{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CF7L6BB5GDBLQMSROCCMRMP2UL","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":"b2d82590706b542a7d6802425b4d9967aeb8a7be1d46adf3207c8c3ff0bc76d3","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-12-12T06:32:33Z","title_canon_sha256":"f048692568160ddfe3d67fb5d6742c5a8d2cb657c8a351b9a625b588a47b138b"},"schema_version":"1.0","source":{"id":"1512.03880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.03880","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"1512.03880v1","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.03880","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"CF7L6BB5GDBL","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"CF7L6BB5GDBLQMSR","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"CF7L6BB5","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:c54a6ab66a76f3ede4f635dcac239c304661e07ce16e66fac8979bd251ca22a3","target":"graph","created_at":"2026-05-18T01:24:23Z","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":"Recent years have witnessed amazing outcomes from \"Big Models\" trained by \"Big Data\". Most popular algorithms for model training are iterative. Due to the surging volumes of data, we can usually afford to process only a fraction of the training data in each iteration. Typically, the data are either uniformly sampled or sequentially accessed.\n  In this paper, we study how the data access pattern can affect model training. We propose an Active Sampler algorithm, where training data with more \"learning value\" to the model are sampled more frequently. The goal is to focus training effort on valuab","authors_text":"Beng Chin Ooi, H.V.Jagadish, Jinyang Gao","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-12-12T06:32:33Z","title":"Active Sampler: Light-weight Accelerator for Complex Data Analytics at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.03880","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:bf545820618627e8d64bc2b6d61779561afa5d62154d303497f2e75ee2b390a8","target":"record","created_at":"2026-05-18T01:24:23Z","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":"b2d82590706b542a7d6802425b4d9967aeb8a7be1d46adf3207c8c3ff0bc76d3","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-12-12T06:32:33Z","title_canon_sha256":"f048692568160ddfe3d67fb5d6742c5a8d2cb657c8a351b9a625b588a47b138b"},"schema_version":"1.0","source":{"id":"1512.03880","kind":"arxiv","version":1}},"canonical_sha256":"117ebf043d30c2b832517084c8b1faa2fafa9f8e67de77cb7c1f8135e7e23be9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"117ebf043d30c2b832517084c8b1faa2fafa9f8e67de77cb7c1f8135e7e23be9","first_computed_at":"2026-05-18T01:24:23.741398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:23.741398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"avgfJK9JbVNtjHKM1DnQfQ3bJktIzU6etKhlMuQsciy/FFJ+8NM29DIkTzJSNPFPtlFyteV1qWVsn5XjRfn1Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:23.742070Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.03880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf545820618627e8d64bc2b6d61779561afa5d62154d303497f2e75ee2b390a8","sha256:c54a6ab66a76f3ede4f635dcac239c304661e07ce16e66fac8979bd251ca22a3"],"state_sha256":"90d2259155f96c40819ccb97dbb45742c0aff81b65799383b0a5491eb40d750e"}