{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ACDEOYH53JMNDGA4OWHPLAYEP3","short_pith_number":"pith:ACDEOYH5","canonical_record":{"source":{"id":"2606.29639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T23:12:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68325b7b9b2a2656606ca3bf849d9534f6ff3cc02aa184b15670f9ed5d9a360a","abstract_canon_sha256":"cad9e2d61c7f86591852c81042f022decfb999423fd27477ec97521299f15ad5"},"schema_version":"1.0"},"canonical_sha256":"00864760fdda58d1981c758ef583047ed1e4ad5707c976cae6a31ec4d9b4ccbd","source":{"kind":"arxiv","id":"2606.29639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29639","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29639v1","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29639","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"ACDEOYH53JMN","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"ACDEOYH53JMNDGA4","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"ACDEOYH5","created_at":"2026-06-30T01:18:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ACDEOYH53JMNDGA4OWHPLAYEP3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.29639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T23:12:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68325b7b9b2a2656606ca3bf849d9534f6ff3cc02aa184b15670f9ed5d9a360a","abstract_canon_sha256":"cad9e2d61c7f86591852c81042f022decfb999423fd27477ec97521299f15ad5"},"schema_version":"1.0"},"canonical_sha256":"00864760fdda58d1981c758ef583047ed1e4ad5707c976cae6a31ec4d9b4ccbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:20.815281Z","signature_b64":"RxaC47MxPAeeVv0V+qqHfrJT4qOLMl9TY+O5Hj21L//z9NHYC944S0Yp5EOOHxJboh6NL32p3Az0bp66PwvbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00864760fdda58d1981c758ef583047ed1e4ad5707c976cae6a31ec4d9b4ccbd","last_reissued_at":"2026-06-30T01:18:20.814670Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:20.814670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.29639","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":"2026-06-30T01:18:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sDCSmwTeBpFlEz+CvhcaWL0YDqvY4fv+QjqE3Gpwuuu9vENlr5bvFhF3GWEHIDtQ9+c7y5VYYZg5I92ipyuSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:21:56.298138Z"},"content_sha256":"6b78390f6d6c4cbfda601182d4f5ed647311b3275e5f559259bd4b2d5721f002","schema_version":"1.0","event_id":"sha256:6b78390f6d6c4cbfda601182d4f5ed647311b3275e5f559259bd4b2d5721f002"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ACDEOYH53JMNDGA4OWHPLAYEP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aunabil Chakma, Eduardo Blanco, Mihai Surdeanu","submitted_at":"2026-06-28T23:12:28Z","abstract_excerpt":"Automatic prompt optimization is still underexplored for episodic few-shot relation extraction with smaller language models. We propose a two-stage framework that combines reasoning-based prompt optimization with gradient-based prompt optimization. The first stage can use any reasoning-based optimizer to make broadprompt improvements in natural language. The second stage applies our GradPO, which uses loss and gradient signals to identify high-impact prompt spans and refine them with local edits. Experiments on FS-TACRED and FS-FewRel show that local refinement usually improves prompts found b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29639","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/2606.29639/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":"2026-06-30T01:18:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J/ZTBIaPd0X5dHHloe4srvXEgZHw+4FI6Sje0GZdlu9OO/1fFzOA0Mfh5rMktJMz0mlAYci7uHLZZ/D9Rx55Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:21:56.298535Z"},"content_sha256":"ee3c86e63aa2e0ec9a304e97a929a8a7f78db291adbe576420c919b0fec678d3","schema_version":"1.0","event_id":"sha256:ee3c86e63aa2e0ec9a304e97a929a8a7f78db291adbe576420c919b0fec678d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACDEOYH53JMNDGA4OWHPLAYEP3/bundle.json","state_url":"https://pith.science/pith/ACDEOYH53JMNDGA4OWHPLAYEP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACDEOYH53JMNDGA4OWHPLAYEP3/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":"2026-06-30T17:21:56Z","links":{"resolver":"https://pith.science/pith/ACDEOYH53JMNDGA4OWHPLAYEP3","bundle":"https://pith.science/pith/ACDEOYH53JMNDGA4OWHPLAYEP3/bundle.json","state":"https://pith.science/pith/ACDEOYH53JMNDGA4OWHPLAYEP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACDEOYH53JMNDGA4OWHPLAYEP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ACDEOYH53JMNDGA4OWHPLAYEP3","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":"cad9e2d61c7f86591852c81042f022decfb999423fd27477ec97521299f15ad5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T23:12:28Z","title_canon_sha256":"68325b7b9b2a2656606ca3bf849d9534f6ff3cc02aa184b15670f9ed5d9a360a"},"schema_version":"1.0","source":{"id":"2606.29639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29639","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29639v1","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29639","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"ACDEOYH53JMN","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"ACDEOYH53JMNDGA4","created_at":"2026-06-30T01:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"ACDEOYH5","created_at":"2026-06-30T01:18:20Z"}],"graph_snapshots":[{"event_id":"sha256:ee3c86e63aa2e0ec9a304e97a929a8a7f78db291adbe576420c919b0fec678d3","target":"graph","created_at":"2026-06-30T01:18:20Z","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/2606.29639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic prompt optimization is still underexplored for episodic few-shot relation extraction with smaller language models. We propose a two-stage framework that combines reasoning-based prompt optimization with gradient-based prompt optimization. The first stage can use any reasoning-based optimizer to make broadprompt improvements in natural language. The second stage applies our GradPO, which uses loss and gradient signals to identify high-impact prompt spans and refine them with local edits. Experiments on FS-TACRED and FS-FewRel show that local refinement usually improves prompts found b","authors_text":"Aunabil Chakma, Eduardo Blanco, Mihai Surdeanu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T23:12:28Z","title":"Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29639","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":"sha256:6b78390f6d6c4cbfda601182d4f5ed647311b3275e5f559259bd4b2d5721f002","target":"record","created_at":"2026-06-30T01:18:20Z","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":"cad9e2d61c7f86591852c81042f022decfb999423fd27477ec97521299f15ad5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T23:12:28Z","title_canon_sha256":"68325b7b9b2a2656606ca3bf849d9534f6ff3cc02aa184b15670f9ed5d9a360a"},"schema_version":"1.0","source":{"id":"2606.29639","kind":"arxiv","version":1}},"canonical_sha256":"00864760fdda58d1981c758ef583047ed1e4ad5707c976cae6a31ec4d9b4ccbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00864760fdda58d1981c758ef583047ed1e4ad5707c976cae6a31ec4d9b4ccbd","first_computed_at":"2026-06-30T01:18:20.814670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:20.814670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RxaC47MxPAeeVv0V+qqHfrJT4qOLMl9TY+O5Hj21L//z9NHYC944S0Yp5EOOHxJboh6NL32p3Az0bp66PwvbAQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:20.815281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b78390f6d6c4cbfda601182d4f5ed647311b3275e5f559259bd4b2d5721f002","sha256:ee3c86e63aa2e0ec9a304e97a929a8a7f78db291adbe576420c919b0fec678d3"],"state_sha256":"1960ae69de30f92d01c7110d82b1ff8df2de5d7cb4353041cb24d1c2da0bccea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tIFg2MNVpCpoiL4KB86lbBec27hl2bt0vHayy3p6kG5iOAP15g32BWGJY4zrHube7BV4GVcnQWBEI/Z7FoODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T17:21:56.300557Z","bundle_sha256":"4e465756e915d623dc731833ad30cc26df6f17d4283038e97f89eaeb4a2c1359"}}