{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TJU2BRHOLTV5VEKKTU7MCYLCV7","short_pith_number":"pith:TJU2BRHO","canonical_record":{"source":{"id":"2602.11171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T08:48:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b31743f76e58fdd8f750d329b572eade5d738e0e0342162aba98e45b64368117","abstract_canon_sha256":"74033c8f8203cd9d472a4cb7b7ef9392058ff644b878780777c1be93590c573b"},"schema_version":"1.0"},"canonical_sha256":"9a69a0c4ee5cebda914a9d3ec16162afd3399380dc6ae155685fe10ea88c6c82","source":{"kind":"arxiv","id":"2602.11171","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.11171","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2602.11171v2","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11171","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"TJU2BRHOLTV5","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"TJU2BRHOLTV5VEKK","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"TJU2BRHO","created_at":"2026-05-29T01:05:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TJU2BRHOLTV5VEKKTU7MCYLCV7","target":"record","payload":{"canonical_record":{"source":{"id":"2602.11171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T08:48:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b31743f76e58fdd8f750d329b572eade5d738e0e0342162aba98e45b64368117","abstract_canon_sha256":"74033c8f8203cd9d472a4cb7b7ef9392058ff644b878780777c1be93590c573b"},"schema_version":"1.0"},"canonical_sha256":"9a69a0c4ee5cebda914a9d3ec16162afd3399380dc6ae155685fe10ea88c6c82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:04.376776Z","signature_b64":"WzSruNctImNaaniXoDWrWBq7veo0nzRI/w1VdKWK87+t9OCJQEF6i5ewy7ArY43sE7nBQdUwA1ribZt/yQWxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a69a0c4ee5cebda914a9d3ec16162afd3399380dc6ae155685fe10ea88c6c82","last_reissued_at":"2026-05-29T01:05:04.375796Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:04.375796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.11171","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bF0d2OUO3crby5gLXL4iIwBePLc2KIaTzufPSxPTMPNSuvI7e8RF3UwphYHq2q5U2Twp/tnt9/EofJai8IRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T13:10:15.945614Z"},"content_sha256":"a003ee3ab5a900a58b41a398ae6ab221e551eb1e97e60597d2d57ccf72482de2","schema_version":"1.0","event_id":"sha256:a003ee3ab5a900a58b41a398ae6ab221e551eb1e97e60597d2d57ccf72482de2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TJU2BRHOLTV5VEKKTU7MCYLCV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baek Seong-Eun, Kim Sung-Bin, Lee Jung-Mok, Tae-Hyun Oh","submitted_at":"2026-01-19T08:48:03Z","abstract_excerpt":"Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) offers a resource-efficient way to personalize or specialize. However, LoRA is highly sensitive to hyperparameter choices, and exhaustive hyperparameter search is computationally expensive. To address this, we propose a Bayesian Optimization (BO) framework that leverages the domain knowledge of pre-trained LLMs to efficiently search for LoRA hyperparameters. Our approach repurposes a pre-trained LLM as a discrete-to-continuous mapping module to link hyperparameters and their domain knowledge to a continuous vector space, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11171","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/2602.11171/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qVBROWnaMoRi8comEN1ZYKjzQagOs2mNqMUfzCeVbSvKhYYU5GbidgIgyphgvWEOowLpdgNTDYKR23UdFnq6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T13:10:15.945991Z"},"content_sha256":"2489c6c6e56a2eda596ad42a61ba76b784269b3d5a2bc2a642de722f8899206c","schema_version":"1.0","event_id":"sha256:2489c6c6e56a2eda596ad42a61ba76b784269b3d5a2bc2a642de722f8899206c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJU2BRHOLTV5VEKKTU7MCYLCV7/bundle.json","state_url":"https://pith.science/pith/TJU2BRHOLTV5VEKKTU7MCYLCV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJU2BRHOLTV5VEKKTU7MCYLCV7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T13:10:15Z","links":{"resolver":"https://pith.science/pith/TJU2BRHOLTV5VEKKTU7MCYLCV7","bundle":"https://pith.science/pith/TJU2BRHOLTV5VEKKTU7MCYLCV7/bundle.json","state":"https://pith.science/pith/TJU2BRHOLTV5VEKKTU7MCYLCV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJU2BRHOLTV5VEKKTU7MCYLCV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TJU2BRHOLTV5VEKKTU7MCYLCV7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"74033c8f8203cd9d472a4cb7b7ef9392058ff644b878780777c1be93590c573b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T08:48:03Z","title_canon_sha256":"b31743f76e58fdd8f750d329b572eade5d738e0e0342162aba98e45b64368117"},"schema_version":"1.0","source":{"id":"2602.11171","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.11171","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2602.11171v2","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11171","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"TJU2BRHOLTV5","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"TJU2BRHOLTV5VEKK","created_at":"2026-05-29T01:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"TJU2BRHO","created_at":"2026-05-29T01:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:2489c6c6e56a2eda596ad42a61ba76b784269b3d5a2bc2a642de722f8899206c","target":"graph","created_at":"2026-05-29T01:05:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.11171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) offers a resource-efficient way to personalize or specialize. However, LoRA is highly sensitive to hyperparameter choices, and exhaustive hyperparameter search is computationally expensive. To address this, we propose a Bayesian Optimization (BO) framework that leverages the domain knowledge of pre-trained LLMs to efficiently search for LoRA hyperparameters. Our approach repurposes a pre-trained LLM as a discrete-to-continuous mapping module to link hyperparameters and their domain knowledge to a continuous vector space, ","authors_text":"Baek Seong-Eun, Kim Sung-Bin, Lee Jung-Mok, Tae-Hyun Oh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T08:48:03Z","title":"A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11171","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a003ee3ab5a900a58b41a398ae6ab221e551eb1e97e60597d2d57ccf72482de2","target":"record","created_at":"2026-05-29T01:05:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"74033c8f8203cd9d472a4cb7b7ef9392058ff644b878780777c1be93590c573b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T08:48:03Z","title_canon_sha256":"b31743f76e58fdd8f750d329b572eade5d738e0e0342162aba98e45b64368117"},"schema_version":"1.0","source":{"id":"2602.11171","kind":"arxiv","version":2}},"canonical_sha256":"9a69a0c4ee5cebda914a9d3ec16162afd3399380dc6ae155685fe10ea88c6c82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a69a0c4ee5cebda914a9d3ec16162afd3399380dc6ae155685fe10ea88c6c82","first_computed_at":"2026-05-29T01:05:04.375796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:04.375796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WzSruNctImNaaniXoDWrWBq7veo0nzRI/w1VdKWK87+t9OCJQEF6i5ewy7ArY43sE7nBQdUwA1ribZt/yQWxCw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:04.376776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.11171","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a003ee3ab5a900a58b41a398ae6ab221e551eb1e97e60597d2d57ccf72482de2","sha256:2489c6c6e56a2eda596ad42a61ba76b784269b3d5a2bc2a642de722f8899206c"],"state_sha256":"4ca38cb4997552415712ec17bffac466f7526a8e77f8b5525f7eb1429d028796"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQalmpkbeiCr6A8JyXYOF+FYTGBF97jBSRyL3ZdCrPTj0kdGpd3gVJBSy+vsyuEP8LBDsABKZXR5JabiRY6XBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T13:10:15.948046Z","bundle_sha256":"2d97d520d70535ce2afaaae7780ffa6195a08aff3a402d7eae5180abacb8b872"}}