{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6UZB74ZXC3I2RFNG4BFDD2GYM4","short_pith_number":"pith:6UZB74ZX","canonical_record":{"source":{"id":"2112.01716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-03T05:01:47Z","cross_cats_sorted":["cs.CL","cs.CV","cs.CY","stat.ML"],"title_canon_sha256":"7311631d73ef5f6040601d6f28393caf490d746c7bc4585070dce5b7b9e44e9e","abstract_canon_sha256":"304d4f7af20f2c80f95597c98cdc63c256d7578268b5da1f14cfa9511dc79024"},"schema_version":"1.0"},"canonical_sha256":"f5321ff33716d1a895a6e04a31e8d867396b29f245c90b238ca9fefc87a5786e","source":{"kind":"arxiv","id":"2112.01716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01716","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01716v1","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01716","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"6UZB74ZXC3I2","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"6UZB74ZXC3I2RFNG","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"6UZB74ZX","created_at":"2026-07-05T03:37:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6UZB74ZXC3I2RFNG4BFDD2GYM4","target":"record","payload":{"canonical_record":{"source":{"id":"2112.01716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-03T05:01:47Z","cross_cats_sorted":["cs.CL","cs.CV","cs.CY","stat.ML"],"title_canon_sha256":"7311631d73ef5f6040601d6f28393caf490d746c7bc4585070dce5b7b9e44e9e","abstract_canon_sha256":"304d4f7af20f2c80f95597c98cdc63c256d7578268b5da1f14cfa9511dc79024"},"schema_version":"1.0"},"canonical_sha256":"f5321ff33716d1a895a6e04a31e8d867396b29f245c90b238ca9fefc87a5786e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:31.297788Z","signature_b64":"cMLrHmkpLu/jzsSI7gRItIVZmmtsLqZCabuEbYAaEQHJRAZWvFu/HcTKDXWv9iwGTSXZVJz64PruF5yIP4D4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5321ff33716d1a895a6e04a31e8d867396b29f245c90b238ca9fefc87a5786e","last_reissued_at":"2026-07-05T03:37:31.297345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:31.297345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.01716","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":"2026-07-05T03:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rAJ4i1tt+tqU/ZpV6FAZthwzkwZb5CrhyHdicMQEKnIIdwTP59BRA1ha64xb4wkxzr8HfNbTBJUCL4uKlrRYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:18:49.854671Z"},"content_sha256":"bcf239761e65ee4044de0dd04665268b01e615f1976a9604ed427fe2022c7b9c","schema_version":"1.0","event_id":"sha256:bcf239761e65ee4044de0dd04665268b01e615f1976a9604ed427fe2022c7b9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6UZB74ZXC3I2RFNG4BFDD2GYM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Hanna, Bernard Koch, Emily Denton, Jacob G. Foster","submitted_at":"2021-12-03T05:01:47Z","abstract_excerpt":"Benchmark datasets play a central role in the organization of machine learning research. They coordinate researchers around shared research problems and serve as a measure of progress towards shared goals. Despite the foundational role of benchmarking practices in this field, relatively little attention has been paid to the dynamics of benchmark dataset use and reuse, within or across machine learning subcommunities. In this paper, we dig into these dynamics. We study how dataset usage patterns differ across machine learning subcommunities and across time from 2015-2020. We find increasing con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01716","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/2112.01716/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":"2026-07-05T03:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"myHQTgIIb8AKPjw2c505kBMjElHZJDvGwV2D5+ATx65Yk7yTv4AI8bZjJtcrJyWh2briEu/TgEV366M7qX0nCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:18:49.855060Z"},"content_sha256":"94a252f24f25796fa6c7d0d49e310371db16e2027ab6c1adbf1e720edc33a34d","schema_version":"1.0","event_id":"sha256:94a252f24f25796fa6c7d0d49e310371db16e2027ab6c1adbf1e720edc33a34d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UZB74ZXC3I2RFNG4BFDD2GYM4/bundle.json","state_url":"https://pith.science/pith/6UZB74ZXC3I2RFNG4BFDD2GYM