{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4AK6KVBVI2U2GNG2N6RWFG6VHP","short_pith_number":"pith:4AK6KVBV","canonical_record":{"source":{"id":"2608.02919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T22:13:12Z","cross_cats_sorted":[],"title_canon_sha256":"6235fe6978cd52e100db523c011fb62e09736e598d4dd8c30f5750b4621e385e","abstract_canon_sha256":"f749d115a9506327df234fd03446e5f0c4d7989a0e62bcf07cd652d625408ebc"},"schema_version":"1.0"},"canonical_sha256":"e015e5543546a9a334da6fa3629bd53bc89ac298f2228470e9b235a1aa58adf6","source":{"kind":"arxiv","id":"2608.02919","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02919","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02919v1","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02919","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"pith_short_12","alias_value":"4AK6KVBVI2U2","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"pith_short_16","alias_value":"4AK6KVBVI2U2GNG2","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"pith_short_8","alias_value":"4AK6KVBV","created_at":"2026-08-05T00:43:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4AK6KVBVI2U2GNG2N6RWFG6VHP","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T22:13:12Z","cross_cats_sorted":[],"title_canon_sha256":"6235fe6978cd52e100db523c011fb62e09736e598d4dd8c30f5750b4621e385e","abstract_canon_sha256":"f749d115a9506327df234fd03446e5f0c4d7989a0e62bcf07cd652d625408ebc"},"schema_version":"1.0"},"canonical_sha256":"e015e5543546a9a334da6fa3629bd53bc89ac298f2228470e9b235a1aa58adf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:43:37.281940Z","signature_b64":"suGA99O7VYJOULHe5fqf6l0urXUdC53NL/FnPS91l4FPX6KIyB9tPacEeBYikqtLxfjp7dVVkUcQHZX0VWyrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e015e5543546a9a334da6fa3629bd53bc89ac298f2228470e9b235a1aa58adf6","last_reissued_at":"2026-08-05T00:43:37.278944Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:43:37.278944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02919","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":"2026-08-05T00:43:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BI7MlGB+NGlhSJuI4eLuBuAOj+LgF86YA6ARD+OSQJTBe843w1FNsw4NuaLVWk9yQXTleT5/TN1rSHSjCq5ZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:45:22.009185Z"},"content_sha256":"eeae9937608cd87990ab58a89f32ec2f86bb9ebdfc17dc50601d4d6bef1c7935","schema_version":"1.0","event_id":"sha256:eeae9937608cd87990ab58a89f32ec2f86bb9ebdfc17dc50601d4d6bef1c7935"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4AK6KVBVI2U2GNG2N6RWFG6VHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FLARE: Few-shot Learning-based Adaptive Reflective Engine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aashna Garg, Bharat Gandhi, Dhanasekar Sundararaman, Minjie Li","submitted_at":"2026-08-03T22:13:12Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization. In this work, we challenge this shift by introducing FLARE (Few-shot Learning-based Adaptive Reflective Engine), a framework that leverages advanced reflective mechanisms and a small set of few-shot reference examples to optimize instructions. We evaluate our method acros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02919","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/2608.02919/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":"2026-08-05T00:43:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+HW1Qz70PDJPzfw7V0DIRqIYLJN4y6n4zf9HMqVxjRoWYCENjCfxgtY0g5cvQ4jPOB6TMKa8fD8yHjC5m7DCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:45:22.010076Z"},"content_sha256":"cbadcdbebda0910fa814192b2d37c0f671b85dae0d2a69c7bd0c7dc9f9e76344","schema_version":"1.0","event_id":"sha256:cbadcdbebda0910fa814192b2d37c0f671b85dae0d2a69c7bd0c7dc9f9e76344"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AK6KVBVI2U2GNG2N6RWFG6VHP/bundle.json","state_url":"