{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TS773D6CYF2VK27JCGO2FJIPUK","short_pith_number":"pith:TS773D6C","canonical_record":{"source":{"id":"2508.18749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T07:25:45Z","cross_cats_sorted":[],"title_canon_sha256":"59aace2bbeff6b89db90b30462945410a068893cb3895526b4b14f43c2718f00","abstract_canon_sha256":"8e4286952030f4bbf8baeee5e08fb6991420a1b6edb5dc37017181dcab627be7"},"schema_version":"1.0"},"canonical_sha256":"9cbffd8fc2c175556be9119da2a50fa28be0aa97a5097cf424fbc3647186fea1","source":{"kind":"arxiv","id":"2508.18749","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18749","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18749v1","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18749","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"TS773D6CYF2V","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"TS773D6CYF2VK27J","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"TS773D6C","created_at":"2026-07-05T11:59:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TS773D6CYF2VK27JCGO2FJIPUK","target":"record","payload":{"canonical_record":{"source":{"id":"2508.18749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T07:25:45Z","cross_cats_sorted":[],"title_canon_sha256":"59aace2bbeff6b89db90b30462945410a068893cb3895526b4b14f43c2718f00","abstract_canon_sha256":"8e4286952030f4bbf8baeee5e08fb6991420a1b6edb5dc37017181dcab627be7"},"schema_version":"1.0"},"canonical_sha256":"9cbffd8fc2c175556be9119da2a50fa28be0aa97a5097cf424fbc3647186fea1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:30.144434Z","signature_b64":"NZNqeAFay8OiknElAaSRQ3CBDHcLonQ5uYcNwKCGdoi1p/emVdidV9RZogGdAhLhvqBVFWt+X2nMVvhk0Me9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cbffd8fc2c175556be9119da2a50fa28be0aa97a5097cf424fbc3647186fea1","last_reissued_at":"2026-07-05T11:59:30.144000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:30.144000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.18749","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":"2026-07-05T11:59:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P4ezgTPSJvN/YJJIM3VsJ+DAw3PfIPWlG7MQBsfDoBfqCX1b9mNdDWRak+K4AFSMU0wZFWHd3PJYDf4pLZb9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:35:10.135694Z"},"content_sha256":"a699dbba0afaa92ee94295c6707efbca817cb5755634030a1408b861cd489889","schema_version":"1.0","event_id":"sha256:a699dbba0afaa92ee94295c6707efbca817cb5755634030a1408b861cd489889"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TS773D6CYF2VK27JCGO2FJIPUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunlong Wu, Zhibo Qu","submitted_at":"2025-08-26T07:25:45Z","abstract_excerpt":"Recent advances in prompt optimization, exemplified by methods such as TextGrad, enable automatic, gradient-like refinement of textual prompts to enhance the performance of large language models (LLMs) on specific downstream tasks. However, current approaches are typically stateless and operate independently across optimization runs, lacking mechanisms to preserve and leverage historical optimization experience. Furthermore, they are susceptible to overfitting, often yielding prompt updates that generalize poorly beyond the immediate task context.\n  To address these limitations, we propose Ref"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18749","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/2508.18749/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":"2026-07-05T11:59:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"clj3Nwq6b5xk0tNWZop7ZLlF3IaBua6Nq83Uu/s+o6n619RZjyBCQvtIptugLuaEkL66MIHf+UEwKXx05oKlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:35:10.136209Z"},"content_sha256":"7974fbca71fd63b3a6d3dffc2d2c43f275b714205b98810c56d4cff22aff83f0","schema_version":"1.0","event_id":"sha256:7974fbca71fd63b3a6d3dffc2d2c43f275b714205b98810c56d4cff22aff83f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TS773D6CYF2VK27JCGO2FJIPUK/bundle.json","state_url":"https://pith.science/pith/TS773D6CYF2VK27JCGO2FJIPUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TS773D6CYF2VK27JCGO2FJIPUK/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":"2026-08-05T08:35:10Z","links":{"resolver":"https://pith.science/pith/TS773D6CYF2VK27JCGO2FJIPUK","bundle":"https://pith.science/pith/TS773D6CYF2VK27JCGO2FJIPUK/bundle.json","state":"https://pith.science/pith/TS773D6CYF2VK27JCGO2FJIPUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TS773D6CYF2VK27JCGO2FJIPUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TS773D6CYF2VK27JCGO2FJIPUK","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":"8e4286952030f4bbf8baeee5e08fb6991420a1b6edb5dc37017181dcab627be7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T07:25:45Z","title_canon_sha256":"59aace2bbeff6b89db90b30462945410a068893cb3895526b4b14f43c2718f00"},"schema_version":"1.0","source":{"id":"2508.18749","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18749","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18749v1","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18749","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"TS773D6CYF2V","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"TS773D6CYF2VK27J","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"TS773D6C","created_at":"2026-07-05T11:59:30Z"}],"graph_snapshots":[{"event_id":"sha256:7974fbca71fd63b3a6d3dffc2d2c43f275b714205b98810c56d4cff22aff83f0","target":"graph","created_at":"2026-07-05T11:59:30Z","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/2508.18749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in prompt optimization, exemplified by methods such as TextGrad, enable automatic, gradient-like refinement of textual prompts to enhance the performance of large language models (LLMs) on specific downstream tasks. However, current approaches are typically stateless and operate independently across optimization runs, lacking mechanisms to preserve and leverage historical optimization experience. Furthermore, they are susceptible to overfitting, often yielding prompt updates that generalize poorly beyond the immediate task context.\n  To address these limitations, we propose Ref","authors_text":"Chunlong Wu, Zhibo Qu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T07:25:45Z","title":"Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18749","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:a699dbba0afaa92ee94295c6707efbca817cb5755634030a1408b861cd489889","target":"record","created_at":"2026-07-05T11:59:30Z","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":"8e4286952030f4bbf8baeee5e08fb6991420a1b6edb5dc37017181dcab627be7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T07:25:45Z","title_canon_sha256":"59aace2bbeff6b89db90b30462945410a068893cb3895526b4b14f43c2718f00"},"schema_version":"1.0","source":{"id":"2508.18749","kind":"arxiv","version":1}},"canonical_sha256":"9cbffd8fc2c175556be9119da2a50fa28be0aa97a5097cf424fbc3647186fea1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cbffd8fc2c175556be9119da2a50fa28be0aa97a5097cf424fbc3647186fea1","first_computed_at":"2026-07-05T11:59:30.144000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:30.144000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NZNqeAFay8OiknElAaSRQ3CBDHcLonQ5uYcNwKCGdoi1p/emVdidV9RZogGdAhLhvqBVFWt+X2nMVvhk0Me9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:30.144434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18749","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a699dbba0afaa92ee94295c6707efbca817cb5755634030a1408b861cd489889","sha256:7974fbca71fd63b3a6d3dffc2d2c43f275b714205b98810c56d4cff22aff83f0"],"state_sha256":"d0ca141f0f39298d6b96999c113cb7f9a96d403bb3b15cdac049b8a2c2b1c20a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VB+JnFBV4VR73Ql4Dlc015ASEUw2/2kZcyTyeEAokreIxZs7kcXKGH+XH+dpF6W03K98OXzE5xkQb+rr/AeUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:35:10.141100Z","bundle_sha256":"dac0760f1a723fc5b31a32665158f57af051ea2ab9d395cedf5622baf11dc03e"}}