{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EUY4N2ZPLQ42J3VOPN3IWYQHAA","short_pith_number":"pith:EUY4N2ZP","canonical_record":{"source":{"id":"2209.10015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T21:52:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a27380741ce4e03dd5282e6b2262ebbd75be8fadb2aa11ca517b47819c9b8a85","abstract_canon_sha256":"207ab32e974b93dd384a5c12d948d4c1578f803141897a9475a37e21aace743f"},"schema_version":"1.0"},"canonical_sha256":"2531c6eb2f5c39a4eeae7b768b62070017b111c8491d949c07aefd5252d4d174","source":{"kind":"arxiv","id":"2209.10015","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10015","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10015v1","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10015","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"EUY4N2ZPLQ42","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"pith_short_16","alias_value":"EUY4N2ZPLQ42J3VO","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"pith_short_8","alias_value":"EUY4N2ZP","created_at":"2026-07-05T04:59:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EUY4N2ZPLQ42J3VOPN3IWYQHAA","target":"record","payload":{"canonical_record":{"source":{"id":"2209.10015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T21:52:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a27380741ce4e03dd5282e6b2262ebbd75be8fadb2aa11ca517b47819c9b8a85","abstract_canon_sha256":"207ab32e974b93dd384a5c12d948d4c1578f803141897a9475a37e21aace743f"},"schema_version":"1.0"},"canonical_sha256":"2531c6eb2f5c39a4eeae7b768b62070017b111c8491d949c07aefd5252d4d174","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:44.072033Z","signature_b64":"0okxjZv0X5KUi5ACVQ7Yer+41tqeUwRyTEZNGzfCmYizEt0tpeG2cVOIk+GyGMRfMXTdKiNotoZrrJpaBN2cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2531c6eb2f5c39a4eeae7b768b62070017b111c8491d949c07aefd5252d4d174","last_reissued_at":"2026-07-05T04:59:44.071570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:44.071570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.10015","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":"2026-07-05T04:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TgI+dyhgl5rXir6AhBTsUbzrSDkxhUUHGNeH+cZZXmb8UF8W6KO3XAsie4c3L+6P7fY4oxedtptuCxhjHZWcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:50:46.277013Z"},"content_sha256":"954d825019e3aa5fa46ccd323504eeab7202675497d9ce18332f5ded49c0dbef","schema_version":"1.0","event_id":"sha256:954d825019e3aa5fa46ccd323504eeab7202675497d9ce18332f5ded49c0dbef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EUY4N2ZPLQ42J3VOPN3IWYQHAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Krueger, Nitarshan Rajkumar, Sara Hooker, Shoaib Ahmed Siddiqui, Tegan Maharaj","submitted_at":"2022-09-20T21:52:39Z","abstract_excerpt":"Modern machine learning research relies on relatively few carefully curated datasets. Even in these datasets, and typically in `untidy' or raw data, practitioners are faced with significant issues of data quality and diversity which can be prohibitively labor intensive to address. Existing methods for dealing with these challenges tend to make strong assumptions about the particular issues at play, and often require a priori knowledge or metadata such as domain labels. Our work is orthogonal to these methods: we instead focus on providing a unified and efficient framework for Metadata Archaeol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10015","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/2209.10015/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":"2026-07-05T04:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h6t5WnGh+bRou164KujFvg5Sl2VOyydTfJXnFBR1RctvPThTIhC3cKTm1QlvAPIqnk4yuMs5PDZ2uVN5a4uiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:50:46.277516Z"},"content_sha256":"0b3ddcfd543bdc70378131e883232dd33747e7e7ff183880e8116202a81cc2fd","schema_version":"1.0","event_id":"sha256:0b3ddcfd543bdc70378131e883232dd33747e7e7ff183880e8116202a81cc2fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EUY4N2ZPLQ42J3VOPN3IWYQHAA/bundle.json","state_url":"https://pith.science/pith/EUY4N2ZPLQ42J3