329a16057176631412184870bdc594edb7e4bd18ddc3bc05e5c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T00:08:59Z","title_canon_sha256":"e8a4f95d3ce9729bb80341a8573ddf6c33fe14bee2a322ba3cc944d21a38e11a"},"schema_version":"1.0","source":{"id":"2506.00319","kind":"arxiv","version":1}},"canonical_sha256":"fb9e2e69f85878d38add4db25ba37cade48ff9a8e7589fa4021d4d513188f8a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb9e2e69f85878d38add4db25ba37cade48ff9a8e7589fa4021d4d513188f8a2","first_computed_at":"2026-07-05T11:13:32.474695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:32.474695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"snR93H6LVnsHEL/dwfQlvUcqBpbkeHhegUGTV0oZp+4ksMoCELPvMOsUDjjHGSgyBthblXVUoCvBA/R7H1v6Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:32.475159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00319","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af4f60f15b1e26302ad5ecfbde70aae1b3a8c986ddaf5a53d511d11baecd2ea8","sha256:bfaba212f42018bf10ab76345da64035db2d1b3ed6645301f2b01e3ab03df201"],"state_sha256":"a19611db2eb5a3d9976b4505618a86fac4acaab58366d40e21cce4b50b6c20de"}