{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QFH7IZY5VJMQ5STIJLA7H7NFGJ","short_pith_number":"pith:QFH7IZY5","schema_version":"1.0","canonical_sha256":"814ff4671daa590eca684ac1f3fda5327597bf96ad1cfa81c786a37f1a64d0e3","source":{"kind":"arxiv","id":"2402.14547","version":6},"attestation_state":"computed","paper":{"title":"OmniPred: Language Models as Universal Regressors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Bangding Yang, Chansoo Lee, Daiyi Peng, Oscar Li, Sagi Perel, Xingyou Song, Yutian Chen","submitted_at":"2024-02-22T13:36:53Z","abstract_excerpt":"Regression is a powerful tool to accurately predict the outcome metric of a system given a set of parameters, but has traditionally been restricted to methods which are only applicable to a specific task. In this paper, we propose OmniPred, a framework for training language models as universal end-to-end regressors over $(x,y)$ data from arbitrary formats. Using data sourced from Google Vizier, one of the largest proprietary blackbox optimization databases in the world, our extensive experiments demonstrate that language models are capable of very precise numerical regression using only textua"},"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":"2402.14547","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T13:36:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"title_canon_sha256":"2515c1208f2325c5282ba7eaa63bcaaec90482535e475242bd7da585a70be5eb","abstract_canon_sha256":"d04e58f96a1d4f91c3274bab8c8caab9aeca2747409979817ae32fbf303653a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:39.500393Z","signature_b64":"3SfrrrJ1T8BQzOeZhv4E4j9n1DLKKuuhfoIABM3Mb8KgFohqy06yE8fyBVIvJHTlyYzNz0QGxap7e5vPKgjUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"814ff4671daa590eca684ac1f3fda5327597bf96ad1cfa81c786a37f1a64d0e3","last_reissued_at":"2026-07-05T10:07:39.499941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:39.499941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniPred: Language Models as Universal Regressors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Bangding Yang, Chansoo Lee, Daiyi Peng, Oscar Li, Sagi Perel, Xingyou Song, Yutian Chen","submitted_at":"2024-02-22T13:36:53Z","abstract_excerpt":"Regression is a powerful tool to accurately predict the outcome metric of a system given a set of parameters, but has traditionally been restricted to methods which are only applicable to a specific task. In this paper, we propose OmniPred, a framework for training language models as universal end-to-end regressors over $(x,y)$ data from arbitrary formats. Using data sourced from Google Vizier, one of the largest proprietary blackbox optimization databases in the world, our extensive experiments demonstrate that language models are capable of very precise numerical regression using only textua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14547","kind":"arxiv","version":6},"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/2402.14547/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":"2402.14547","created_at":"2026-07-05T10:07:39.499991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14547v6","created_at":"2026-07-05T10:07:39.499991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14547","created_at":"2026-07-05T10:07:39.499991+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFH7IZY5VJMQ","created_at":"2026-07-05T10:07:39.499991+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFH7IZY5VJMQ5STI","created_at":"2026-07-05T10:07:39.499991+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFH7IZY5","created_at":"2026-07-05T10:07:39.499991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29408","citing_title":"Large language model for unified and accurate description of multidimensional nuclear properties","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20740","citing_title":"Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ","json":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ.json","graph_json":"https://pith.science/api/pith-number/QFH7IZY5VJMQ5STIJLA7H7NFGJ/graph.json","events_json":"https://pith.science/api/pith-number/QFH7IZY5VJMQ5STIJLA7H7NFGJ/events.json","paper":"https://pith.science/paper/QFH7IZY5"},"agent_actions":{"view_html":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ","download_json":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ.json","view_paper":"https://pith.science/paper/QFH7IZY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14547&json=true","fetch_graph":"https://pith.science/api/pith-number/QFH7IZY5VJMQ5STIJLA7H7NFGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QFH7IZY5VJMQ5STIJLA7H7NFGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ/action/storage_attestation","attest_author":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ/action/author_attestation","sign_citation":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ/action/citation_signature","submit_replication":"https://pith.science/pith/QFH7IZY5VJMQ5STIJLA7H7NFGJ/action/replication_record"}},"created_at":"2026-07-05T10:07:39.499991+00:00","updated_at":"2026-07-05T10:07:39.499991+00:00"}