{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F6JUYVTM7GVZOKOACRIQORMSQJ","short_pith_number":"pith:F6JUYVTM","canonical_record":{"source":{"id":"2410.12457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:08:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"041967e2da98940b584208e290f8bf3e6a3ed92f75de9e9c8b39e9ed499779ff","abstract_canon_sha256":"257e385d9079e47a672c9974d4a76e252b92b9df56162806291d82d9a2cb5de0"},"schema_version":"1.0"},"canonical_sha256":"2f934c566cf9ab9729c01451074592824815880ac43c4497b3553f52dbe8fa5d","source":{"kind":"arxiv","id":"2410.12457","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12457","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12457v1","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12457","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"pith_short_12","alias_value":"F6JUYVTM7GVZ","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"pith_short_16","alias_value":"F6JUYVTM7GVZOKOA","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"pith_short_8","alias_value":"F6JUYVTM","created_at":"2026-07-05T09:21:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F6JUYVTM7GVZOKOACRIQORMSQJ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:08:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"041967e2da98940b584208e290f8bf3e6a3ed92f75de9e9c8b39e9ed499779ff","abstract_canon_sha256":"257e385d9079e47a672c9974d4a76e252b92b9df56162806291d82d9a2cb5de0"},"schema_version":"1.0"},"canonical_sha256":"2f934c566cf9ab9729c01451074592824815880ac43c4497b3553f52dbe8fa5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:29.250195Z","signature_b64":"rdjppWaH+6NkoTN3QIs5EOGH1zjZc4Z/ftvGMmRzwfka6/bKCjAtwTVCNJ7bN2O6E29s4fs4K9iG0Aiswc9QDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f934c566cf9ab9729c01451074592824815880ac43c4497b3553f52dbe8fa5d","last_reissued_at":"2026-07-05T09:21:29.249790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:29.249790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12457","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":"2026-07-05T09:21:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k3DCzw5l/fXLBOKQ2+lxi9Qoa8K8NaoJbqdZahKTaHa8w/wQoLeysDnWY0f9oFmx5UDyv6RBir7VpYGpo9JCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:16:48.459092Z"},"content_sha256":"432033365e23bfb737f081bb006031ee23fc28df11fba1a7dc5a47698ad1cc14","schema_version":"1.0","event_id":"sha256:432033365e23bfb737f081bb006031ee23fc28df11fba1a7dc5a47698ad1cc14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F6JUYVTM7GVZOKOACRIQORMSQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sharpness-Aware Black-Box Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Feiyang Ye, Ivor Tsang, Masashi Sugiyama, Xuehao Wang, Yueming Lyu, Yu Zhang","submitted_at":"2024-10-16T11:08:06Z","abstract_excerpt":"Black-box optimization algorithms have been widely used in various machine learning problems, including reinforcement learning and prompt fine-tuning. However, directly optimizing the training loss value, as commonly done in existing black-box optimization methods, could lead to suboptimal model quality and generalization performance. To address those problems in black-box optimization, we propose a novel Sharpness-Aware Black-box Optimization (SABO) algorithm, which applies a sharpness-aware minimization strategy to improve the model generalization. Specifically, the proposed SABO method firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12457","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/2410.12457/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":"2026-07-05T09:21:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20m7p83G1xNs48cVfSfMK5QEhG9tlzeRwiXhcXZqbSWe8yVpA5yQPEYGFQ+exAVtnLDZy7xjtPbgJyspEHApBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:16:48.459509Z"},"content_sha256":"c0cebab12b2272b793f77357ac666d3d97011fd680efef4da94dd52258fce7b6","schema_version":"1.0","event_id":"sha256:c0cebab12b2272b793f77357ac666d3d97011fd680efef4da94dd52258fce7b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F6JUYVTM7GVZOKOACRIQORMSQJ/bundle.json","state_url":"https://pith.science/pith