{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QEDO5S4C6ONVWFLP77PN6GCLGL","short_pith_number":"pith:QEDO5S4C","canonical_record":{"source":{"id":"1703.06476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-19T17:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"ededf2c4a708900f4113512098a9263133553938d21848c20ef9e7df241ec83e","abstract_canon_sha256":"59924536c83025bd584f7bd5b8002f661ec8f84129267fe2d0d96b676e71bd9b"},"schema_version":"1.0"},"canonical_sha256":"8106eecb82f39b5b156fffdedf184b32c06232e2bab5029dbe5304cedda30d95","source":{"kind":"arxiv","id":"1703.06476","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06476","created_at":"2026-05-18T00:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06476v2","created_at":"2026-05-18T00:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06476","created_at":"2026-05-18T00:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"QEDO5S4C6ONV","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QEDO5S4C6ONVWFLP","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QEDO5S4C","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QEDO5S4C6ONVWFLP77PN6GCLGL","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-19T17:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"ededf2c4a708900f4113512098a9263133553938d21848c20ef9e7df241ec83e","abstract_canon_sha256":"59924536c83025bd584f7bd5b8002f661ec8f84129267fe2d0d96b676e71bd9b"},"schema_version":"1.0"},"canonical_sha256":"8106eecb82f39b5b156fffdedf184b32c06232e2bab5029dbe5304cedda30d95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:08.470898Z","signature_b64":"8N75gOrnP7sXPnnPmAlTCNLdjMm3b8UrB3BT76n5Styw1f7s3aqZ+k3jrBbKfrvaUyUZgK6cP+kzsn4j3KbEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8106eecb82f39b5b156fffdedf184b32c06232e2bab5029dbe5304cedda30d95","last_reissued_at":"2026-05-18T00:43:08.470267Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:08.470267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06476","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":"2026-05-18T00:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IaIIiQaWoZ+a1YdRYq6N+5whqgZHjCQUnirm3tFDtDj/sp2OfehPAsob7axu6sqWYyLOn8dxsHNumnCNKrulDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T13:08:51.862933Z"},"content_sha256":"54d2661a36b9c2c059651b3f113823b5b6c66f635ff8c528cfc167d6a5cee390","schema_version":"1.0","event_id":"sha256:54d2661a36b9c2c059651b3f113823b5b6c66f635ff8c528cfc167d6a5cee390"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QEDO5S4C6ONVWFLP77PN6GCLGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical Coreset Constructions for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem","submitted_at":"2017-03-19T17:45:29Z","abstract_excerpt":"We investigate coresets - succinct, small summaries of large data sets - so that solutions found on the summary are provably competitive with solution found on the full data set. We provide an overview over the state-of-the-art in coreset construction for machine learning. In Section 2, we present both the intuition behind and a theoretically sound framework to construct coresets for general problems and apply it to $k$-means clustering. In Section 3 we summarize existing coreset construction algorithms for a variety of machine learning problems such as maximum likelihood estimation of mixture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06476","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":""},"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":"2026-05-18T00:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DBf5cD35u9Mtck9hHwtcHirSEa1jrhvDLoYWU1yJVqtlAWH7xa2BhzHuDYMEcN/QlHUOXGECcLlcEfV8aESXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T13:08:51.863584Z"},"content_sha256":"881abf0b5ec310d0cd201e189d1c8b0fbc8a3238262781b67cb71e6a49332307","schema_version":"1.0","event_id":"sha256:881abf0b5ec310d0cd201e189d1c8b0fbc8a3238262781b67cb71e6a49332307"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/bundle.json","state_url":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/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":"2026-05-22T13:08:51Z","links":{"resolver":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL","bundle":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/bundle.json","state":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QEDO5S4C6ONVWFLP77PN6GCLGL","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":"59924536c83025bd584f7bd5b8002f661ec8f84129267fe2d0d96b676e71bd9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-19T17:45:29Z","title_canon_sha256":"ededf2c4a708900f4113512098a9263133553938d21848c20ef9e7df241ec83e"},"schema_version":"1.0","source":{"id":"1703.06476","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06476","created_at":"2026-05-18T00:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06476v2","created_at":"2026-05-18T00:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06476","created_at":"2026-05-18T00:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"QEDO5S4C6ONV","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QEDO5S4C6ONVWFLP","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QEDO5S4C","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:881abf0b5ec310d0cd201e189d1c8b0fbc8a3238262781b67cb71e6a49332307","target":"graph","created_at":"2026-05-18T00:43:08Z","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"},"paper":{"abstract_excerpt":"We investigate coresets - succinct, small summaries of large data sets - so that solutions found on the summary are provably competitive with solution found on the full data set. We provide an overview over the state-of-the-art in coreset construction for machine learning. In Section 2, we present both the intuition behind and a theoretically sound framework to construct coresets for general problems and apply it to $k$-means clustering. In Section 3 we summarize existing coreset construction algorithms for a variety of machine learning problems such as maximum likelihood estimation of mixture","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-19T17:45:29Z","title":"Practical Coreset Constructions for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06476","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":"sha256:54d2661a36b9c2c059651b3f113823b5b6c66f635ff8c528cfc167d6a5cee390","target":"record","created_at":"2026-05-18T00:43:08Z","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":"59924536c83025bd584f7bd5b8002f661ec8f84129267fe2d0d96b676e71bd9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-19T17:45:29Z","title_canon_sha256":"ededf2c4a708900f4113512098a9263133553938d21848c20ef9e7df241ec83e"},"schema_version":"1.0","source":{"id":"1703.06476","kind":"arxiv","version":2}},"canonical_sha256":"8106eecb82f39b5b156fffdedf184b32c06232e2bab5029dbe5304cedda30d95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8106eecb82f39b5b156fffdedf184b32c06232e2bab5029dbe5304cedda30d95","first_computed_at":"2026-05-18T00:43:08.470267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:08.470267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8N75gOrnP7sXPnnPmAlTCNLdjMm3b8UrB3BT76n5Styw1f7s3aqZ+k3jrBbKfrvaUyUZgK6cP+kzsn4j3KbEBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:08.470898Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06476","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54d2661a36b9c2c059651b3f113823b5b6c66f635ff8c528cfc167d6a5cee390","sha256:881abf0b5ec310d0cd201e189d1c8b0fbc8a3238262781b67cb71e6a49332307"],"state_sha256":"16990572a624d84fe4e72aa5ba8b6d737ac91a4c37bb3f221fd62c18e489e4a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kO9srLMrVb3WU/AWUNYsauyC0jcsHhnwYMTQ/Il+AzYDg1Mq7Uje9/VPeADq1rgr1HXosTkY9xqRop3PvKuVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T13:08:51.866007Z","bundle_sha256":"c8c92f063fe605eea949f7b1ec78100a216efab87063a4178cdc74635576b319"}}