{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OQCB2IISBTWR23FAZWF27MYMDP","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":"2d2a9e3893b7705f7f0262f92504025c1ec79a88d76723003f4d9f86aa049fc4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T17:54:12Z","title_canon_sha256":"29645f1e6fc09ea3a89e814da3dd6e02c806f5d1286df55f69f2a18029516124"},"schema_version":"1.0","source":{"id":"2607.24717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24717","created_at":"2026-07-28T02:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24717v1","created_at":"2026-07-28T02:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24717","created_at":"2026-07-28T02:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"OQCB2IISBTWR","created_at":"2026-07-28T02:24:23Z"},{"alias_kind":"pith_short_16","alias_value":"OQCB2IISBTWR23FA","created_at":"2026-07-28T02:24:23Z"},{"alias_kind":"pith_short_8","alias_value":"OQCB2IIS","created_at":"2026-07-28T02:24:23Z"}],"graph_snapshots":[{"event_id":"sha256:718c49a67de173852f76411a8ca48490a51e25f1fa4ffaa3f57e7764f43ce093","target":"graph","created_at":"2026-07-28T02:24:23Z","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/2607.24717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining data processing is critical to the downstream performance of Large Language Models (LLMs). However, many existing approaches define a fixed processing strategy at the corpus or domain level and apply it uniformly to many examples, without adapting to the needs of each example. We propose DataOrchestra, a framework that unifies different processing operations and orchestrates an example-specific pipeline for each example. Given a chunk of pretraining data, an orchestrator decides whether to drop, untouch, or clean it. For a chunk to be cleaned, it selects one or more downstream oper","authors_text":"Pengfei Liu, Shijie Xia, Yikun Wang, Zhen Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T17:54:12Z","title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24717","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":"sha256:7503a60845c569b8dd363da549268a09b2ed3078edf7fc679c3def8245a7bd16","target":"record","created_at":"2026-07-28T02:24:23Z","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":"2d2a9e3893b7705f7f0262f92504025c1ec79a88d76723003f4d9f86aa049fc4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T17:54:12Z","title_canon_sha256":"29645f1e6fc09ea3a89e814da3dd6e02c806f5d1286df55f69f2a18029516124"},"schema_version":"1.0","source":{"id":"2607.24717","kind":"arxiv","version":1}},"canonical_sha256":"74041d21120ced1d6ca0cd8bafb30c1bfe8b38333a6e614494779d60b7780711","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74041d21120ced1d6ca0cd8bafb30c1bfe8b38333a6e614494779d60b7780711","first_computed_at":"2026-07-28T02:24:23.944769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:24:23.944769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hjijbxol4qLjP/VzRWcadJfY7hGOuL6ZiAjp/vw/T9O/gxFdzZWRBPGJx7OjmTYk68E6s/XWmmH2Rh/rcp6UCg==","signature_status":"signed_v1","signed_at":"2026-07-28T02:24:23.945554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7503a60845c569b8dd363da549268a09b2ed3078edf7fc679c3def8245a7bd16","sha256:718c49a67de173852f76411a8ca48490a51e25f1fa4ffaa3f57e7764f43ce093"],"state_sha256":"a5ed41b62c375d6ddd40a97b7aca7ad7107e6ace1b5f7d1fa5670c33071f7555"}