{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2Y53Z5MGNLY6UU4VB42EAYFEDG","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":"2de6203743b36cb283d0b631ad599958250c3233c203cee14e47025ebe963247","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T14:49:29Z","title_canon_sha256":"0cca7305e4d3183a090a1b3e62350e0655be39e060378314e258aeaa4c8989d1"},"schema_version":"1.0","source":{"id":"2409.16986","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16986","created_at":"2026-07-05T09:16:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16986v2","created_at":"2026-07-05T09:16:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16986","created_at":"2026-07-05T09:16:21Z"},{"alias_kind":"pith_short_12","alias_value":"2Y53Z5MGNLY6","created_at":"2026-07-05T09:16:21Z"},{"alias_kind":"pith_short_16","alias_value":"2Y53Z5MGNLY6UU4V","created_at":"2026-07-05T09:16:21Z"},{"alias_kind":"pith_short_8","alias_value":"2Y53Z5MG","created_at":"2026-07-05T09:16:21Z"}],"graph_snapshots":[{"event_id":"sha256:b1e1b227236e7cb5425c78a456b8d0a5aec40e7cd0355145aefd46b9f82d8a38","target":"graph","created_at":"2026-07-05T09:16:21Z","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/2409.16986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection is of great significance in pre-training large language models, given the variation in quality within the large-scale available training corpora. To achieve this, researchers are currently investigating the use of data influence to measure the importance of data instances, $i.e.,$ a high influence score indicates that incorporating this instance to the training set is likely to enhance the model performance. Consequently, they select the top-$k$ instances with the highest scores. However, this approach has several limitations. (1) Computing the influence of all available data is","authors_text":"Chengliang Chai, Chi Zhang, Conghui He, Guoren Wang, Huaping Zhong, Jiantao Qiu, Ju Fan, Kuan Zhang, Lei Cao, Rui Wang, Tianyi Bai, Xinlin Zhuang, Ye Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T14:49:29Z","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16986","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:f79c807e2049e0d6560ae5392af23b67b71830720e819ab01cae60e41b5189d6","target":"record","created_at":"2026-07-05T09:16:21Z","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":"2de6203743b36cb283d0b631ad599958250c3233c203cee14e47025ebe963247","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T14:49:29Z","title_canon_sha256":"0cca7305e4d3183a090a1b3e62350e0655be39e060378314e258aeaa4c8989d1"},"schema_version":"1.0","source":{"id":"2409.16986","kind":"arxiv","version":2}},"canonical_sha256":"d63bbcf5866af1ea53950f344060a419bca3329f47d9200f87aee20cf937d2af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d63bbcf5866af1ea53950f344060a419bca3329f47d9200f87aee20cf937d2af","first_computed_at":"2026-07-05T09:16:21.724161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:21.724161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X7eEGijAWy8dUjHCeTzCGtRBndx1vLvi0ocvnBY5eRuzZDA7yT9PjWCNFGXw7JOVfS/hMgMKixUB4W8c45rpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:21.724687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16986","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f79c807e2049e0d6560ae5392af23b67b71830720e819ab01cae60e41b5189d6","sha256:b1e1b227236e7cb5425c78a456b8d0a5aec40e7cd0355145aefd46b9f82d8a38"],"state_sha256":"a12fe54c7f32738e4c9190934891ccc2ba98d857fe926b89d5cd1c87cf106b55"}