{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HUK4T3J2UGY43QXA5TXUWBXFKX","short_pith_number":"pith:HUK4T3J2","canonical_record":{"source":{"id":"2402.17564","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T15:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"5a6b5d5156e09234b49c529962def107fd132885dbc9c1860d4c598faa0bb69f","abstract_canon_sha256":"eabe503c2a1531da6318b2cf3a7e07ce7dc0d3cabc9d2e6b5fe86a9638beeaf7"},"schema_version":"1.0"},"canonical_sha256":"3d15c9ed3aa1b1cdc2e0ecef4b06e555e0f7a4b2942d89168e7c30b9dfe48986","source":{"kind":"arxiv","id":"2402.17564","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17564","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17564v3","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17564","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"HUK4T3J2UGY4","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"HUK4T3J2UGY43QXA","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"HUK4T3J2","created_at":"2026-07-05T10:05:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HUK4T3J2UGY43QXA5TXUWBXFKX","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17564","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T15:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"5a6b5d5156e09234b49c529962def107fd132885dbc9c1860d4c598faa0bb69f","abstract_canon_sha256":"eabe503c2a1531da6318b2cf3a7e07ce7dc0d3cabc9d2e6b5fe86a9638beeaf7"},"schema_version":"1.0"},"canonical_sha256":"3d15c9ed3aa1b1cdc2e0ecef4b06e555e0f7a4b2942d89168e7c30b9dfe48986","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:09.328544Z","signature_b64":"ouVfyAgxl6FSpmhEcKhgTxDigrBJ5iSYbmnAJlhX+/hXCFKPoJnjttun9mF4aIPj4WjqMiSiOiup9owbDocbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d15c9ed3aa1b1cdc2e0ecef4b06e555e0f7a4b2942d89168e7c30b9dfe48986","last_reissued_at":"2026-07-05T10:05:09.328100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:09.328100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17564","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N2277gZdAZsWvhFVa8sNBUNm5CztYn5tCxtyl10NOjCOSF+dSjiQgstdQCvvLV3bGn/fJyj2nMN8fY7zlwcvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:51:10.337847Z"},"content_sha256":"9d7992c7e183896aef169c9a4af2ea1683dce1367db4757c9cac0d33a89de434","schema_version":"1.0","event_id":"sha256:9d7992c7e183896aef169c9a4af2ea1683dce1367db4757c9cac0d33a89de434"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HUK4T3J2UGY43QXA5TXUWBXFKX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji-Rong Wen, Siyuan Lu, Wayne Xin Zhao, Xiaolei Wang, Xinyu Tang, Yaliang Li","submitted_at":"2024-02-27T15:05:32Z","abstract_excerpt":"Automatic prompt optimization is an important approach to improving the performance of large language models (LLMs). Recent research demonstrates the potential of using LLMs as prompt optimizers, which can generate improved task prompts via iterative refinement. In this paper, we propose a novel perspective to investigate the design of LLM-based prompt optimizers, by drawing an analogy with gradient-based model optimizers. To connect these two approaches, we identify two pivotal factors in model parameter learning: update direction and update method. By systematically analyzing a rich set of i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17564","kind":"arxiv","version":3},"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/2402.17564/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":"2026-07-05T10:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CGX9ag8PZhMX69CNdXYnVCXhCPLWhoLYBqz6h1mjZD/NrzA45AxLp/Iimby8jcnOG19fPaMWXkWBC+fQ273BAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:51:10.338453Z"},"content_sha256":"f7da0189755c39be5272138ad260807856c626c648b67b3e088ba3c977220aa2","schema_version":"1.0","event_id":"sha256:f7da0189755c39be5272138ad260807856c626c648b67b3e088ba3c977220aa2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HUK4T3J2UGY43QXA5TXUWBXFKX/bundle.json","state_url":"https://pith.science/pith/HUK4T3J2UGY43QXA5TXUWBXFKX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