{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5VMBB3DYXKKBZDZZQNG7OLIGZP","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"42175351bc3b7d56aa4dd8726ffb675d5d0abf72809631ada0af480dc2c9a799","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T18:30:37Z","title_canon_sha256":"75209c69393653c2afba553e7a6b4fb9c3af469f2913e0cab1f728363d858ab5"},"schema_version":"1.0","source":{"id":"2605.17110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17110","created_at":"2026-05-20T00:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17110v1","created_at":"2026-05-20T00:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17110","created_at":"2026-05-20T00:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"5VMBB3DYXKKB","created_at":"2026-05-20T00:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"5VMBB3DYXKKBZDZZ","created_at":"2026-05-20T00:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"5VMBB3DY","created_at":"2026-05-20T00:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:3a464aad61035fe24d476e94a86b1d82d8966c07fc80208134750bd548d51b47","target":"graph","created_at":"2026-05-20T00:03:40Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.789929Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.717159Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17110/integrity.json","findings":[],"snapshot_sha256":"ea29fc4bf75dc052e9f3ddfc002c71a6c16785d17326162bea80c4ce76c9f1f2","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Query clustering organizes queries into groups that reflect shared latent capability demands, enabling capability-aware LLM evaluation. Existing clustering methods, which primarily rely on semantic taxonomies or embeddings, often fail to capture such latent capability requirements due to a misalignment between surface-level semantics and actual model performance. We propose ECC, an algorithm that calibrates prior semantic embeddings using limited posterior model comparisons to bridge the gap between surface-level semantics and latent capability requirements. ECC characterizes each cluster thro","authors_text":"Fangzhou Wu, Qiuyi Zhang, Sandeep Silwal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T18:30:37Z","title":"Capturing LLM Capabilities via Evidence-Calibrated Query Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17110","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":"sha256:66e9b5970f21495d2b4d8d31534b0fbb82203ddd0dfcb322979d0e62c1f6e514","target":"record","created_at":"2026-05-20T00:03:40Z","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":"42175351bc3b7d56aa4dd8726ffb675d5d0abf72809631ada0af480dc2c9a799","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T18:30:37Z","title_canon_sha256":"75209c69393653c2afba553e7a6b4fb9c3af469f2913e0cab1f728363d858ab5"},"schema_version":"1.0","source":{"id":"2605.17110","kind":"arxiv","version":1}},"canonical_sha256":"ed5810ec78ba941c8f39834df72d06cbf112dc5efb47fc022de3880e738cf8e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed5810ec78ba941c8f39834df72d06cbf112dc5efb47fc022de3880e738cf8e4","first_computed_at":"2026-05-20T00:03:40.604142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:40.604142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fP3sjlUfuB/seSz2l6GwVjsvRacjZQGDVqiK1OOq21zuqsHEWPaF+D3N/SQFt5yOHzsoFvOzggJaIEMEiKBfDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:40.604872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66e9b5970f21495d2b4d8d31534b0fbb82203ddd0dfcb322979d0e62c1f6e514","sha256:3a464aad61035fe24d476e94a86b1d82d8966c07fc80208134750bd548d51b47","sha256:6b0b0f8af023aae4dc380288cfaa3b7b9c56f3a754de5f84b8e8f8ac23beb96d"],"state_sha256":"77553bd859c7b890160d3f712d1f45cb1d09923f9bf8102805acd3b36c1674f6"}