{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EWZWQPQQ65DEJNIG23HS3YHJ2S","short_pith_number":"pith:EWZWQPQQ","schema_version":"1.0","canonical_sha256":"25b3683e10f74644b506d6cf2de0e9d486bcb68beded879ef3f92522188244b3","source":{"kind":"arxiv","id":"2605.07096","version":2},"attestation_state":"computed","paper":{"title":"Query-efficient model evaluation using cached responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DKPS with cached responses allows benchmark evaluation of new models using far fewer queries while matching baseline accuracy.","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Ben Johnson, Carey Priebe, Hayden Helm","submitted_at":"2026-05-08T01:24:06Z","abstract_excerpt":"Evaluating a new model on an existing benchmark is often necessary to understand its behavior before deployment. For modern evaluation frameworks, generating and evaluating a response for all queries can be prohibitively expensive. In practice, responses from previously-evaluated models are often cached -- creating a potential opportunity to use this additional information to decrease the number of queries required to accurately evaluate a new model. In this paper, we introduce an approach for predicting benchmark performance that leverages cached model responses based on the Data Kernel Persp"},"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":true},"canonical_record":{"source":{"id":"2605.07096","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:24:06Z","cross_cats_sorted":["cs.AI","stat.ME"],"title_canon_sha256":"8f44e85ebbcbce3a8e5132595228ef7a59c57ba89ba148d4188406011ec3bb6b","abstract_canon_sha256":"dd978c8478367cca2f1a62480a3e7fac9b963ffba13c4ee72d1e82372576c895"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:25.229800Z","signature_b64":"5EF9Ieapn2bwwjznVdy4454FpETaMFTo6gIHdDbM8Uol5cG5+xMKm+FyiiDsTSrq/mTxSvty6aZiH1zAdrwyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25b3683e10f74644b506d6cf2de0e9d486bcb68beded879ef3f92522188244b3","last_reissued_at":"2026-06-05T01:15:25.229360Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:25.229360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query-efficient model evaluation using cached responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DKPS with cached responses allows benchmark evaluation of new models using far fewer queries while matching baseline accuracy.","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Ben Johnson, Carey Priebe, Hayden Helm","submitted_at":"2026-05-08T01:24:06Z","abstract_excerpt":"Evaluating a new model on an existing benchmark is often necessary to understand its behavior before deployment. For modern evaluation frameworks, generating and evaluating a response for all queries can be prohibitively expensive. In practice, responses from previously-evaluated models are often cached -- creating a potential opportunity to use this additional information to decrease the number of queries required to accurately evaluate a new model. In this paper, we introduce an approach for predicting benchmark performance that leverages cached model responses based on the Data Kernel Persp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DKPS-based methods achieve the same mean absolute error as baselines with a substantially decreased query budget.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Data Kernel Perspective Space reliably quantifies black-box relationships between models and that the stated theoretical conditions for query-efficiency translate to practical benchmark settings.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DKPS-based methods leverage cached model responses to achieve equivalent benchmark prediction accuracy with substantially fewer queries than standard evaluation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DKPS with cached responses allows benchmark evaluation of new models using far fewer queries while matching baseline accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4c072ff360ac02f2a8ee2b02b8c9cc2a4f60f0364dc67aab3ea0bc97a666147d"},"source":{"id":"2605.07096","kind":"arxiv","version":2},"verdict":{"id":"4e016987-7957-4e68-929c-91e0c52e784c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T00:50:12.566768Z","strongest_claim":"DKPS-based methods achieve the same mean absolute error as baselines with a substantially decreased query budget.","one_line_summary":"DKPS-based methods leverage cached model responses to achieve equivalent benchmark prediction accuracy with substantially fewer queries than standard evaluation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Data Kernel Perspective Space reliably quantifies black-box relationships between models and that the stated theoretical conditions for query-efficiency translate to practical benchmark settings.","pith_extraction_headline":"DKPS with cached responses allows benchmark evaluation of new models using far fewer queries while matching baseline accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07096/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T11:22:03.427819Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T06:36:30.857371Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.589559Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:03:25.328571Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"cda9af02d44944d27322c7b56280a87d616ea44d08eea623d517094b72a544bd"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e372b0d3207c98a1cf5f2f12df769165ebf183137bd6defdff129a61f890384e"},"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":"2605.07096","created_at":"2026-06-05T01:15:25.229419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.07096v2","created_at":"2026-06-05T01:15:25.229419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07096","created_at":"2026-06-05T01:15:25.229419+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWZWQPQQ65DE","created_at":"2026-06-05T01:15:25.229419+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWZWQPQQ65DEJNIG","created_at":"2026-06-05T01:15:25.229419+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWZWQPQQ","created_at":"2026-06-05T01:15:25.229419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.26409","citing_title":"Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S","json":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S.json","graph_json":"https://pith.science/api/pith-number/EWZWQPQQ65DEJNIG23HS3YHJ2S/graph.json","events_json":"https://pith.science/api/pith-number/EWZWQPQQ65DEJNIG23HS3YHJ2S/events.json","paper":"https://pith.science/paper/EWZWQPQQ"},"agent_actions":{"view_html":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S","download_json":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S.json","view_paper":"https://pith.science/paper/EWZWQPQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.07096&json=true","fetch_graph":"https://pith.science/api/pith-number/EWZWQPQQ65DEJNIG23HS3YHJ2S/graph.json","fetch_events":"https://pith.science/api/pith-number/EWZWQPQQ65DEJNIG23HS3YHJ2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/action/storage_attestation","attest_author":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/action/author_attestation","sign_citation":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/action/citation_signature","submit_replication":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/action/replication_record"}},"created_at":"2026-06-05T01:15:25.229419+00:00","updated_at":"2026-06-05T01:15:25.229419+00:00"}