{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7Z524MWSFTJZHLJROI4GVJRD4H","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":"8bad813b605d409f9d7c1d719edb8b52a671827c1856025c717415ab64571da8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T16:10:11Z","title_canon_sha256":"88039abb123b77c4fb865eeffa2ca5a2a418d0bb69cab82c3ae4ad3272f31c98"},"schema_version":"1.0","source":{"id":"2507.16729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16729","created_at":"2026-07-05T11:41:29Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16729v1","created_at":"2026-07-05T11:41:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16729","created_at":"2026-07-05T11:41:29Z"},{"alias_kind":"pith_short_12","alias_value":"7Z524MWSFTJZ","created_at":"2026-07-05T11:41:29Z"},{"alias_kind":"pith_short_16","alias_value":"7Z524MWSFTJZHLJR","created_at":"2026-07-05T11:41:29Z"},{"alias_kind":"pith_short_8","alias_value":"7Z524MWS","created_at":"2026-07-05T11:41:29Z"}],"graph_snapshots":[{"event_id":"sha256:5ae822f4a6bb81a6055e50838511c77986bf3ef42560739bf4e8f072e9255db0","target":"graph","created_at":"2026-07-05T11:41:29Z","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/2507.16729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of data-centric AI, the ability to curate high-quality training data is as crucial as model design. Coresets offer a principled approach to data reduction, enabling efficient learning on large datasets through importance sampling. However, conventional sensitivity-based coreset construction often falls short in optimizing for classification performance metrics, e.g., $F1$ score, focusing instead on loss approximation. In this work, we present a systematic framework for tuning the coreset generation process to enhance downstream classification quality. Our method introduces new tunab","authors_text":"Eitan Netzer, Liran Sigalat, Loay Mualem, Morad Tukan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T16:10:11Z","title":"Improving Model Classification by Optimizing the Training Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16729","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:a5edea14a2abc26a99a5aa15e75a79fd55d8a97ae2cebcbb8cfe08b4910b78eb","target":"record","created_at":"2026-07-05T11:41:29Z","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":"8bad813b605d409f9d7c1d719edb8b52a671827c1856025c717415ab64571da8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T16:10:11Z","title_canon_sha256":"88039abb123b77c4fb865eeffa2ca5a2a418d0bb69cab82c3ae4ad3272f31c98"},"schema_version":"1.0","source":{"id":"2507.16729","kind":"arxiv","version":1}},"canonical_sha256":"fe7bae32d22cd393ad3172386aa623e1f4385cc8b36137e5da21a0ea720a5975","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe7bae32d22cd393ad3172386aa623e1f4385cc8b36137e5da21a0ea720a5975","first_computed_at":"2026-07-05T11:41:29.972460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:29.972460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TJtlK2eGqnpzCBZQxyFvrd3ieR7VvoS0foPBkcGkeQXRPet3RGAPWTnqbvCLijdhRJA9ETcgTGlJvXiPyk31Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:29.972950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5edea14a2abc26a99a5aa15e75a79fd55d8a97ae2cebcbb8cfe08b4910b78eb","sha256:5ae822f4a6bb81a6055e50838511c77986bf3ef42560739bf4e8f072e9255db0"],"state_sha256":"943890a0ba9988b2cca78ecf9399571706ad26ea62a89aaf208ced52f221bc09"}