{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3WGJGZ47ZPBLAZ2IICLMN67IEE","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":"21cda24e38800e411b4092eb5b9c164411473c0be86dc2aa03db0a30abde05b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:06:57Z","title_canon_sha256":"4b120f2d81b7f1a4250cd9e2096cfa2ccc1cc0e44f8cc0efbe81b267d891361e"},"schema_version":"1.0","source":{"id":"2410.07064","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07064","created_at":"2026-07-05T10:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07064v2","created_at":"2026-07-05T10:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07064","created_at":"2026-07-05T10:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"3WGJGZ47ZPBL","created_at":"2026-07-05T10:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"3WGJGZ47ZPBLAZ2I","created_at":"2026-07-05T10:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"3WGJGZ47","created_at":"2026-07-05T10:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:3723c9ce2015faccbbb8820e55e5ac2026163871b36f2dd12cc60b3011294ccd","target":"graph","created_at":"2026-07-05T10:34:11Z","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/2410.07064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work investigates the selection of high-quality pre-training data from massive corpora to enhance LMs' capabilities for downstream usage. We formulate data selection as a generalized Optimal Control problem, which can be solved theoretically by Pontryagin's Maximum Principle (PMP), yielding a set of necessary conditions that characterize the relationship between optimal data selection and LM training dynamics. Based on these theoretical results, we introduce PMP-based Data Selection (PDS), a framework that approximates optimal data selection by solving the PMP conditions. In our experimen","authors_text":"Furu Wei, Hongning Wang, Li Dong, Minlie Huang, Qingxiu Dong, Yaru Hao, Yuxian Gu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:06:57Z","title":"Data Selection via Optimal Control for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07064","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":"sha256:330360d144581482104b4614ee457b9ab370abb0d4977bfc851019d5fcf60831","target":"record","created_at":"2026-07-05T10:34:11Z","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":"21cda24e38800e411b4092eb5b9c164411473c0be86dc2aa03db0a30abde05b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:06:57Z","title_canon_sha256":"4b120f2d81b7f1a4250cd9e2096cfa2ccc1cc0e44f8cc0efbe81b267d891361e"},"schema_version":"1.0","source":{"id":"2410.07064","kind":"arxiv","version":2}},"canonical_sha256":"dd8c93679fcbc2b067484096c6fbe82114e8acc561cbcd1c39d33c514b9da173","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd8c93679fcbc2b067484096c6fbe82114e8acc561cbcd1c39d33c514b9da173","first_computed_at":"2026-07-05T10:34:11.387516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:11.387516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xd0lG2cxiIx2oGE7IYusyY6E7YjMwdnVSZvx0rtbarOY7YB7Clkd9keXqLyWw79ZW0in+WzCOkUwSIeZu+DBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:11.388562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07064","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:330360d144581482104b4614ee457b9ab370abb0d4977bfc851019d5fcf60831","sha256:3723c9ce2015faccbbb8820e55e5ac2026163871b36f2dd12cc60b3011294ccd"],"state_sha256":"a547333954ac76feb04b39741236a0052f39a82ab4d4df2942b1f85f5fd174d6"}