{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:72OJIUJIRTQ34IBBW4MY2AZNJ4","short_pith_number":"pith:72OJIUJI","schema_version":"1.0","canonical_sha256":"fe9c9451288ce1be2021b7198d032d4f3cb189768be83e900219d327c677f651","source":{"kind":"arxiv","id":"2408.02498","version":2},"attestation_state":"computed","paper":{"title":"Flow with FlorDB: Incremental Context Maintenance for the Machine Learning Lifecycle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.DB","authors_text":"Aditya G. Parameswaran, Chithra Anand, Erin Michelle Turner Kerrison, Joseph M. Hellerstein, Pragya Kallanagoudar, Rolando Garcia, Sarah E. Chasins","submitted_at":"2024-08-05T14:21:00Z","abstract_excerpt":"In this paper we present techniques to incrementally harvest and query arbitrary metadata from machine learning pipelines, without disrupting agile practices. We center our approach on the developer-favored technique for generating metadata -- log statements -- leveraging the fact that logging creates context. We show how hindsight logging allows such statements to be added and executed post-hoc, without requiring developer foresight. Relational views of incomplete metadata can be queried to dynamically materialize new metadata in bulk and on demand across multiple versions of workflows. This "},"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":"2408.02498","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-08-05T14:21:00Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"61873b09b8a4fb74e24ce162519442d231480d4de301c98d91be4f975ee2610c","abstract_canon_sha256":"4f02164b20b50fcb27a6506227f4fb9bd8e1b1ab02d2d807f2b8712de92541a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:13.845740Z","signature_b64":"vBOYq0jjKA8f6/b7ccYFVB55nqGVgRFjUheV/GCIXyUuAIL7CbS17KDDjIcPqmUpRu24ykAlqBKLPg04hmDmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9c9451288ce1be2021b7198d032d4f3cb189768be83e900219d327c677f651","last_reissued_at":"2026-07-05T09:36:13.845233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:13.845233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow with FlorDB: Incremental Context Maintenance for the Machine Learning Lifecycle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.DB","authors_text":"Aditya G. Parameswaran, Chithra Anand, Erin Michelle Turner Kerrison, Joseph M. Hellerstein, Pragya Kallanagoudar, Rolando Garcia, Sarah E. Chasins","submitted_at":"2024-08-05T14:21:00Z","abstract_excerpt":"In this paper we present techniques to incrementally harvest and query arbitrary metadata from machine learning pipelines, without disrupting agile practices. We center our approach on the developer-favored technique for generating metadata -- log statements -- leveraging the fact that logging creates context. We show how hindsight logging allows such statements to be added and executed post-hoc, without requiring developer foresight. Relational views of incomplete metadata can be queried to dynamically materialize new metadata in bulk and on demand across multiple versions of workflows. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02498","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/2408.02498/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":"2408.02498","created_at":"2026-07-05T09:36:13.845297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02498v2","created_at":"2026-07-05T09:36:13.845297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02498","created_at":"2026-07-05T09:36:13.845297+00:00"},{"alias_kind":"pith_short_12","alias_value":"72OJIUJIRTQ3","created_at":"2026-07-05T09:36:13.845297+00:00"},{"alias_kind":"pith_short_16","alias_value":"72OJIUJIRTQ34IBB","created_at":"2026-07-05T09:36:13.845297+00:00"},{"alias_kind":"pith_short_8","alias_value":"72OJIUJI","created_at":"2026-07-05T09:36:13.845297+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/72OJIUJIRTQ34IBBW4MY2AZNJ4","json":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4.json","graph_json":"https://pith.science/api/pith-number/72OJIUJIRTQ34IBBW4MY2AZNJ4/graph.json","events_json":"https://pith.science/api/pith-number/72OJIUJIRTQ34IBBW4MY2AZNJ4/events.json","paper":"https://pith.science/paper/72OJIUJI"},"agent_actions":{"view_html":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4","download_json":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4.json","view_paper":"https://pith.science/paper/72OJIUJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02498&json=true","fetch_graph":"https://pith.science/api/pith-number/72OJIUJIRTQ34IBBW4MY2AZNJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/72OJIUJIRTQ34IBBW4MY2AZNJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4/action/storage_attestation","attest_author":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4/action/author_attestation","sign_citation":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4/action/citation_signature","submit_replication":"https://pith.science/pith/72OJIUJIRTQ34IBBW4MY2AZNJ4/action/replication_record"}},"created_at":"2026-07-05T09:36:13.845297+00:00","updated_at":"2026-07-05T09:36:13.845297+00:00"}