{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7T3KL53YYYFG4S6H2DFU2O42EW","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":"cac60f08dab1e9f98fc2794b5dbd3bd94722ff1b5c8201659d7e730a16602f94","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T08:21:37Z","title_canon_sha256":"0ef6657e5ebdb86b39edfc2f0c904c801aba2f9f6cf3c78c038e0205dd30e403"},"schema_version":"1.0","source":{"id":"2505.14070","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14070","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14070v2","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14070","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"7T3KL53YYYFG","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"7T3KL53YYYFG4S6H","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"7T3KL53Y","created_at":"2026-07-05T11:13:26Z"}],"graph_snapshots":[{"event_id":"sha256:c7da2655224441bc793e8d913c912602614e15a09a40746cbcdb12545811994b","target":"graph","created_at":"2026-07-05T11:13:26Z","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/2505.14070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of Large Language Models (LLMs) is intrinsically linked to the quality of its training data. Although several studies have proposed methods for high-quality data selection, they do not consider the importance of knowledge richness in text corpora. In this paper, we propose a novel and gradient-free High-Knowledge Scorer (HKS) to select high-quality data from the dimension of knowledge, to alleviate the problem of knowledge scarcity in the pre-trained corpus. We propose a comprehensive multi-domain knowledge element pool and introduce knowledge density and coverage as metrics to","authors_text":"Feiyu Duan, Haoran Que, Sirui Wang, Wenge Rong, Xuemiao Zhang, Xunliang Cai, Yuqi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T08:21:37Z","title":"Enhancing LLMs via High-Knowledge Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14070","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:bd48de1cf3ceee2cc7052c61631ae220ed17f98943c44400599823769ec33b0e","target":"record","created_at":"2026-07-05T11:13:26Z","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":"cac60f08dab1e9f98fc2794b5dbd3bd94722ff1b5c8201659d7e730a16602f94","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T08:21:37Z","title_canon_sha256":"0ef6657e5ebdb86b39edfc2f0c904c801aba2f9f6cf3c78c038e0205dd30e403"},"schema_version":"1.0","source":{"id":"2505.14070","kind":"arxiv","version":2}},"canonical_sha256":"fcf6a5f778c60a6e4bc7d0cb4d3b9a25a7910519eacf229672774cf0b4110faa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcf6a5f778c60a6e4bc7d0cb4d3b9a25a7910519eacf229672774cf0b4110faa","first_computed_at":"2026-07-05T11:13:26.026833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:26.026833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KQp6bATAHo8EpcYhNUwYC4t34bv0ATuQAPk+OIyx7tDvW6k40CjnU0Ow1Qv/GwPKR7Ug0cA0YETwNakH4nm7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:26.027262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14070","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd48de1cf3ceee2cc7052c61631ae220ed17f98943c44400599823769ec33b0e","sha256:c7da2655224441bc793e8d913c912602614e15a09a40746cbcdb12545811994b"],"state_sha256":"92450dae5d50e6bdb861e258d3a77d8f544617ae4a97adde815bc4f8466d1ceb"}