{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NIPY4YKV6VG22N5FPHPBF25FGI","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":"bdf3f74ac8bb03f8ec6fde5cf08680b00fdafdf206b1d8dc7723d906e20e0e20","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:37:26Z","title_canon_sha256":"d47c7fc6b2865b33b4a7473267e810d77e47ffefe3e48eec77527fe6edbeb8c7"},"schema_version":"1.0","source":{"id":"2503.01807","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01807","created_at":"2026-07-05T11:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01807v2","created_at":"2026-07-05T11:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01807","created_at":"2026-07-05T11:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"NIPY4YKV6VG2","created_at":"2026-07-05T11:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"NIPY4YKV6VG22N5F","created_at":"2026-07-05T11:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"NIPY4YKV","created_at":"2026-07-05T11:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:ccffe0ae2ddca375e315c5fbbdefd6b6ad99c366026e130a188c30dc0b30b2ca","target":"graph","created_at":"2026-07-05T11:24:15Z","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/2503.01807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Selecting high-quality training data from a larger pool is a crucial step when instruction-tuning language models, as carefully curated datasets often produce models that outperform those trained on much larger, noisier datasets. Automated data selection approaches for instruction-tuning are typically tested by selecting small datasets (roughly 10k samples) from small pools (100-200k samples). However, popular deployed instruction-tuned models often train on hundreds of thousands to millions of samples, subsampled from even larger data pools. We present a systematic study of how well data sele","authors_text":"Faeze Brahman, Hamish Ivison, Muru Zhang, Pang Wei Koh, Pradeep Dasigi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:37:26Z","title":"Large-Scale Data Selection for Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01807","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":"sha256:1a64b878d99968f4dfef370960fb9ef0c3a91376d624fd1d8953c87b85ece934","target":"record","created_at":"2026-07-05T11:24:15Z","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":"bdf3f74ac8bb03f8ec6fde5cf08680b00fdafdf206b1d8dc7723d906e20e0e20","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:37:26Z","title_canon_sha256":"d47c7fc6b2865b33b4a7473267e810d77e47ffefe3e48eec77527fe6edbeb8c7"},"schema_version":"1.0","source":{"id":"2503.01807","kind":"arxiv","version":2}},"canonical_sha256":"6a1f8e6155f54dad37a579de12eba5322fe6aa25c71ed25facc8cc83fccce8db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a1f8e6155f54dad37a579de12eba5322fe6aa25c71ed25facc8cc83fccce8db","first_computed_at":"2026-07-05T11:24:15.663523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:15.663523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"soeYA+rD79G7W0rBOubXpjnSsjWKEytq4IC6Tcm9pqY7JyF7JE+9LRpi9eoTa2MzNiIZzWCWNs//InBmysg9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:15.664078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01807","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a64b878d99968f4dfef370960fb9ef0c3a91376d624fd1d8953c87b85ece934","sha256:ccffe0ae2ddca375e315c5fbbdefd6b6ad99c366026e130a188c30dc0b30b2ca"],"state_sha256":"ef1fd143773529b01559711fcf76c8864e9bb5550018634706bcb22400be6c83"}