{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4YKN2PYM23BRXWHCADKROZWOMT","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":"7655b7a3a40712ef0b86f7954c6be5083f68cc92eb45de618524365c01804bd4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T10:08:12Z","title_canon_sha256":"354ce3755cd51587d93ed75b05e823a91be3b20c22960771c0fe566377cb3944"},"schema_version":"1.0","source":{"id":"2606.30077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30077","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30077v1","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30077","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"4YKN2PYM23BR","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"4YKN2PYM23BRXWHC","created_at":"2026-06-30T02:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"4YKN2PYM","created_at":"2026-06-30T02:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:215ab180c335d0b787ee9bdf75e365de4ecfc2cc89c0237d4ac546b44523d2c1","target":"graph","created_at":"2026-06-30T02:17:48Z","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/2606.30077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With Large Language Model (LLM) pre-training and fine-tuning shifting its focus from data volume to data quality, quality data selection has emerged as a critical research topic. Existing online data selection methods for LLM training are typically \"batch-constrained\", limiting optimization to local utility within random batches. To overcome this, we propose GAIA (Global Adaptive Instruction tuning via GAussian processes), a framework that formulates data valuation as a global estimation process. GAIA employs Gaussian Process regression to model continuous utility manifolds across the semantic","authors_text":"Julien Monteil, Jun Wang, Quoc Phong Nguyen, Vu Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T10:08:12Z","title":"Online Data Selection for Instruction Tuning via Gaussian Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30077","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":"sha256:7f19fd27a7be19edc1a8977bd50385050e2c91cb9e7ba13402d6524bf62ae1f2","target":"record","created_at":"2026-06-30T02:17:48Z","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":"7655b7a3a40712ef0b86f7954c6be5083f68cc92eb45de618524365c01804bd4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T10:08:12Z","title_canon_sha256":"354ce3755cd51587d93ed75b05e823a91be3b20c22960771c0fe566377cb3944"},"schema_version":"1.0","source":{"id":"2606.30077","kind":"arxiv","version":1}},"canonical_sha256":"e614dd3f0cd6c31bd8e200d51766ce64e3f0a40ab3d92cddcb615a50b771468a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e614dd3f0cd6c31bd8e200d51766ce64e3f0a40ab3d92cddcb615a50b771468a","first_computed_at":"2026-06-30T02:17:48.543857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:48.543857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vxVVQ1GwAmUT6UCcjwkKaNfa6st8ibqYCaiuei1UPc/p4LqBbK3ob6OxSL8saSAaoMDQ3TjdjrypMENJndRxBQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:48.544365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f19fd27a7be19edc1a8977bd50385050e2c91cb9e7ba13402d6524bf62ae1f2","sha256:215ab180c335d0b787ee9bdf75e365de4ecfc2cc89c0237d4ac546b44523d2c1"],"state_sha256":"a820d60280327dbc993f396f3ed7bc56d51abc8f3162045e904d5b21df7cd10d"}