{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5HRNFCI66BKHCCG5FPVYGXCAD3","short_pith_number":"pith:5HRNFCI6","canonical_record":{"source":{"id":"2605.25773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-25T12:23:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"3e499a652f7d52b2c8d79d54cbf3175286431727139223651e80f790ecd67182","abstract_canon_sha256":"5fffd110a9b3fb52ce61e0c8c3d8c6d8b929ff61308a263512b5b61d56cefdff"},"schema_version":"1.0"},"canonical_sha256":"e9e2d2891ef0547108dd2beb835c401ef35b3a29141c2c4274fdbb837b0a792f","source":{"kind":"arxiv","id":"2605.25773","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25773","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25773v1","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25773","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"5HRNFCI66BKH","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"5HRNFCI66BKHCCG5","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"5HRNFCI6","created_at":"2026-05-26T02:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5HRNFCI66BKHCCG5FPVYGXCAD3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-25T12:23:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"3e499a652f7d52b2c8d79d54cbf3175286431727139223651e80f790ecd67182","abstract_canon_sha256":"5fffd110a9b3fb52ce61e0c8c3d8c6d8b929ff61308a263512b5b61d56cefdff"},"schema_version":"1.0"},"canonical_sha256":"e9e2d2891ef0547108dd2beb835c401ef35b3a29141c2c4274fdbb837b0a792f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:54.127601Z","signature_b64":"WbeWvDXC0aik2w0b4hlHWA74/YmURxXQopmn9GFlulzX2vQwrYfY7yAwRX+SoLK/La4KKTXPH+PpMKMXQ4W1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9e2d2891ef0547108dd2beb835c401ef35b3a29141c2c4274fdbb837b0a792f","last_reissued_at":"2026-05-26T02:04:54.127156Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:54.127156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25773","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6kl4VAoKPX+hUi+PeFZ+SAn16Gtca4ejgJXwK65unWMMLnzUiCh3EneZSaeJa5qq6zIroDxG2oYqY7kpk+NCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:38:03.452387Z"},"content_sha256":"12612826af65917db8102dd6741ed509344161a5d3ec4dbe9b96f5a7cac332d1","schema_version":"1.0","event_id":"sha256:12612826af65917db8102dd6741ed509344161a5d3ec4dbe9b96f5a7cac332d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5HRNFCI66BKHCCG5FPVYGXCAD3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Acyr Locatelli, Kris Cao, Sam Bowyer","submitted_at":"2026-05-25T12:23:31Z","abstract_excerpt":"Efficient benchmarking techniques aim to lower the computational cost of evaluating LLMs by predicting full benchmark scores using only a subset of a benchmark's questions. By reframing this problem as an instance of multiple regression with feature selection, we find that existing efficient benchmarking methods can be greatly improved by simply using kernel ridge regression at the prediction stage. Additionally, using an information-theoretic feature-selection algorithm called minimum redundancy maximum relevance (mRMR), we can further improve upon these methods by selecting question subsets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25773","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/2605.25773/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fTl/QQ8jwgwcd+R3n9g+oapV9RRg9Pwcs8UYom2d00SFqb74G8aCPaag+E69uD9tcbSAXYs44+mZW0fl+zKkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:38:03.452770Z"},"content_sha256":"a3f56257ac8821a6d618795389abdd3872434b7146b7d7ce1f0700967cfc74f6","schema_version":"1.0","event_id":"sha256:a3f56257ac8821a6d618795389abdd3872434b7146b7d7ce1f0700967cfc74f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HRNFCI66BKHCCG5FPVYGXCAD3/bundle.json","state_url":"https://pith.science/pith/5HRNFCI66BKHCCG5FPVYGXCAD3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HRNFCI66BKHCCG5FPVYGXCAD3/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":"2026-06-03T08:38:03Z","links":{"resolver":"https://pith.science/pith/5HRNFCI66BKHCCG5FPVYGXCAD3","bundle":"https://pith.science/pith/5HRNFCI66BKHCCG5FPVYGXCAD3/bundle.json","state":"https://pith.science/pith/5HRNFCI66BKHCCG5FPVYGXCAD3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HRNFCI66BKHCCG5FPVYGXCAD3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5HRNFCI66BKHCCG5FPVYGXCAD3","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":"5fffd110a9b3fb52ce61e0c8c3d8c6d8b929ff61308a263512b5b61d56cefdff","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-25T12:23:31Z","title_canon_sha256":"3e499a652f7d52b2c8d79d54cbf3175286431727139223651e80f790ecd67182"},"schema_version":"1.0","source":{"id":"2605.25773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25773","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25773v1","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25773","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"5HRNFCI66BKH","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"5HRNFCI66BKHCCG5","created_at":"2026-05-26T02:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"5HRNFCI6","created_at":"2026-05-26T02:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:a3f56257ac8821a6d618795389abdd3872434b7146b7d7ce1f0700967cfc74f6","target":"graph","created_at":"2026-05-26T02:04:54Z","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/2605.25773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient benchmarking techniques aim to lower the computational cost of evaluating LLMs by predicting full benchmark scores using only a subset of a benchmark's questions. By reframing this problem as an instance of multiple regression with feature selection, we find that existing efficient benchmarking methods can be greatly improved by simply using kernel ridge regression at the prediction stage. Additionally, using an information-theoretic feature-selection algorithm called minimum redundancy maximum relevance (mRMR), we can further improve upon these methods by selecting question subsets ","authors_text":"Acyr Locatelli, Kris Cao, Sam Bowyer","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-25T12:23:31Z","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25773","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":"sha256:12612826af65917db8102dd6741ed509344161a5d3ec4dbe9b96f5a7cac332d1","target":"record","created_at":"2026-05-26T02:04:54Z","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":"5fffd110a9b3fb52ce61e0c8c3d8c6d8b929ff61308a263512b5b61d56cefdff","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-25T12:23:31Z","title_canon_sha256":"3e499a652f7d52b2c8d79d54cbf3175286431727139223651e80f790ecd67182"},"schema_version":"1.0","source":{"id":"2605.25773","kind":"arxiv","version":1}},"canonical_sha256":"e9e2d2891ef0547108dd2beb835c401ef35b3a29141c2c4274fdbb837b0a792f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9e2d2891ef0547108dd2beb835c401ef35b3a29141c2c4274fdbb837b0a792f","first_computed_at":"2026-05-26T02:04:54.127156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:54.127156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WbeWvDXC0aik2w0b4hlHWA74/YmURxXQopmn9GFlulzX2vQwrYfY7yAwRX+SoLK/La4KKTXPH+PpMKMXQ4W1CA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:54.127601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12612826af65917db8102dd6741ed509344161a5d3ec4dbe9b96f5a7cac332d1","sha256:a3f56257ac8821a6d618795389abdd3872434b7146b7d7ce1f0700967cfc74f6"],"state_sha256":"41db64c8b170b86924f3de5c02b7980ff094108f2bf2ddbc80257d2848790e5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FlrcR7iVPQic6A64ESYfcnfBDPcOVWGLbugGPQO1kba135b+7RrFBRU3eLX8MM+ylpYD/Yz8vqAK0Un744hZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:38:03.454872Z","bundle_sha256":"788ca2f6b40c5e4fc0fbf5c4e1df1948fe25c52d02d098ce6ffe6e4e0ec7e9cd"}}