{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:SQTT7ML6MOBFIUJL6WKXKZHZPJ","short_pith_number":"pith:SQTT7ML6","canonical_record":{"source":{"id":"1007.1032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2010-07-07T01:24:41Z","cross_cats_sorted":[],"title_canon_sha256":"068b88d96a13d4ec3b8e46a2332cbaf780e225b6fb2bb5109eb07ddcb3a5a153","abstract_canon_sha256":"78cfeee8865fc27c83840e4b7eae3715c9c56d8cee62bb1598ad98617e69719e"},"schema_version":"1.0"},"canonical_sha256":"94273fb17e638254512bf5957564f97a6bb30689e348054af09418672a4354bc","source":{"kind":"arxiv","id":"1007.1032","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1007.1032","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"arxiv_version","alias_value":"1007.1032v1","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1007.1032","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"pith_short_12","alias_value":"SQTT7ML6MOBF","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"pith_short_16","alias_value":"SQTT7ML6MOBFIUJL","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"pith_short_8","alias_value":"SQTT7ML6","created_at":"2026-07-04T17:31:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:SQTT7ML6MOBFIUJL6WKXKZHZPJ","target":"record","payload":{"canonical_record":{"source":{"id":"1007.1032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2010-07-07T01:24:41Z","cross_cats_sorted":[],"title_canon_sha256":"068b88d96a13d4ec3b8e46a2332cbaf780e225b6fb2bb5109eb07ddcb3a5a153","abstract_canon_sha256":"78cfeee8865fc27c83840e4b7eae3715c9c56d8cee62bb1598ad98617e69719e"},"schema_version":"1.0"},"canonical_sha256":"94273fb17e638254512bf5957564f97a6bb30689e348054af09418672a4354bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T17:31:25.077967Z","signature_b64":"f5PY7bBkNYWTQoi+LkYLj4AB2k8DFq6rkVgts59pzrYMBIAcSY/leMe1CemtIyL5IptC1wN545awk//tByVlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94273fb17e638254512bf5957564f97a6bb30689e348054af09418672a4354bc","last_reissued_at":"2026-07-04T17:31:25.077593Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T17:31:25.077593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1007.1032","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":"2026-07-04T17:31:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uMIpz2x/UaNNBi4kY2dMQsA7/in1ZF46+ZM2G+ipm6VN7MoAUbryywXDyPdUiy+s1vo5O7IVNc8FpMtr4vCZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T08:34:06.073823Z"},"content_sha256":"f90ee15d8f4a62cbd46839f13717f82c58d292140d1d10f6556cb86ce62498c8","schema_version":"1.0","event_id":"sha256:f90ee15d8f4a62cbd46839f13717f82c58d292140d1d10f6556cb86ce62498c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:SQTT7ML6MOBFIUJL6WKXKZHZPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximating quantiles in very large datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Reza Hosseini","submitted_at":"2010-07-07T01:24:41Z","abstract_excerpt":"Very large datasets are often encountered in climatology, either from a multiplicity of observations over time and space or outputs from deterministic models (sometimes in petabytes= 1 million gigabytes). Loading a large data vector and sorting it, is impossible sometimes due to memory limitations or computing power. We show that a proposed algorithm to approximating the median, \"the median of the median\" performs poorly. Instead we develop an algorithm to approximate quantiles of very large datasets which works by partitioning the data or use existing partitions (possibly of non-equal size). "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1007.1032","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/1007.1032/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":"2026-07-04T17:31:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JpUcksMVs9PM/NLpcpeHWIzRPEzOuTnic5VZaaZID+3ShHiNbjT8pzB05Esnmb9JjIsJd+DOLvD6IROEsT1JDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T08:34:06.074194Z"},"content_sha256":"8b5fe15c66077176514ca4076c39de82f1fe55e2e6b518d4622ed75f59923e21","schema_version":"1.0","event_id":"sha256:8b5fe15c66077176514ca4076c39de82f1fe55e2e6b518d4622ed75f59923e21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQTT7ML6MOBFIUJL6WKXKZHZPJ/bundle.json","state_url":"https://pith.science