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UZB74ZXC3I2RFNG4BFDD2GYM4/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":"2026-07-06T23:18:49Z","links":{"resolver":"https://pith.science/pith/6UZB74ZXC3I2RFNG4BFDD2GYM4","bundle":"https://pith.science/pith/6UZB74ZXC3I2RFNG4BFDD2GYM4/bundle.json","state":"https://pith.science/pith/6UZB74ZXC3I2RFNG4BFDD2GYM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UZB74ZXC3I2RFNG4BFDD2GYM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6UZB74ZXC3I2RFNG4BFDD2GYM4","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":"304d4f7af20f2c80f95597c98cdc63c256d7578268b5da1f14cfa9511dc79024","cross_cats_sorted":["cs.CL","cs.CV","cs.CY","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-03T05:01:47Z","title_canon_sha256":"7311631d73ef5f6040601d6f28393caf490d746c7bc4585070dce5b7b9e44e9e"},"schema_version":"1.0","source":{"id":"2112.01716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01716","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01716v1","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01716","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"6UZB74ZXC3I2","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"6UZB74ZXC3I2RFNG","created_at":"2026-07-05T03:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"6UZB74ZX","created_at":"2026-07-05T03:37:31Z"}],"graph_snapshots":[{"event_id":"sha256:94a252f24f25796fa6c7d0d49e310371db16e2027ab6c1adbf1e720edc33a34d","target":"graph","created_at":"2026-07-05T03:37:31Z","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/2112.01716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark datasets play a central role in the organization of machine learning research. They coordinate researchers around shared research problems and serve as a measure of progress towards shared goals. Despite the foundational role of benchmarking practices in this field, relatively little attention has been paid to the dynamics of benchmark dataset use and reuse, within or across machine learning subcommunities. In this paper, we dig into these dynamics. We study how dataset usage patterns differ across machine learning subcommunities and across time from 2015-2020. We find increasing con","authors_text":"Alex Hanna, Bernard Koch, Emily Denton, Jacob G. Foster","cross_cats":["cs.CL","cs.CV","cs.CY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-03T05:01:47Z","title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01716","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:bcf239761e65ee4044de0dd04665268b01e615f1976a9604ed427fe2022c7b9c","target":"record","created_at":"2026-07-05T03:37:31Z","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":"304d4f7af20f2c80f95597c98cdc63c256d7578268b5da1f14cfa9511dc79024","cross_cats_sorted":["cs.CL","cs.CV","cs.CY","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-03T05:01:47Z","title_canon_sha256":"7311631d73ef5f6040601d6f28393caf490d746c7bc4585070dce5b7b9e44e9e"},"schema_version":"1.0","source":{"id":"2112.01716","kind":"arxiv","version":1}},"canonical_sha256":"f5321ff33716d1a895a6e04a31e8d867396b29f245c90b238ca9fefc87a5786e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5321ff33716d1a895a6e04a31e8d867396b29f245c90b238ca9fefc87a5786e","first_computed_at":"2026-07-05T03:37:31.297345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:31.297345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cMLrHmkpLu/jzsSI7gRItIVZmmtsLqZCabuEbYAaEQHJRAZWvFu/HcTKDXWv9iwGTSXZVJz64PruF5yIP4D4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:31.297788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcf239761e65ee4044de0dd04665268b01e615f1976a9604ed427fe2022c7b9c","sha256:94a252f24f25796fa6c7d0d49e310371db16e2027ab6c1adbf1e720edc33a34d"],"state_sha256":"048f151fea16809ba20314c9def42ba3e4fe059cbe288be43ec6193cbc036a1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9+WFg81AVFowzNMCcwPX3Bv0kSjUzV9iMd06cgpWsdKTG/eqYU98e0A0NESvneM+wSFrOo5wBPl7RczuiqjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:18:49.857386Z","bundle_sha256":"fee0911a3f58828da3f5ffe6311b9b4c73589da3c134f70c6d28c12491e4f5c7"}}