{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TKHEOLP7J6OQISQLJ23IJPSB3I","short_pith_number":"pith:TKHEOLP7","schema_version":"1.0","canonical_sha256":"9a8e472dff4f9d044a0b4eb684be41da2442dae8fd94d6254328b3ae4f6bdd9f","source":{"kind":"arxiv","id":"2606.12913","version":1},"attestation_state":"computed","paper":{"title":"Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Changxin Gao, Dongyue Wu, Jiajia Liu, Jingdong Chen, Nong Sang, Xiaoyu Li, Zilin Guo","submitted_at":"2026-06-11T05:13:32Z","abstract_excerpt":"The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost.\n  Existing pruning criteria typically rely on either intrinsic signals that assess samples independently or extrinsic signals that promote diversity via pairwise relations.\n  While effective in their own specific regimes, each captures only one aspect of sample utility and lacks robustness across different pruning ratios or data distribution.\n  In this work, we present a unified graph-base"},"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":"2606.12913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T05:13:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"21bc575c8d0121d58dcfbf1e34d4aeda876c725763aa41597903754c6068b34c","abstract_canon_sha256":"b76024c60101a26b5f0b93c77e311244c9be52bcfdd508df02b2b5c0e0c976b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:34.257797Z","signature_b64":"Nc9DienXrU928YSOsb6oNqVhqouph2vxpD5odG+ZeXFQSAPte/l298/i5eAJXZpuheV3NFinXgf6TvvU/aZVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a8e472dff4f9d044a0b4eb684be41da2442dae8fd94d6254328b3ae4f6bdd9f","last_reissued_at":"2026-06-12T01:09:34.257367Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:34.257367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Changxin Gao, Dongyue Wu, Jiajia Liu, Jingdong Chen, Nong Sang, Xiaoyu Li, Zilin Guo","submitted_at":"2026-06-11T05:13:32Z","abstract_excerpt":"The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost.\n  Existing pruning criteria typically rely on either intrinsic signals that assess samples independently or extrinsic signals that promote diversity via pairwise relations.\n  While effective in their own specific regimes, each captures only one aspect of sample utility and lacks robustness across different pruning ratios or data distribution.\n  In this work, we present a unified graph-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12913","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/2606.12913/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":"2606.12913","created_at":"2026-06-12T01:09:34.257422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12913v1","created_at":"2026-06-12T01:09:34.257422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12913","created_at":"2026-06-12T01:09:34.257422+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKHEOLP7J6OQ","created_at":"2026-06-12T01:09:34.257422+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKHEOLP7J6OQISQL","created_at":"2026-06-12T01:09:34.257422+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKHEOLP7","created_at":"2026-06-12T01:09:34.257422+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/TKHEOLP7J6OQISQLJ23IJPSB3I","json":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I.json","graph_json":"https://pith.science/api/pith-number/TKHEOLP7J6OQISQLJ23IJPSB3I/graph.json","events_json":"https://pith.science/api/pith-number/TKHEOLP7J6OQISQLJ23IJPSB3I/events.json","paper":"https://pith.science/paper/TKHEOLP7"},"agent_actions":{"view_html":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I","download_json":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I.json","view_paper":"https://pith.science/paper/TKHEOLP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12913&json=true","fetch_graph":"https://pith.science/api/pith-number/TKHEOLP7J6OQISQLJ23IJPSB3I/graph.json","fetch_events":"https://pith.science/api/pith-number/TKHEOLP7J6OQISQLJ23IJPSB3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I/action/storage_attestation","attest_author":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I/action/author_attestation","sign_citation":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I/action/citation_signature","submit_replication":"https://pith.science/pith/TKHEOLP7J6OQISQLJ23IJPSB3I/action/replication_record"}},"created_at":"2026-06-12T01:09:34.257422+00:00","updated_at":"2026-06-12T01:09:34.257422+00:00"}