{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TNC2ABXZHR3R7XPEXW2ZLXNIZ5","short_pith_number":"pith:TNC2ABXZ","schema_version":"1.0","canonical_sha256":"9b45a006f93c771fdde4bdb595dda8cf5b2bfcb3ee53d59f5b3c5cff392cd39e","source":{"kind":"arxiv","id":"2507.15485","version":1},"attestation_state":"computed","paper":{"title":"Information Preserving Line Search via Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Robin Labryga, S\\\"oren Laue, Tomislav Prusina","submitted_at":"2025-07-21T10:42:12Z","abstract_excerpt":"Line search is a fundamental part of iterative optimization methods for unconstrained and bound-constrained optimization problems to determine suitable step lengths that provide sufficient improvement in each iteration. Traditional line search methods are based on iterative interval refinement, where valuable information about function value and gradient is discarded in each iteration. We propose a line search method via Bayesian optimization, preserving and utilizing otherwise discarded information to improve step-length choices. Our approach is guaranteed to converge and shows superior perfo"},"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":"2507.15485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-07-21T10:42:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c4b6fd0f98a5587c10e030e6ba7beda40c497ea7bd388b40e6c8f8950a45638","abstract_canon_sha256":"f313515a0028aedfb4be803c738a9a0c17c8ba8d56fffcaab341f9f2bcaa2c41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:37.926363Z","signature_b64":"mbE/VpXVYmcGYIGA+hfouAVlfoZXNmUaGKvjCXq4tGqbwd6P3bBLLpxg9qrldqFHm8431UvZmcAB1B9WvYpzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b45a006f93c771fdde4bdb595dda8cf5b2bfcb3ee53d59f5b3c5cff392cd39e","last_reissued_at":"2026-07-05T11:40:37.925863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:37.925863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information Preserving Line Search via Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Robin Labryga, S\\\"oren Laue, Tomislav Prusina","submitted_at":"2025-07-21T10:42:12Z","abstract_excerpt":"Line search is a fundamental part of iterative optimization methods for unconstrained and bound-constrained optimization problems to determine suitable step lengths that provide sufficient improvement in each iteration. Traditional line search methods are based on iterative interval refinement, where valuable information about function value and gradient is discarded in each iteration. We propose a line search method via Bayesian optimization, preserving and utilizing otherwise discarded information to improve step-length choices. Our approach is guaranteed to converge and shows superior perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15485","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/2507.15485/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":"2507.15485","created_at":"2026-07-05T11:40:37.925918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15485v1","created_at":"2026-07-05T11:40:37.925918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15485","created_at":"2026-07-05T11:40:37.925918+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNC2ABXZHR3R","created_at":"2026-07-05T11:40:37.925918+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNC2ABXZHR3R7XPE","created_at":"2026-07-05T11:40:37.925918+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNC2ABXZ","created_at":"2026-07-05T11:40:37.925918+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/TNC2ABXZHR3R7XPEXW2ZLXNIZ5","json":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5.json","graph_json":"https://pith.science/api/pith-number/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/graph.json","events_json":"https://pith.science/api/pith-number/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/events.json","paper":"https://pith.science/paper/TNC2ABXZ"},"agent_actions":{"view_html":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5","download_json":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5.json","view_paper":"https://pith.science/paper/TNC2ABXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15485&json=true","fetch_graph":"https://pith.science/api/pith-number/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/action/storage_attestation","attest_author":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/action/author_attestation","sign_citation":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/action/citation_signature","submit_replication":"https://pith.science/pith/TNC2ABXZHR3R7XPEXW2ZLXNIZ5/action/replication_record"}},"created_at":"2026-07-05T11:40:37.925918+00:00","updated_at":"2026-07-05T11:40:37.925918+00:00"}