{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FNJJPLKLFP3O676R4FC4LVTPNA","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":"964442b9127ef1c6081b96f70ab22367480921a1e1b3b1b509d9982f52c8d197","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T02:27:57Z","title_canon_sha256":"ae9abe1ec66c1688fd78f24ac60cf1858ee87e2c502d5ac3fee71f8b3584eeff"},"schema_version":"1.0","source":{"id":"2402.09668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09668","created_at":"2026-07-05T07:45:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09668v1","created_at":"2026-07-05T07:45:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09668","created_at":"2026-07-05T07:45:34Z"},{"alias_kind":"pith_short_12","alias_value":"FNJJPLKLFP3O","created_at":"2026-07-05T07:45:34Z"},{"alias_kind":"pith_short_16","alias_value":"FNJJPLKLFP3O676R","created_at":"2026-07-05T07:45:34Z"},{"alias_kind":"pith_short_8","alias_value":"FNJJPLKL","created_at":"2026-07-05T07:45:34Z"}],"graph_snapshots":[{"event_id":"sha256:b481b259aa8930e1af326efb42d9e7f5484c6cb6dcc770cd7b38097d0185f3bc","target":"graph","created_at":"2026-07-05T07:45:34Z","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/2402.09668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data consumption. We seek to understand the tradeoffs associated with data selection routines based on (i) expensive-to-compute data-quality estimates, and (ii) maximization of coverage and diversity-based measures in the feature space. Our first technique, Ask-LLM, leverages the zero-shot reasoning capabilities of instruction-tuned LLMs to directly assess the quality ","authors_text":"Benjamin Coleman, Derek Zhiyuan Cheng, Ed H. Chi, James Caverlee, Jianmo Ni, Julian McAuley, Lichan Hong, Noveen Sachdeva, Wang-Cheng Kang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T02:27:57Z","title":"How to Train Data-Efficient LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09668","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:a8e41e53fe9a2e495f771df6921bcc7a95da012eefc42e29021c23270636f13d","target":"record","created_at":"2026-07-05T07:45:34Z","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":"964442b9127ef1c6081b96f70ab22367480921a1e1b3b1b509d9982f52c8d197","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T02:27:57Z","title_canon_sha256":"ae9abe1ec66c1688fd78f24ac60cf1858ee87e2c502d5ac3fee71f8b3584eeff"},"schema_version":"1.0","source":{"id":"2402.09668","kind":"arxiv","version":1}},"canonical_sha256":"2b5297ad4b2bf6ef7fd1e145c5d66f6832763243db391199463d0d8f8def052d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b5297ad4b2bf6ef7fd1e145c5d66f6832763243db391199463d0d8f8def052d","first_computed_at":"2026-07-05T07:45:34.618944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:34.618944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g1ppw1yOv3cbZlfGsH+31Vtr5GtqvpZxOIxHMCtyZjE7CKsfrsmJ7mLkvwkmUyru0mhlBR7raZBXShI6LSH/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:34.619387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8e41e53fe9a2e495f771df6921bcc7a95da012eefc42e29021c23270636f13d","sha256:b481b259aa8930e1af326efb42d9e7f5484c6cb6dcc770cd7b38097d0185f3bc"],"state_sha256":"90602e2fcf492d03127b04dba761a5693da705c837c7ab55a9563ae9a18b8917"}