{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NZWTWYASEP46ZRYGLLQHDO73X5","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":"13ff86f0342d8e9bdaf9b4e15c38f74c8579881526619ba374d8a9a909641618","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T18:58:03Z","title_canon_sha256":"d3bacb75c53b537893aca2ec724d70577d58c2d24642930b0e3131a43787a54f"},"schema_version":"1.0","source":{"id":"2411.12736","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12736","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12736v2","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12736","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"NZWTWYASEP46","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"NZWTWYASEP46ZRYG","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"NZWTWYAS","created_at":"2026-07-05T12:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:822e2296ebb7a46eda8c9bf8168398b5fb37939ed646e63cf659d65372b73d44","target":"graph","created_at":"2026-07-05T12:05:03Z","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/2411.12736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effectiveness of Large Language Models (LLMs) in solving tasks depends significantly on the quality of their instructions, which often require substantial human effort to craft. This underscores the need for automated instruction optimization. However, optimizing instructions is particularly challenging when working with black-box LLMs, where model parameters and gradients are inaccessible. We introduce ACING, an actor-critic reinforcement learning framework that formulates instruction optimization as a stateless, continuous-action problem, enabling exploration of infinite instruction spac","authors_text":"Fares Fourati, Marco Canini, Salma Kharrat","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T18:58:03Z","title":"ACING: Actor-Critic for Instruction Learning in Black-Box LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12736","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":"sha256:7be5ed28647e9517ec7d75f7e74d3abf715809535f67c204a858e2f8656b9ecd","target":"record","created_at":"2026-07-05T12:05:03Z","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":"13ff86f0342d8e9bdaf9b4e15c38f74c8579881526619ba374d8a9a909641618","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T18:58:03Z","title_canon_sha256":"d3bacb75c53b537893aca2ec724d70577d58c2d24642930b0e3131a43787a54f"},"schema_version":"1.0","source":{"id":"2411.12736","kind":"arxiv","version":2}},"canonical_sha256":"6e6d3b601223f9ecc7065ae071bbfbbf4c9d69e047778112302679efdc4d8e3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e6d3b601223f9ecc7065ae071bbfbbf4c9d69e047778112302679efdc4d8e3c","first_computed_at":"2026-07-05T12:05:03.528782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:03.528782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rPiqh3ZFuaCVIBI8K+ZkCRIIYyzsj4OGzsIZSiVsSXE7RAiVDpea0PY2Q+XoE2pV9TA+UoJ2+6f+9X6iZ1Q3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:03.529291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12736","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7be5ed28647e9517ec7d75f7e74d3abf715809535f67c204a858e2f8656b9ecd","sha256:822e2296ebb7a46eda8c9bf8168398b5fb37939ed646e63cf659d65372b73d44"],"state_sha256":"0c840b0b2c7b11e40503914e3cdc20e2eb44d54f06a8c19c4ecc6bfe5abd79ba"}