{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:N6YE2DBROAS4CMUOWUAPAXMN7O","short_pith_number":"pith:N6YE2DBR","schema_version":"1.0","canonical_sha256":"6fb04d0c317025c1328eb500f05d8dfb83d1b1cb7e26ee11834021f328afc8a7","source":{"kind":"arxiv","id":"1207.2189","version":3},"attestation_state":"computed","paper":{"title":"Reordering Rows for Better Compression: Beyond the Lexicographic Order","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Daniel Lemire, Eduardo Gutarra, Owen Kaser","submitted_at":"2012-07-09T21:47:13Z","abstract_excerpt":"Sorting database tables before compressing them improves the compression rate. Can we do better than the lexicographical order? For minimizing the number of runs in a run-length encoding compression scheme, the best approaches to row-ordering are derived from traveling salesman heuristics, although there is a significant trade-off between running time and compression. A new heuristic, Multiple Lists, which is a variant on Nearest Neighbor that trades off compression for a major running-time speedup, is a good option for very large tables. However, for some compression schemes, it is more impor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1207.2189","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-07-09T21:47:13Z","cross_cats_sorted":[],"title_canon_sha256":"e2f1ec6cf5f438369cc26bc56fbdaebd2eaf2ee7c64c595fcdae07d94b134f48","abstract_canon_sha256":"e009d2c6c16f5244a1849e91523b4b7d678c1288abe311e3c00e20383b61c2ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:00:27.001381Z","signature_b64":"KQTHF1v1TLJxJrYG89ORk6kyGsj8UBOrKHMdns+BNt1B31fiLWlZZt8djB/po8JNf4DwwAK4BxWRfzbJd9prDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fb04d0c317025c1328eb500f05d8dfb83d1b1cb7e26ee11834021f328afc8a7","last_reissued_at":"2026-05-18T03:00:27.000549Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:00:27.000549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reordering Rows for Better Compression: Beyond the Lexicographic Order","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Daniel Lemire, Eduardo Gutarra, Owen Kaser","submitted_at":"2012-07-09T21:47:13Z","abstract_excerpt":"Sorting database tables before compressing them improves the compression rate. Can we do better than the lexicographical order? For minimizing the number of runs in a run-length encoding compression scheme, the best approaches to row-ordering are derived from traveling salesman heuristics, although there is a significant trade-off between running time and compression. A new heuristic, Multiple Lists, which is a variant on Nearest Neighbor that trades off compression for a major running-time speedup, is a good option for very large tables. However, for some compression schemes, it is more impor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.2189","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1207.2189","created_at":"2026-05-18T03:00:27.000649+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.2189v3","created_at":"2026-05-18T03:00:27.000649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.2189","created_at":"2026-05-18T03:00:27.000649+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6YE2DBROAS4","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6YE2DBROAS4CMUO","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6YE2DBR","created_at":"2026-05-18T12:27:16.716162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O","json":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O.json","graph_json":"https://pith.science/api/pith-number/N6YE2DBROAS4CMUOWUAPAXMN7O/graph.json","events_json":"https://pith.science/api/pith-number/N6YE2DBROAS4CMUOWUAPAXMN7O/events.json","paper":"https://pith.science/paper/N6YE2DBR"},"agent_actions":{"view_html":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O","download_json":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O.json","view_paper":"https://pith.science/paper/N6YE2DBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.2189&json=true","fetch_graph":"https://pith.science/api/pith-number/N6YE2DBROAS4CMUOWUAPAXMN7O/graph.json","fetch_events":"https://pith.science/api/pith-number/N6YE2DBROAS4CMUOWUAPAXMN7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O/action/storage_attestation","attest_author":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O/action/author_attestation","sign_citation":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O/action/citation_signature","submit_replication":"https://pith.science/pith/N6YE2DBROAS4CMUOWUAPAXMN7O/action/replication_record"}},"created_at":"2026-05-18T03:00:27.000649+00:00","updated_at":"2026-05-18T03:00:27.000649+00:00"}