{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5NGGKRIJELMSTMGM3FZXVUWMZM","short_pith_number":"pith:5NGGKRIJ","canonical_record":{"source":{"id":"2410.24100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:30:08Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"202271ae43bdf6a1a5b6c5c1ede9a0fde86cbf0866683b6483c6e9c6efaa8499","abstract_canon_sha256":"a4482510c4dd6e73b7362aee99cf372e2f3507bec0c6db0f57e98522b2a768e3"},"schema_version":"1.0"},"canonical_sha256":"eb4c65450922d929b0ccd9737ad2cccb0e07ae28e9ac8702f13dedf5292dba6d","source":{"kind":"arxiv","id":"2410.24100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24100","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24100v1","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24100","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_12","alias_value":"5NGGKRIJELMS","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"5NGGKRIJELMSTMGM","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"5NGGKRIJ","created_at":"2026-07-05T09:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5NGGKRIJELMSTMGM3FZXVUWMZM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.24100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:30:08Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"202271ae43bdf6a1a5b6c5c1ede9a0fde86cbf0866683b6483c6e9c6efaa8499","abstract_canon_sha256":"a4482510c4dd6e73b7362aee99cf372e2f3507bec0c6db0f57e98522b2a768e3"},"schema_version":"1.0"},"canonical_sha256":"eb4c65450922d929b0ccd9737ad2cccb0e07ae28e9ac8702f13dedf5292dba6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:19.953130Z","signature_b64":"UubquvxFdZtMlHhJjfa6oLhyMwnadf0X6G0+08ETpXHy0EWTiA1hYNzJC9x+DQ2D3UKiarLgCFU3ygP5VlAeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb4c65450922d929b0ccd9737ad2cccb0e07ae28e9ac8702f13dedf5292dba6d","last_reissued_at":"2026-07-05T09:29:19.952656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:19.952656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.24100","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":"2026-07-05T09:29:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p/kqj/zAEVge8byf++ZNnVs1S18zb4cySv2Idb9y5621EaXPF4RblI9MlfzfEZdbmRN9kDxR8KxXaspjX3WsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:19:18.754110Z"},"content_sha256":"78715934b1460ac79e4511be3cf379b4b6861db3fe3840e122be7cc5769e477f","schema_version":"1.0","event_id":"sha256:78715934b1460ac79e4511be3cf379b4b6861db3fe3840e122be7cc5769e477f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5NGGKRIJELMSTMGM3FZXVUWMZM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmark Data Repositories for Better Benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.LG","authors_text":"Markelle Kelly, Padhraic Smyth, Rachel Longjohn, Sameer Singh","submitted_at":"2024-10-31T16:30:08Z","abstract_excerpt":"In machine learning research, it is common to evaluate algorithms via their performance on standard benchmark datasets. While a growing body of work establishes guidelines for -- and levies criticisms at -- data and benchmarking practices in machine learning, comparatively less attention has been paid to the data repositories where these datasets are stored, documented, and shared. In this paper, we analyze the landscape of these $\\textit{benchmark data repositories}$ and the role they can play in improving benchmarking. This role includes addressing issues with both datasets themselves (e.g.,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24100","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/2410.24100/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":"2026-07-05T09:29:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+dGjWCyMTbPwagMucWH6yw8yOSc7BUYwFZSHuifJNXTIsfTAY5mlLeHsSQ4c+u2wB9mxGytHDhu+GHaKt9nbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:19:18.754598Z"},"content_sha256":"aa8635b74b4208ed73fc292afe0321fa97c3712b020d10afdc1fbef13bd71761","schema_version":"1.0","event_id":"sha256:aa8635b74b4208ed73fc292afe0321fa97c3712b020d10afdc1fbef13bd71761"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NGGKRIJELMSTMGM3FZXVUWMZM/bundle.json","state_url":"https://pith.science/pith/5NGGKRIJELMSTMGM3FZXVUWMZM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NGGKRIJELMSTMGM3FZXVUWMZM/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":"2026-08-10T23:19:18Z","links":{"resolver":"https://pith.science/pith/5NGGKRIJELMSTMGM3FZXVUWMZM","bundle":"https://pith.science/pith/5NGGKRIJELMSTMGM3FZXVUWMZM/bundle.json","state":"https://pith.science/pith/5NGGKRIJELMSTMGM3FZXVUWMZM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NGGKRIJELMSTMGM3FZXVUWMZM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5NGGKRIJELMSTMGM3FZXVUWMZM","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":"a4482510c4dd6e73b7362aee99cf372e2f3507bec0c6db0f57e98522b2a768e3","cross_cats_sorted":["cs.DL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:30:08Z","title_canon_sha256":"202271ae43bdf6a1a5b6c5c1ede9a0fde86cbf0866683b6483c6e9c6efaa8499"},"schema_version":"1.0","source":{"id":"2410.24100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24100","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24100v1","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24100","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_12","alias_value":"5NGGKRIJELMS","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"5NGGKRIJELMSTMGM","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"5NGGKRIJ","created_at":"2026-07-05T09:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:aa8635b74b4208ed73fc292afe0321fa97c3712b020d10afdc1fbef13bd71761","target":"graph","created_at":"2026-07-05T09:29:19Z","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/2410.24100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In machine learning research, it is common to evaluate algorithms via their performance on standard benchmark datasets. While a growing body of work establishes guidelines for -- and levies criticisms at -- data and benchmarking practices in machine learning, comparatively less attention has been paid to the data repositories where these datasets are stored, documented, and shared. In this paper, we analyze the landscape of these $\\textit{benchmark data repositories}$ and the role they can play in improving benchmarking. This role includes addressing issues with both datasets themselves (e.g.,","authors_text":"Markelle Kelly, Padhraic Smyth, Rachel Longjohn, Sameer Singh","cross_cats":["cs.DL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:30:08Z","title":"Benchmark Data Repositories for Better Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24100","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":"sha256:78715934b1460ac79e4511be3cf379b4b6861db3fe3840e122be7cc5769e477f","target":"record","created_at":"2026-07-05T09:29:19Z","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":"a4482510c4dd6e73b7362aee99cf372e2f3507bec0c6db0f57e98522b2a768e3","cross_cats_sorted":["cs.DL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:30:08Z","title_canon_sha256":"202271ae43bdf6a1a5b6c5c1ede9a0fde86cbf0866683b6483c6e9c6efaa8499"},"schema_version":"1.0","source":{"id":"2410.24100","kind":"arxiv","version":1}},"canonical_sha256":"eb4c65450922d929b0ccd9737ad2cccb0e07ae28e9ac8702f13dedf5292dba6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb4c65450922d929b0ccd9737ad2cccb0e07ae28e9ac8702f13dedf5292dba6d","first_computed_at":"2026-07-05T09:29:19.952656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:19.952656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UubquvxFdZtMlHhJjfa6oLhyMwnadf0X6G0+08ETpXHy0EWTiA1hYNzJC9x+DQ2D3UKiarLgCFU3ygP5VlAeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:19.953130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.24100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78715934b1460ac79e4511be3cf379b4b6861db3fe3840e122be7cc5769e477f","sha256:aa8635b74b4208ed73fc292afe0321fa97c3712b020d10afdc1fbef13bd71761"],"state_sha256":"21f4cf85ea461abd96d144bafb0e6942ecbc7a236a1780a0c0043ecef8f31dac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D6/xjfRbYXNQsrIm7Jaoa40F2rfn87QQMNJqoD3LasmMMGF48zqmp99FCo0YOsLkZp5+I6leXIHDEYNhwAzuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:19:18.759245Z","bundle_sha256":"a1e15d6e4023fa6cb1d84604a8d600691c34b25b9e6ab881d5f82961bb15044b"}}