VOPN3IWYQHAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EUY4N2ZPLQ42J3VOPN3IWYQHAA/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":"2026-08-07T04:50:46Z","links":{"resolver":"https://pith.science/pith/EUY4N2ZPLQ42J3VOPN3IWYQHAA","bundle":"https://pith.science/pith/EUY4N2ZPLQ42J3VOPN3IWYQHAA/bundle.json","state":"https://pith.science/pith/EUY4N2ZPLQ42J3VOPN3IWYQHAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EUY4N2ZPLQ42J3VOPN3IWYQHAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EUY4N2ZPLQ42J3VOPN3IWYQHAA","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":"207ab32e974b93dd384a5c12d948d4c1578f803141897a9475a37e21aace743f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T21:52:39Z","title_canon_sha256":"a27380741ce4e03dd5282e6b2262ebbd75be8fadb2aa11ca517b47819c9b8a85"},"schema_version":"1.0","source":{"id":"2209.10015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10015","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10015v1","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10015","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"EUY4N2ZPLQ42","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"pith_short_16","alias_value":"EUY4N2ZPLQ42J3VO","created_at":"2026-07-05T04:59:44Z"},{"alias_kind":"pith_short_8","alias_value":"EUY4N2ZP","created_at":"2026-07-05T04:59:44Z"}],"graph_snapshots":[{"event_id":"sha256:0b3ddcfd543bdc70378131e883232dd33747e7e7ff183880e8116202a81cc2fd","target":"graph","created_at":"2026-07-05T04:59:44Z","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/2209.10015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern machine learning research relies on relatively few carefully curated datasets. Even in these datasets, and typically in `untidy' or raw data, practitioners are faced with significant issues of data quality and diversity which can be prohibitively labor intensive to address. Existing methods for dealing with these challenges tend to make strong assumptions about the particular issues at play, and often require a priori knowledge or metadata such as domain labels. Our work is orthogonal to these methods: we instead focus on providing a unified and efficient framework for Metadata Archaeol","authors_text":"David Krueger, Nitarshan Rajkumar, Sara Hooker, Shoaib Ahmed Siddiqui, Tegan Maharaj","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T21:52:39Z","title":"Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10015","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":"sha256:954d825019e3aa5fa46ccd323504eeab7202675497d9ce18332f5ded49c0dbef","target":"record","created_at":"2026-07-05T04:59:44Z","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":"207ab32e974b93dd384a5c12d948d4c1578f803141897a9475a37e21aace743f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T21:52:39Z","title_canon_sha256":"a27380741ce4e03dd5282e6b2262ebbd75be8fadb2aa11ca517b47819c9b8a85"},"schema_version":"1.0","source":{"id":"2209.10015","kind":"arxiv","version":1}},"canonical_sha256":"2531c6eb2f5c39a4eeae7b768b62070017b111c8491d949c07aefd5252d4d174","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2531c6eb2f5c39a4eeae7b768b62070017b111c8491d949c07aefd5252d4d174","first_computed_at":"2026-07-05T04:59:44.071570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:44.071570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0okxjZv0X5KUi5ACVQ7Yer+41tqeUwRyTEZNGzfCmYizEt0tpeG2cVOIk+GyGMRfMXTdKiNotoZrrJpaBN2cDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:44.072033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.10015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:954d825019e3aa5fa46ccd323504eeab7202675497d9ce18332f5ded49c0dbef","sha256:0b3ddcfd543bdc70378131e883232dd33747e7e7ff183880e8116202a81cc2fd"],"state_sha256":"66e3bbf7490ba2470a500bf8f78f51ef5501b9e10a2b2a5d4741125fff74ad41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfhNpVMJma8FHd4U2qRFqWXPqFGRKDdJ831gjC+DaB1UjdRaonYd/UH8wlmQR+uu8Kfp/NyN7yu0EAYDhO76Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:50:46.282602Z","bundle_sha256":"f799b794d37084528bb667831a425dd9e6e68bd9647e9622c2bdc9d08e50c384"}}