{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3TYMJP6V6BIZW7DASQMWKRTW3H","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":"6f4e0756030981b74e200bc9acb8d8d30429455fa37eb7ddb9453aa68a134be5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:25:31Z","title_canon_sha256":"5d20e36be7c28af0bcad074f947824bee814e9cb2dbaa7176266ee4a94929000"},"schema_version":"1.0","source":{"id":"2409.11378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11378","created_at":"2026-07-05T09:08:17Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11378v1","created_at":"2026-07-05T09:08:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11378","created_at":"2026-07-05T09:08:17Z"},{"alias_kind":"pith_short_12","alias_value":"3TYMJP6V6BIZ","created_at":"2026-07-05T09:08:17Z"},{"alias_kind":"pith_short_16","alias_value":"3TYMJP6V6BIZW7DA","created_at":"2026-07-05T09:08:17Z"},{"alias_kind":"pith_short_8","alias_value":"3TYMJP6V","created_at":"2026-07-05T09:08:17Z"}],"graph_snapshots":[{"event_id":"sha256:cbde40f59249b41e1c2bf88cc529c5c0724a3c1d82130c694defd3518350964b","target":"graph","created_at":"2026-07-05T09:08:17Z","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/2409.11378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finetuning large language models on instruction data is crucial for enhancing pre-trained knowledge and improving instruction-following capabilities. As instruction datasets proliferate, selecting optimal data for effective training becomes increasingly important. This work addresses the question: How can we determine the optimal subset of data for effective training? While existing research often emphasizes local criteria like instance quality for subset selection, we argue that a global approach focused on data diversity is more critical. Our method employs k-means clustering to ensure the s","authors_text":"Liangyu Chen, Marzieh Fadaee, Sara Ahmadian, Simon Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:25:31Z","title":"Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11378","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:fb0962aac3ed74a0449bc796b73e34c7b201965d92bba6fbb94ee30bbd43f452","target":"record","created_at":"2026-07-05T09:08:17Z","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":"6f4e0756030981b74e200bc9acb8d8d30429455fa37eb7ddb9453aa68a134be5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:25:31Z","title_canon_sha256":"5d20e36be7c28af0bcad074f947824bee814e9cb2dbaa7176266ee4a94929000"},"schema_version":"1.0","source":{"id":"2409.11378","kind":"arxiv","version":1}},"canonical_sha256":"dcf0c4bfd5f0519b7c609419654676d9cf31a65a2938f26f8f90ee46eb101766","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcf0c4bfd5f0519b7c609419654676d9cf31a65a2938f26f8f90ee46eb101766","first_computed_at":"2026-07-05T09:08:17.264996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:17.264996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yvh/HbvWRLv0vzjV2bgOPwq3P7ynbNIX6fcaqR1nfUJc2wQ0RM+8j+xbpKwQAh77ygxK7exXI0uoRVVLKJCbCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:17.265498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb0962aac3ed74a0449bc796b73e34c7b201965d92bba6fbb94ee30bbd43f452","sha256:cbde40f59249b41e1c2bf88cc529c5c0724a3c1d82130c694defd3518350964b"],"state_sha256":"907b9ec4e1136d61fc5caab32d7ed54eaf62d670f9bfdd2b8739dff4afc38fb0"}