{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7Z524MWSFTJZHLJROI4GVJRD4H","short_pith_number":"pith:7Z524MWS","canonical_record":{"source":{"id":"2507.16729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T16:10:11Z","cross_cats_sorted":[],"title_canon_sha256":"88039abb123b77c4fb865eeffa2ca5a2a418d0bb69cab82c3ae4ad3272f31c98","abstract_canon_sha256":"8bad813b605d409f9d7c1d719edb8b52a671827c1856025c717415ab64571da8"},"schema_version":"1.0"},"canonical_sha256":"fe7bae32d22cd393ad3172386aa623e1f4385cc8b36137e5da21a0ea720a5975","source":{"kind":"arxiv","id":"2507.16729","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7Z524MWSFTJZHLJROI4GVJRD4H","target":"record","payload":{"canonical_record":{"source":{"id":"2507.16729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T16:10:11Z","cross_cats_sorted":[],"title_canon_sha256":"88039abb123b77c4fb865eeffa2ca5a2a418d0bb69cab82c3ae4ad3272f31c98","abstract_canon_sha256":"8bad813b605d409f9d7c1d719edb8b52a671827c1856025c717415ab64571da8"},"schema_version":"1.0"},"canonical_sha256":"fe7bae32d22cd393ad3172386aa623e1f4385cc8b36137e5da21a0ea720a5975","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:29.972950Z","signature_b64":"TJtlK2eGqnpzCBZQxyFvrd3ieR7VvoS0foPBkcGkeQXRPet3RGAPWTnqbvCLijdhRJA9ETcgTGlJvXiPyk31Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe7bae32d22cd393ad3172386aa623e1f4385cc8b36137e5da21a0ea720a5975","last_reissued_at":"2026-07-05T11:41:29.972460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:29.972460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.16729","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":"2026-07-05T11:41:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"czhj9LJ1Wu4nhhPbVRZE+UAt2tNpgGJsnXrNsrK9Nb3R2DNqJEqIT1G3nsPex6NZ188c31eJXd9LIcpMxK/tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:39:24.929936Z"},"content_sha256":"a5edea14a2abc26a99a5aa15e75a79fd55d8a97ae2cebcbb8cfe08b4910b78eb","schema_version":"1.0","event_id":"sha256:a5edea14a2abc26a99a5aa15e75a79fd55d8a97ae2cebcbb8cfe08b4910b78eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7Z524MWSFTJZHLJROI4GVJRD4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Model Classification by Optimizing the Training Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eitan Netzer, Liran Sigalat, Loay Mualem, Morad Tukan","submitted_at":"2025-07-22T16:10:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16729","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/2507.16729/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":"2026-07-05T11:41:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X9yrP4Vlske6EFSVrGZuNEdLBtT5Ms23l+msXp7HyUUrNbCHkV77XvAmF8b4iXYoGZ9CApg2puVBE7vyfV3lAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:39:24.930849Z"},"content_sha256":"5ae822f4a6bb81a6055e50838511c77986bf3ef42560739bf4e8f072e9255db0","schema_version":"1.0","event_id":"sha256:5ae822f4a6bb81a6055e50838511c77986bf3ef42560739bf4e8f072e9255db0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7Z524MWSFTJZHLJROI4GVJRD4H/bundle.json","state_url":"https://pith.science/pith/7Z524MWSFTJZHLJROI4GVJRD4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7Z524MWSFTJZHLJROI4GVJRD4H/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":"2026-08-16T13:39:24Z","links":{"resolver":"https://pith.science/pith/7Z524MWSFTJZHLJROI4GVJRD4H","bundle":"https://pith.science/pith/7Z524MWSFTJZHLJROI4GVJRD4H/bundle.json","state":"https://pith.science/pith/7Z524MWSFTJZHLJROI4GVJRD4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7Z524MWSFTJZHLJROI4GVJRD4H/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8WSHt6fCYn/MjOGnQxI93zFs4ag5cwLbZZRyrLrJOh7lyOry/TWVs+vho1dyTt4sUgMp7TUxQFAZwYrxwoJuCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T13:39:24.936684Z","bundle_sha256":"8aca7607cd23e2aacd9574ee18128bf11fbf2d1114d4f78e826f0e837726fcd4"}}