{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L3WEEC5ZTQBHXFWYFTU7NBCAW2","short_pith_number":"pith:L3WEEC5Z","schema_version":"1.0","canonical_sha256":"5eec420bb99c027b96d82ce9f68440b69dc640e6b60b4c3b7b03bd852235073f","source":{"kind":"arxiv","id":"2506.09010","version":2},"attestation_state":"computed","paper":{"title":"Effective Data Pruning through Score Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bj\\\"orn Nieth, Christoffer L\\\"offler, Leo Schwinn, Prasanga Dhungel, Sebastian Schmidt, Stephan G\\\"unnemann","submitted_at":"2025-06-10T17:38:49Z","abstract_excerpt":"Training advanced machine learning models demands massive datasets, resulting in prohibitive computational costs. To address this challenge, data pruning techniques identify and remove redundant training samples while preserving model performance. Yet, existing pruning techniques predominantly require a full initial training pass to identify removable samples, negating any efficiency benefits for single training runs. To overcome this limitation, we introduce a novel importance score extrapolation framework that requires training on only a small subset of data. We present two initial approache"},"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":"2506.09010","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:38:49Z","cross_cats_sorted":[],"title_canon_sha256":"59f71ccd03abcc5cbabe3d033a7bd79b6a0c05b4cf2f5d0488c1c7ec0e29e66f","abstract_canon_sha256":"9c6df01d66578fb617e8c6db3c175777e100748a0ad50da122e4a52a8d049c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:22.674486Z","signature_b64":"D//FbWQP+D2BLzKX5hB0ERWb5UPtrwOAKivjyk8lA3mOzf5+yk+iDU5ZedNs6w4JD5mvkN9XsdCTI92adYvSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eec420bb99c027b96d82ce9f68440b69dc640e6b60b4c3b7b03bd852235073f","last_reissued_at":"2026-07-05T11:24:22.673975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:22.673975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Data Pruning through Score Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bj\\\"orn Nieth, Christoffer L\\\"offler, Leo Schwinn, Prasanga Dhungel, Sebastian Schmidt, Stephan G\\\"unnemann","submitted_at":"2025-06-10T17:38:49Z","abstract_excerpt":"Training advanced machine learning models demands massive datasets, resulting in prohibitive computational costs. To address this challenge, data pruning techniques identify and remove redundant training samples while preserving model performance. Yet, existing pruning techniques predominantly require a full initial training pass to identify removable samples, negating any efficiency benefits for single training runs. To overcome this limitation, we introduce a novel importance score extrapolation framework that requires training on only a small subset of data. We present two initial approache"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09010","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/2506.09010/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":"2506.09010","created_at":"2026-07-05T11:24:22.674036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09010v2","created_at":"2026-07-05T11:24:22.674036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09010","created_at":"2026-07-05T11:24:22.674036+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3WEEC5ZTQBH","created_at":"2026-07-05T11:24:22.674036+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3WEEC5ZTQBHXFWY","created_at":"2026-07-05T11:24:22.674036+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3WEEC5Z","created_at":"2026-07-05T11:24:22.674036+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/L3WEEC5ZTQBHXFWYFTU7NBCAW2","json":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2.json","graph_json":"https://pith.science/api/pith-number/L3WEEC5ZTQBHXFWYFTU7NBCAW2/graph.json","events_json":"https://pith.science/api/pith-number/L3WEEC5ZTQBHXFWYFTU7NBCAW2/events.json","paper":"https://pith.science/paper/L3WEEC5Z"},"agent_actions":{"view_html":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2","download_json":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2.json","view_paper":"https://pith.science/paper/L3WEEC5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09010&json=true","fetch_graph":"https://pith.science/api/pith-number/L3WEEC5ZTQBHXFWYFTU7NBCAW2/graph.json","fetch_events":"https://pith.science/api/pith-number/L3WEEC5ZTQBHXFWYFTU7NBCAW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2/action/storage_attestation","attest_author":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2/action/author_attestation","sign_citation":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2/action/citation_signature","submit_replication":"https://pith.science/pith/L3WEEC5ZTQBHXFWYFTU7NBCAW2/action/replication_record"}},"created_at":"2026-07-05T11:24:22.674036+00:00","updated_at":"2026-07-05T11:24:22.674036+00:00"}