{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RWBAPBSVZM3UP4PNVJUGQNEGRG","short_pith_number":"pith:RWBAPBSV","schema_version":"1.0","canonical_sha256":"8d82078655cb3747f1edaa6868348689adffb6661b239f0d0570d1a274bb09df","source":{"kind":"arxiv","id":"2507.23018","version":1},"attestation_state":"computed","paper":{"title":"Data Readiness for Scientific AI at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.DC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Arjun Shankar, Feiyi Wang, Patrick Widener, Sarp Oral, Tom Beck, Valentine Anantharaj, Wesley Brewer","submitted_at":"2025-07-30T18:30:37Z","abstract_excerpt":"This paper examines how Data Readiness for AI (DRAI) principles apply to leadership-scale scientific datasets used to train foundation models. We analyze archetypal workflows across four representative domains - climate, nuclear fusion, bio/health, and materials - to identify common preprocessing patterns and domain-specific constraints. We introduce a two-dimensional readiness framework composed of Data Readiness Levels (raw to AI-ready) and Data Processing Stages (ingest to shard), both tailored to high performance computing (HPC) environments. This framework outlines key challenges in trans"},"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":"2507.23018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-30T18:30:37Z","cross_cats_sorted":["cs.CE","cs.DC","cs.LG"],"title_canon_sha256":"8eea7daa81925b0e18ab1c741fda11e118406326e941fe26a8671240dbb113ed","abstract_canon_sha256":"a2350db7de04f7799b99999dec20644bbce8f1545870d6fe16721c53f6214bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:03.873535Z","signature_b64":"IMk+yEer1w94nXoqH0wVk+r7irgjkL3wVQQQeE+KVNmAyDIRf3y7ImOv6G3ytA77HBiAn9neRBlCLl76hhngCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d82078655cb3747f1edaa6868348689adffb6661b239f0d0570d1a274bb09df","last_reissued_at":"2026-07-05T11:46:03.872855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:03.872855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Readiness for Scientific AI at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.DC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Arjun Shankar, Feiyi Wang, Patrick Widener, Sarp Oral, Tom Beck, Valentine Anantharaj, Wesley Brewer","submitted_at":"2025-07-30T18:30:37Z","abstract_excerpt":"This paper examines how Data Readiness for AI (DRAI) principles apply to leadership-scale scientific datasets used to train foundation models. We analyze archetypal workflows across four representative domains - climate, nuclear fusion, bio/health, and materials - to identify common preprocessing patterns and domain-specific constraints. We introduce a two-dimensional readiness framework composed of Data Readiness Levels (raw to AI-ready) and Data Processing Stages (ingest to shard), both tailored to high performance computing (HPC) environments. This framework outlines key challenges in trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23018","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/2507.23018/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":"2507.23018","created_at":"2026-07-05T11:46:03.872923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23018v1","created_at":"2026-07-05T11:46:03.872923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23018","created_at":"2026-07-05T11:46:03.872923+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWBAPBSVZM3U","created_at":"2026-07-05T11:46:03.872923+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWBAPBSVZM3UP4PN","created_at":"2026-07-05T11:46:03.872923+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWBAPBSV","created_at":"2026-07-05T11:46:03.872923+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/RWBAPBSVZM3UP4PNVJUGQNEGRG","json":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG.json","graph_json":"https://pith.science/api/pith-number/RWBAPBSVZM3UP4PNVJUGQNEGRG/graph.json","events_json":"https://pith.science/api/pith-number/RWBAPBSVZM3UP4PNVJUGQNEGRG/events.json","paper":"https://pith.science/paper/RWBAPBSV"},"agent_actions":{"view_html":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG","download_json":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG.json","view_paper":"https://pith.science/paper/RWBAPBSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23018&json=true","fetch_graph":"https://pith.science/api/pith-number/RWBAPBSVZM3UP4PNVJUGQNEGRG/graph.json","fetch_events":"https://pith.science/api/pith-number/RWBAPBSVZM3UP4PNVJUGQNEGRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/action/storage_attestation","attest_author":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/action/author_attestation","sign_citation":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/action/citation_signature","submit_replication":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/action/replication_record"}},"created_at":"2026-07-05T11:46:03.872923+00:00","updated_at":"2026-07-05T11:46:03.872923+00:00"}