{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2ATKOXJA7POFHEVG3B6LLF3666","short_pith_number":"pith:2ATKOXJA","schema_version":"1.0","canonical_sha256":"d026a75d20fbdc5392a6d87cb5977ef78fe1478c68ac33cc2393f1b4997a1dc5","source":{"kind":"arxiv","id":"2310.04830","version":1},"attestation_state":"computed","paper":{"title":"Extract-Transform-Load for Video Streams","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.DB","authors_text":"Eugenie Lai, Ferdinand Kossmann, Lei Cao, Nesime Tatbul, Samuel Madden, Tim Kraska, Ziniu Wu","submitted_at":"2023-10-07T14:38:43Z","abstract_excerpt":"Social media, self-driving cars, and traffic cameras produce video streams at large scales and cheap cost. However, storing and querying video at such scales is prohibitively expensive. We propose to treat large-scale video analytics as a data warehousing problem: Video is a format that is easy to produce but needs to be transformed into an application-specific format that is easy to query. Analogously, we define the problem of Video Extract-Transform-Load (V-ETL). V-ETL systems need to reduce the cost of running a user-defined V-ETL job while also giving throughput guarantees to keep up with "},"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":"2310.04830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-10-07T14:38:43Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c0e9eed0f40fdb539c16c899f8c7dac3a4499d784547068ee72a6e30f01db58b","abstract_canon_sha256":"449e6ac6f03f1fca812caa1c4e8c402d3b1961272af775ad5f3b4d1789d1b42b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:06.640984Z","signature_b64":"jue7l0eIEjyXApAdd9feEQ7t9t+bZ2EY4VBE+4sTbVypxxHAWG+o0tJbntOcdaRQN7Zn5RMKK9ustvDaQ7BRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d026a75d20fbdc5392a6d87cb5977ef78fe1478c68ac33cc2393f1b4997a1dc5","last_reissued_at":"2026-07-05T08:34:06.640487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:06.640487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extract-Transform-Load for Video Streams","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.DB","authors_text":"Eugenie Lai, Ferdinand Kossmann, Lei Cao, Nesime Tatbul, Samuel Madden, Tim Kraska, Ziniu Wu","submitted_at":"2023-10-07T14:38:43Z","abstract_excerpt":"Social media, self-driving cars, and traffic cameras produce video streams at large scales and cheap cost. However, storing and querying video at such scales is prohibitively expensive. We propose to treat large-scale video analytics as a data warehousing problem: Video is a format that is easy to produce but needs to be transformed into an application-specific format that is easy to query. Analogously, we define the problem of Video Extract-Transform-Load (V-ETL). V-ETL systems need to reduce the cost of running a user-defined V-ETL job while also giving throughput guarantees to keep up with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04830","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/2310.04830/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":"2310.04830","created_at":"2026-07-05T08:34:06.640552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04830v1","created_at":"2026-07-05T08:34:06.640552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04830","created_at":"2026-07-05T08:34:06.640552+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ATKOXJA7POF","created_at":"2026-07-05T08:34:06.640552+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ATKOXJA7POFHEVG","created_at":"2026-07-05T08:34:06.640552+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ATKOXJA","created_at":"2026-07-05T08:34:06.640552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08923","citing_title":"Mycelium: A Transformation-Embedded LSM-Tree","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666","json":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666.json","graph_json":"https://pith.science/api/pith-number/2ATKOXJA7POFHEVG3B6LLF3666/graph.json","events_json":"https://pith.science/api/pith-number/2ATKOXJA7POFHEVG3B6LLF3666/events.json","paper":"https://pith.science/paper/2ATKOXJA"},"agent_actions":{"view_html":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666","download_json":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666.json","view_paper":"https://pith.science/paper/2ATKOXJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04830&json=true","fetch_graph":"https://pith.science/api/pith-number/2ATKOXJA7POFHEVG3B6LLF3666/graph.json","fetch_events":"https://pith.science/api/pith-number/2ATKOXJA7POFHEVG3B6LLF3666/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666/action/storage_attestation","attest_author":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666/action/author_attestation","sign_citation":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666/action/citation_signature","submit_replication":"https://pith.science/pith/2ATKOXJA7POFHEVG3B6LLF3666/action/replication_record"}},"created_at":"2026-07-05T08:34:06.640552+00:00","updated_at":"2026-07-05T08:34:06.640552+00:00"}