{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZOK27OFHMEETYJQKGPPPZX5U5","short_pith_number":"pith:UZOK27OF","schema_version":"1.0","canonical_sha256":"a65cad7dc53b0849e130519ef7e6fda75f0a3c7f823c4d83a3ba31c129bf6b3f","source":{"kind":"arxiv","id":"2501.13018","version":2},"attestation_state":"computed","paper":{"title":"Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Amirmohammad Farzaneh, Osvaldo Simeone","submitted_at":"2025-01-22T17:05:38Z","abstract_excerpt":"The selection of hyperparameters, such as prompt templates in large language models (LLMs), must often strike a balance between reliability and cost. In many cases, structural relationships between the expected reliability levels of the hyperparameters can be inferred from prior information and held-out data -- e.g., longer prompt templates may be more detailed and thus more reliable. However, existing hyperparameter selection methods either do not provide formal reliability guarantees or are unable to incorporate structured knowledge in the hyperparameter space. This paper introduces reliabil"},"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":"2501.13018","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T17:05:38Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"287a8107088782456f3b18e426181a9acda681926b4d4e473470bed47d6f2c5a","abstract_canon_sha256":"ae5c989e7b77bfbc1bb0e282525fc76723694bbb8a0ce447c9452ab6bd811a61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:20.592070Z","signature_b64":"gg+X6EI8BX8yaq99OqayHtgtUYieuPfs+mahzarbQgfZvvY4G7Hb4H4UvBESy/3HTIB0LRZmIkjIMTOlyN/ACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a65cad7dc53b0849e130519ef7e6fda75f0a3c7f823c4d83a3ba31c129bf6b3f","last_reissued_at":"2026-07-05T11:03:20.591655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:20.591655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Amirmohammad Farzaneh, Osvaldo Simeone","submitted_at":"2025-01-22T17:05:38Z","abstract_excerpt":"The selection of hyperparameters, such as prompt templates in large language models (LLMs), must often strike a balance between reliability and cost. In many cases, structural relationships between the expected reliability levels of the hyperparameters can be inferred from prior information and held-out data -- e.g., longer prompt templates may be more detailed and thus more reliable. However, existing hyperparameter selection methods either do not provide formal reliability guarantees or are unable to incorporate structured knowledge in the hyperparameter space. This paper introduces reliabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13018","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/2501.13018/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":"2501.13018","created_at":"2026-07-05T11:03:20.591708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13018v2","created_at":"2026-07-05T11:03:20.591708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13018","created_at":"2026-07-05T11:03:20.591708+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZOK27OFHMEE","created_at":"2026-07-05T11:03:20.591708+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZOK27OFHMEETYJQ","created_at":"2026-07-05T11:03:20.591708+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZOK27OF","created_at":"2026-07-05T11:03:20.591708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04206","citing_title":"Ensuring Reliability via Hyperparameter Selection: Review and Advances","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5","json":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5.json","graph_json":"https://pith.science/api/pith-number/UZOK27OFHMEETYJQKGPPPZX5U5/graph.json","events_json":"https://pith.science/api/pith-number/UZOK27OFHMEETYJQKGPPPZX5U5/events.json","paper":"https://pith.science/paper/UZOK27OF"},"agent_actions":{"view_html":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5","download_json":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5.json","view_paper":"https://pith.science/paper/UZOK27OF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13018&json=true","fetch_graph":"https://pith.science/api/pith-number/UZOK27OFHMEETYJQKGPPPZX5U5/graph.json","fetch_events":"https://pith.science/api/pith-number/UZOK27OFHMEETYJQKGPPPZX5U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5/action/storage_attestation","attest_author":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5/action/author_attestation","sign_citation":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5/action/citation_signature","submit_replication":"https://pith.science/pith/UZOK27OFHMEETYJQKGPPPZX5U5/action/replication_record"}},"created_at":"2026-07-05T11:03:20.591708+00:00","updated_at":"2026-07-05T11:03:20.591708+00:00"}