{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:75QJ73FWS4DEGRKRDG5DHRC2HZ","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":"e57384890bf26edf728fdd6f210015b7e3a9fd6f1bdbcf81bb14e00eee9e588d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T02:47:12Z","title_canon_sha256":"e7653280f85ceae24765501a4f1edc8c498b7f091ff51e68b151d2d195732fb8"},"schema_version":"1.0","source":{"id":"2507.16178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16178","created_at":"2026-07-05T11:41:04Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16178v1","created_at":"2026-07-05T11:41:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16178","created_at":"2026-07-05T11:41:04Z"},{"alias_kind":"pith_short_12","alias_value":"75QJ73FWS4DE","created_at":"2026-07-05T11:41:04Z"},{"alias_kind":"pith_short_16","alias_value":"75QJ73FWS4DEGRKR","created_at":"2026-07-05T11:41:04Z"},{"alias_kind":"pith_short_8","alias_value":"75QJ73FW","created_at":"2026-07-05T11:41:04Z"}],"graph_snapshots":[{"event_id":"sha256:03da493d89424ee919c8e3af1c415ee05b5938b440f8de8a48fe4c006f9e7f17","target":"graph","created_at":"2026-07-05T11:41:04Z","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/2507.16178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large-scale training data is fundamental for developing capable large language models (LLMs), strategically selecting high-quality data has emerged as a critical approach to enhance training efficiency and reduce computational costs. Current data selection methodologies predominantly rely on static, training-agnostic criteria, failing to account for the dynamic model training and data interactions. In this paper, we propose a new Data Weighting Model (DWM) to adjust the weight of selected data within each batch to achieve a dynamic data utilization during LLM training. Specially, to bett","authors_text":"Dacheng Tao, Hang Zhou, Kai Han, Kaiqi Huang, Yang Yu, Yehui Tang, Yunhe Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T02:47:12Z","title":"LLM Data Selection and Utilization via Dynamic Bi-level Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16178","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":"sha256:171cba8ddfea57a96e50dc2c96aff45a5b450fec6f8a1fa337a88140583f0904","target":"record","created_at":"2026-07-05T11:41:04Z","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":"e57384890bf26edf728fdd6f210015b7e3a9fd6f1bdbcf81bb14e00eee9e588d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T02:47:12Z","title_canon_sha256":"e7653280f85ceae24765501a4f1edc8c498b7f091ff51e68b151d2d195732fb8"},"schema_version":"1.0","source":{"id":"2507.16178","kind":"arxiv","version":1}},"canonical_sha256":"ff609fecb6970643455119ba33c45a3e73cbeca486e143080415ee5959859bfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff609fecb6970643455119ba33c45a3e73cbeca486e143080415ee5959859bfa","first_computed_at":"2026-07-05T11:41:04.638308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:04.638308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qo+lL/0lC8F8qwBQanPqFnKYdrgAMI+f9Aj0DPqSRlwEQjN8XZzv+K+AzRL2O23gwuok6pMYw/qPjejCoj10Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:04.638695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:171cba8ddfea57a96e50dc2c96aff45a5b450fec6f8a1fa337a88140583f0904","sha256:03da493d89424ee919c8e3af1c415ee05b5938b440f8de8a48fe4c006f9e7f17"],"state_sha256":"cbdafcea3ee1d8449d046e91f2166a32d6c8cf901ba050091f8cf522bcca63a0"}