{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZS33TOMXABPDQD5GNJIQLCPFNN","short_pith_number":"pith:ZS33TOMX","schema_version":"1.0","canonical_sha256":"ccb7b9b997005e380fa66a510589e56b71ef28ca18cfa31aa910d5b38793331d","source":{"kind":"arxiv","id":"2112.06280","version":2},"attestation_state":"computed","paper":{"title":"In-Memory Indexed Caching for Distributed Data Processing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Alexandru Uta, Ankur Dave, Bogdan Ghit, Jan Rellermeyer, Peter Boncz","submitted_at":"2021-12-12T17:09:30Z","abstract_excerpt":"Powerful abstractions such as dataframes are only as efficient as their underlying runtime system. The de-facto distributed data processing framework, Apache Spark, is poorly suited for the modern cloud-based data-science workloads due to its outdated assumptions: static datasets analyzed using coarse-grained transformations. In this paper, we introduce the Indexed DataFrame, an in-memory cache that supports a dataframe abstraction which incorporates indexing capabilities to support fast lookup and join operations. Moreover, it supports appends with multi-version concurrency control. We implem"},"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":"2112.06280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2021-12-12T17:09:30Z","cross_cats_sorted":[],"title_canon_sha256":"a8da089c94b905acae165596245f47ce7e309a16ee28e16e0bc55230745f55b8","abstract_canon_sha256":"d40ac975c187485880cfb4d9adde484a800e10bef4855a71f467b2a5e0a60112"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:43.207701Z","signature_b64":"osVhhC2m83irL0wuITWC8bHJX3ZDAAheErT3hgknZp5GMZgF7jouCE9xyVBw771n9Z6MtRqsmkQqP/wFDb0tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccb7b9b997005e380fa66a510589e56b71ef28ca18cfa31aa910d5b38793331d","last_reissued_at":"2026-07-05T03:54:43.207146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:43.207146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Memory Indexed Caching for Distributed Data Processing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Alexandru Uta, Ankur Dave, Bogdan Ghit, Jan Rellermeyer, Peter Boncz","submitted_at":"2021-12-12T17:09:30Z","abstract_excerpt":"Powerful abstractions such as dataframes are only as efficient as their underlying runtime system. The de-facto distributed data processing framework, Apache Spark, is poorly suited for the modern cloud-based data-science workloads due to its outdated assumptions: static datasets analyzed using coarse-grained transformations. In this paper, we introduce the Indexed DataFrame, an in-memory cache that supports a dataframe abstraction which incorporates indexing capabilities to support fast lookup and join operations. Moreover, it supports appends with multi-version concurrency control. We implem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06280","kind":"arxiv","version":2},"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/2112.06280/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2112.06280","created_at":"2026-07-05T03:54:43.207204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.06280v2","created_at":"2026-07-05T03:54:43.207204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06280","created_at":"2026-07-05T03:54:43.207204+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZS33TOMXABPD","created_at":"2026-07-05T03:54:43.207204+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZS33TOMXABPDQD5G","created_at":"2026-07-05T03:54:43.207204+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZS33TOMX","created_at":"2026-07-05T03:54:43.207204+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/ZS33TOMXABPDQD5GNJIQLCPFNN","json":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN.json","graph_json":"https://pith.science/api/pith-number/ZS33TOMXABPDQD5GNJIQLCPFNN/graph.json","events_json":"https://pith.science/api/pith-number/ZS33TOMXABPDQD5GNJIQLCPFNN/events.json","paper":"https://pith.science/paper/ZS33TOMX"},"agent_actions":{"view_html":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN","download_json":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN.json","view_paper":"https://pith.science/paper/ZS33TOMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.06280&json=true","fetch_graph":"https://pith.science/api/pith-number/ZS33TOMXABPDQD5GNJIQLCPFNN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZS33TOMXABPDQD5GNJIQLCPFNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN/action/storage_attestation","attest_author":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN/action/author_attestation","sign_citation":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN/action/citation_signature","submit_replication":"https://pith.science/pith/ZS33TOMXABPDQD5GNJIQLCPFNN/action/replication_record"}},"created_at":"2026-07-05T03:54:43.207204+00:00","updated_at":"2026-07-05T03:54:43.207204+00:00"}