{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:73NN3ML2UYNB7LNCFW2DDHFP5O","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":"1795239dc4e84bab8a9a7559cb8f76f7aff374fda40e40a57ef40cf995283dd2","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T14:54:26Z","title_canon_sha256":"753aa5ce5b527a7ece264627d6eaa77411e18fb68383941deb8ac6c61d8ff2aa"},"schema_version":"1.0","source":{"id":"2410.00759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00759","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00759v2","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00759","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"73NN3ML2UYNB","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"73NN3ML2UYNB7LNC","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"73NN3ML2","created_at":"2026-07-05T10:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:0ad471490bcf5f356e6056f771734e410876adad4d382687f0decd25e91e0173","target":"graph","created_at":"2026-07-05T10:11:25Z","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/2410.00759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation via synthetic data generation has been shown to be effective in improving model performance and robustness in the context of scarce or low-quality data. Using the data valuation framework to statistically identify beneficial and detrimental observations, we introduce a simple augmentation pipeline that generates only high-value training points based on hardness characterization, in a computationally efficient manner. We first empirically demonstrate via benchmarks on real data that Shapley-based data valuation methods perform comparably with learning-based methods in hardness","authors_text":"Anton Hinel, Francesco Sanna Passino, Leonie Tabea Goldmann, Tommaso Ferracci","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T14:54:26Z","title":"Targeted synthetic data generation for tabular data via hardness characterization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00759","kind":"arxiv","version":2},"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":"sha256:08ed6456e5ffd3ac5b926660325c0e0a041498a3c3433194d2188372ecfdbfe8","target":"record","created_at":"2026-07-05T10:11:25Z","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":"1795239dc4e84bab8a9a7559cb8f76f7aff374fda40e40a57ef40cf995283dd2","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T14:54:26Z","title_canon_sha256":"753aa5ce5b527a7ece264627d6eaa77411e18fb68383941deb8ac6c61d8ff2aa"},"schema_version":"1.0","source":{"id":"2410.00759","kind":"arxiv","version":2}},"canonical_sha256":"fedaddb17aa61a1fada22db4319cafeb82452a0b97e20120c0db02fce5847e09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fedaddb17aa61a1fada22db4319cafeb82452a0b97e20120c0db02fce5847e09","first_computed_at":"2026-07-05T10:11:25.096642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:25.096642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jc6k4qaODhu/ciaQDXLP9+noochu0y5yM1622G3jPpnlBF9n8hLWSRcpfBCyEO+jC1oW2dtuxDPEw5IWk52OBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:25.097169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08ed6456e5ffd3ac5b926660325c0e0a041498a3c3433194d2188372ecfdbfe8","sha256:0ad471490bcf5f356e6056f771734e410876adad4d382687f0decd25e91e0173"],"state_sha256":"3d2cb86a609fe6b9d78e0a2fb2f8af5c1eb5425175bd4f9e7b1a96519f7ad979"}