{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TTHIC7VIPFISZGDDX7GEV5LVA4","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":"ea2f2f01d1bd6b073da7bf1089010e15ec486397716418a7eb8d61b006d340a5","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T17:22:00Z","title_canon_sha256":"90cec4c354114e457b173ef28fb5a1868c482aceb15ed78738f2d651f2401f2c"},"schema_version":"1.0","source":{"id":"2401.12926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12926","created_at":"2026-07-05T07:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12926v1","created_at":"2026-07-05T07:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12926","created_at":"2026-07-05T07:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"TTHIC7VIPFIS","created_at":"2026-07-05T07:36:45Z"},{"alias_kind":"pith_short_16","alias_value":"TTHIC7VIPFISZGDD","created_at":"2026-07-05T07:36:45Z"},{"alias_kind":"pith_short_8","alias_value":"TTHIC7VI","created_at":"2026-07-05T07:36:45Z"}],"graph_snapshots":[{"event_id":"sha256:77d43bfae58efe8eeb26a26a34ab1fe6f30944db4c1d8992d3999a06af14b685","target":"graph","created_at":"2026-07-05T07:36:45Z","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/2401.12926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When selecting data for training large-scale models, standard practice is to filter for examples that match human notions of data quality. Such filtering yields qualitatively clean datapoints that intuitively should improve model behavior. However, in practice the opposite can often happen: we find that selecting according to similarity with \"high quality\" data sources may not increase (and can even hurt) performance compared to randomly selecting data.\n  To develop better methods for selecting data, we start by framing dataset selection as an optimization problem that we can directly solve fo","authors_text":"Aleksander Madry, Axel Feldmann, Logan Engstrom","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T17:22:00Z","title":"DsDm: Model-Aware Dataset Selection with Datamodels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12926","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":"sha256:5a7186411a52dab956b05969660cf7e4ac880f59456b3a1adca82a76275c773a","target":"record","created_at":"2026-07-05T07:36:45Z","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":"ea2f2f01d1bd6b073da7bf1089010e15ec486397716418a7eb8d61b006d340a5","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T17:22:00Z","title_canon_sha256":"90cec4c354114e457b173ef28fb5a1868c482aceb15ed78738f2d651f2401f2c"},"schema_version":"1.0","source":{"id":"2401.12926","kind":"arxiv","version":1}},"canonical_sha256":"9cce817ea879512c9863bfcc4af5750720fb8a24133358524fdc9a2991b3bf79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cce817ea879512c9863bfcc4af5750720fb8a24133358524fdc9a2991b3bf79","first_computed_at":"2026-07-05T07:36:45.815826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:45.815826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iu4RSfYy+AxWpNkJbdSVnqwQSyuCbtQX3DnwrM9hcWyxY4t/Ad3LACCJzu5tnXA9W2kVI0mobndwyOYlAADHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:45.816240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a7186411a52dab956b05969660cf7e4ac880f59456b3a1adca82a76275c773a","sha256:77d43bfae58efe8eeb26a26a34ab1fe6f30944db4c1d8992d3999a06af14b685"],"state_sha256":"05dc754285e2e530f1733d1b09a21696fdcbf73477ed02dc9f5b3e16ff94f65e"}