{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7GYTYXCZINHO3FIRS5UGUUW5U6","short_pith_number":"pith:7GYTYXCZ","canonical_record":{"source":{"id":"2605.14553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:31:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c149f0a446ae0b8ac99743af2877fb60c45c6e55da7fa3e0aad129f942dc622","abstract_canon_sha256":"f050c93ebd59f08f662dc444c16665764f030df1eef20bb1bde6cb98a3ae691b"},"schema_version":"1.0"},"canonical_sha256":"f9b13c5c59434eed951197686a52dda7857842c3d601f2d8a70f0ddd4a739b9c","source":{"kind":"arxiv","id":"2605.14553","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14553","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14553v1","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14553","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"7GYTYXCZINHO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7GYTYXCZINHO3FIR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7GYTYXCZ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7GYTYXCZINHO3FIRS5UGUUW5U6","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:31:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c149f0a446ae0b8ac99743af2877fb60c45c6e55da7fa3e0aad129f942dc622","abstract_canon_sha256":"f050c93ebd59f08f662dc444c16665764f030df1eef20bb1bde6cb98a3ae691b"},"schema_version":"1.0"},"canonical_sha256":"f9b13c5c59434eed951197686a52dda7857842c3d601f2d8a70f0ddd4a739b9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.682736Z","signature_b64":"he57Oo1NPBwiXG6PDg4uqtqbghRbY4mlJ6znf7Mu2B13nneMiP7Z8NMGlu374Bcf5JK2j//Tf081f1nfuA3sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9b13c5c59434eed951197686a52dda7857842c3d601f2d8a70f0ddd4a739b9c","last_reissued_at":"2026-05-17T23:39:05.682032Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.682032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14553","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5JqfQ36lYYjxbhdHpykHoIRUMPSjRDcdGDC9OlLkKPf/ekQnfM1zWLp+yZBTNWo9T2PAhXgjTuH/v5Y8oHfiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:11:27.316693Z"},"content_sha256":"0f962790002485eb05c0a6e168a75a62b2f3773430a81c284cad7da2f0eb77db","schema_version":"1.0","event_id":"sha256:0f962790002485eb05c0a6e168a75a62b2f3773430a81c284cad7da2f0eb77db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7GYTYXCZINHO3FIRS5UGUUW5U6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengshuai Shi, Cong Shen, Donghao Li, Jing Yang, Weijuan Ou","submitted_at":"2026-05-14T08:31:17Z","abstract_excerpt":"Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt performance, which cannot be captured by a single metric. To fill this gap, we study the multi-objective prompt selection problem under two practical settings: Pareto prompt set recovery and best feasible prompt identification. Casting the problem into the pure-exploration bandits framework, we adapt p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Prompt performance across multiple objectives can be modeled as rewards from independent or linearly structured arms in a pure-exploration bandit setting without significant interference or non-stationarity from LLM stochasticity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c558920ac2ac792c7247d4fc736c4717fb47f4e8affad22e63b6cedd3eccd3f1"},"source":{"id":"2605.14553","kind":"arxiv","version":1},"verdict":{"id":"ae9d7599-fe60-4212-afc9-226b40e7a23c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:47:29.025982Z","strongest_claim":"Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines.","one_line_summary":"Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Prompt performance across multiple objectives can be modeled as rewards from independent or linearly structured arms in a pure-exploration bandit setting without significant interference or non-stationarity from LLM stochasticity.","pith_extraction_headline":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees."},"references":{"count":33,"sample":[{"doi":"","year":2025,"title":"Gepa: Reflective prompt evolution can outperform reinforcement learning","work_id":"3de5a529-96e4-4800-82cd-546562b68f98","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Best arm identification in multi-armed bandits","work_id":"8c40c1c5-f69c-4f4d-966c-e335bdb85b4e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901","work_id":"84780adb-76cf-44ac-a8b7-e24d4fa5c592","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Leaf: A benchmark for federated settings","work_id":"94ec8be1-6cf1-4962-994c-e762a0b9c3ee","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Discrete prompt optimization via constrained generation for zero-shot re-ranker","work_id":"0c01ab93-25b2-4bca-b51b-919144ac6c2c","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"9a0161828a6a59d6c66ffc98eb97c27ce3a8e511285d867ad587ec3324b600cd","internal_anchors":4},"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":"ae9d7599-fe60-4212-afc9-226b40e7a23c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l7C0DRs0IqYvyxQnRyW/6EpUab4a34ojxLCMS4w7WVbZS1cwhQQRblLP8aipjJ6IaDwiARsRtb7x99CeMpsuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:11:27.317862Z"},"content_sha256":"33445f0b4adf09e2be7d2546150d06248b3197fdd32b919289c430b4728f44de","schema_version":"1.0","event_id":"sha256:33445f0b4adf09e2be7d2546150d06248b3197fdd32b919289c430b4728f44de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/bundle.json","state_url":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/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":"2026-05-25T17:11:27Z","links":{"resolver":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6","bundle":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/bundle.json","state":"https://pith.science/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GYTYXCZINHO3FIRS5UGUUW5U6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7GYTYXCZINHO3FIRS5UGUUW5U6","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":"f050c93ebd59f08f662dc444c16665764f030df1eef20bb1bde6cb98a3ae691b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:31:17Z","title_canon_sha256":"2c149f0a446ae0b8ac99743af2877fb60c45c6e55da7fa3e0aad129f942dc622"},"schema_version":"1.0","source":{"id":"2605.14553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14553","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14553v1","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14553","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"7GYTYXCZINHO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7GYTYXCZINHO3FIR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7GYTYXCZ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:33445f0b4adf09e2be7d2546150d06248b3197fdd32b919289c430b4728f44de","target":"graph","created_at":"2026-05-17T23:39:05Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Prompt performance across multiple objectives can be modeled as rewards from independent or linearly structured arms in a pure-exploration bandit setting without significant interference or non-stationarity from LLM stochasticity."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees."}],"snapshot_sha256":"c558920ac2ac792c7247d4fc736c4717fb47f4e8affad22e63b6cedd3eccd3f1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt performance, which cannot be captured by a single metric. To fill this gap, we study the multi-objective prompt selection problem under two practical settings: Pareto prompt set recovery and best feasible prompt identification. Casting the problem into the pure-exploration bandits framework, we adapt p","authors_text":"Chengshuai Shi, Cong Shen, Donghao Li, Jing Yang, Weijuan Ou","cross_cats":["cs.AI"],"headline":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits"},"references":{"count":33,"internal_anchors":4,"resolved_work":33,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Gepa: Reflective prompt evolution can outperform reinforcement learning","work_id":"3de5a529-96e4-4800-82cd-546562b68f98","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Best arm identification in multi-armed bandits","work_id":"8c40c1c5-f69c-4f4d-966c-e335bdb85b4e","year":2010},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901","work_id":"84780adb-76cf-44ac-a8b7-e24d4fa5c592","year":1901},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Leaf: A benchmark for federated settings","work_id":"94ec8be1-6cf1-4962-994c-e762a0b9c3ee","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":6,"title":"Discrete prompt optimization via constrained generation for zero-shot re-ranker","work_id":"0c01ab93-25b2-4bca-b51b-919144ac6c2c","year":2023}],"snapshot_sha256":"9a0161828a6a59d6c66ffc98eb97c27ce3a8e511285d867ad587ec3324b600cd"},"source":{"id":"2605.14553","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:47:29.025982Z","id":"ae9d7599-fe60-4212-afc9-226b40e7a23c","model_set":{"reader":"grok-4.3"},"one_line_summary":"Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multi-objective prompt selection for large language models reduces to pure-exploration bandit problems, enabling efficient algorithms with theoretical guarantees.","strongest_claim":"Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines.","weakest_assumption":"Prompt performance across multiple objectives can be modeled as rewards from independent or linearly structured arms in a pure-exploration bandit setting without significant interference or non-stationarity from LLM stochasticity."}},"verdict_id":"ae9d7599-fe60-4212-afc9-226b40e7a23c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0f962790002485eb05c0a6e168a75a62b2f3773430a81c284cad7da2f0eb77db","target":"record","created_at":"2026-05-17T23:39:05Z","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":"f050c93ebd59f08f662dc444c16665764f030df1eef20bb1bde6cb98a3ae691b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:31:17Z","title_canon_sha256":"2c149f0a446ae0b8ac99743af2877fb60c45c6e55da7fa3e0aad129f942dc622"},"schema_version":"1.0","source":{"id":"2605.14553","kind":"arxiv","version":1}},"canonical_sha256":"f9b13c5c59434eed951197686a52dda7857842c3d601f2d8a70f0ddd4a739b9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9b13c5c59434eed951197686a52dda7857842c3d601f2d8a70f0ddd4a739b9c","first_computed_at":"2026-05-17T23:39:05.682032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:05.682032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"he57Oo1NPBwiXG6PDg4uqtqbghRbY4mlJ6znf7Mu2B13nneMiP7Z8NMGlu374Bcf5JK2j//Tf081f1nfuA3sDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:05.682736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f962790002485eb05c0a6e168a75a62b2f3773430a81c284cad7da2f0eb77db","sha256:33445f0b4adf09e2be7d2546150d06248b3197fdd32b919289c430b4728f44de"],"state_sha256":"1bb842642e231df6223364b8918b22586f411fe963e8995cb96453b2f367d4e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FSXtglotSscLHUnsJsc5gu6c/8BR6/TdqDeEnf3biyUPPIjoy8MlOUC/AjdQj6++PIqxZL43kHy+uSCEJFqjCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:11:27.323242Z","bundle_sha256":"ed0b2eb9cd2eea575a53617ae3325989994ae0aad48096dafa5e5dae9f6538eb"}}