{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QEZUQRSMDFIRLAND7AZ6GDLGZL","short_pith_number":"pith:QEZUQRSM","schema_version":"1.0","canonical_sha256":"813348464c19511581a3f833e30d66cae777a10a36d6ccdd04faee30d33f7b68","source":{"kind":"arxiv","id":"2303.11761","version":1},"attestation_state":"computed","paper":{"title":"Reasonable Scale Machine Learning with Open-Source Metaflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SE"],"primary_cat":"cs.LG","authors_text":"David Berg, Hugo Bowne-Anderson, Jacopo Tagliabue, Romain Cledat, Savin Goyal, Ville Tuulos","submitted_at":"2023-03-21T11:28:09Z","abstract_excerpt":"As Machine Learning (ML) gains adoption across industries and new use cases, practitioners increasingly realize the challenges around effectively developing and iterating on ML systems: reproducibility, debugging, scalability, and documentation are elusive goals for real-world pipelines outside tech-first companies. In this paper, we review the nature of ML-oriented workloads and argue that re-purposing existing tools won't solve the current productivity issues, as ML peculiarities warrant specialized development tooling. We then introduce Metaflow, an open-source framework for ML projects exp"},"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":"2303.11761","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-21T11:28:09Z","cross_cats_sorted":["cs.DC","cs.SE"],"title_canon_sha256":"34d34b2b003ba402eef444e441ef422b3d0da7ff160dd81718afa7f7cde088db","abstract_canon_sha256":"ef63e6c46aa4ddc2934d8476450d30ae4ae0e2cbed6811941b63d92c3ab87cb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:21.996757Z","signature_b64":"m7oO16A/fwwkcY6aKtuhBe2gxUm6Do0MxLW+VW92DJo5v95IR79TmLv3hU2XUfRjpA7p3msyYzoyPGeUThfGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813348464c19511581a3f833e30d66cae777a10a36d6ccdd04faee30d33f7b68","last_reissued_at":"2026-07-05T05:53:21.996276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:21.996276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasonable Scale Machine Learning with Open-Source Metaflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SE"],"primary_cat":"cs.LG","authors_text":"David Berg, Hugo Bowne-Anderson, Jacopo Tagliabue, Romain Cledat, Savin Goyal, Ville Tuulos","submitted_at":"2023-03-21T11:28:09Z","abstract_excerpt":"As Machine Learning (ML) gains adoption across industries and new use cases, practitioners increasingly realize the challenges around effectively developing and iterating on ML systems: reproducibility, debugging, scalability, and documentation are elusive goals for real-world pipelines outside tech-first companies. In this paper, we review the nature of ML-oriented workloads and argue that re-purposing existing tools won't solve the current productivity issues, as ML peculiarities warrant specialized development tooling. We then introduce Metaflow, an open-source framework for ML projects exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11761","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/2303.11761/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":"2303.11761","created_at":"2026-07-05T05:53:21.996343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11761v1","created_at":"2026-07-05T05:53:21.996343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11761","created_at":"2026-07-05T05:53:21.996343+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEZUQRSMDFIR","created_at":"2026-07-05T05:53:21.996343+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEZUQRSMDFIRLAND","created_at":"2026-07-05T05:53:21.996343+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEZUQRSM","created_at":"2026-07-05T05:53:21.996343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08203","citing_title":"FaaS and Furious: abstractions and differential caching for efficient data pre-processing","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL","json":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL.json","graph_json":"https://pith.science/api/pith-number/QEZUQRSMDFIRLAND7AZ6GDLGZL/graph.json","events_json":"https://pith.science/api/pith-number/QEZUQRSMDFIRLAND7AZ6GDLGZL/events.json","paper":"https://pith.science/paper/QEZUQRSM"},"agent_actions":{"view_html":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL","download_json":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL.json","view_paper":"https://pith.science/paper/QEZUQRSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11761&json=true","fetch_graph":"https://pith.science/api/pith-number/QEZUQRSMDFIRLAND7AZ6GDLGZL/graph.json","fetch_events":"https://pith.science/api/pith-number/QEZUQRSMDFIRLAND7AZ6GDLGZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL/action/storage_attestation","attest_author":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL/action/author_attestation","sign_citation":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL/action/citation_signature","submit_replication":"https://pith.science/pith/QEZUQRSMDFIRLAND7AZ6GDLGZL/action/replication_record"}},"created_at":"2026-07-05T05:53:21.996343+00:00","updated_at":"2026-07-05T05:53:21.996343+00:00"}