{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OQCB2IISBTWR23FAZWF27MYMDP","short_pith_number":"pith:OQCB2IIS","schema_version":"1.0","canonical_sha256":"74041d21120ced1d6ca0cd8bafb30c1bfe8b38333a6e614494779d60b7780711","source":{"kind":"arxiv","id":"2607.24717","version":1},"attestation_state":"computed","paper":{"title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Shijie Xia, Yikun Wang, Zhen Huang","submitted_at":"2026-07-27T17:54:12Z","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"},"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":"2607.24717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T17:54:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29645f1e6fc09ea3a89e814da3dd6e02c806f5d1286df55f69f2a18029516124","abstract_canon_sha256":"2d2a9e3893b7705f7f0262f92504025c1ec79a88d76723003f4d9f86aa049fc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:23.945554Z","signature_b64":"hjijbxol4qLjP/VzRWcadJfY7hGOuL6ZiAjp/vw/T9O/gxFdzZWRBPGJx7OjmTYk68E6s/XWmmH2Rh/rcp6UCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74041d21120ced1d6ca0cd8bafb30c1bfe8b38333a6e614494779d60b7780711","last_reissued_at":"2026-07-28T02:24:23.944769Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:23.944769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Shijie Xia, Yikun Wang, Zhen Huang","submitted_at":"2026-07-27T17:54:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24717","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/2607.24717/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":"2607.24717","created_at":"2026-07-28T02:24:23.945183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24717v1","created_at":"2026-07-28T02:24:23.945183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24717","created_at":"2026-07-28T02:24:23.945183+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQCB2IISBTWR","created_at":"2026-07-28T02:24:23.945183+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQCB2IISBTWR23FA","created_at":"2026-07-28T02:24:23.945183+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQCB2IIS","created_at":"2026-07-28T02:24:23.945183+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/OQCB2IISBTWR23FAZWF27MYMDP","json":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP.json","graph_json":"https://pith.science/api/pith-number/OQCB2IISBTWR23FAZWF27MYMDP/graph.json","events_json":"https://pith.science/api/pith-number/OQCB2IISBTWR23FAZWF27MYMDP/events.json","paper":"https://pith.science/paper/OQCB2IIS"},"agent_actions":{"view_html":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP","download_json":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP.json","view_paper":"https://pith.science/paper/OQCB2IIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24717&json=true","fetch_graph":"https://pith.science/api/pith-number/OQCB2IISBTWR23FAZWF27MYMDP/graph.json","fetch_events":"https://pith.science/api/pith-number/OQCB2IISBTWR23FAZWF27MYMDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP/action/storage_attestation","attest_author":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP/action/author_attestation","sign_citation":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP/action/citation_signature","submit_replication":"https://pith.science/pith/OQCB2IISBTWR23FAZWF27MYMDP/action/replication_record"}},"created_at":"2026-07-28T02:24:23.945183+00:00","updated_at":"2026-07-28T02:24:23.945183+00:00"}