{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BFRFAVTAPDEQXK46PLS5OBYQ67","short_pith_number":"pith:BFRFAVTA","canonical_record":{"source":{"id":"2406.17188","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T00:02:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c07534a80c57b917cf98fd583e5f377e7d8dbbb3b3f11497c6194dd81141286f","abstract_canon_sha256":"5a0af18f2dc129cccb35cb35c729406d1bf70aea90abbfd287dc3bd076ff51e2"},"schema_version":"1.0"},"canonical_sha256":"096250566078c90bab9e7ae5d70710f7e19bff14c830b6b695bd5da12075d7ab","source":{"kind":"arxiv","id":"2406.17188","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17188","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17188v2","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17188","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"BFRFAVTAPDEQ","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_16","alias_value":"BFRFAVTAPDEQXK46","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_8","alias_value":"BFRFAVTA","created_at":"2026-07-05T10:02:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BFRFAVTAPDEQXK46PLS5OBYQ67","target":"record","payload":{"canonical_record":{"source":{"id":"2406.17188","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T00:02:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c07534a80c57b917cf98fd583e5f377e7d8dbbb3b3f11497c6194dd81141286f","abstract_canon_sha256":"5a0af18f2dc129cccb35cb35c729406d1bf70aea90abbfd287dc3bd076ff51e2"},"schema_version":"1.0"},"canonical_sha256":"096250566078c90bab9e7ae5d70710f7e19bff14c830b6b695bd5da12075d7ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:04.598963Z","signature_b64":"gCEm7ligItuZH+XD1NEju922pCDObCyQKfcDkOqAniT4/7+ymE4NM/Dh0ZzXWjPD7am8e+4hnA/TPIL0nlXCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"096250566078c90bab9e7ae5d70710f7e19bff14c830b6b695bd5da12075d7ab","last_reissued_at":"2026-07-05T10:02:04.598546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:04.598546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.17188","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":"2026-07-05T10:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RjqBE6gTpi+OYNpgqrSOo+Ckt6p28HOPLLS9Z0YZca0kbUgGqqSJMr9MpS6PsBFApdONynkPabcqd/6shlrHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:09:24.793160Z"},"content_sha256":"f037fa0228774ae3b0ae062d9f295696e56542ce2fced80b6d1e1112e11e390c","schema_version":"1.0","event_id":"sha256:f037fa0228774ae3b0ae062d9f295696e56542ce2fced80b6d1e1112e11e390c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BFRFAVTAPDEQXK46PLS5OBYQ67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Median (GM) Matching for Robust Data Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anish Acharya, Inderjit S Dhillon, Sujay Sanghavi","submitted_at":"2024-06-25T00:02:01Z","abstract_excerpt":"Large-scale data collections in the wild, are invariably noisy. Thus developing data pruning strategies that remain robust even in the presence of corruption is critical in practice. In this work, we propose Geometric Median ($\\gm$) Matching -- a herding style greedy algorithm that yields a $k$-subset such that the mean of the subset approximates the geometric median of the (potentially) noisy dataset. Theoretically, we show that $\\gm$ Matching enjoys an improved $\\gO(1/k)$ scaling over $\\gO(1/\\sqrt{k})$ scaling of uniform sampling; while achieving {\\bf optimal breakdown point} of {\\bf 1/2} ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17188","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/2406.17188/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":"2026-07-05T10:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CTPv9CHVcyLLiFkJL1cYSdmtSsKrcDbw0GKrxL5BW6pbshQhXw6PGeK9BAwRsoPzo/TE46ge4e1m0q2HWxGcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:09:24.794526Z"},"content_sha256":"0917dc2db3101e5d48747262342666ea25992bcfc91398465f64adc5d9992817","schema_version":"1.0","event_id":"sha256:0917dc2db3101e5d48747262342666ea25992bcfc91398465f64adc5d9992817"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BFRFAVTAPDEQXK46PLS5OBYQ67/bundle.json","state_url":"https://pith.