{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CKHA4YFZH744ZHHGIJPS3ZHHJL","short_pith_number":"pith:CKHA4YFZ","schema_version":"1.0","canonical_sha256":"128e0e60b93ff9cc9ce6425f2de4e74ae327bbb717553685cb63ef883876540b","source":{"kind":"arxiv","id":"2112.00833","version":3},"attestation_state":"computed","paper":{"title":"AWESOME: Empowering Scalable Data Science on Social Media Data with an Optimized Tri-Store Data System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Amarnath Gupta, Arun Kumar, Subhasis Dasgupta, Xiuwen Zheng","submitted_at":"2021-12-01T21:24:42Z","abstract_excerpt":"Modern data science applications increasingly use heterogeneous data sources and analytics. This has led to growing interest in polystore systems, especially analytical polystores. In this work, we focus on emerging multi-data model analytics workloads over social media data that fluidly straddle relational, graph, and text analytics. Instead of a generic polystore, we build a \"tri-store\" system that is more aware of the underlying data models to better optimize execution to improve scalability and runtime efficiency. We name our system AWESOME (Analytics WorkbEnch for SOcial MEdia). It featur"},"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":"2112.00833","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-12-01T21:24:42Z","cross_cats_sorted":[],"title_canon_sha256":"54eb3f6e2bd56f97af49077b0d9d2174e6ab1ca2ccd759626bfd4f7db66db9d3","abstract_canon_sha256":"0494bef814a1606a13797f72c21a4a5fbdc389d6f228e6ca5c84a313f90a7f7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:48.608443Z","signature_b64":"jz90fQipfYcb2Zyw1IQ4L0cBBtJulnVrDehogDdHEFa7rj/GQp67TQ6JluA5fS++vnAayFr0udysAH1OsgesDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"128e0e60b93ff9cc9ce6425f2de4e74ae327bbb717553685cb63ef883876540b","last_reissued_at":"2026-07-05T04:40:48.608005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:48.608005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AWESOME: Empowering Scalable Data Science on Social Media Data with an Optimized Tri-Store Data System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Amarnath Gupta, Arun Kumar, Subhasis Dasgupta, Xiuwen Zheng","submitted_at":"2021-12-01T21:24:42Z","abstract_excerpt":"Modern data science applications increasingly use heterogeneous data sources and analytics. This has led to growing interest in polystore systems, especially analytical polystores. In this work, we focus on emerging multi-data model analytics workloads over social media data that fluidly straddle relational, graph, and text analytics. Instead of a generic polystore, we build a \"tri-store\" system that is more aware of the underlying data models to better optimize execution to improve scalability and runtime efficiency. We name our system AWESOME (Analytics WorkbEnch for SOcial MEdia). It featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00833","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/2112.00833/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":"2112.00833","created_at":"2026-07-05T04:40:48.608060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00833v3","created_at":"2026-07-05T04:40:48.608060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00833","created_at":"2026-07-05T04:40:48.608060+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKHA4YFZH744","created_at":"2026-07-05T04:40:48.608060+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKHA4YFZH744ZHHG","created_at":"2026-07-05T04:40:48.608060+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKHA4YFZ","created_at":"2026-07-05T04:40:48.608060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02802","citing_title":"A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL","json":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL.json","graph_json":"https://pith.science/api/pith-number/CKHA4YFZH744ZHHGIJPS3ZHHJL/graph.json","events_json":"https://pith.science/api/pith-number/CKHA4YFZH744ZHHGIJPS3ZHHJL/events.json","paper":"https://pith.science/paper/CKHA4YFZ"},"agent_actions":{"view_html":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL","download_json":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL.json","view_paper":"https://pith.science/paper/CKHA4YFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00833&json=true","fetch_graph":"https://pith.science/api/pith-number/CKHA4YFZH744ZHHGIJPS3ZHHJL/graph.json","fetch_events":"https://pith.science/api/pith-number/CKHA4YFZH744ZHHGIJPS3ZHHJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL/action/storage_attestation","attest_author":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL/action/author_attestation","sign_citation":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL/action/citation_signature","submit_replication":"https://pith.science/pith/CKHA4YFZH744ZHHGIJPS3ZHHJL/action/replication_record"}},"created_at":"2026-07-05T04:40:48.608060+00:00","updated_at":"2026-07-05T04:40:48.608060+00:00"}