{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RZUH4B37N47YBVY5GK55FFXAJV","short_pith_number":"pith:RZUH4B37","canonical_record":{"source":{"id":"1906.11289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T18:27:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1c527b3febbec2f92d848d2c0f51f315e9a00b04ddac38f8fb686fa0df18328f","abstract_canon_sha256":"68e371412480fe66dc464993503fb99db0b392cb604a0c041389a491481325a2"},"schema_version":"1.0"},"canonical_sha256":"8e687e077f6f3f80d71d32bbd296e04d5a85a85d589399e5af4aca2c6ff0bb9f","source":{"kind":"arxiv","id":"1906.11289","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11289","created_at":"2026-05-17T23:39:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11289v2","created_at":"2026-05-17T23:39:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11289","created_at":"2026-05-17T23:39:29Z"},{"alias_kind":"pith_short_12","alias_value":"RZUH4B37N47Y","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RZUH4B37N47YBVY5","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RZUH4B37","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RZUH4B37N47YBVY5GK55FFXAJV","target":"record","payload":{"canonical_record":{"source":{"id":"1906.11289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T18:27:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1c527b3febbec2f92d848d2c0f51f315e9a00b04ddac38f8fb686fa0df18328f","abstract_canon_sha256":"68e371412480fe66dc464993503fb99db0b392cb604a0c041389a491481325a2"},"schema_version":"1.0"},"canonical_sha256":"8e687e077f6f3f80d71d32bbd296e04d5a85a85d589399e5af4aca2c6ff0bb9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:29.994971Z","signature_b64":"WDt4ZENpsud4tAfCITMrdglV6EXxaCIJU/ESDbmDjU7iFfwnRsDlOZSUBWlIslez5tEx3bcSM8t7I0yjUWlqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e687e077f6f3f80d71d32bbd296e04d5a85a85d589399e5af4aca2c6ff0bb9f","last_reissued_at":"2026-05-17T23:39:29.994408Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:29.994408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.11289","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":"2026-05-17T23:39:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R81oYsl22TegFgdkmjzdO6adV+m43g85ctl0wCPBsfdnDsBqk3e/6Ekd41wZcWNc+2+lGVeITmUC/ksznGreAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T10:20:03.498919Z"},"content_sha256":"1438909fadea3b36557ea6457d6a5ff4c670cf3f48494bcdd4e2b5b1b255a2c9","schema_version":"1.0","event_id":"sha256:1438909fadea3b36557ea6457d6a5ff4c670cf3f48494bcdd4e2b5b1b255a2c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RZUH4B37N47YBVY5GK55FFXAJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near Optimal Stratified Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Suvrit Sra, Tiancheng Yu, Xiyu Zhai","submitted_at":"2019-06-26T18:27:31Z","abstract_excerpt":"The performance of a machine learning system is usually evaluated by using i.i.d.\\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaining unlabeled samples may be cheaper. Stratified sampling can be beneficial in such settings and can reduce the number of true labels required without compromising the evaluation accuracy. Stratified sampling exploits statistical properties (e.g., variance) across strata of the unlabeled population, though usually under the unrealistic assumption that these properties are known. We propose two new algorithms that simu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11289","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":"2026-05-17T23:39:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A85X+vpzMZb2TF00NpsbcjZ+0vmhTMYNE5m8TSs6YwVlX0BQ5y6wc3+fGjZ5EEBHT6gERPVr4po5os+NeBmQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T10:20:03.499254Z"},"content_sha256":"c29527e45d11985205cd6283817bafe79d30b8e3011c4760b25a7f6a9938b4f8","schema_version":"1.0","event_id":"sha256:c29527e45d11985205cd6283817bafe79d30b8e3011c4760b25a7f6a9938b4f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZUH4B37N47YBVY5GK55FFXAJV/bundle.json","state_url":"https://pith.science/pith/RZUH4B37N47YBVY5GK55FFXAJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZUH4B37N47YBVY5GK55FFXAJV/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":"2026-06-28T10:20:03Z","links":{"resolver":"https://pith.science/pith/RZUH4B37N47YBVY5GK55FFXAJV","bundle":"https://pith.science/pith/RZUH4B37N47YBVY5GK55FFXAJV/bundle.json","state":"https://pith.science/pith/RZUH4B37N47YBVY5GK55FFXAJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZUH4B37N47YBVY5GK55FFXAJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RZUH4B37N47YBVY5GK55FFXAJV","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":"68e371412480fe66dc464993503fb99db0b392cb604a0c041389a491481325a2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T18:27:31Z","title_canon_sha256":"1c527b3febbec2f92d848d2c0f51f315e9a00b04ddac38f8fb686fa0df18328f"},"schema_version":"1.0","source":{"id":"1906.11289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11289","created_at":"2026-05-17T23:39:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11289v2","created_at":"2026-05-17T23:39:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11289","created_at":"2026-05-17T23:39:29Z"},{"alias_kind":"pith_short_12","alias_value":"RZUH4B37N47Y","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RZUH4B37N47YBVY5","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RZUH4B37","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:c29527e45d11985205cd6283817bafe79d30b8e3011c4760b25a7f6a9938b4f8","target":"graph","created_at":"2026-05-17T23:39:29Z","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":"The performance of a machine learning system is usually evaluated by using i.i.d.\\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaining unlabeled samples may be cheaper. Stratified sampling can be beneficial in such settings and can reduce the number of true labels required without compromising the evaluation accuracy. Stratified sampling exploits statistical properties (e.g., variance) across strata of the unlabeled population, though usually under the unrealistic assumption that these properties are known. We propose two new algorithms that simu","authors_text":"Suvrit Sra, Tiancheng Yu, Xiyu Zhai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T18:27:31Z","title":"Near Optimal Stratified Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11289","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":"sha256:1438909fadea3b36557ea6457d6a5ff4c670cf3f48494bcdd4e2b5b1b255a2c9","target":"record","created_at":"2026-05-17T23:39:29Z","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":"68e371412480fe66dc464993503fb99db0b392cb604a0c041389a491481325a2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T18:27:31Z","title_canon_sha256":"1c527b3febbec2f92d848d2c0f51f315e9a00b04ddac38f8fb686fa0df18328f"},"schema_version":"1.0","source":{"id":"1906.11289","kind":"arxiv","version":2}},"canonical_sha256":"8e687e077f6f3f80d71d32bbd296e04d5a85a85d589399e5af4aca2c6ff0bb9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e687e077f6f3f80d71d32bbd296e04d5a85a85d589399e5af4aca2c6ff0bb9f","first_computed_at":"2026-05-17T23:39:29.994408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:29.994408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WDt4ZENpsud4tAfCITMrdglV6EXxaCIJU/ESDbmDjU7iFfwnRsDlOZSUBWlIslez5tEx3bcSM8t7I0yjUWlqDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:29.994971Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.11289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1438909fadea3b36557ea6457d6a5ff4c670cf3f48494bcdd4e2b5b1b255a2c9","sha256:c29527e45d11985205cd6283817bafe79d30b8e3011c4760b25a7f6a9938b4f8"],"state_sha256":"d98792e33afda1f9c27cc3df1f8d1914731d93a27d1de8af55c78006bc5834c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGzGZ9G3DgNk57Sdr4NqHcxLmuKfp/RqLQ+tDftqqXd1YclKZL7wgxtXboLVTlWi/UQhjoch364o2C1xePwfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T10:20:03.501102Z","bundle_sha256":"0dd5f243510ed1fb61b199dfe14917e8ae73ce14a7550e3f7a9eb30cb47b805f"}}