{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4YKN2PYM23BRXWHCADKROZWOMT","short_pith_number":"pith:4YKN2PYM","canonical_record":{"source":{"id":"2606.30077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T10:08:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"354ce3755cd51587d93ed75b05e823a91be3b20c22960771c0fe566377cb3944","abstract_canon_sha256":"7655b7a3a40712ef0b86f7954c6be5083f68cc92eb45de618524365c01804bd4"},"schema_version":"1.0"},"canonical_sha256":"e614dd3f0cd6c31bd8e200d51766ce64e3f0a40ab3d92cddcb615a50b771468a","source":{"kind":"arxiv","id":"2606.30077","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4YKN2PYM23BRXWHCADKROZWOMT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T10:08:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"354ce3755cd51587d93ed75b05e823a91be3b20c22960771c0fe566377cb3944","abstract_canon_sha256":"7655b7a3a40712ef0b86f7954c6be5083f68cc92eb45de618524365c01804bd4"},"schema_version":"1.0"},"canonical_sha256":"e614dd3f0cd6c31bd8e200d51766ce64e3f0a40ab3d92cddcb615a50b771468a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:48.544365Z","signature_b64":"vxVVQ1GwAmUT6UCcjwkKaNfa6st8ibqYCaiuei1UPc/p4LqBbK3ob6OxSL8saSAaoMDQ3TjdjrypMENJndRxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e614dd3f0cd6c31bd8e200d51766ce64e3f0a40ab3d92cddcb615a50b771468a","last_reissued_at":"2026-06-30T02:17:48.543857Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:48.543857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30077","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":"2026-06-30T02:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXzf871Sr+Vt/u9MJGShgosfBct/Js96JejWOv1INCe0dbnkJvh1OPLFRGBs/WuroRq3+T1ZkYBWQ8uiWy5XBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:02:11.455629Z"},"content_sha256":"7f19fd27a7be19edc1a8977bd50385050e2c91cb9e7ba13402d6524bf62ae1f2","schema_version":"1.0","event_id":"sha256:7f19fd27a7be19edc1a8977bd50385050e2c91cb9e7ba13402d6524bf62ae1f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4YKN2PYM23BRXWHCADKROZWOMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Data Selection for Instruction Tuning via Gaussian Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Julien Monteil, Jun Wang, Quoc Phong Nguyen, Vu Nguyen","submitted_at":"2026-06-29T10:08:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30077","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/2606.30077/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":"2026-06-30T02:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UnydlhFGL/Ef0jMIfyUfDFB9OFgffxvXxMah9wLq9UX/lkYft1a5uEURTvgPbMzvp+fngSPHLoAO204rmkpBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:02:11.455995Z"},"content_sha256":"215ab180c335d0b787ee9bdf75e365de4ecfc2cc89c0237d4ac546b44523d2c1","schema_version":"1.0","event_id":"sha256:215ab180c335d0b787ee9bdf75e365de4ecfc2cc89c0237d4ac546b44523d2c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YKN2PYM23BRXWHCADKROZWOMT/bundle.json","state_url":"https://pith.science/pith/4YKN2PYM23BRXWHCADKROZWOMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YKN2PYM23BRXWHCADKROZWOMT/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":"2026-07-02T21:02:11Z","links":{"resolver":"https://pith.science/pith/4YKN2PYM23BRXWHCADKROZWOMT","bundle":"https://pith.science/pith/4YKN2PYM23BRXWHCADKROZWOMT/bundle.json","state":"https://pith.science/pith/4YKN2PYM23BRXWHCADKROZWOMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YKN2PYM23BRXWHCADKROZWOMT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7CKKJQuYIHcNLmpElPRMQuALpKzUpiggeFtsrIlmLsu5bPYKmZi+MMDWTth43BZvLLyN+YbTTiTqcoa2pG9BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T21:02:11.458109Z","bundle_sha256":"839ea2f7458af6418891549304f5879306fd5192ae0d11171ad5f59b6524f216"}}