{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VTXKBM2TBLFHSZYIVLQ7NVRRJE","short_pith_number":"pith:VTXKBM2T","canonical_record":{"source":{"id":"2606.27997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fac874f8f4d20acdc485e17b3505e624ab1ed6598d7b79e9dea3809c56af60a3","abstract_canon_sha256":"7f494c816d78221da5cdc9638e3b9e66059df939154c9e8717c3263eed90b6c0"},"schema_version":"1.0"},"canonical_sha256":"aceea0b3530aca796708aae1f6d6314935322b5a570652eac4966b2190703b31","source":{"kind":"arxiv","id":"2606.27997","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27997","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27997v1","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27997","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"VTXKBM2TBLFH","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"VTXKBM2TBLFHSZYI","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"VTXKBM2T","created_at":"2026-06-29T01:14:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VTXKBM2TBLFHSZYIVLQ7NVRRJE","target":"record","payload":{"canonical_record":{"source":{"id":"2606.27997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fac874f8f4d20acdc485e17b3505e624ab1ed6598d7b79e9dea3809c56af60a3","abstract_canon_sha256":"7f494c816d78221da5cdc9638e3b9e66059df939154c9e8717c3263eed90b6c0"},"schema_version":"1.0"},"canonical_sha256":"aceea0b3530aca796708aae1f6d6314935322b5a570652eac4966b2190703b31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:54.792097Z","signature_b64":"OX+eJ+vhlOqr768UYWLP8A7oiJyCVAKyQAbmlxs95w7ZfN4vFy7IXQIMHE54ttOfGBOXKw57BbDs/uCXjwUrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aceea0b3530aca796708aae1f6d6314935322b5a570652eac4966b2190703b31","last_reissued_at":"2026-06-29T01:14:54.791732Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:54.791732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.27997","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":"2026-06-29T01:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L+OhidBWjWThSSsh1vnG/Qv01r9kI6T+kMuW9qIvq7y3l4+lGQU/xXLGa5YJieE9kVBMKZ8A4iGnKFfwMEW7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T14:09:38.308685Z"},"content_sha256":"a6d9063ff30baff3c8d5fbe3fa1691dba8fd881cdeca9ea12ba07611e7c1c6ab","schema_version":"1.0","event_id":"sha256:a6d9063ff30baff3c8d5fbe3fa1691dba8fd881cdeca9ea12ba07611e7c1c6ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VTXKBM2TBLFHSZYIVLQ7NVRRJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexey Zaytsev, Rostislav Gusev","submitted_at":"2026-06-26T11:50:22Z","abstract_excerpt":"Benchmarks of machine learning models often include many datasets, making evaluation expensive. For efficiency, it is preferable to perform evaluations on small, representative datasets instead. The selection of such subsets typically relies on heuristics and is rarely analyzed for the robustness of the resulting model rankings.\n  We introduce a framework to perform the task of selecting datasets subsets with an evaluation of how different selection strategies preserve the global model rankings. Our framework includes bootstrap aggregation, which provides valid confidence intervals, allowing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27997","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/2606.27997/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":"2026-06-29T01:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zs2QJAaQQEVlgqfEbIbv/Cb669z/zdSDgrH9DZBgNV5hd4MD9M0npekEq+965UvietGq8x3CEaxyoajF3DRrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T14:09:38.309044Z"},"content_sha256":"770881f86470db46c82b8c3ad489670288d07374a93cca978024b61ab4a7d8b4","schema_version":"1.0","event_id":"sha256:770881f86470db46c82b8c3ad489670288d07374a93cca978024b61ab4a7d8b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTXKBM2TBLFHSZYIVLQ7NVRRJE/bundle.json","state_url":"https://pith.science/pith/VTXKBM2TBLFHSZYIVLQ7NVRRJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTXKBM2TBLFHSZYIVLQ7NVRRJE/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":"2026-06-29T14:09:38Z","links":{"resolver":"https://pith.science/pith/VTXKBM2TBLFHSZYIVLQ7NVRRJE","bundle":"https://pith.science/pith/VTXKBM2TBLFHSZYIVLQ7NVRRJE/bundle.json","state":"https://pith.science/pith/VTXKBM2TBLFHSZYIVLQ7NVRRJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTXKBM2TBLFHSZYIVLQ7NVRRJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VTXKBM2TBLFHSZYIVLQ7NVRRJE","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":"7f494c816d78221da5cdc9638e3b9e66059df939154c9e8717c3263eed90b6c0","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:22Z","title_canon_sha256":"fac874f8f4d20acdc485e17b3505e624ab1ed6598d7b79e9dea3809c56af60a3"},"schema_version":"1.0","source":{"id":"2606.27997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27997","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27997v1","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27997","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"VTXKBM2TBLFH","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"VTXKBM2TBLFHSZYI","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"VTXKBM2T","created_at":"2026-06-29T01:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:770881f86470db46c82b8c3ad489670288d07374a93cca978024b61ab4a7d8b4","target":"graph","created_at":"2026-06-29T01:14:54Z","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/2606.27997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarks of machine learning models often include many datasets, making evaluation expensive. For efficiency, it is preferable to perform evaluations on small, representative datasets instead. The selection of such subsets typically relies on heuristics and is rarely analyzed for the robustness of the resulting model rankings.\n  We introduce a framework to perform the task of selecting datasets subsets with an evaluation of how different selection strategies preserve the global model rankings. Our framework includes bootstrap aggregation, which provides valid confidence intervals, allowing a","authors_text":"Alexey Zaytsev, Rostislav Gusev","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:22Z","title":"Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27997","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:a6d9063ff30baff3c8d5fbe3fa1691dba8fd881cdeca9ea12ba07611e7c1c6ab","target":"record","created_at":"2026-06-29T01:14:54Z","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":"7f494c816d78221da5cdc9638e3b9e66059df939154c9e8717c3263eed90b6c0","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:22Z","title_canon_sha256":"fac874f8f4d20acdc485e17b3505e624ab1ed6598d7b79e9dea3809c56af60a3"},"schema_version":"1.0","source":{"id":"2606.27997","kind":"arxiv","version":1}},"canonical_sha256":"aceea0b3530aca796708aae1f6d6314935322b5a570652eac4966b2190703b31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aceea0b3530aca796708aae1f6d6314935322b5a570652eac4966b2190703b31","first_computed_at":"2026-06-29T01:14:54.791732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:54.791732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OX+eJ+vhlOqr768UYWLP8A7oiJyCVAKyQAbmlxs95w7ZfN4vFy7IXQIMHE54ttOfGBOXKw57BbDs/uCXjwUrAA==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:54.792097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6d9063ff30baff3c8d5fbe3fa1691dba8fd881cdeca9ea12ba07611e7c1c6ab","sha256:770881f86470db46c82b8c3ad489670288d07374a93cca978024b61ab4a7d8b4"],"state_sha256":"6119c300943381c69c18406998de0b617a0dc3122a65ca67377f47f7b216e061"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgKsH36TVJMhiCkxckwmn6RY4Bbb4pNqZWSOvngtBZaIbzNwThDzGMRHAIpITyXbe4+2G0BgM4AlRPBS6bD+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T14:09:38.310944Z","bundle_sha256":"a686761cc51d78ebe2dd2cfc9060c41a09d63e6a2cde51ddbe8c95c9a111499d"}}