{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:35RUCORFLZLIC3ANVJLTOCHFHX","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":"6c341e2f46e9edcf7d2f8a21a29487af4d124b52a85c0a1c3d70ebeaadc2db19","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T05:36:35Z","title_canon_sha256":"a0f50e6d37ca879f62a24d3d060b8067328e96ed49f2f46c048c20ba48eb58cb"},"schema_version":"1.0","source":{"id":"2205.09329","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09329","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09329v2","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09329","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"pith_short_12","alias_value":"35RUCORFLZLI","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"pith_short_16","alias_value":"35RUCORFLZLIC3AN","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"pith_short_8","alias_value":"35RUCORF","created_at":"2026-07-05T05:45:28Z"}],"graph_snapshots":[{"event_id":"sha256:6ed87cd0d6464d7b30cc790c813fd3a86bb246407fb0a724c548233a08049be6","target":"graph","created_at":"2026-07-05T05:45:28Z","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/2205.09329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's performance? How much does each individual training sample or a sub-training-set affect the model's generalization, and how to construct the smallest subset from the entire training data as a proxy training set without significantly sacrificing the model's performance? To answer these, we propose dataset pruning, an optimization-based sample selection method t","authors_text":"Hanyu Peng, Mingming Sun, Min Xu, Ping Li, Shuo Yang, Zeke Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T05:36:35Z","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09329","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":"sha256:1920f6b16dca065592491d43fcfc27ebdc49f0cee79a22eb6ae6bb10927f520d","target":"record","created_at":"2026-07-05T05:45:28Z","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":"6c341e2f46e9edcf7d2f8a21a29487af4d124b52a85c0a1c3d70ebeaadc2db19","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T05:36:35Z","title_canon_sha256":"a0f50e6d37ca879f62a24d3d060b8067328e96ed49f2f46c048c20ba48eb58cb"},"schema_version":"1.0","source":{"id":"2205.09329","kind":"arxiv","version":2}},"canonical_sha256":"df63413a255e56816c0daa573708e53dd1b3f8687e73e02a568e69ec5edcfb51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df63413a255e56816c0daa573708e53dd1b3f8687e73e02a568e69ec5edcfb51","first_computed_at":"2026-07-05T05:45:28.444118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:28.444118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DCg7aeZzfOH/b+6a42DWFu8llj0rsO5gn31TK8IMVkrD0Ns3YQ0uUgCi3zFpnl05dhzNrGzhE+v08GvkyMl6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:28.444523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.09329","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1920f6b16dca065592491d43fcfc27ebdc49f0cee79a22eb6ae6bb10927f520d","sha256:6ed87cd0d6464d7b30cc790c813fd3a86bb246407fb0a724c548233a08049be6"],"state_sha256":"700903709dd654ff3e3564d6ca058a6dc289ecf641d285a527380713553f5262"}