{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LAVXGHZ7EWHGKGKG2BSWOWSUGM","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":"243d69894553073b925ceea7ad1b939fe0ccb66545e8d9ae5e3788ccf420c74e","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T10:57:51Z","title_canon_sha256":"d356dd2b2166383354c28645461002109d7cf0c8572e48ee67a52443aca0034a"},"schema_version":"1.0","source":{"id":"2505.07437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07437","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07437v1","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07437","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"LAVXGHZ7EWHG","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"LAVXGHZ7EWHGKGKG","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"LAVXGHZ7","created_at":"2026-07-05T11:01:47Z"}],"graph_snapshots":[{"event_id":"sha256:cb082f890e7e6a2e7cfa563d71488debb1a762184e1e2d6596b6c0f723f49f99","target":"graph","created_at":"2026-07-05T11:01:47Z","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/2505.07437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as they rely on repeatedly performing full-dataset model inference to estimate sample utility for subsequent training iterations, creating a fundamental efficiency bottleneck. In this paper, we propose LEAD, an efficient iterative data selection framework that accurately estimates sample utility entirely within the standard training loop, eliminating the need f","authors_text":"Chengliang Chai, Nan Tang, Themis Palpanas, Xiaotian Lin, Yanlin Qi, Yizhang Zhu, Yuyu Luo","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T10:57:51Z","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07437","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":"sha256:0e33f9da95ecf0b03dec08f01cf1330575f963e94f12a10e3f37c04fad884b6b","target":"record","created_at":"2026-07-05T11:01:47Z","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":"243d69894553073b925ceea7ad1b939fe0ccb66545e8d9ae5e3788ccf420c74e","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T10:57:51Z","title_canon_sha256":"d356dd2b2166383354c28645461002109d7cf0c8572e48ee67a52443aca0034a"},"schema_version":"1.0","source":{"id":"2505.07437","kind":"arxiv","version":1}},"canonical_sha256":"582b731f3f258e651946d065675a54331c7b8d31ef38b1ad5ca6dc8f009c8afa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"582b731f3f258e651946d065675a54331c7b8d31ef38b1ad5ca6dc8f009c8afa","first_computed_at":"2026-07-05T11:01:47.804243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:47.804243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7RTqNoo0i/4rf5KFldvIYsx/ov1L7UfhLoHzzFFMysKldHqiaXe7i2ej2mpEFNqjGtIfn3S3If23enPXzY1kBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:47.804645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e33f9da95ecf0b03dec08f01cf1330575f963e94f12a10e3f37c04fad884b6b","sha256:cb082f890e7e6a2e7cfa563d71488debb1a762184e1e2d6596b6c0f723f49f99"],"state_sha256":"971ef6c649d0857b33ba9b047407dae59cc18a5c4d30c2620a352149dc649878"}