{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QLELZKGR5MJIDMSP5A4MWKR6CR","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":"9b18ef7b0aae1a98b4a753e804a781c2ae40f5a26c208b067e889cf0624d40f6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T23:50:20Z","title_canon_sha256":"ed94d694829432a9f9f9ba397cb3fe96ccc5fa75235806fe1ec854070ecd157c"},"schema_version":"1.0","source":{"id":"2405.20541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20541","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20541v1","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20541","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"QLELZKGR5MJI","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"QLELZKGR5MJIDMSP","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"QLELZKGR","created_at":"2026-07-05T08:25:38Z"}],"graph_snapshots":[{"event_id":"sha256:2fb0d49ca62d1239711a51874ad0d0814aba7a3b8297e34b4db5dc970dd8be22","target":"graph","created_at":"2026-07-05T08:25:38Z","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/2405.20541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. While existing work has shown that pruning based on the perplexity of a larger model can yield high-quality data, we investigate whether smaller models can be used for perplexity-based pruning and how pruning is affected by the domain composition of the data being pruned. We demonstrate that for multiple dataset compositions, perplexity-based pruning of pretraining data can \\emph{significantly} improve downstream task","authors_text":"Cody Blakeney, Kartik Sreenivasan, Mansheej Paul, Matthew L. Leavitt, Max Marion, Zachary Ankner","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T23:50:20Z","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20541","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":"sha256:95c9c4e420311b70ab07c352e97b3450e7fddb933f2d4171e1b8b4c8f2c31a37","target":"record","created_at":"2026-07-05T08:25:38Z","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":"9b18ef7b0aae1a98b4a753e804a781c2ae40f5a26c208b067e889cf0624d40f6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T23:50:20Z","title_canon_sha256":"ed94d694829432a9f9f9ba397cb3fe96ccc5fa75235806fe1ec854070ecd157c"},"schema_version":"1.0","source":{"id":"2405.20541","kind":"arxiv","version":1}},"canonical_sha256":"82c8bca8d1eb1281b24fe838cb2a3e145410c8892e0c2f3ee79e8c954c3e28d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82c8bca8d1eb1281b24fe838cb2a3e145410c8892e0c2f3ee79e8c954c3e28d0","first_computed_at":"2026-07-05T08:25:38.776459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:38.776459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZxKzAoyY5ICrb/L9nOBS+Iqg0k5uBmRG0aNllzgxp3RmULqApE4/r0tz1Ko8MUtOJIkIE865vnpzhGQiPrbLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:38.776855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95c9c4e420311b70ab07c352e97b3450e7fddb933f2d4171e1b8b4c8f2c31a37","sha256:2fb0d49ca62d1239711a51874ad0d0814aba7a3b8297e34b4db5dc970dd8be22"],"state_sha256":"5f2b7c525d9030c798828e39d1cdb594c69a7487a2dc40a9fe7fbfee906a8ffc"}