{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RWBAPBSVZM3UP4PNVJUGQNEGRG","short_pith_number":"pith:RWBAPBSV","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"},"canonical_sha256":"8d82078655cb3747f1edaa6868348689adffb6661b239f0d0570d1a274bb09df","source":{"kind":"arxiv","id":"2507.23018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23018","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23018v1","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23018","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"RWBAPBSVZM3U","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"pith_short_16","alias_value":"RWBAPBSVZM3UP4PN","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"pith_short_8","alias_value":"RWBAPBSV","created_at":"2026-07-05T11:46:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RWBAPBSVZM3UP4PNVJUGQNEGRG","target":"record","payload":{"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"},"canonical_sha256":"8d82078655cb3747f1edaa6868348689adffb6661b239f0d0570d1a274bb09df","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"},"source_kind":"arxiv","source_id":"2507.23018","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSf5Gyb+jRvBDEw3lQ0xjgCvDQvAw3Rafl4otPM8ZbO/SA2hs0MOWlUU1fviSOO0BDxVu32djsFwWTivwxOnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:39:26.842307Z"},"content_sha256":"e9bb66ee228e29ebc77feefafb6b7cf864e8187d0857a7f194c4a0f2bb12e41f","schema_version":"1.0","event_id":"sha256:e9bb66ee228e29ebc77feefafb6b7cf864e8187d0857a7f194c4a0f2bb12e41f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RWBAPBSVZM3UP4PNVJUGQNEGRG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2iHby6pWW3nKcIajOTiTrhBpF0DL+QFK0mnx2l+lmVPpYaQPziWJznBYERmvg/S8E9LNaK9K9yTuXGmS9GfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:39:26.843404Z"},"content_sha256":"af0068923bdfbdc7a0bd4d940095967bf905fd67d8e82d75516305ee02ea00de","schema_version":"1.0","event_id":"sha256:af0068923bdfbdc7a0bd4d940095967bf905fd67d8e82d75516305ee02ea00de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/bundle.json","state_url":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T15:39:26Z","links":{"resolver":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG","bundle":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/bundle.json","state":"https://pith.science/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWBAPBSVZM3UP4PNVJUGQNEGRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RWBAPBSVZM3UP4PNVJUGQNEGRG","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":"a2350db7de04f7799b99999dec20644bbce8f1545870d6fe16721c53f6214bf8","cross_cats_sorted":["cs.CE","cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-30T18:30:37Z","title_canon_sha256":"8eea7daa81925b0e18ab1c741fda11e118406326e941fe26a8671240dbb113ed"},"schema_version":"1.0","source":{"id":"2507.23018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23018","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23018v1","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23018","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"RWBAPBSVZM3U","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"pith_short_16","alias_value":"RWBAPBSVZM3UP4PN","created_at":"2026-07-05T11:46:03Z"},{"alias_kind":"pith_short_8","alias_value":"RWBAPBSV","created_at":"2026-07-05T11:46:03Z"}],"graph_snapshots":[{"event_id":"sha256:af0068923bdfbdc7a0bd4d940095967bf905fd67d8e82d75516305ee02ea00de","target":"graph","created_at":"2026-07-05T11:46:03Z","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/2507.23018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arjun Shankar, Feiyi Wang, Patrick Widener, Sarp Oral, Tom Beck, Valentine Anantharaj, Wesley Brewer","cross_cats":["cs.CE","cs.DC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-30T18:30:37Z","title":"Data Readiness for Scientific AI at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23018","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:e9bb66ee228e29ebc77feefafb6b7cf864e8187d0857a7f194c4a0f2bb12e41f","target":"record","created_at":"2026-07-05T11:46:03Z","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":"a2350db7de04f7799b99999dec20644bbce8f1545870d6fe16721c53f6214bf8","cross_cats_sorted":["cs.CE","cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-30T18:30:37Z","title_canon_sha256":"8eea7daa81925b0e18ab1c741fda11e118406326e941fe26a8671240dbb113ed"},"schema_version":"1.0","source":{"id":"2507.23018","kind":"arxiv","version":1}},"canonical_sha256":"8d82078655cb3747f1edaa6868348689adffb6661b239f0d0570d1a274bb09df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d82078655cb3747f1edaa6868348689adffb6661b239f0d0570d1a274bb09df","first_computed_at":"2026-07-05T11:46:03.872855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:03.872855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IMk+yEer1w94nXoqH0wVk+r7irgjkL3wVQQQeE+KVNmAyDIRf3y7ImOv6G3ytA77HBiAn9neRBlCLl76hhngCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:03.873535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9bb66ee228e29ebc77feefafb6b7cf864e8187d0857a7f194c4a0f2bb12e41f","sha256:af0068923bdfbdc7a0bd4d940095967bf905fd67d8e82d75516305ee02ea00de"],"state_sha256":"48cf79045cdc92d08c18070b24cede6f52c737260970dcdfc638c2f279ac4779"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJTjT2VnhZtAPCorRlz1Y3KqvcRu3P6wJP5ZGwa9lLef9Y3qKS1C94nWDGN0l2rxVyKSXKT76eNhgydk+hDfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:39:26.853363Z","bundle_sha256":"785f0976e4b639cfafced521412f33a372ea6d5c58dfdc23a6a96e6dceba78ff"}}