https://pith.science/pith/4AK6KVBVI2U2GNG2N6RWFG6VHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AK6KVBVI2U2GNG2N6RWFG6VHP/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":"2026-08-18T06:45:22Z","links":{"resolver":"https://pith.science/pith/4AK6KVBVI2U2GNG2N6RWFG6VHP","bundle":"https://pith.science/pith/4AK6KVBVI2U2GNG2N6RWFG6VHP/bundle.json","state":"https://pith.science/pith/4AK6KVBVI2U2GNG2N6RWFG6VHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AK6KVBVI2U2GNG2N6RWFG6VHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4AK6KVBVI2U2GNG2N6RWFG6VHP","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":"f749d115a9506327df234fd03446e5f0c4d7989a0e62bcf07cd652d625408ebc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T22:13:12Z","title_canon_sha256":"6235fe6978cd52e100db523c011fb62e09736e598d4dd8c30f5750b4621e385e"},"schema_version":"1.0","source":{"id":"2608.02919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02919","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02919v1","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02919","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"pith_short_12","alias_value":"4AK6KVBVI2U2","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"pith_short_16","alias_value":"4AK6KVBVI2U2GNG2","created_at":"2026-08-05T00:43:37Z"},{"alias_kind":"pith_short_8","alias_value":"4AK6KVBV","created_at":"2026-08-05T00:43:37Z"}],"graph_snapshots":[{"event_id":"sha256:cbadcdbebda0910fa814192b2d37c0f671b85dae0d2a69c7bd0c7dc9f9e76344","target":"graph","created_at":"2026-08-05T00:43:37Z","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/2608.02919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization. In this work, we challenge this shift by introducing FLARE (Few-shot Learning-based Adaptive Reflective Engine), a framework that leverages advanced reflective mechanisms and a small set of few-shot reference examples to optimize instructions. We evaluate our method acros","authors_text":"Aashna Garg, Bharat Gandhi, Dhanasekar Sundararaman, Minjie Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T22:13:12Z","title":"FLARE: Few-shot Learning-based Adaptive Reflective Engine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02919","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:eeae9937608cd87990ab58a89f32ec2f86bb9ebdfc17dc50601d4d6bef1c7935","target":"record","created_at":"2026-08-05T00:43:37Z","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":"f749d115a9506327df234fd03446e5f0c4d7989a0e62bcf07cd652d625408ebc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T22:13:12Z","title_canon_sha256":"6235fe6978cd52e100db523c011fb62e09736e598d4dd8c30f5750b4621e385e"},"schema_version":"1.0","source":{"id":"2608.02919","kind":"arxiv","version":1}},"canonical_sha256":"e015e5543546a9a334da6fa3629bd53bc89ac298f2228470e9b235a1aa58adf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e015e5543546a9a334da6fa3629bd53bc89ac298f2228470e9b235a1aa58adf6","first_computed_at":"2026-08-05T00:43:37.278944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:43:37.278944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"suGA99O7VYJOULHe5fqf6l0urXUdC53NL/FnPS91l4FPX6KIyB9tPacEeBYikqtLxfjp7dVVkUcQHZX0VWyrBg==","signature_status":"signed_v1","signed_at":"2026-08-05T00:43:37.281940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeae9937608cd87990ab58a89f32ec2f86bb9ebdfc17dc50601d4d6bef1c7935","sha256:cbadcdbebda0910fa814192b2d37c0f671b85dae0d2a69c7bd0c7dc9f9e76344"],"state_sha256":"71df147e22ab23d90814c7a451d0cae4a692f51e293fb124bfbf83f3f3af699d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9d5x5oIjTNYpLBeP6m9F7Tq6VHcRTol+nhr4Eqd24sQsioZYWvbC2fG2bGWCwsrr0gpB72TCqNI6bit2M7NKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:45:22.016113Z","bundle_sha256":"cf23335540c9a8ab52afe0dde943e78cd5bebe5a6ed65b435eeeb2836e179472"}}