{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QNHVG6UPZLXU2LG5LPU7RXVDGV","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":"b1f797b793b4733c8a4502b9ae89ad686cedabd9197a249138338d89ac9545e7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-06T17:39:47Z","title_canon_sha256":"63baa7e85a487c1a3f0b336804c016458574fa6fcea48b2359d5022c80e9fc8c"},"schema_version":"1.0","source":{"id":"2512.20638","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.20638","created_at":"2026-06-02T01:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2512.20638v2","created_at":"2026-06-02T01:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.20638","created_at":"2026-06-02T01:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"QNHVG6UPZLXU","created_at":"2026-06-02T01:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"QNHVG6UPZLXU2LG5","created_at":"2026-06-02T01:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"QNHVG6UP","created_at":"2026-06-02T01:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:becc505cf1e018ad26461f908e754ba65df719440655bed320bf41588435345e","target":"graph","created_at":"2026-06-02T01:03:40Z","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/2512.20638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation of large language models relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics, but can obscure (i) particular sub-areas where the models are weak (\"model gaps\") and (ii) imbalanced coverage in the benchmarks themselves (\"benchmark gaps\"). To automatically uncover both types of gaps, we propose a simple new method using concept activations from sparse autoencoders, to identify fine-grained gaps on a per-concept basis. The method also benefits from grounding evaluation in the model's internal representations, as well as easy comparison acro","authors_text":"Christoph Bregler, Maty Bohacek, Nicholas Dufour, Nino Scherrer, Stephanie C. Y. Chan, Thomas Leung","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-06T17:39:47Z","title":"Uncovering Competency Gaps in Large Language Models and Their Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.20638","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":"sha256:5887cbda820a4491ee8af392c1d476b9820a5522f640da265d7c9aa2966ebeed","target":"record","created_at":"2026-06-02T01:03:40Z","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":"b1f797b793b4733c8a4502b9ae89ad686cedabd9197a249138338d89ac9545e7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-06T17:39:47Z","title_canon_sha256":"63baa7e85a487c1a3f0b336804c016458574fa6fcea48b2359d5022c80e9fc8c"},"schema_version":"1.0","source":{"id":"2512.20638","kind":"arxiv","version":2}},"canonical_sha256":"834f537a8fcaef4d2cdd5be9f8dea3357d8aa81d4c263becfa0b9192ddb2afd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"834f537a8fcaef4d2cdd5be9f8dea3357d8aa81d4c263becfa0b9192ddb2afd2","first_computed_at":"2026-06-02T01:03:40.163441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:40.163441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WUehgjt78HQ0ZVEVJM/VxQFFEri3I8s0NKvrb54wxGT6KwvRVBL3AToutmkEKKEx3pt2qJJbewTFOL/H4MWGDg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:40.163977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.20638","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5887cbda820a4491ee8af392c1d476b9820a5522f640da265d7c9aa2966ebeed","sha256:becc505cf1e018ad26461f908e754ba65df719440655bed320bf41588435345e"],"state_sha256":"273579d59c86f518f2c240ea3e605a8876728bc287b6c91f92d16ea4cf6b9a51"}