{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DKN4MFFD3EU6H5QK2WWSUSOMSE","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":"6ad111b462f366e371d55e0f823bf83eac3c055debd2ecf7dda7ad9cdd36d08d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T12:44:49Z","title_canon_sha256":"34c5b478a059d762ec09bb17c7ade5cdc2d80ce5f7df8db3e0a85160b5818088"},"schema_version":"1.0","source":{"id":"2408.05541","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05541","created_at":"2026-07-05T09:22:21Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05541v2","created_at":"2026-07-05T09:22:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05541","created_at":"2026-07-05T09:22:21Z"},{"alias_kind":"pith_short_12","alias_value":"DKN4MFFD3EU6","created_at":"2026-07-05T09:22:21Z"},{"alias_kind":"pith_short_16","alias_value":"DKN4MFFD3EU6H5QK","created_at":"2026-07-05T09:22:21Z"},{"alias_kind":"pith_short_8","alias_value":"DKN4MFFD","created_at":"2026-07-05T09:22:21Z"}],"graph_snapshots":[{"event_id":"sha256:490ef0f2142a2b68296bdaeef766a2e8f525d9b90733cb9333215e474021a80b","target":"graph","created_at":"2026-07-05T09:22:21Z","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/2408.05541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the rapidly advancing field of Large Language Models (LLMs), effectively leveraging existing datasets during fine-tuning to maximize the model's potential is of paramount importance. This paper introduces P3, an adaptive framework aimed at optimizing the task-specific fine-tuning process through iterative data pruning. P3 consists of three key components: (1) Policy-driven Difficulty Measurement, which dynamically assesses data difficulty based on the model's real-time performance, replacing static metrics with adaptable evaluations; (2) Pace-Adaptive Selection, leveraging self-paced learni","authors_text":"Huayi Wang, Jun Wang, Muning Wen, Qiuying Peng, Weinan Zhang, Xiaoyun Mo, Yingxuan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T12:44:49Z","title":"P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05541","kind":"arxiv","version":2},"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":"sha256:25d9a56aaa560750c216d4535cc8ac73ce7573737ca9afb02cf18b9369fe879e","target":"record","created_at":"2026-07-05T09:22:21Z","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":"6ad111b462f366e371d55e0f823bf83eac3c055debd2ecf7dda7ad9cdd36d08d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T12:44:49Z","title_canon_sha256":"34c5b478a059d762ec09bb17c7ade5cdc2d80ce5f7df8db3e0a85160b5818088"},"schema_version":"1.0","source":{"id":"2408.05541","kind":"arxiv","version":2}},"canonical_sha256":"1a9bc614a3d929e3f60ad5ad2a49cc912c9664b803b2cc95f27efa1dcdfd68f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a9bc614a3d929e3f60ad5ad2a49cc912c9664b803b2cc95f27efa1dcdfd68f0","first_computed_at":"2026-07-05T09:22:21.073324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:21.073324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I4pHne5plOBT6Q+kV5L7yYvA27rCOnPFbVl2Bsae7fbIRPjekRGEM2rznJeWd2rLrYSZQ5DxsrpQoz9/khBHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:21.073751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05541","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25d9a56aaa560750c216d4535cc8ac73ce7573737ca9afb02cf18b9369fe879e","sha256:490ef0f2142a2b68296bdaeef766a2e8f525d9b90733cb9333215e474021a80b"],"state_sha256":"d78c258c5f2d616adf94baf38201e73fc388f34f71930b446ccd281adca0bd87"}