{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:35RUCORFLZLIC3ANVJLTOCHFHX","short_pith_number":"pith:35RUCORF","schema_version":"1.0","canonical_sha256":"df63413a255e56816c0daa573708e53dd1b3f8687e73e02a568e69ec5edcfb51","source":{"kind":"arxiv","id":"2205.09329","version":2},"attestation_state":"computed","paper":{"title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanyu Peng, Mingming Sun, Min Xu, Ping Li, Shuo Yang, Zeke Xie","submitted_at":"2022-05-19T05:36:35Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.09329","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T05:36:35Z","cross_cats_sorted":[],"title_canon_sha256":"a0f50e6d37ca879f62a24d3d060b8067328e96ed49f2f46c048c20ba48eb58cb","abstract_canon_sha256":"6c341e2f46e9edcf7d2f8a21a29487af4d124b52a85c0a1c3d70ebeaadc2db19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:28.444523Z","signature_b64":"DCg7aeZzfOH/b+6a42DWFu8llj0rsO5gn31TK8IMVkrD0Ns3YQ0uUgCi3zFpnl05dhzNrGzhE+v08GvkyMl6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df63413a255e56816c0daa573708e53dd1b3f8687e73e02a568e69ec5edcfb51","last_reissued_at":"2026-07-05T05:45:28.444118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:28.444118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanyu Peng, Mingming Sun, Min Xu, Ping Li, Shuo Yang, Zeke Xie","submitted_at":"2022-05-19T05:36:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09329","kind":"arxiv","version":2},"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/2205.09329/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.09329","created_at":"2026-07-05T05:45:28.444171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09329v2","created_at":"2026-07-05T05:45:28.444171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09329","created_at":"2026-07-05T05:45:28.444171+00:00"},{"alias_kind":"pith_short_12","alias_value":"35RUCORFLZLI","created_at":"2026-07-05T05:45:28.444171+00:00"},{"alias_kind":"pith_short_16","alias_value":"35RUCORFLZLIC3AN","created_at":"2026-07-05T05:45:28.444171+00:00"},{"alias_kind":"pith_short_8","alias_value":"35RUCORF","created_at":"2026-07-05T05:45:28.444171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25927","citing_title":"Knowledge Cascade: Reverse Knowledge Distillation on Nonparametric Multivariate Functional Estimation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08574","citing_title":"OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23969","citing_title":"SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09001","citing_title":"Surprisingly High Redundancy in Electronic Structure Data Across Materials Explained by Low Intrinsic Dimensionality","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03247","citing_title":"Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12945","citing_title":"Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":140,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX","json":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX.json","graph_json":"https://pith.science/api/pith-number/35RUCORFLZLIC3ANVJLTOCHFHX/graph.json","events_json":"https://pith.science/api/pith-number/35RUCORFLZLIC3ANVJLTOCHFHX/events.json","paper":"https://pith.science/paper/35RUCORF"},"agent_actions":{"view_html":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX","download_json":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX.json","view_paper":"https://pith.science/paper/35RUCORF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09329&json=true","fetch_graph":"https://pith.science/api/pith-number/35RUCORFLZLIC3ANVJLTOCHFHX/graph.json","fetch_events":"https://pith.science/api/pith-number/35RUCORFLZLIC3ANVJLTOCHFHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX/action/storage_attestation","attest_author":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX/action/author_attestation","sign_citation":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX/action/citation_signature","submit_replication":"https://pith.science/pith/35RUCORFLZLIC3ANVJLTOCHFHX/action/replication_record"}},"created_at":"2026-07-05T05:45:28.444171+00:00","updated_at":"2026-07-05T05:45:28.444171+00:00"}