{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y7MFSICGLE276QRYCOG4ZRRSYS","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":"1468c2ee2c8b7aea220bd350ac07ef65fcaa256030e6cd3ce660550e988ac964","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T08:50:15Z","title_canon_sha256":"b28804ea30c444cb209b4d03c338f9a8e6ec00797923cbf70ec82aefdfc8f4f6"},"schema_version":"1.0","source":{"id":"2606.29975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29975","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29975v1","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29975","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"pith_short_12","alias_value":"Y7MFSICGLE27","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"pith_short_16","alias_value":"Y7MFSICGLE276QRY","created_at":"2026-06-30T02:17:43Z"},{"alias_kind":"pith_short_8","alias_value":"Y7MFSICG","created_at":"2026-06-30T02:17:43Z"}],"graph_snapshots":[{"event_id":"sha256:3b4e4ada90f107b8796aed9996734d8a00875ba0315c6a6bfc6ffbd5c46831e6","target":"graph","created_at":"2026-06-30T02:17:43Z","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/2606.29975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Atomistic machine learning datasets are increasingly used for training: large immutable snapshots are read repeatedly, shuffled across epochs, staged across clusters' storage systems, and republished as reusable scientific artifacts. This workload differs from interactive scientific curation, where mutable records and ad hoc inspection are often more important than random indexed throughput. We present Atompack, an append-oriented storage format and distribution layer designed around a simple workload: training pipelines usually consume complete molecular records, while the order of records is","authors_text":"Alexandre Duval, Ali Ramlaoui, Daniel T. Speckhard, Fragkiskos D. Malliaros, Sagar Pal, Victor Schmidt","cross_cats":["cond-mat.mtrl-sci"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T08:50:15Z","title":"Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29975","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:ad39c47c536871a6b20c0f81f2b380bb76250b032384744a76ddd3283f2df4c0","target":"record","created_at":"2026-06-30T02:17:43Z","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":"1468c2ee2c8b7aea220bd350ac07ef65fcaa256030e6cd3ce660550e988ac964","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T08:50:15Z","title_canon_sha256":"b28804ea30c444cb209b4d03c338f9a8e6ec00797923cbf70ec82aefdfc8f4f6"},"schema_version":"1.0","source":{"id":"2606.29975","kind":"arxiv","version":1}},"canonical_sha256":"c7d85920465935ff4238138dccc632c4919555e18970af819f4365353f60f88b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7d85920465935ff4238138dccc632c4919555e18970af819f4365353f60f88b","first_computed_at":"2026-06-30T02:17:43.622781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:43.622781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PLgIliES+VBpugZVOotrH3YaSPcoOlH48zCKnZw0QeGO9jbvn10Ilb82iawBy8dY1QOsZ8NtkwtB/kLiYE/nBA==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:43.623611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad39c47c536871a6b20c0f81f2b380bb76250b032384744a76ddd3283f2df4c0","sha256:3b4e4ada90f107b8796aed9996734d8a00875ba0315c6a6bfc6ffbd5c46831e6"],"state_sha256":"83ec37b51d4b0a9552a9d2594431d1c494e6da822f2407d6df05f9162dea9a13"}