{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:753FT7B5GNC32ZOKVCOCNSYG5O","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":"a95a82b14a3484f31c8451acdeccf55ed2d2666e400061e584d0589521a78882","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T21:12:48Z","title_canon_sha256":"eca805a0e8361006482dacc2017cfa7a725fc70d19aadc3b093930c212df8235"},"schema_version":"1.0","source":{"id":"2503.08893","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08893","created_at":"2026-07-05T11:35:12Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08893v2","created_at":"2026-07-05T11:35:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08893","created_at":"2026-07-05T11:35:12Z"},{"alias_kind":"pith_short_12","alias_value":"753FT7B5GNC3","created_at":"2026-07-05T11:35:12Z"},{"alias_kind":"pith_short_16","alias_value":"753FT7B5GNC32ZOK","created_at":"2026-07-05T11:35:12Z"},{"alias_kind":"pith_short_8","alias_value":"753FT7B5","created_at":"2026-07-05T11:35:12Z"}],"graph_snapshots":[{"event_id":"sha256:b1fc716def92d7a57572f2fed92748b76914f6f3e47d81a19526e427d90f833d","target":"graph","created_at":"2026-07-05T11:35:12Z","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/2503.08893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An ideal model evaluation should achieve two goals: identifying where the model fails and providing actionable improvement guidance. Toward these goals for language model (LM) evaluations, we formulate the problem of generating a weakness profile, a set of weaknesses expressed in natural language, given an LM's performance on every individual instance in a benchmark. We introduce a suite of quantitative assessments to compare different weakness profiling methods. We also introduce a weakness profiling method EvalTree. EvalTree constructs a capability tree where each node represents a capabilit","authors_text":"Hannaneh Hajishirzi, Pang Wei Koh, Yizhong Wang, Zhiyuan Zeng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T21:12:48Z","title":"EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08893","kind":"arxiv","version":2},"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":"sha256:2bcf4fb748b72e220e764031ccb673fb77bea6de95c3805d82b4fc8dc2e29916","target":"record","created_at":"2026-07-05T11:35:12Z","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":"a95a82b14a3484f31c8451acdeccf55ed2d2666e400061e584d0589521a78882","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T21:12:48Z","title_canon_sha256":"eca805a0e8361006482dacc2017cfa7a725fc70d19aadc3b093930c212df8235"},"schema_version":"1.0","source":{"id":"2503.08893","kind":"arxiv","version":2}},"canonical_sha256":"ff7659fc3d3345bd65caa89c26cb06eb9e8ba0587a17177ebbbc2372a980a790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff7659fc3d3345bd65caa89c26cb06eb9e8ba0587a17177ebbbc2372a980a790","first_computed_at":"2026-07-05T11:35:12.574611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:12.574611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oP9S+MVZEa9hGNy2SKPO9CCit8Nhx96RX1yi+29KpUxyfdT67HiZBYgdtsd/TqZJaW4W1buFGQM/K0cV6QT3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:12.575100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08893","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bcf4fb748b72e220e764031ccb673fb77bea6de95c3805d82b4fc8dc2e29916","sha256:b1fc716def92d7a57572f2fed92748b76914f6f3e47d81a19526e427d90f833d"],"state_sha256":"b20e75a51d2407f845fd687319ebd43d386e17f379aa40a3be526e064ff8ab09"}