{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3JEVIF4ZY4DZQWXAL5EETZTZ72","short_pith_number":"pith:3JEVIF4Z","canonical_record":{"source":{"id":"2111.11517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-11-22T20:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"71b18331ee553303871e47ff22467e2f1ff5f5d40321a555dd47e92b2dd6f6bd","abstract_canon_sha256":"085bf1d0c872ea67d4a038da4f0b80c222f9acbb17fb20df520515170f0c66af"},"schema_version":"1.0"},"canonical_sha256":"da49541799c707985ae05f4849e679fe80dac2fc6ec40fdd55f206c31eba7668","source":{"kind":"arxiv","id":"2111.11517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11517","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11517v1","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11517","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"3JEVIF4ZY4DZ","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"3JEVIF4ZY4DZQWXA","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"3JEVIF4Z","created_at":"2026-07-05T03:34:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3JEVIF4ZY4DZQWXAL5EETZTZ72","target":"record","payload":{"canonical_record":{"source":{"id":"2111.11517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-11-22T20:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"71b18331ee553303871e47ff22467e2f1ff5f5d40321a555dd47e92b2dd6f6bd","abstract_canon_sha256":"085bf1d0c872ea67d4a038da4f0b80c222f9acbb17fb20df520515170f0c66af"},"schema_version":"1.0"},"canonical_sha256":"da49541799c707985ae05f4849e679fe80dac2fc6ec40fdd55f206c31eba7668","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:09.849448Z","signature_b64":"YE/a3CXKXolodaExGMjSN+U05rj5mY86PmywjKjJ5onLemmsZveePA8vGDPFOH/4DIkfNH/6jA1pv4x9ywyTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da49541799c707985ae05f4849e679fe80dac2fc6ec40fdd55f206c31eba7668","last_reissued_at":"2026-07-05T03:34:09.848984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:09.848984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.11517","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":"2026-07-05T03:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+03KeUfl55TnKjEk3+YuySk0Tmh3wLwgHJyjAkH1lpT5vghF9Wd/fL0vLrtruc132E4Uew906tXxtm2cF+uDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:08:47.735882Z"},"content_sha256":"1ea50df9e1f8468c23589d6cc06868abd1426b37177086760d297fed8c29fc01","schema_version":"1.0","event_id":"sha256:1ea50df9e1f8468c23589d6cc06868abd1426b37177086760d297fed8c29fc01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3JEVIF4ZY4DZQWXAL5EETZTZ72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Columnar Formats for Schemaless LSM-based Document Stores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Michael J. Carey, Wail Y. Alkowaileet","submitted_at":"2021-11-22T20:28:59Z","abstract_excerpt":"In the last decade, document store database systems have gained more traction for storing and querying large volumes of semi-structured data. However, the flexibility of the document stores' data models has limited their ability to store data in a columnar-major layout - making them less performant for analytical workloads than column store relational databases. In this paper, we propose several techniques based on piggy-backing on Log-Structured Merge (LSM) tree events and tailored to document stores to store document data in a columnar layout. We first extend the Dremel format, a popular on-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11517","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/2111.11517/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":"2026-07-05T03:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"atKdCoN+aNe6Vop4/7taMybt/5ReZfWu3yqlaPd7ATCjBAoUg6/IhRw5Xqe1St5Go+QkN8FBbPl0hv0mfgl+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:08:47.737116Z"},"content_sha256":"b269dbac9b43c84e8d171500bdf523d96ab844d45f6f9d01108582407b7df02a","schema_version":"1.0","event_id":"sha256:b269dbac9b43c84e8d171500bdf523d96ab844d45f6f9d01108582407b7df02a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JEVIF4ZY4DZQWXAL5EETZTZ72/bundle.json","state_url":"https://pith.science/pith/3JEVIF4ZY4DZQWXAL5EETZTZ72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JEVIF4ZY4DZQWXAL5EETZTZ72/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":"2026-08-13T11:08:47Z","links":{"resolver":"https://pith.science/pith/3JEVIF4ZY4DZQWXAL5EETZTZ72","bundle":"https://pith.science/pith/3JEVIF4ZY4DZQWXAL5EETZTZ72/bundle.json","state":"https://pith.science/pith/3JEVIF4ZY4DZQWXAL5EETZTZ72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JEVIF4ZY4DZQWXAL5EETZTZ72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3JEVIF4ZY4DZQWXAL5EETZTZ72","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":"085bf1d0c872ea67d4a038da4f0b80c222f9acbb17fb20df520515170f0c66af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-11-22T20:28:59Z","title_canon_sha256":"71b18331ee553303871e47ff22467e2f1ff5f5d40321a555dd47e92b2dd6f6bd"},"schema_version":"1.0","source":{"id":"2111.11517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11517","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11517v1","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11517","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"3JEVIF4ZY4DZ","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"3JEVIF4ZY4DZQWXA","created_at":"2026-07-05T03:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"3JEVIF4Z","created_at":"2026-07-05T03:34:09Z"}],"graph_snapshots":[{"event_id":"sha256:b269dbac9b43c84e8d171500bdf523d96ab844d45f6f9d01108582407b7df02a","target":"graph","created_at":"2026-07-05T03:34:09Z","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/2111.11517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the last decade, document store database systems have gained more traction for storing and querying large volumes of semi-structured data. However, the flexibility of the document stores' data models has limited their ability to store data in a columnar-major layout - making them less performant for analytical workloads than column store relational databases. In this paper, we propose several techniques based on piggy-backing on Log-Structured Merge (LSM) tree events and tailored to document stores to store document data in a columnar layout. We first extend the Dremel format, a popular on-","authors_text":"Michael J. Carey, Wail Y. Alkowaileet","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-11-22T20:28:59Z","title":"Columnar Formats for Schemaless LSM-based Document Stores"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11517","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":"sha256:1ea50df9e1f8468c23589d6cc06868abd1426b37177086760d297fed8c29fc01","target":"record","created_at":"2026-07-05T03:34:09Z","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":"085bf1d0c872ea67d4a038da4f0b80c222f9acbb17fb20df520515170f0c66af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-11-22T20:28:59Z","title_canon_sha256":"71b18331ee553303871e47ff22467e2f1ff5f5d40321a555dd47e92b2dd6f6bd"},"schema_version":"1.0","source":{"id":"2111.11517","kind":"arxiv","version":1}},"canonical_sha256":"da49541799c707985ae05f4849e679fe80dac2fc6ec40fdd55f206c31eba7668","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da49541799c707985ae05f4849e679fe80dac2fc6ec40fdd55f206c31eba7668","first_computed_at":"2026-07-05T03:34:09.848984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:09.848984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YE/a3CXKXolodaExGMjSN+U05rj5mY86PmywjKjJ5onLemmsZveePA8vGDPFOH/4DIkfNH/6jA1pv4x9ywyTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:09.849448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.11517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ea50df9e1f8468c23589d6cc06868abd1426b37177086760d297fed8c29fc01","sha256:b269dbac9b43c84e8d171500bdf523d96ab844d45f6f9d01108582407b7df02a"],"state_sha256":"5ef2b97918c94048a9781f3f5dddb595fb34fa23753d6d86193dc4420fb7574b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i5uTfe2jrcqZc9ysDjdMPKvJp9/uNuaebsFaXJuLZJ7QEJg1VMI4+oYbvVVN3L9bmdQDOdAvf+zXxs0HCN7/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T11:08:47.744071Z","bundle_sha256":"6d6b95553a2647d2f81b4543948dceaca9246d43e8646f9ef8ed8488b9c38fa0"}}