{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5VMBB3DYXKKBZDZZQNG7OLIGZP","short_pith_number":"pith:5VMBB3DY","schema_version":"1.0","canonical_sha256":"ed5810ec78ba941c8f39834df72d06cbf112dc5efb47fc022de3880e738cf8e4","source":{"kind":"arxiv","id":"2605.17110","version":1},"attestation_state":"computed","paper":{"title":"Capturing LLM Capabilities via Evidence-Calibrated Query Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fangzhou Wu, Qiuyi Zhang, Sandeep Silwal","submitted_at":"2026-05-16T18:30:37Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.17110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T18:30:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"75209c69393653c2afba553e7a6b4fb9c3af469f2913e0cab1f728363d858ab5","abstract_canon_sha256":"42175351bc3b7d56aa4dd8726ffb675d5d0abf72809631ada0af480dc2c9a799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:40.604872Z","signature_b64":"fP3sjlUfuB/seSz2l6GwVjsvRacjZQGDVqiK1OOq21zuqsHEWPaF+D3N/SQFt5yOHzsoFvOzggJaIEMEiKBfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed5810ec78ba941c8f39834df72d06cbf112dc5efb47fc022de3880e738cf8e4","last_reissued_at":"2026-05-20T00:03:40.604142Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:40.604142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capturing LLM Capabilities via Evidence-Calibrated Query Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fangzhou Wu, Qiuyi Zhang, Sandeep Silwal","submitted_at":"2026-05-16T18:30:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17110","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17110/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"ea29fc4bf75dc052e9f3ddfc002c71a6c16785d17326162bea80c4ce76c9f1f2"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.17110","created_at":"2026-05-20T00:03:40.604269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17110v1","created_at":"2026-05-20T00:03:40.604269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17110","created_at":"2026-05-20T00:03:40.604269+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VMBB3DYXKKB","created_at":"2026-05-20T00:03:40.604269+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VMBB3DYXKKBZDZZ","created_at":"2026-05-20T00:03:40.604269+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VMBB3DY","created_at":"2026-05-20T00:03:40.604269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP","json":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP.json","graph_json":"https://pith.science/api/pith-number/5VMBB3DYXKKBZDZZQNG7OLIGZP/graph.json","events_json":"https://pith.science/api/pith-number/5VMBB3DYXKKBZDZZQNG7OLIGZP/events.json","paper":"https://pith.science/paper/5VMBB3DY"},"agent_actions":{"view_html":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP","download_json":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP.json","view_paper":"https://pith.science/paper/5VMBB3DY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17110&json=true","fetch_graph":"https://pith.science/api/pith-number/5VMBB3DYXKKBZDZZQNG7OLIGZP/graph.json","fetch_events":"https://pith.science/api/pith-number/5VMBB3DYXKKBZDZZQNG7OLIGZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP/action/storage_attestation","attest_author":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP/action/author_attestation","sign_citation":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP/action/citation_signature","submit_replication":"https://pith.science/pith/5VMBB3DYXKKBZDZZQNG7OLIGZP/action/replication_record"}},"created_at":"2026-05-20T00:03:40.604269+00:00","updated_at":"2026-05-20T00:03:40.604269+00:00"}