{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6ZGNYH2GKWIPXDQVBJWBXEVXI3","short_pith_number":"pith:6ZGNYH2G","canonical_record":{"source":{"id":"1707.03527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-07-12T03:42:21Z","cross_cats_sorted":[],"title_canon_sha256":"e9329ff861dc2bd152837e3d4c6226b35ffed0c5cc536b889758524a1da92fca","abstract_canon_sha256":"c797661cb174aebbb9b6f5a96c6664f9b4c51493350428a238778962b59c0c0d"},"schema_version":"1.0"},"canonical_sha256":"f64cdc1f465590fb8e150a6c1b92b746eb8c6926db9698fffec605d4ef4e5fc1","source":{"kind":"arxiv","id":"1707.03527","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03527","created_at":"2026-05-18T00:40:25Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03527v1","created_at":"2026-05-18T00:40:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03527","created_at":"2026-05-18T00:40:25Z"},{"alias_kind":"pith_short_12","alias_value":"6ZGNYH2GKWIP","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6ZGNYH2GKWIPXDQV","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6ZGNYH2G","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6ZGNYH2GKWIPXDQVBJWBXEVXI3","target":"record","payload":{"canonical_record":{"source":{"id":"1707.03527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-07-12T03:42:21Z","cross_cats_sorted":[],"title_canon_sha256":"e9329ff861dc2bd152837e3d4c6226b35ffed0c5cc536b889758524a1da92fca","abstract_canon_sha256":"c797661cb174aebbb9b6f5a96c6664f9b4c51493350428a238778962b59c0c0d"},"schema_version":"1.0"},"canonical_sha256":"f64cdc1f465590fb8e150a6c1b92b746eb8c6926db9698fffec605d4ef4e5fc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:25.725175Z","signature_b64":"XfZNiEdnjMj8dCMsCDDr3rkJUUOHUz2891UhIuK2HclmfL595Zk5gQ3YZQi2V+1CeL5AE2csVHWYQBTNzYzrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f64cdc1f465590fb8e150a6c1b92b746eb8c6926db9698fffec605d4ef4e5fc1","last_reissued_at":"2026-05-18T00:40:25.724652Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:25.724652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.03527","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":"2026-05-18T00:40:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sn1trAXD3tmsN664qbc3mayP+hcyW1zQ0BqSdFX7LpdQaK/wuIIhZeYglP2DvKkrcHzxqDpgSlyTCDTEPldQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:37:57.363672Z"},"content_sha256":"4f90c231bcba42325cac25fb9c62e9450f484a55f61dc6e363229a82e2eb7acc","schema_version":"1.0","event_id":"sha256:4f90c231bcba42325cac25fb9c62e9450f484a55f61dc6e363229a82e2eb7acc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6ZGNYH2GKWIPXDQVBJWBXEVXI3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Oseba: Optimization for Selective Bulk Analysis in Big Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jun Wang, Rui Wang","submitted_at":"2017-07-12T03:42:21Z","abstract_excerpt":"Selective bulk analyses, such as statistical learning on temporal/spatial data, are fundamental to a wide range of contemporary data analysis. However, with the increasingly larger data-sets, such as weather data and marketing transactions, the data organization/access becomes more challenging in selective bulk data processing with the use of current big data processing frameworks such as Spark or keyvalue stores. In this paper, we propose a method to optimize selective bulk analysis in big data processing and referred to as Oseba. Oseba maintains a super index for the data organization in mem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03527","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":""},"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":"2026-05-18T00:40:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIJpr7Jf1y+2+bmFiz9Rj9SdtJVOECOj545RM7Hoa8Hcl0mfeb/+BqLzTVZ/yekgVUNmXu1m6x+0LWUpuoEOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:37:57.364020Z"},"content_sha256":"2f527858c7763a3d4ff4c21d0f2969cb7ba4770d73e3958e031c73ef4b26a3df","schema_version":"1.0","event_id":"sha256:2f527858c7763a3d4ff4c21d0f2969cb7ba4770d73e3958e031c73ef4b26a3df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/bundle.json","state_url":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/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":"2026-06-01T10:37:57Z","links":{"resolver":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3","bundle":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/bundle.json","state":"https://pith.science/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ZGNYH2GKWIPXDQVBJWBXEVXI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6ZGNYH2GKWIPXDQVBJWBXEVXI3","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":"c797661cb174aebbb9b6f5a96c6664f9b4c51493350428a238778962b59c0c0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-07-12T03:42:21Z","title_canon_sha256":"e9329ff861dc2bd152837e3d4c6226b35ffed0c5cc536b889758524a1da92fca"},"schema_version":"1.0","source":{"id":"1707.03527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03527","created_at":"2026-05-18T00:40:25Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03527v1","created_at":"2026-05-18T00:40:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03527","created_at":"2026-05-18T00:40:25Z"},{"alias_kind":"pith_short_12","alias_value":"6ZGNYH2GKWIP","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6ZGNYH2GKWIPXDQV","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6ZGNYH2G","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:2f527858c7763a3d4ff4c21d0f2969cb7ba4770d73e3958e031c73ef4b26a3df","target":"graph","created_at":"2026-05-18T00:40:25Z","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"},"paper":{"abstract_excerpt":"Selective bulk analyses, such as statistical learning on temporal/spatial data, are fundamental to a wide range of contemporary data analysis. However, with the increasingly larger data-sets, such as weather data and marketing transactions, the data organization/access becomes more challenging in selective bulk data processing with the use of current big data processing frameworks such as Spark or keyvalue stores. In this paper, we propose a method to optimize selective bulk analysis in big data processing and referred to as Oseba. Oseba maintains a super index for the data organization in mem","authors_text":"Jun Wang, Rui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-07-12T03:42:21Z","title":"Oseba: Optimization for Selective Bulk Analysis in Big Data Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03527","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":"sha256:4f90c231bcba42325cac25fb9c62e9450f484a55f61dc6e363229a82e2eb7acc","target":"record","created_at":"2026-05-18T00:40:25Z","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":"c797661cb174aebbb9b6f5a96c6664f9b4c51493350428a238778962b59c0c0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-07-12T03:42:21Z","title_canon_sha256":"e9329ff861dc2bd152837e3d4c6226b35ffed0c5cc536b889758524a1da92fca"},"schema_version":"1.0","source":{"id":"1707.03527","kind":"arxiv","version":1}},"canonical_sha256":"f64cdc1f465590fb8e150a6c1b92b746eb8c6926db9698fffec605d4ef4e5fc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f64cdc1f465590fb8e150a6c1b92b746eb8c6926db9698fffec605d4ef4e5fc1","first_computed_at":"2026-05-18T00:40:25.724652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:25.724652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XfZNiEdnjMj8dCMsCDDr3rkJUUOHUz2891UhIuK2HclmfL595Zk5gQ3YZQi2V+1CeL5AE2csVHWYQBTNzYzrCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:25.725175Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.03527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f90c231bcba42325cac25fb9c62e9450f484a55f61dc6e363229a82e2eb7acc","sha256:2f527858c7763a3d4ff4c21d0f2969cb7ba4770d73e3958e031c73ef4b26a3df"],"state_sha256":"1334d130f3d337448c6d0058d30959c95f00128cc687ebb59a09afeafb9fd4ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Ps6eyg14CY28be/Tgkc2Nc/yqc8ZeQdTL9x4BDFX8i2//wM4X6kcmUo1jewc86r5LHb+mvcL/qP6z1VnRwYCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T10:37:57.365952Z","bundle_sha256":"582494a18bb25bdc50cc893d3824b7fe837ed2faa6b00150e0314ae7f18a76f6"}}