HUK4T3J2UGY43QXA5TXUWBXFKX/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":"2026-08-20T14:51:10Z","links":{"resolver":"https://pith.science/pith/HUK4T3J2UGY43QXA5TXUWBXFKX","bundle":"https://pith.science/pith/HUK4T3J2UGY43QXA5TXUWBXFKX/bundle.json","state":"https://pith.science/pith/HUK4T3J2UGY43QXA5TXUWBXFKX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HUK4T3J2UGY43QXA5TXUWBXFKX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HUK4T3J2UGY43QXA5TXUWBXFKX","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":"eabe503c2a1531da6318b2cf3a7e07ce7dc0d3cabc9d2e6b5fe86a9638beeaf7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T15:05:32Z","title_canon_sha256":"5a6b5d5156e09234b49c529962def107fd132885dbc9c1860d4c598faa0bb69f"},"schema_version":"1.0","source":{"id":"2402.17564","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17564","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17564v3","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17564","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"HUK4T3J2UGY4","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"HUK4T3J2UGY43QXA","created_at":"2026-07-05T10:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"HUK4T3J2","created_at":"2026-07-05T10:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:f7da0189755c39be5272138ad260807856c626c648b67b3e088ba3c977220aa2","target":"graph","created_at":"2026-07-05T10:05:09Z","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/2402.17564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic prompt optimization is an important approach to improving the performance of large language models (LLMs). Recent research demonstrates the potential of using LLMs as prompt optimizers, which can generate improved task prompts via iterative refinement. In this paper, we propose a novel perspective to investigate the design of LLM-based prompt optimizers, by drawing an analogy with gradient-based model optimizers. To connect these two approaches, we identify two pivotal factors in model parameter learning: update direction and update method. By systematically analyzing a rich set of i","authors_text":"Ji-Rong Wen, Siyuan Lu, Wayne Xin Zhao, Xiaolei Wang, Xinyu Tang, Yaliang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T15:05:32Z","title":"Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17564","kind":"arxiv","version":3},"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":"sha256:9d7992c7e183896aef169c9a4af2ea1683dce1367db4757c9cac0d33a89de434","target":"record","created_at":"2026-07-05T10:05:09Z","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":"eabe503c2a1531da6318b2cf3a7e07ce7dc0d3cabc9d2e6b5fe86a9638beeaf7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T15:05:32Z","title_canon_sha256":"5a6b5d5156e09234b49c529962def107fd132885dbc9c1860d4c598faa0bb69f"},"schema_version":"1.0","source":{"id":"2402.17564","kind":"arxiv","version":3}},"canonical_sha256":"3d15c9ed3aa1b1cdc2e0ecef4b06e555e0f7a4b2942d89168e7c30b9dfe48986","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d15c9ed3aa1b1cdc2e0ecef4b06e555e0f7a4b2942d89168e7c30b9dfe48986","first_computed_at":"2026-07-05T10:05:09.328100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:09.328100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ouVfyAgxl6FSpmhEcKhgTxDigrBJ5iSYbmnAJlhX+/hXCFKPoJnjttun9mF4aIPj4WjqMiSiOiup9owbDocbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:09.328544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17564","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d7992c7e183896aef169c9a4af2ea1683dce1367db4757c9cac0d33a89de434","sha256:f7da0189755c39be5272138ad260807856c626c648b67b3e088ba3c977220aa2"],"state_sha256":"c07a3d11ed9fd647ba47808bfe4d06dbff76067f9177952354342aea88a3fe67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bpyaxutEKCi82CyeYNdyTaeX9MAoEqnzGMBdKktsWADuC6aL4uo7Dxz/K1xZES5H7qJMXM2xKCFw3vDh+v65Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T14:51:10.342276Z","bundle_sha256":"469388b21f789f1d2fbed0dc9bde1ad2f9abb58de5294cd3d3e8ad6a7bec0ce0"}}