{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RKTJIRACN23ESGNCLL52MRQNKP","short_pith_number":"pith:RKTJIRAC","schema_version":"1.0","canonical_sha256":"8aa69444026eb64919a25afba6460d53cf73673bc79b2172564fe90af3e5d655","source":{"kind":"arxiv","id":"2209.10785","version":2},"attestation_state":"computed","paper":{"title":"Deep Lake: a Lakehouse for Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.DB"],"primary_cat":"cs.DC","authors_text":"Abhinav Tuli, David Isayan, Davit Buniatyan, Fariz Rahman, Hrant Topchyan, Ivo Stranic, Levon Ghukasyan, Mark McQuade, Mikayel Harutyunyan, Sasun Hambardzumyan, Tatevik Hakobyan","submitted_at":"2022-09-22T05:04:09Z","abstract_excerpt":"Traditional data lakes provide critical data infrastructure for analytical workloads by enabling time travel, running SQL queries, ingesting data with ACID transactions, and visualizing petabyte-scale datasets on cloud storage. They allow organizations to break down data silos, unlock data-driven decision-making, improve operational efficiency, and reduce costs. However, as deep learning usage increases, traditional data lakes are not well-designed for applications such as natural language processing (NLP), audio processing, computer vision, and applications involving non-tabular datasets. Thi"},"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":"2209.10785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-09-22T05:04:09Z","cross_cats_sorted":["cs.AI","cs.CV","cs.DB"],"title_canon_sha256":"312e365c6c94f880524125b540bb9e5c0c738a22dcc1c10e1f71b601250cf442","abstract_canon_sha256":"bab80e89aa374b9b4ffc0fb8a6d1550e0e09153264b11b9f953ec1616a93001d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:16.617615Z","signature_b64":"F+BZn1kb2xd1ObHYUW/KX2aqbEAGmVsDNX4YQaSnH0o27YA4TFtMVoeq5tYW13gHZzk3bP0ZrruLjjUtm6fVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aa69444026eb64919a25afba6460d53cf73673bc79b2172564fe90af3e5d655","last_reissued_at":"2026-07-05T05:25:16.617166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:16.617166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Lake: a Lakehouse for Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.DB"],"primary_cat":"cs.DC","authors_text":"Abhinav Tuli, David Isayan, Davit Buniatyan, Fariz Rahman, Hrant Topchyan, Ivo Stranic, Levon Ghukasyan, Mark McQuade, Mikayel Harutyunyan, Sasun Hambardzumyan, Tatevik Hakobyan","submitted_at":"2022-09-22T05:04:09Z","abstract_excerpt":"Traditional data lakes provide critical data infrastructure for analytical workloads by enabling time travel, running SQL queries, ingesting data with ACID transactions, and visualizing petabyte-scale datasets on cloud storage. They allow organizations to break down data silos, unlock data-driven decision-making, improve operational efficiency, and reduce costs. However, as deep learning usage increases, traditional data lakes are not well-designed for applications such as natural language processing (NLP), audio processing, computer vision, and applications involving non-tabular datasets. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10785","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/2209.10785/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":"2209.10785","created_at":"2026-07-05T05:25:16.617223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10785v2","created_at":"2026-07-05T05:25:16.617223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10785","created_at":"2026-07-05T05:25:16.617223+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKTJIRACN23E","created_at":"2026-07-05T05:25:16.617223+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKTJIRACN23ESGNC","created_at":"2026-07-05T05:25:16.617223+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKTJIRAC","created_at":"2026-07-05T05:25:16.617223+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/RKTJIRACN23ESGNCLL52MRQNKP","json":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP.json","graph_json":"https://pith.science/api/pith-number/RKTJIRACN23ESGNCLL52MRQNKP/graph.json","events_json":"https://pith.science/api/pith-number/RKTJIRACN23ESGNCLL52MRQNKP/events.json","paper":"https://pith.science/paper/RKTJIRAC"},"agent_actions":{"view_html":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP","download_json":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP.json","view_paper":"https://pith.science/paper/RKTJIRAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10785&json=true","fetch_graph":"https://pith.science/api/pith-number/RKTJIRACN23ESGNCLL52MRQNKP/graph.json","fetch_events":"https://pith.science/api/pith-number/RKTJIRACN23ESGNCLL52MRQNKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP/action/storage_attestation","attest_author":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP/action/author_attestation","sign_citation":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP/action/citation_signature","submit_replication":"https://pith.science/pith/RKTJIRACN23ESGNCLL52MRQNKP/action/replication_record"}},"created_at":"2026-07-05T05:25:16.617223+00:00","updated_at":"2026-07-05T05:25:16.617223+00:00"}