{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2W6U6JEWDCCPA5G4VD6R5LRSRC","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":"94aca8849a0206dbf44b8b3052842a64bc645dd8b4b1f0e97cfed8971ff8a0e3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-06T23:57:56Z","title_canon_sha256":"92bf449ead3da75abf53b69965b628ab48b6481ff1d9af273b45c519265fee0a"},"schema_version":"1.0","source":{"id":"2302.03169","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03169","created_at":"2026-07-05T07:14:09Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03169v3","created_at":"2026-07-05T07:14:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03169","created_at":"2026-07-05T07:14:09Z"},{"alias_kind":"pith_short_12","alias_value":"2W6U6JEWDCCP","created_at":"2026-07-05T07:14:09Z"},{"alias_kind":"pith_short_16","alias_value":"2W6U6JEWDCCPA5G4","created_at":"2026-07-05T07:14:09Z"},{"alias_kind":"pith_short_8","alias_value":"2W6U6JEW","created_at":"2026-07-05T07:14:09Z"}],"graph_snapshots":[{"event_id":"sha256:5ddc86c38ff71c2a90561a63fecd38b375167b41da9c90632a41e1cdb9c6dea4","target":"graph","created_at":"2026-07-05T07:14:09Z","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/2302.03169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Selecting a suitable pretraining dataset is crucial for both general-domain (e.g., GPT-3) and domain-specific (e.g., Codex) language models (LMs). We formalize this problem as selecting a subset of a large raw unlabeled dataset to match a desired target distribution given unlabeled target samples. Due to the scale and dimensionality of the raw text data, existing methods use simple heuristics or require human experts to manually curate data. Instead, we extend the classic importance resampling approach used in low-dimensions for LM data selection. We propose Data Selection with Importance Resa","authors_text":"Percy Liang, Sang Michael Xie, Shibani Santurkar, Tengyu Ma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-06T23:57:56Z","title":"Data Selection for Language Models via Importance Resampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03169","kind":"arxiv","version":3},"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":"sha256:8e76ec8b88d7172348c50c90a83cde58924cf35aaa441acc733e8a33946c21fa","target":"record","created_at":"2026-07-05T07:14:09Z","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":"94aca8849a0206dbf44b8b3052842a64bc645dd8b4b1f0e97cfed8971ff8a0e3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-06T23:57:56Z","title_canon_sha256":"92bf449ead3da75abf53b69965b628ab48b6481ff1d9af273b45c519265fee0a"},"schema_version":"1.0","source":{"id":"2302.03169","kind":"arxiv","version":3}},"canonical_sha256":"d5bd4f24961884f074dca8fd1eae32888ace09328114e62b4b9f9f379bbb5103","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5bd4f24961884f074dca8fd1eae32888ace09328114e62b4b9f9f379bbb5103","first_computed_at":"2026-07-05T07:14:09.197092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:09.197092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W0hjaJ7jH1MJXQQ9//aGHUGKIH3RZo63ATZphYrEcv3kIdaZuko6te8pJfx2X93tp4sdOk/QgWszzPiJlQfGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:09.197558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03169","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e76ec8b88d7172348c50c90a83cde58924cf35aaa441acc733e8a33946c21fa","sha256:5ddc86c38ff71c2a90561a63fecd38b375167b41da9c90632a41e1cdb9c6dea4"],"state_sha256":"52fe6c024913e6efcbea9aa8e4d34dedbdf86447abe5a8638b30c7ff22f943e1"}