{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LUFL44LSNPEATFTE7GQFF7KMBO","short_pith_number":"pith:LUFL44LS","schema_version":"1.0","canonical_sha256":"5d0abe71726bc8099664f9a052fd4c0bb42e391aaf807dc74d4700775c402613","source":{"kind":"arxiv","id":"2411.08203","version":1},"attestation_state":"computed","paper":{"title":"FaaS and Furious: abstractions and differential caching for efficient data pre-processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ciro Greco, Jacopo Tagliabue, Ryan Curtin","submitted_at":"2024-11-12T21:50:03Z","abstract_excerpt":"Data pre-processing pipelines are the bread and butter of any successful AI project. We introduce a novel programming model for pipelines in a data lakehouse, allowing users to interact declaratively with assets in object storage. Motivated by real-world industry usage patterns, we exploit these new abstractions with a columnar and differential cache to maximize iteration speed for data scientists, who spent most of their time in pre-processing - adding or removing features, restricting or relaxing time windows, wrangling current or older datasets. We show how the new cache works transparently"},"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":"2411.08203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-11-12T21:50:03Z","cross_cats_sorted":[],"title_canon_sha256":"53b3ad8c08ea4bab792ba98506f3ab3fad1eddd8edc6bb63416670a042e82cc0","abstract_canon_sha256":"d39afc4bba719f08ff978ba2c73a1a2e6b9a6b1c34a53d190264277ec2c96f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:43.277705Z","signature_b64":"NskygCHVSXHaf1n+QnchbXh52QQ5284hcrm7lf7ssMgj3Jx41NUsLA9NhRakYh6S/EXLBV1crbYA8nbaYHoyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0abe71726bc8099664f9a052fd4c0bb42e391aaf807dc74d4700775c402613","last_reissued_at":"2026-07-05T09:34:43.277203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:43.277203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaaS and Furious: abstractions and differential caching for efficient data pre-processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ciro Greco, Jacopo Tagliabue, Ryan Curtin","submitted_at":"2024-11-12T21:50:03Z","abstract_excerpt":"Data pre-processing pipelines are the bread and butter of any successful AI project. We introduce a novel programming model for pipelines in a data lakehouse, allowing users to interact declaratively with assets in object storage. Motivated by real-world industry usage patterns, we exploit these new abstractions with a columnar and differential cache to maximize iteration speed for data scientists, who spent most of their time in pre-processing - adding or removing features, restricting or relaxing time windows, wrangling current or older datasets. We show how the new cache works transparently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08203","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/2411.08203/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":"2411.08203","created_at":"2026-07-05T09:34:43.277262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08203v1","created_at":"2026-07-05T09:34:43.277262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08203","created_at":"2026-07-05T09:34:43.277262+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUFL44LSNPEA","created_at":"2026-07-05T09:34:43.277262+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUFL44LSNPEATFTE","created_at":"2026-07-05T09:34:43.277262+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUFL44LS","created_at":"2026-07-05T09:34:43.277262+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/LUFL44LSNPEATFTE7GQFF7KMBO","json":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO.json","graph_json":"https://pith.science/api/pith-number/LUFL44LSNPEATFTE7GQFF7KMBO/graph.json","events_json":"https://pith.science/api/pith-number/LUFL44LSNPEATFTE7GQFF7KMBO/events.json","paper":"https://pith.science/paper/LUFL44LS"},"agent_actions":{"view_html":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO","download_json":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO.json","view_paper":"https://pith.science/paper/LUFL44LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08203&json=true","fetch_graph":"https://pith.science/api/pith-number/LUFL44LSNPEATFTE7GQFF7KMBO/graph.json","fetch_events":"https://pith.science/api/pith-number/LUFL44LSNPEATFTE7GQFF7KMBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO/action/storage_attestation","attest_author":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO/action/author_attestation","sign_citation":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO/action/citation_signature","submit_replication":"https://pith.science/pith/LUFL44LSNPEATFTE7GQFF7KMBO/action/replication_record"}},"created_at":"2026-07-05T09:34:43.277262+00:00","updated_at":"2026-07-05T09:34:43.277262+00:00"}