{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XQBSJW46LSM5LPNML53IXJZMHM","short_pith_number":"pith:XQBSJW46","schema_version":"1.0","canonical_sha256":"bc0324db9e5c99d5bdac5f768ba72c3b34be4d8d212a73fb098afe80da1f41ec","source":{"kind":"arxiv","id":"2508.11551","version":2},"attestation_state":"computed","paper":{"title":"ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jonathan Richard Schwarz, Michael Arthur Leopold Pearce, Shengzhuang Chen, Thomas Hartvigsen, Xu Ouyang","submitted_at":"2025-08-15T15:53:09Z","abstract_excerpt":"Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no learning-based approach has emerged as a reliable solution. In this work, we propose to view the selection of training data mixtures as a black-box hyperparameter optimization problem, for which Bayesian Optimization is a well-established class of appropriate algorithms. Firstly, we cast data mixture learning as a sequential decision-making problem, in which we aim t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.11551","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-15T15:53:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5d2954414be9884c2a21ea6d4bf3504c1343befeeb905f1600185cb42ee2d77e","abstract_canon_sha256":"64f6c9a8930c89c9967646679a78597c84d8fb30c7e2a46dd912920a9c373957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:22.619969Z","signature_b64":"ctOKNJzJ3gKnYaU5blz5j2l4MyM4mXDGDu91gWSGWsZ7Tm8z1gYd/JNs3saMeyI+Tyzfw2ks2ZMzc9iXbTSMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc0324db9e5c99d5bdac5f768ba72c3b34be4d8d212a73fb098afe80da1f41ec","last_reissued_at":"2026-07-05T11:55:22.619407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:22.619407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jonathan Richard Schwarz, Michael Arthur Leopold Pearce, Shengzhuang Chen, Thomas Hartvigsen, Xu Ouyang","submitted_at":"2025-08-15T15:53:09Z","abstract_excerpt":"Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no learning-based approach has emerged as a reliable solution. In this work, we propose to view the selection of training data mixtures as a black-box hyperparameter optimization problem, for which Bayesian Optimization is a well-established class of appropriate algorithms. Firstly, we cast data mixture learning as a sequential decision-making problem, in which we aim t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11551","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.11551/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.11551","created_at":"2026-07-05T11:55:22.619463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11551v2","created_at":"2026-07-05T11:55:22.619463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11551","created_at":"2026-07-05T11:55:22.619463+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQBSJW46LSM5","created_at":"2026-07-05T11:55:22.619463+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQBSJW46LSM5LPNM","created_at":"2026-07-05T11:55:22.619463+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQBSJW46","created_at":"2026-07-05T11:55:22.619463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16380","citing_title":"Data Mixing for Large Language Models Pretraining: A Survey and Outlook","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM","json":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM.json","graph_json":"https://pith.science/api/pith-number/XQBSJW46LSM5LPNML53IXJZMHM/graph.json","events_json":"https://pith.science/api/pith-number/XQBSJW46LSM5LPNML53IXJZMHM/events.json","paper":"https://pith.science/paper/XQBSJW46"},"agent_actions":{"view_html":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM","download_json":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM.json","view_paper":"https://pith.science/paper/XQBSJW46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11551&json=true","fetch_graph":"https://pith.science/api/pith-number/XQBSJW46LSM5LPNML53IXJZMHM/graph.json","fetch_events":"https://pith.science/api/pith-number/XQBSJW46LSM5LPNML53IXJZMHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM/action/storage_attestation","attest_author":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM/action/author_attestation","sign_citation":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM/action/citation_signature","submit_replication":"https://pith.science/pith/XQBSJW46LSM5LPNML53IXJZMHM/action/replication_record"}},"created_at":"2026-07-05T11:55:22.619463+00:00","updated_at":"2026-07-05T11:55:22.619463+00:00"}