{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TE7V6A5WEALWYXKWWJMDRLQ4TZ","short_pith_number":"pith:TE7V6A5W","canonical_record":{"source":{"id":"2304.05028","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-04-11T07:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"3b3eb56992dc8e1283b4fcd3d8b0dcc248476565d7c7e208c02493104a0fa24c","abstract_canon_sha256":"618e549ab92aa2ba34345923b240d0cc6bad33da0c0e31bdf26d6be5270883c7"},"schema_version":"1.0"},"canonical_sha256":"993f5f03b620176c5d56b25838ae1c9e605b4c97bdeafe208dd1269df820560a","source":{"kind":"arxiv","id":"2304.05028","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05028","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05028v3","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05028","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"TE7V6A5WEALW","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"TE7V6A5WEALWYXKW","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"TE7V6A5W","created_at":"2026-07-05T07:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TE7V6A5WEALWYXKWWJMDRLQ4TZ","target":"record","payload":{"canonical_record":{"source":{"id":"2304.05028","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-04-11T07:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"3b3eb56992dc8e1283b4fcd3d8b0dcc248476565d7c7e208c02493104a0fa24c","abstract_canon_sha256":"618e549ab92aa2ba34345923b240d0cc6bad33da0c0e31bdf26d6be5270883c7"},"schema_version":"1.0"},"canonical_sha256":"993f5f03b620176c5d56b25838ae1c9e605b4c97bdeafe208dd1269df820560a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:47.183082Z","signature_b64":"oPuQxne8m9LuSsEH7NkatyH82dVci5oNOkBoIR0OgLryxygvm5wLd4+S4Q8OtQmbB/BHsJ+SkZkzGVVv3ryDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"993f5f03b620176c5d56b25838ae1c9e605b4c97bdeafe208dd1269df820560a","last_reissued_at":"2026-07-05T07:09:47.182570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:47.182570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.05028","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2ZBGh5LIZmQTXicPEevXsvxPDhv1XG5kw64oKDshszOw+kEhKB4jOg/SJmZachblpQ1/3v3yKBGI/56XsPOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:15:52.593941Z"},"content_sha256":"d283574361f352fec9cf4b0d88740a9fbe5291a812d5d2b8190f8a8461b09080","schema_version":"1.0","event_id":"sha256:d283574361f352fec9cf4b0d88740a9fbe5291a812d5d2b8190f8a8461b09080"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TE7V6A5WEALWYXKWWJMDRLQ4TZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Evaluation of Columnar Storage Formats","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrew Pavlo, Huanchen Zhang, Jiahong Shen, Wes McKinney, Xinyu Zeng, Yulong Hui","submitted_at":"2023-04-11T07:34:25Z","abstract_excerpt":"Columnar storage is a core component of a modern data analytics system. Although many database management systems (DBMSs) have proprietary storage formats, most provide extensive support to open-source storage formats such as Parquet and ORC to facilitate cross-platform data sharing. But these formats were developed over a decade ago, in the early 2010s, for the Hadoop ecosystem. Since then, both the hardware and workload landscapes have changed.\n  In this paper, we revisit the most widely adopted open-source columnar storage formats (Parquet and ORC) with a deep dive into their internals. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05028","kind":"arxiv","version":3},"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/2304.05028/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":"2026-07-05T07:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j11o0HF7XFlmIprTGvOJiICQdN+qN/++TlFDKAwCPRDrGb0/oZCpxFZ2sTvUB/Qxb9aBDW6g7VBu+2IWUDiTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:15:52.594589Z"},"content_sha256":"b8b7ec61e8fde6cf938fdc24cf4277ef7dba9d01de0f30167efcb3aa3a17dc38","schema_version":"1.0","event_id":"sha256:b8b7ec61e8fde6cf938fdc24cf4277ef7dba9d01de0f30167efcb3aa3a17dc38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/bundle.json","state_url":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/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":"2026-08-13T19:15:52Z","links":{"resolver":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ","bundle":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/bundle.json","state":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TE7V6A5WEALWYXKWWJMDRLQ4TZ","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":"618e549ab92aa2ba34345923b240d0cc6bad33da0c0e31bdf26d6be5270883c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-04-11T07:34:25Z","title_canon_sha256":"3b3eb56992dc8e1283b4fcd3d8b0dcc248476565d7c7e208c02493104a0fa24c"},"schema_version":"1.0","source":{"id":"2304.05028","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05028","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05028v3","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05028","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"TE7V6A5WEALW","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"TE7V6A5WEALWYXKW","created_at":"2026-07-05T07:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"TE7V6A5W","created_at":"2026-07-05T07:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:b8b7ec61e8fde6cf938fdc24cf4277ef7dba9d01de0f30167efcb3aa3a17dc38","target":"graph","created_at":"2026-07-05T07:09:47Z","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/2304.05028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Columnar storage is a core component of a modern data analytics system. Although many database management systems (DBMSs) have proprietary storage formats, most provide extensive support to open-source storage formats such as Parquet and ORC to facilitate cross-platform data sharing. But these formats were developed over a decade ago, in the early 2010s, for the Hadoop ecosystem. Since then, both the hardware and workload landscapes have changed.\n  In this paper, we revisit the most widely adopted open-source columnar storage formats (Parquet and ORC) with a deep dive into their internals. We ","authors_text":"Andrew Pavlo, Huanchen Zhang, Jiahong Shen, Wes McKinney, Xinyu Zeng, Yulong Hui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-04-11T07:34:25Z","title":"An Empirical Evaluation of Columnar Storage Formats"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05028","kind":"arxiv","version":3},"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:d283574361f352fec9cf4b0d88740a9fbe5291a812d5d2b8190f8a8461b09080","target":"record","created_at":"2026-07-05T07:09:47Z","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":"618e549ab92aa2ba34345923b240d0cc6bad33da0c0e31bdf26d6be5270883c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-04-11T07:34:25Z","title_canon_sha256":"3b3eb56992dc8e1283b4fcd3d8b0dcc248476565d7c7e208c02493104a0fa24c"},"schema_version":"1.0","source":{"id":"2304.05028","kind":"arxiv","version":3}},"canonical_sha256":"993f5f03b620176c5d56b25838ae1c9e605b4c97bdeafe208dd1269df820560a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"993f5f03b620176c5d56b25838ae1c9e605b4c97bdeafe208dd1269df820560a","first_computed_at":"2026-07-05T07:09:47.182570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:47.182570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oPuQxne8m9LuSsEH7NkatyH82dVci5oNOkBoIR0OgLryxygvm5wLd4+S4Q8OtQmbB/BHsJ+SkZkzGVVv3ryDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:47.183082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05028","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d283574361f352fec9cf4b0d88740a9fbe5291a812d5d2b8190f8a8461b09080","sha256:b8b7ec61e8fde6cf938fdc24cf4277ef7dba9d01de0f30167efcb3aa3a17dc38"],"state_sha256":"4885f30ebd18d5c2a3447d1c6032af7d7ea16c69e8a7aca4f4ea163e676e53e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xB3ojrpmPeu/bzzgzaibPGJX3zRHuHOt2yE7vPhKgNQNfsvXF9w29G0mOIld3eWBEgImNcet+wyZ4Xdiw58ECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:15:52.604219Z","bundle_sha256":"527057767f22b9541bf8c7dc64c893f968ebe8b681a15b15843f40e24d3fce18"}}