{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VG4MCIMTLS62PB4QB6FZOEZ45A","short_pith_number":"pith:VG4MCIMT","canonical_record":{"source":{"id":"2408.07465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T11:19:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96f52a895ec9258bff740ba2b120c29cfa913466a66aa19617e4bb8d0c60e26d","abstract_canon_sha256":"129545ee997bb95584a652d99b2eccb2cbf59c0163c926839b57dee9ebdde86e"},"schema_version":"1.0"},"canonical_sha256":"a9b8c121935cbda787900f8b97133ce83c547630be9ddbedfcedeec3d49321d5","source":{"kind":"arxiv","id":"2408.07465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07465","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07465v1","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07465","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"pith_short_12","alias_value":"VG4MCIMTLS62","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"pith_short_16","alias_value":"VG4MCIMTLS62PB4Q","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"pith_short_8","alias_value":"VG4MCIMT","created_at":"2026-07-05T08:55:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VG4MCIMTLS62PB4QB6FZOEZ45A","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T11:19:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96f52a895ec9258bff740ba2b120c29cfa913466a66aa19617e4bb8d0c60e26d","abstract_canon_sha256":"129545ee997bb95584a652d99b2eccb2cbf59c0163c926839b57dee9ebdde86e"},"schema_version":"1.0"},"canonical_sha256":"a9b8c121935cbda787900f8b97133ce83c547630be9ddbedfcedeec3d49321d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:25.698176Z","signature_b64":"81a2MbMBRVMHa2X76Yr0fH1B5DoI0idu36ORcwmOtAk0H8UcXbI2BfZnnl3doFmNoBMebnjeYQFTApeIhasZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b8c121935cbda787900f8b97133ce83c547630be9ddbedfcedeec3d49321d5","last_reissued_at":"2026-07-05T08:55:25.697685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:25.697685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07465","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":"2026-07-05T08:55:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bb7Lda49aGbQ29DpMp7bCVF1MgbWQKhkbSI9G1Pw+dohHeWE9VL3WDHZFeXWFykDDsNouJmvq3l+mnke8yo3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:32:48.853900Z"},"content_sha256":"5ddb61f5da6b84a36e139c5d7e8c131e2e3ec15cc627d85ca427f2da04bd3944","schema_version":"1.0","event_id":"sha256:5ddb61f5da6b84a36e139c5d7e8c131e2e3ec15cc627d85ca427f2da04bd3944"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VG4MCIMTLS62PB4QB6FZOEZ45A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Prompting With Episodic Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dai Do, Hung Le, Quan Tran, Svetha Venkatesh","submitted_at":"2024-08-14T11:19:28Z","abstract_excerpt":"Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated directly into the prompt. Despite the growing interest in optimizing prompts with few-shot examples, existing methods for prompt optimization are often resource-intensive or perform inadequately. In this work, we propose PrOmpting with Episodic Memory (POEM), a novel prompt optimization technique that is simple, efficient, and demonstrates strong generalizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07465","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/2408.07465/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":"2026-07-05T08:55:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6gF/sB6KlLQZEJ1qNyfm5NuU1Idqy3H1F156gm57cQVFo8A2YSlTuLhHd/1tdx4VMmU0/7A1xfhO6Fj/OdhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:32:48.854794Z"},"content_sha256":"ff220ec35ddbd379363906a5d0c8ce5707070a9fc56fab3375cb6586e7303964","schema_version":"1.0","event_id":"sha256:ff220ec35ddbd379363906a5d0c8ce5707070a9fc56fab3375cb6586e7303964"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VG4MCIMTLS62PB4QB6FZOEZ45A/bundle.json","state_url":"https://pith.science/pith/VG4MCIMTLS62PB4QB6FZOEZ45A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VG4MCIMTLS62PB4QB6FZOEZ45A/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":"2026-08-07T15:32:48Z","links":{"resolver":"https://pith.science/pith/VG4MCIMTLS62PB4QB6FZOEZ45A","bundle":"https://pith.science/pith/VG4MCIMTLS62PB4QB6FZOEZ45A/bundle.json","state":"https://pith.science/pith/VG4MCIMTLS62PB4QB6FZOEZ45A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VG4MCIMTLS62PB4QB6FZOEZ45A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VG4MCIMTLS62PB4QB6FZOEZ45A","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":"129545ee997bb95584a652d99b2eccb2cbf59c0163c926839b57dee9ebdde86e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T11:19:28Z","title_canon_sha256":"96f52a895ec9258bff740ba2b120c29cfa913466a66aa19617e4bb8d0c60e26d"},"schema_version":"1.0","source":{"id":"2408.07465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07465","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07465v1","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07465","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"pith_short_12","alias_value":"VG4MCIMTLS62","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"pith_short_16","alias_value":"VG4MCIMTLS62PB4Q","created_at":"2026-07-05T08:55:25Z"},{"alias_kind":"pith_short_8","alias_value":"VG4MCIMT","created_at":"2026-07-05T08:55:25Z"}],"graph_snapshots":[{"event_id":"sha256:ff220ec35ddbd379363906a5d0c8ce5707070a9fc56fab3375cb6586e7303964","target":"graph","created_at":"2026-07-05T08:55:25Z","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/2408.07465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated directly into the prompt. Despite the growing interest in optimizing prompts with few-shot examples, existing methods for prompt optimization are often resource-intensive or perform inadequately. In this work, we propose PrOmpting with Episodic Memory (POEM), a novel prompt optimization technique that is simple, efficient, and demonstrates strong generalizatio","authors_text":"Dai Do, Hung Le, Quan Tran, Svetha Venkatesh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T11:19:28Z","title":"Large Language Models Prompting With Episodic Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07465","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":"sha256:5ddb61f5da6b84a36e139c5d7e8c131e2e3ec15cc627d85ca427f2da04bd3944","target":"record","created_at":"2026-07-05T08:55:25Z","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":"129545ee997bb95584a652d99b2eccb2cbf59c0163c926839b57dee9ebdde86e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T11:19:28Z","title_canon_sha256":"96f52a895ec9258bff740ba2b120c29cfa913466a66aa19617e4bb8d0c60e26d"},"schema_version":"1.0","source":{"id":"2408.07465","kind":"arxiv","version":1}},"canonical_sha256":"a9b8c121935cbda787900f8b97133ce83c547630be9ddbedfcedeec3d49321d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9b8c121935cbda787900f8b97133ce83c547630be9ddbedfcedeec3d49321d5","first_computed_at":"2026-07-05T08:55:25.697685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:25.697685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"81a2MbMBRVMHa2X76Yr0fH1B5DoI0idu36ORcwmOtAk0H8UcXbI2BfZnnl3doFmNoBMebnjeYQFTApeIhasZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:25.698176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ddb61f5da6b84a36e139c5d7e8c131e2e3ec15cc627d85ca427f2da04bd3944","sha256:ff220ec35ddbd379363906a5d0c8ce5707070a9fc56fab3375cb6586e7303964"],"state_sha256":"d161de52254db0ecd3f8396c2fb06ccb45485c12ce059306acc5d00570360d91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fr6AKPLRfDY+RKD0/AVQuPE9Q+WEh9mf/HlGYN5dLJnaPlWjj83b34ewQ0PXAQTAtcanbK7YJjSguLuY6kIwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:32:48.862374Z","bundle_sha256":"dbb40e880b23a4fd99356574d7f10b8e9665da4b4343bd2ac62b7d7c4dae14af"}}