science/pith/BFRFAVTAPDEQXK46PLS5OBYQ67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BFRFAVTAPDEQXK46PLS5OBYQ67/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":"2026-08-17T17:09:24Z","links":{"resolver":"https://pith.science/pith/BFRFAVTAPDEQXK46PLS5OBYQ67","bundle":"https://pith.science/pith/BFRFAVTAPDEQXK46PLS5OBYQ67/bundle.json","state":"https://pith.science/pith/BFRFAVTAPDEQXK46PLS5OBYQ67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BFRFAVTAPDEQXK46PLS5OBYQ67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BFRFAVTAPDEQXK46PLS5OBYQ67","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":"5a0af18f2dc129cccb35cb35c729406d1bf70aea90abbfd287dc3bd076ff51e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T00:02:01Z","title_canon_sha256":"c07534a80c57b917cf98fd583e5f377e7d8dbbb3b3f11497c6194dd81141286f"},"schema_version":"1.0","source":{"id":"2406.17188","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17188","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17188v2","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17188","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"BFRFAVTAPDEQ","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_16","alias_value":"BFRFAVTAPDEQXK46","created_at":"2026-07-05T10:02:04Z"},{"alias_kind":"pith_short_8","alias_value":"BFRFAVTA","created_at":"2026-07-05T10:02:04Z"}],"graph_snapshots":[{"event_id":"sha256:0917dc2db3101e5d48747262342666ea25992bcfc91398465f64adc5d9992817","target":"graph","created_at":"2026-07-05T10:02:04Z","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/2406.17188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale data collections in the wild, are invariably noisy. Thus developing data pruning strategies that remain robust even in the presence of corruption is critical in practice. In this work, we propose Geometric Median ($\\gm$) Matching -- a herding style greedy algorithm that yields a $k$-subset such that the mean of the subset approximates the geometric median of the (potentially) noisy dataset. Theoretically, we show that $\\gm$ Matching enjoys an improved $\\gO(1/k)$ scaling over $\\gO(1/\\sqrt{k})$ scaling of uniform sampling; while achieving {\\bf optimal breakdown point} of {\\bf 1/2} ev","authors_text":"Anish Acharya, Inderjit S Dhillon, Sujay Sanghavi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T00:02:01Z","title":"Geometric Median (GM) Matching for Robust Data Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17188","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:f037fa0228774ae3b0ae062d9f295696e56542ce2fced80b6d1e1112e11e390c","target":"record","created_at":"2026-07-05T10:02:04Z","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":"5a0af18f2dc129cccb35cb35c729406d1bf70aea90abbfd287dc3bd076ff51e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T00:02:01Z","title_canon_sha256":"c07534a80c57b917cf98fd583e5f377e7d8dbbb3b3f11497c6194dd81141286f"},"schema_version":"1.0","source":{"id":"2406.17188","kind":"arxiv","version":2}},"canonical_sha256":"096250566078c90bab9e7ae5d70710f7e19bff14c830b6b695bd5da12075d7ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"096250566078c90bab9e7ae5d70710f7e19bff14c830b6b695bd5da12075d7ab","first_computed_at":"2026-07-05T10:02:04.598546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:04.598546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gCEm7ligItuZH+XD1NEju922pCDObCyQKfcDkOqAniT4/7+ymE4NM/Dh0ZzXWjPD7am8e+4hnA/TPIL0nlXCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:04.598963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17188","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f037fa0228774ae3b0ae062d9f295696e56542ce2fced80b6d1e1112e11e390c","sha256:0917dc2db3101e5d48747262342666ea25992bcfc91398465f64adc5d9992817"],"state_sha256":"445c79505df6c2e19f4723928e73c8af9099b2e349c1e422b4cb15773d403603"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZgsezSes8gOm7ogaesjnVgLE66e2h3va3XTJODd5ssJvtj9ToezsfWwDNSXVHxix5T5diq0XALNPGz6lomRsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T17:09:24.805959Z","bundle_sha256":"792201479247a8d7a5212f3cf1a411194075dfcfdd9f2a9f96add8dca36f0e36"}}