/F6JUYVTM7GVZOKOACRIQORMSQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F6JUYVTM7GVZOKOACRIQORMSQJ/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":"2026-07-06T20:16:48Z","links":{"resolver":"https://pith.science/pith/F6JUYVTM7GVZOKOACRIQORMSQJ","bundle":"https://pith.science/pith/F6JUYVTM7GVZOKOACRIQORMSQJ/bundle.json","state":"https://pith.science/pith/F6JUYVTM7GVZOKOACRIQORMSQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F6JUYVTM7GVZOKOACRIQORMSQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F6JUYVTM7GVZOKOACRIQORMSQJ","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":"257e385d9079e47a672c9974d4a76e252b92b9df56162806291d82d9a2cb5de0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:08:06Z","title_canon_sha256":"041967e2da98940b584208e290f8bf3e6a3ed92f75de9e9c8b39e9ed499779ff"},"schema_version":"1.0","source":{"id":"2410.12457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12457","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12457v1","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12457","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"pith_short_12","alias_value":"F6JUYVTM7GVZ","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"pith_short_16","alias_value":"F6JUYVTM7GVZOKOA","created_at":"2026-07-05T09:21:29Z"},{"alias_kind":"pith_short_8","alias_value":"F6JUYVTM","created_at":"2026-07-05T09:21:29Z"}],"graph_snapshots":[{"event_id":"sha256:c0cebab12b2272b793f77357ac666d3d97011fd680efef4da94dd52258fce7b6","target":"graph","created_at":"2026-07-05T09:21:29Z","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/2410.12457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Black-box optimization algorithms have been widely used in various machine learning problems, including reinforcement learning and prompt fine-tuning. However, directly optimizing the training loss value, as commonly done in existing black-box optimization methods, could lead to suboptimal model quality and generalization performance. To address those problems in black-box optimization, we propose a novel Sharpness-Aware Black-box Optimization (SABO) algorithm, which applies a sharpness-aware minimization strategy to improve the model generalization. Specifically, the proposed SABO method firs","authors_text":"Feiyang Ye, Ivor Tsang, Masashi Sugiyama, Xuehao Wang, Yueming Lyu, Yu Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:08:06Z","title":"Sharpness-Aware Black-Box Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12457","kind":"arxiv","version":1},"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":"sha256:432033365e23bfb737f081bb006031ee23fc28df11fba1a7dc5a47698ad1cc14","target":"record","created_at":"2026-07-05T09:21:29Z","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":"257e385d9079e47a672c9974d4a76e252b92b9df56162806291d82d9a2cb5de0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:08:06Z","title_canon_sha256":"041967e2da98940b584208e290f8bf3e6a3ed92f75de9e9c8b39e9ed499779ff"},"schema_version":"1.0","source":{"id":"2410.12457","kind":"arxiv","version":1}},"canonical_sha256":"2f934c566cf9ab9729c01451074592824815880ac43c4497b3553f52dbe8fa5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f934c566cf9ab9729c01451074592824815880ac43c4497b3553f52dbe8fa5d","first_computed_at":"2026-07-05T09:21:29.249790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:29.249790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdjppWaH+6NkoTN3QIs5EOGH1zjZc4Z/ftvGMmRzwfka6/bKCjAtwTVCNJ7bN2O6E29s4fs4K9iG0Aiswc9QDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:29.250195Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:432033365e23bfb737f081bb006031ee23fc28df11fba1a7dc5a47698ad1cc14","sha256:c0cebab12b2272b793f77357ac666d3d97011fd680efef4da94dd52258fce7b6"],"state_sha256":"9aaa38b2e2418d22f98cc0a4f74f3dbbbc37e25dc2dee98386a4dff784251da7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ENonxeD01rikoK0g5X6TgeVAgltUOPVeSED24y8szguNbaxhVhHe+vd27/3yMprJuzxjBhEGq4MYbjo6hdiGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:16:48.461546Z","bundle_sha256":"1c3e396761f3c2873289c75b6d1921861cc49e78fe3f2d0f1cdb5ce0b499a2fe"}}