{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZQJR5PQ77WRWGZ7I4XNJHKESOI","short_pith_number":"pith:ZQJR5PQ7","schema_version":"1.0","canonical_sha256":"cc131ebe1ffda36367e8e5da93a892720b6cb223b2f277b30d72843e0bddf97a","source":{"kind":"arxiv","id":"2606.21641","version":1},"attestation_state":"computed","paper":{"title":"When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carson Rodrigues, Oysturn Vas","submitted_at":"2026-06-19T17:52:36Z","abstract_excerpt":"Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that \"warm-start\" search from prior knowledge, proposing strong configurations in very few evaluations. We test that claim under a budget-matched, multi-seed protocol on eight PMLB tabular benchmarks, comparing an LLM advisor (LLM-OptFlow) against four classical baselines (random search, Optuna-TPE, Gaussian-process Bayesian optimization, and successive halving) over one shared search space, with paired tests and bootstrap 95% CIs across 8 x 5 = 40 (task, seed) units. The finding is cautionary. The ad"},"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":"2606.21641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:52:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22e1f0585d48aba316a407108ad2fc4f5174fffe3ae24ccc5043a92c1acad582","abstract_canon_sha256":"8217609e7b33f793aecb45b123b0500e90fc0fc17db1d76a71b6e66bd2b93a2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:17.596933Z","signature_b64":"C5J/PwmSH5hAAiLaRB9TBdqPKEDaNa1mmLTIhvtSqdjeIM2P7I+dBluFR4ZHJFkHVkDmAyvbwFX7YnXupKgUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc131ebe1ffda36367e8e5da93a892720b6cb223b2f277b30d72843e0bddf97a","last_reissued_at":"2026-06-23T01:13:17.596395Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:17.596395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carson Rodrigues, Oysturn Vas","submitted_at":"2026-06-19T17:52:36Z","abstract_excerpt":"Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that \"warm-start\" search from prior knowledge, proposing strong configurations in very few evaluations. We test that claim under a budget-matched, multi-seed protocol on eight PMLB tabular benchmarks, comparing an LLM advisor (LLM-OptFlow) against four classical baselines (random search, Optuna-TPE, Gaussian-process Bayesian optimization, and successive halving) over one shared search space, with paired tests and bootstrap 95% CIs across 8 x 5 = 40 (task, seed) units. The finding is cautionary. The ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21641","kind":"arxiv","version":1},"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/2606.21641/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":"2606.21641","created_at":"2026-06-23T01:13:17.596471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21641v1","created_at":"2026-06-23T01:13:17.596471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21641","created_at":"2026-06-23T01:13:17.596471+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQJR5PQ77WRW","created_at":"2026-06-23T01:13:17.596471+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQJR5PQ77WRWGZ7I","created_at":"2026-06-23T01:13:17.596471+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQJR5PQ7","created_at":"2026-06-23T01:13:17.596471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI","json":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI.json","graph_json":"https://pith.science/api/pith-number/ZQJR5PQ77WRWGZ7I4XNJHKESOI/graph.json","events_json":"https://pith.science/api/pith-number/ZQJR5PQ77WRWGZ7I4XNJHKESOI/events.json","paper":"https://pith.science/paper/ZQJR5PQ7"},"agent_actions":{"view_html":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI","download_json":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI.json","view_paper":"https://pith.science/paper/ZQJR5PQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21641&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQJR5PQ77WRWGZ7I4XNJHKESOI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQJR5PQ77WRWGZ7I4XNJHKESOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI/action/storage_attestation","attest_author":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI/action/author_attestation","sign_citation":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI/action/citation_signature","submit_replication":"https://pith.science/pith/ZQJR5PQ77WRWGZ7I4XNJHKESOI/action/replication_record"}},"created_at":"2026-06-23T01:13:17.596471+00:00","updated_at":"2026-06-23T01:13:17.596471+00:00"}