{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EWZWQPQQ65DEJNIG23HS3YHJ2S","short_pith_number":"pith:EWZWQPQQ","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"},"canonical_sha256":"25b3683e10f74644b506d6cf2de0e9d486bcb68beded879ef3f92522188244b3","source":{"kind":"arxiv","id":"2605.07096","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07096","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07096v2","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07096","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"EWZWQPQQ65DE","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"EWZWQPQQ65DEJNIG","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"EWZWQPQQ","created_at":"2026-06-05T01:15:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EWZWQPQQ65DEJNIG23HS3YHJ2S","target":"record","payload":{"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"},"canonical_sha256":"25b3683e10f74644b506d6cf2de0e9d486bcb68beded879ef3f92522188244b3","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"},"source_kind":"arxiv","source_id":"2605.07096","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLytoMqNW02dFy0Wpjdkxjwrt5r90HUAiKKsbkwCSRJ05n4ZxjyAZ617ubmUx8FLSxzYa9Cxh2/ODyID1OQ0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:05:49.063333Z"},"content_sha256":"e2fb612931db619487c82e3692e4eb95972a873f7cea4c8093f80f29483d19c7","schema_version":"1.0","event_id":"sha256:e2fb612931db619487c82e3692e4eb95972a873f7cea4c8093f80f29483d19c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EWZWQPQQ65DEJNIG23HS3YHJ2S","target":"graph","payload":{"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"},"verdict_id":"4e016987-7957-4e68-929c-91e0c52e784c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ypseaPrf8mQy687iILoY/ycShF/qje/EURxwS4bVjVYJy3LUrj4P86BGTd8PgpX2gg051Ww68DVOLAy4Eys9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:05:49.063849Z"},"content_sha256":"cdb9e6c03edc1f36e957c3a9a5df6df6b2f87e635029ba5486cffe2b3fc05780","schema_version":"1.0","event_id":"sha256:cdb9e6c03edc1f36e957c3a9a5df6df6b2f87e635029ba5486cffe2b3fc05780"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/bundle.json","state_url":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T04:05:49Z","links":{"resolver":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S","bundle":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/bundle.json","state":"https://pith.science/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWZWQPQQ65DEJNIG23HS3YHJ2S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EWZWQPQQ65DEJNIG23HS3YHJ2S","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":"dd978c8478367cca2f1a62480a3e7fac9b963ffba13c4ee72d1e82372576c895","cross_cats_sorted":["cs.AI","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:24:06Z","title_canon_sha256":"8f44e85ebbcbce3a8e5132595228ef7a59c57ba89ba148d4188406011ec3bb6b"},"schema_version":"1.0","source":{"id":"2605.07096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07096","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07096v2","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07096","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"EWZWQPQQ65DE","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"EWZWQPQQ65DEJNIG","created_at":"2026-06-05T01:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"EWZWQPQQ","created_at":"2026-06-05T01:15:25Z"}],"graph_snapshots":[{"event_id":"sha256:cdb9e6c03edc1f36e957c3a9a5df6df6b2f87e635029ba5486cffe2b3fc05780","target":"graph","created_at":"2026-06-05T01:15:25Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"DKPS-based methods achieve the same mean absolute error as baselines with a substantially decreased query budget."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DKPS-based methods leverage cached model responses to achieve equivalent benchmark prediction accuracy with substantially fewer queries than standard evaluation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DKPS with cached responses allows benchmark evaluation of new models using far fewer queries while matching baseline accuracy."}],"snapshot_sha256":"4c072ff360ac02f2a8ee2b02b8c9cc2a4f60f0364dc67aab3ea0bc97a666147d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e372b0d3207c98a1cf5f2f12df769165ebf183137bd6defdff129a61f890384e"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.07096/integrity.json","findings":[],"snapshot_sha256":"cda9af02d44944d27322c7b56280a87d616ea44d08eea623d517094b72a544bd","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ben Johnson, Carey Priebe, Hayden Helm","cross_cats":["cs.AI","stat.ME"],"headline":"DKPS with cached responses allows benchmark evaluation of new models using far fewer queries while matching baseline accuracy.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:24:06Z","title":"Query-efficient model evaluation using cached responses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07096","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T00:50:12.566768Z","id":"4e016987-7957-4e68-929c-91e0c52e784c","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"DKPS with cached responses allows benchmark evaluation of new models using far fewer queries while matching baseline accuracy.","strongest_claim":"DKPS-based methods achieve the same mean absolute error as baselines with a substantially decreased query budget.","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."}},"verdict_id":"4e016987-7957-4e68-929c-91e0c52e784c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e2fb612931db619487c82e3692e4eb95972a873f7cea4c8093f80f29483d19c7","target":"record","created_at":"2026-06-05T01:15:25Z","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":"dd978c8478367cca2f1a62480a3e7fac9b963ffba13c4ee72d1e82372576c895","cross_cats_sorted":["cs.AI","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:24:06Z","title_canon_sha256":"8f44e85ebbcbce3a8e5132595228ef7a59c57ba89ba148d4188406011ec3bb6b"},"schema_version":"1.0","source":{"id":"2605.07096","kind":"arxiv","version":2}},"canonical_sha256":"25b3683e10f74644b506d6cf2de0e9d486bcb68beded879ef3f92522188244b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25b3683e10f74644b506d6cf2de0e9d486bcb68beded879ef3f92522188244b3","first_computed_at":"2026-06-05T01:15:25.229360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:25.229360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5EF9Ieapn2bwwjznVdy4454FpETaMFTo6gIHdDbM8Uol5cG5+xMKm+FyiiDsTSrq/mTxSvty6aZiH1zAdrwyCg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:25.229800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2fb612931db619487c82e3692e4eb95972a873f7cea4c8093f80f29483d19c7","sha256:cdb9e6c03edc1f36e957c3a9a5df6df6b2f87e635029ba5486cffe2b3fc05780"],"state_sha256":"5b740d028eadffd1bda0a712bf21ef7cdaf8f3e89cc23b596b971387c242971e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hx+nzqldgHS7Ra/U+Van7cSBZpKoQBfnb/kMEA5VnJs9W1mEGFyGeo6Cjio7Msi9ZPQE3HT25HtVleOEj0YCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T04:05:49.066236Z","bundle_sha256":"4d3c9f4d6d98d95fc9df5f46d0f131215709f65173245a7429a5767443f377e7"}}