{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BZZPQ7MMDB5WLULGVKBTMD3NJV","short_pith_number":"pith:BZZPQ7MM","canonical_record":{"source":{"id":"2504.00564","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T09:22:05Z","cross_cats_sorted":[],"title_canon_sha256":"38901f88108d888f26a09608d415bd4ef591fadc26130ecb5e34fe74355dc5f8","abstract_canon_sha256":"2e4df17f6493500fc93390ff3963ebac26c8c7d07123b84441aff00568dd0208"},"schema_version":"1.0"},"canonical_sha256":"0e72f87d8c187b65d166aa83360f6d4d49e326769b0d599ac34dbb9121a16b16","source":{"kind":"arxiv","id":"2504.00564","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00564","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00564v2","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00564","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"pith_short_12","alias_value":"BZZPQ7MMDB5W","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"pith_short_16","alias_value":"BZZPQ7MMDB5WLULG","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"pith_short_8","alias_value":"BZZPQ7MM","created_at":"2026-07-05T10:43:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BZZPQ7MMDB5WLULGVKBTMD3NJV","target":"record","payload":{"canonical_record":{"source":{"id":"2504.00564","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T09:22:05Z","cross_cats_sorted":[],"title_canon_sha256":"38901f88108d888f26a09608d415bd4ef591fadc26130ecb5e34fe74355dc5f8","abstract_canon_sha256":"2e4df17f6493500fc93390ff3963ebac26c8c7d07123b84441aff00568dd0208"},"schema_version":"1.0"},"canonical_sha256":"0e72f87d8c187b65d166aa83360f6d4d49e326769b0d599ac34dbb9121a16b16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:47.302100Z","signature_b64":"mR3xPUMkzDYljGuh9X1nWEHapQqDUnLW81yUAEex8bzu43Kjcp/fDSufkag+O8pF/9nmE7zYjCuFkch80AjcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e72f87d8c187b65d166aa83360f6d4d49e326769b0d599ac34dbb9121a16b16","last_reissued_at":"2026-07-05T10:43:47.301480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:47.301480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.00564","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XmLwe/UmKoCyXZkUlRo+jp+AlVF5r8qLV/xMhkqgaGtblC+LNDB9owvWYECVbAxN5ziGTynNsHPFKDoCtuzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:45:02.570056Z"},"content_sha256":"d390e587d0f7f974a48cb0b7c82d477817bde11b8223d87b21c9269cf3bff3bd","schema_version":"1.0","event_id":"sha256:d390e587d0f7f974a48cb0b7c82d477817bde11b8223d87b21c9269cf3bff3bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BZZPQ7MMDB5WLULGVKBTMD3NJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Median Matching for Robust k-Subset Selection from Noisy Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandros G. Dimakis, Anish Acharya, Inderjit S Dhillon, Sujay Sanghavi","submitted_at":"2025-04-01T09:22:05Z","abstract_excerpt":"Data pruning -- the combinatorial task of selecting a small and representative subset from a large dataset, is crucial for mitigating the enormous computational costs associated with training data-hungry modern deep learning models at scale. Since large scale data collections are invariably noisy, developing data pruning strategies that remain robust even in the presence of corruption is critical in practice. However, existing data pruning methods often fail under high corruption rates due to their reliance on empirical mean estimation, which is highly sensitive to outliers.\n  In response, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00564","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/2504.00564/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Kdjt1ixIYjwpsb9Mhw2cZx/knpRcysB9XxhBORFZ5yuTfG9/gAkY+YE0UbUhHTKYJps+Rre9eq2YyJixUgCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:45:02.570437Z"},"content_sha256":"34f8165bd9b85a384c6341ffa4468803188c1e07205e0f8049d3e88f41d37a2e","schema_version":"1.0","event_id":"sha256:34f8165bd9b85a384c6341ffa4468803188c1e07205e0f8049d3e88f41d37a2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZZPQ7MMDB5WLULGVKBTMD3NJV/bundle.json","state_url":"https://pith.science/pith/BZZPQ7MMDB5WLULGVKBTMD3NJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZZPQ7MMDB5WLULGVKBTMD3NJV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T10:45:02Z","links":{"resolver":"https://pith.science/pith/BZZPQ7MMDB5WLULGVKBTMD3NJV","bundle":"https://pith.science/pith/BZZPQ7MMDB5WLULGVKBTMD3NJV/bundle.json","state":"https://pith.science/pith/BZZPQ7MMDB5WLULGVKBTMD3NJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZZPQ7MMDB5WLULGVKBTMD3NJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BZZPQ7MMDB5WLULGVKBTMD3NJV","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":"2e4df17f6493500fc93390ff3963ebac26c8c7d07123b84441aff00568dd0208","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T09:22:05Z","title_canon_sha256":"38901f88108d888f26a09608d415bd4ef591fadc26130ecb5e34fe74355dc5f8"},"schema_version":"1.0","source":{"id":"2504.00564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00564","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00564v2","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00564","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"pith_short_12","alias_value":"BZZPQ7MMDB5W","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"pith_short_16","alias_value":"BZZPQ7MMDB5WLULG","created_at":"2026-07-05T10:43:47Z"},{"alias_kind":"pith_short_8","alias_value":"BZZPQ7MM","created_at":"2026-07-05T10:43:47Z"}],"graph_snapshots":[{"event_id":"sha256:34f8165bd9b85a384c6341ffa4468803188c1e07205e0f8049d3e88f41d37a2e","target":"graph","created_at":"2026-07-05T10:43:47Z","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/2504.00564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data pruning -- the combinatorial task of selecting a small and representative subset from a large dataset, is crucial for mitigating the enormous computational costs associated with training data-hungry modern deep learning models at scale. Since large scale data collections are invariably noisy, developing data pruning strategies that remain robust even in the presence of corruption is critical in practice. However, existing data pruning methods often fail under high corruption rates due to their reliance on empirical mean estimation, which is highly sensitive to outliers.\n  In response, we ","authors_text":"Alexandros G. Dimakis, Anish Acharya, Inderjit S Dhillon, Sujay Sanghavi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T09:22:05Z","title":"Geometric Median Matching for Robust k-Subset Selection from Noisy Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00564","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:d390e587d0f7f974a48cb0b7c82d477817bde11b8223d87b21c9269cf3bff3bd","target":"record","created_at":"2026-07-05T10:43:47Z","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":"2e4df17f6493500fc93390ff3963ebac26c8c7d07123b84441aff00568dd0208","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T09:22:05Z","title_canon_sha256":"38901f88108d888f26a09608d415bd4ef591fadc26130ecb5e34fe74355dc5f8"},"schema_version":"1.0","source":{"id":"2504.00564","kind":"arxiv","version":2}},"canonical_sha256":"0e72f87d8c187b65d166aa83360f6d4d49e326769b0d599ac34dbb9121a16b16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e72f87d8c187b65d166aa83360f6d4d49e326769b0d599ac34dbb9121a16b16","first_computed_at":"2026-07-05T10:43:47.301480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:47.301480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mR3xPUMkzDYljGuh9X1nWEHapQqDUnLW81yUAEex8bzu43Kjcp/fDSufkag+O8pF/9nmE7zYjCuFkch80AjcAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:47.302100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d390e587d0f7f974a48cb0b7c82d477817bde11b8223d87b21c9269cf3bff3bd","sha256:34f8165bd9b85a384c6341ffa4468803188c1e07205e0f8049d3e88f41d37a2e"],"state_sha256":"c7aa92e34a45acae38607b49876f8306c31f08ae5ec3eab48713f7b544e5c9da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wU5NfvcXUppQ+9ruo2it6Y9U10fb7ejaYGxnG8+vpDges66AhKz8vwk+kLwmGVOOG/VhpbvkFgVQUOef9gpsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:45:02.572353Z","bundle_sha256":"49ec22ab8db5f911444ca026a19d5a7fb99bd636d5e76cfbf38dc0debf281ad5"}}