{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KX54OV3CUD2563IC7DBNUMC4N3","short_pith_number":"pith:KX54OV3C","canonical_record":{"source":{"id":"2402.17327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T09:03:43Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"8eb56bcfec1b177958d65e50d0a31256b98902764c058c7d2b2c8dd05d96c9e0","abstract_canon_sha256":"d4ebc087157faf4859e15ee4316332029fa9d1b8a7862359c42b44a533a2e0e2"},"schema_version":"1.0"},"canonical_sha256":"55fbc75762a0f5df6d02f8c2da305c6ed2044ff5cab660f69bf65543e6e69439","source":{"kind":"arxiv","id":"2402.17327","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17327","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17327v1","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17327","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"KX54OV3CUD25","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"KX54OV3CUD2563IC","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"KX54OV3C","created_at":"2026-07-05T07:49:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KX54OV3CUD2563IC7DBNUMC4N3","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T09:03:43Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"8eb56bcfec1b177958d65e50d0a31256b98902764c058c7d2b2c8dd05d96c9e0","abstract_canon_sha256":"d4ebc087157faf4859e15ee4316332029fa9d1b8a7862359c42b44a533a2e0e2"},"schema_version":"1.0"},"canonical_sha256":"55fbc75762a0f5df6d02f8c2da305c6ed2044ff5cab660f69bf65543e6e69439","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:45.457631Z","signature_b64":"JdOnx+iyT2BFnF/A9FipK+eNGTcp1ihCTtegK/e7TVQjFIpTATRVJEwRimad5HxcPKKtJo1iuGPz64rfHJpVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55fbc75762a0f5df6d02f8c2da305c6ed2044ff5cab660f69bf65543e6e69439","last_reissued_at":"2026-07-05T07:49:45.457144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:45.457144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17327","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vF5CazyN+9qvf5/htb8WaPdixmKbM/J4uG5SnSSHbM7Xt0AeghZRJccHV/WfyfOMmvPa9qvND7KawexuYwUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:58:15.919286Z"},"content_sha256":"98f472dafa447362ff62315c6a34200713939718797144d47e871aebe101ab98","schema_version":"1.0","event_id":"sha256:98f472dafa447362ff62315c6a34200713939718797144d47e871aebe101ab98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KX54OV3CUD2563IC7DBNUMC4N3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"David Saulpic, David Woodruff, Kyriakos Axiotis, Michael Wunder, Monika Henzinger, Sammy Jerome, Vahab Mirrokni, Vincent Cohen-Addad","submitted_at":"2024-02-27T09:03:43Z","abstract_excerpt":"We study the data selection problem, whose aim is to select a small representative subset of data that can be used to efficiently train a machine learning model. We present a new data selection approach based on $k$-means clustering and sensitivity sampling. Assuming access to an embedding representation of the data with respect to which the model loss is H\\\"older continuous, our approach provably allows selecting a set of ``typical'' $k + 1/\\varepsilon^2$ elements whose average loss corresponds to the average loss of the whole dataset, up to a multiplicative $(1\\pm\\varepsilon)$ factor and an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17327","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/2402.17327/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":"2026-07-05T07:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0723qg5FxwEIDNoqZM7JgK1gYaDSvix1jpV78EWiUgM7YidcTydcs5fy5mvRnX5FFdzxxg3B9TwvCwMMiG3RCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:58:15.919673Z"},"content_sha256":"e746615a623094521a33de859440e84160d688a7b5420582a3c4aeea0cec2d6c","schema_version":"1.0","event_id":"sha256:e746615a623094521a33de859440e84160d688a7b5420582a3c4aeea0cec2d6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/bundle.json","state_url":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KX54OV3CUD2563IC7DBNUMC4N3/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":"2026-07-07T09:58:15Z","links":{"resolver":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3","bundle":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/bundle.json","state":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KX54OV3CUD2563IC7DBNUMC4N3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KX54OV3CUD2563IC7DBNUMC4N3","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":"d4ebc087157faf4859e15ee4316332029fa9d1b8a7862359c42b44a533a2e0e2","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T09:03:43Z","title_canon_sha256":"8eb56bcfec1b177958d65e50d0a31256b98902764c058c7d2b2c8dd05d96c9e0"},"schema_version":"1.0","source":{"id":"2402.17327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17327","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17327v1","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17327","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"KX54OV3CUD25","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"KX54OV3CUD2563IC","created_at":"2026-07-05T07:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"KX54OV3C","created_at":"2026-07-05T07:49:45Z"}],"graph_snapshots":[{"event_id":"sha256:e746615a623094521a33de859440e84160d688a7b5420582a3c4aeea0cec2d6c","target":"graph","created_at":"2026-07-05T07:49:45Z","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/2402.17327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the data selection problem, whose aim is to select a small representative subset of data that can be used to efficiently train a machine learning model. We present a new data selection approach based on $k$-means clustering and sensitivity sampling. Assuming access to an embedding representation of the data with respect to which the model loss is H\\\"older continuous, our approach provably allows selecting a set of ``typical'' $k + 1/\\varepsilon^2$ elements whose average loss corresponds to the average loss of the whole dataset, up to a multiplicative $(1\\pm\\varepsilon)$ factor and an ","authors_text":"David Saulpic, David Woodruff, Kyriakos Axiotis, Michael Wunder, Monika Henzinger, Sammy Jerome, Vahab Mirrokni, Vincent Cohen-Addad","cross_cats":["cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T09:03:43Z","title":"Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17327","kind":"arxiv","version":1},"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":"sha256:98f472dafa447362ff62315c6a34200713939718797144d47e871aebe101ab98","target":"record","created_at":"2026-07-05T07:49:45Z","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":"d4ebc087157faf4859e15ee4316332029fa9d1b8a7862359c42b44a533a2e0e2","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T09:03:43Z","title_canon_sha256":"8eb56bcfec1b177958d65e50d0a31256b98902764c058c7d2b2c8dd05d96c9e0"},"schema_version":"1.0","source":{"id":"2402.17327","kind":"arxiv","version":1}},"canonical_sha256":"55fbc75762a0f5df6d02f8c2da305c6ed2044ff5cab660f69bf65543e6e69439","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55fbc75762a0f5df6d02f8c2da305c6ed2044ff5cab660f69bf65543e6e69439","first_computed_at":"2026-07-05T07:49:45.457144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:45.457144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JdOnx+iyT2BFnF/A9FipK+eNGTcp1ihCTtegK/e7TVQjFIpTATRVJEwRimad5HxcPKKtJo1iuGPz64rfHJpVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:45.457631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98f472dafa447362ff62315c6a34200713939718797144d47e871aebe101ab98","sha256:e746615a623094521a33de859440e84160d688a7b5420582a3c4aeea0cec2d6c"],"state_sha256":"af63efc2f175aba28e719df044c4b083a8c470660a901fd7bfb13fbe7f8cb96d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJ7Kp2YAXdczwEJ7sG9X+K2mETf9W5ujTRBeyNRjv1codhpApBojpeB85Te9r0y85eWZF+OoAO1eER/FccPYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:58:15.921591Z","bundle_sha256":"4b56e377724a77db08f88705d54b0766bd5debf391bc6be7962f15abad97210b"}}