{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LUFL44LSNPEATFTE7GQFF7KMBO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d39afc4bba719f08ff978ba2c73a1a2e6b9a6b1c34a53d190264277ec2c96f0f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-11-12T21:50:03Z","title_canon_sha256":"53b3ad8c08ea4bab792ba98506f3ab3fad1eddd8edc6bb63416670a042e82cc0"},"schema_version":"1.0","source":{"id":"2411.08203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08203","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08203v1","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08203","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"LUFL44LSNPEA","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"LUFL44LSNPEATFTE","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"LUFL44LS","created_at":"2026-07-05T09:34:43Z"}],"graph_snapshots":[{"event_id":"sha256:89413aa859f457f15ddefe7450c2366ffaa173a6791332acc241b048e8fe9e44","target":"graph","created_at":"2026-07-05T09:34:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.08203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ciro Greco, Jacopo Tagliabue, Ryan Curtin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-11-12T21:50:03Z","title":"FaaS and Furious: abstractions and differential caching for efficient data pre-processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08203","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2c0c2f20ffcfa225b9ee2ef9d09a0eb0e86c6037a84f22342745f3affe67065a","target":"record","created_at":"2026-07-05T09:34:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d39afc4bba719f08ff978ba2c73a1a2e6b9a6b1c34a53d190264277ec2c96f0f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-11-12T21:50:03Z","title_canon_sha256":"53b3ad8c08ea4bab792ba98506f3ab3fad1eddd8edc6bb63416670a042e82cc0"},"schema_version":"1.0","source":{"id":"2411.08203","kind":"arxiv","version":1}},"canonical_sha256":"5d0abe71726bc8099664f9a052fd4c0bb42e391aaf807dc74d4700775c402613","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d0abe71726bc8099664f9a052fd4c0bb42e391aaf807dc74d4700775c402613","first_computed_at":"2026-07-05T09:34:43.277203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:43.277203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NskygCHVSXHaf1n+QnchbXh52QQ5284hcrm7lf7ssMgj3Jx41NUsLA9NhRakYh6S/EXLBV1crbYA8nbaYHoyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:43.277705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c0c2f20ffcfa225b9ee2ef9d09a0eb0e86c6037a84f22342745f3affe67065a","sha256:89413aa859f457f15ddefe7450c2366ffaa173a6791332acc241b048e8fe9e44"],"state_sha256":"257d2d736ee03921923759c4bb70033d4647271defbe0610d15ccb74d1866762"}