{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BS7RTEHE2BI2E2DLQUVLZFSBXP","short_pith_number":"pith:BS7RTEHE","schema_version":"1.0","canonical_sha256":"0cbf1990e4d051a2686b852abc9641bbf484cbf78e79ed0c30804d5c80285dc7","source":{"kind":"arxiv","id":"2606.08574","version":1},"attestation_state":"computed","paper":{"title":"OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chenhan Jin, Dingshuo Chen, Fan Jia, Qingsong Wang, Shengze Xu, Tieyong Zeng","submitted_at":"2026-06-07T11:11:51Z","abstract_excerpt":"Data pruning (DP), as an oft-stated strategy to alleviate heavy training burdens, reduces the volume of training samples according to a well-defined pruning method while striving for near-lossless performance. However, existing approaches, which commonly select highly informative samples, can lead to biased gradient estimation compared to full-dataset training. Furthermore, the analysis of this bias and its impact on final performance remains ambiguous. To address these challenges, we propose OrderDP, a plug-and-play framework that aims to obtain stable, unbiased, and near-lossless training ac"},"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":"2606.08574","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T11:11:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"745b27321295ed037a18b5adc09818289043c3465f122c8759af29ed50c2c94b","abstract_canon_sha256":"c3be3904525ab6ed3c1bbbba625d787f2144e6c8bfead62088371421c52d9e7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:40.557724Z","signature_b64":"2aeYeQoAs0VM/Q1XyJHOlHVDAmLZY7d/0ztz9fCTo5FXN5A0M0L7wSaRvTFpAgsxwYJ0X5fX/JCWXQmW3mvXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cbf1990e4d051a2686b852abc9641bbf484cbf78e79ed0c30804d5c80285dc7","last_reissued_at":"2026-06-09T01:05:40.557261Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:40.557261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chenhan Jin, Dingshuo Chen, Fan Jia, Qingsong Wang, Shengze Xu, Tieyong Zeng","submitted_at":"2026-06-07T11:11:51Z","abstract_excerpt":"Data pruning (DP), as an oft-stated strategy to alleviate heavy training burdens, reduces the volume of training samples according to a well-defined pruning method while striving for near-lossless performance. However, existing approaches, which commonly select highly informative samples, can lead to biased gradient estimation compared to full-dataset training. Furthermore, the analysis of this bias and its impact on final performance remains ambiguous. To address these challenges, we propose OrderDP, a plug-and-play framework that aims to obtain stable, unbiased, and near-lossless training ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08574","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/2606.08574/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":"2606.08574","created_at":"2026-06-09T01:05:40.557337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08574v1","created_at":"2026-06-09T01:05:40.557337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08574","created_at":"2026-06-09T01:05:40.557337+00:00"},{"alias_kind":"pith_short_12","alias_value":"BS7RTEHE2BI2","created_at":"2026-06-09T01:05:40.557337+00:00"},{"alias_kind":"pith_short_16","alias_value":"BS7RTEHE2BI2E2DL","created_at":"2026-06-09T01:05:40.557337+00:00"},{"alias_kind":"pith_short_8","alias_value":"BS7RTEHE","created_at":"2026-06-09T01:05:40.557337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP","json":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP.json","graph_json":"https://pith.science/api/pith-number/BS7RTEHE2BI2E2DLQUVLZFSBXP/graph.json","events_json":"https://pith.science/api/pith-number/BS7RTEHE2BI2E2DLQUVLZFSBXP/events.json","paper":"https://pith.science/paper/BS7RTEHE"},"agent_actions":{"view_html":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP","download_json":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP.json","view_paper":"https://pith.science/paper/BS7RTEHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08574&json=true","fetch_graph":"https://pith.science/api/pith-number/BS7RTEHE2BI2E2DLQUVLZFSBXP/graph.json","fetch_events":"https://pith.science/api/pith-number/BS7RTEHE2BI2E2DLQUVLZFSBXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP/action/storage_attestation","attest_author":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP/action/author_attestation","sign_citation":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP/action/citation_signature","submit_replication":"https://pith.science/pith/BS7RTEHE2BI2E2DLQUVLZFSBXP/action/replication_record"}},"created_at":"2026-06-09T01:05:40.557337+00:00","updated_at":"2026-06-09T01:05:40.557337+00:00"}