/pith/SQTT7ML6MOBFIUJL6WKXKZHZPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQTT7ML6MOBFIUJL6WKXKZHZPJ/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":"2026-07-05T08:34:06Z","links":{"resolver":"https://pith.science/pith/SQTT7ML6MOBFIUJL6WKXKZHZPJ","bundle":"https://pith.science/pith/SQTT7ML6MOBFIUJL6WKXKZHZPJ/bundle.json","state":"https://pith.science/pith/SQTT7ML6MOBFIUJL6WKXKZHZPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQTT7ML6MOBFIUJL6WKXKZHZPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:SQTT7ML6MOBFIUJL6WKXKZHZPJ","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":"78cfeee8865fc27c83840e4b7eae3715c9c56d8cee62bb1598ad98617e69719e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2010-07-07T01:24:41Z","title_canon_sha256":"068b88d96a13d4ec3b8e46a2332cbaf780e225b6fb2bb5109eb07ddcb3a5a153"},"schema_version":"1.0","source":{"id":"1007.1032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1007.1032","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"arxiv_version","alias_value":"1007.1032v1","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1007.1032","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"pith_short_12","alias_value":"SQTT7ML6MOBF","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"pith_short_16","alias_value":"SQTT7ML6MOBFIUJL","created_at":"2026-07-04T17:31:25Z"},{"alias_kind":"pith_short_8","alias_value":"SQTT7ML6","created_at":"2026-07-04T17:31:25Z"}],"graph_snapshots":[{"event_id":"sha256:8b5fe15c66077176514ca4076c39de82f1fe55e2e6b518d4622ed75f59923e21","target":"graph","created_at":"2026-07-04T17:31:25Z","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/1007.1032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Very large datasets are often encountered in climatology, either from a multiplicity of observations over time and space or outputs from deterministic models (sometimes in petabytes= 1 million gigabytes). Loading a large data vector and sorting it, is impossible sometimes due to memory limitations or computing power. We show that a proposed algorithm to approximating the median, \"the median of the median\" performs poorly. Instead we develop an algorithm to approximate quantiles of very large datasets which works by partitioning the data or use existing partitions (possibly of non-equal size). ","authors_text":"Reza Hosseini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2010-07-07T01:24:41Z","title":"Approximating quantiles in very large datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1007.1032","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:f90ee15d8f4a62cbd46839f13717f82c58d292140d1d10f6556cb86ce62498c8","target":"record","created_at":"2026-07-04T17:31:25Z","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":"78cfeee8865fc27c83840e4b7eae3715c9c56d8cee62bb1598ad98617e69719e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2010-07-07T01:24:41Z","title_canon_sha256":"068b88d96a13d4ec3b8e46a2332cbaf780e225b6fb2bb5109eb07ddcb3a5a153"},"schema_version":"1.0","source":{"id":"1007.1032","kind":"arxiv","version":1}},"canonical_sha256":"94273fb17e638254512bf5957564f97a6bb30689e348054af09418672a4354bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94273fb17e638254512bf5957564f97a6bb30689e348054af09418672a4354bc","first_computed_at":"2026-07-04T17:31:25.077593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T17:31:25.077593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f5PY7bBkNYWTQoi+LkYLj4AB2k8DFq6rkVgts59pzrYMBIAcSY/leMe1CemtIyL5IptC1wN545awk//tByVlDg==","signature_status":"signed_v1","signed_at":"2026-07-04T17:31:25.077967Z","signed_message":"canonical_sha256_bytes"},"source_id":"1007.1032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f90ee15d8f4a62cbd46839f13717f82c58d292140d1d10f6556cb86ce62498c8","sha256:8b5fe15c66077176514ca4076c39de82f1fe55e2e6b518d4622ed75f59923e21"],"state_sha256":"4b4ebcb2693d541b3e518b8c502d46f0749f55dd2d86d26bc17752eeb6f87307"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfTU6UNGtrF5JAZrqwqQAwQI1Ens1He+i08SV+fYQudKf3HXFn0ILKER2lLpeXb0e2Ku1dhL2n0oNs2QZOyBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T08:34:06.076208Z","bundle_sha256":"f472299a7d3ac8f1f97b545da7cdbf98a717cafc156fb944fec78a10f59b611f"}}