{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CUHW2KBBGF7KEPB4MTGT7WPZY4","short_pith_number":"pith:CUHW2KBB","schema_version":"1.0","canonical_sha256":"150f6d2821317ea23c3c64cd3fd9f9c733accf6123b96132f0a5f43a5ccd0350","source":{"kind":"arxiv","id":"2601.15037","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gongqing Wu, Jiapu Wang, Lang Sun, Xiaonan Jing, Xingrui Zhuo","submitted_at":"2026-01-21T14:42:13Z","abstract_excerpt":"Open-domain Relational Triplet Extraction (ORTE) aims to mine structured knowledge without predefined relation schemas. Large Language Models (LLMs) have advanced ORTE toward a prompt-driven paradigm through powerful in-context learning. However, adapting their extraction behavior to varying open-domain contexts remains challenging. Existing methods typically rely on manually crafted prompts that remain fixed across inputs, despite substantial variation in linguistic expressions and contextual structures. This mismatch may lead to unsupported triplets, while the absence of ground-truth annotat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.15037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-21T14:42:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1365f88684ee81325073e31bd3fe08b0dd42dd18ffbb86be3f1b02ed2ed16d14","abstract_canon_sha256":"0d1229bcb80038e65f9034c66d86217e083212cf087f152149b7a41e2842773c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:12:46.646338Z","signature_b64":"vGl6kzaGYZkBeuPhiSrbXFrI4sop3baqoNuVCxlMmgTXPeSYTyXNQcVZhRxGM21ywxrE2MopngvR5bigBWqYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"150f6d2821317ea23c3c64cd3fd9f9c733accf6123b96132f0a5f43a5ccd0350","last_reissued_at":"2026-08-03T01:12:46.644215Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:12:46.644215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gongqing Wu, Jiapu Wang, Lang Sun, Xiaonan Jing, Xingrui Zhuo","submitted_at":"2026-01-21T14:42:13Z","abstract_excerpt":"Open-domain Relational Triplet Extraction (ORTE) aims to mine structured knowledge without predefined relation schemas. Large Language Models (LLMs) have advanced ORTE toward a prompt-driven paradigm through powerful in-context learning. However, adapting their extraction behavior to varying open-domain contexts remains challenging. Existing methods typically rely on manually crafted prompts that remain fixed across inputs, despite substantial variation in linguistic expressions and contextual structures. This mismatch may lead to unsupported triplets, while the absence of ground-truth annotat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.15037","kind":"arxiv","version":2},"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/2601.15037/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.15037","created_at":"2026-08-03T01:12:46.645385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.15037v2","created_at":"2026-08-03T01:12:46.645385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15037","created_at":"2026-08-03T01:12:46.645385+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUHW2KBBGF7K","created_at":"2026-08-03T01:12:46.645385+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUHW2KBBGF7KEPB4","created_at":"2026-08-03T01:12:46.645385+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUHW2KBB","created_at":"2026-08-03T01:12:46.645385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4","json":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4.json","graph_json":"https://pith.science/api/pith-number/CUHW2KBBGF7KEPB4MTGT7WPZY4/graph.json","events_json":"https://pith.science/api/pith-number/CUHW2KBBGF7KEPB4MTGT7WPZY4/events.json","paper":"https://pith.science/paper/CUHW2KBB"},"agent_actions":{"view_html":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4","download_json":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4.json","view_paper":"https://pith.science/paper/CUHW2KBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.15037&json=true","fetch_graph":"https://pith.science/api/pith-number/CUHW2KBBGF7KEPB4MTGT7WPZY4/graph.json","fetch_events":"https://pith.science/api/pith-number/CUHW2KBBGF7KEPB4MTGT7WPZY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4/action/storage_attestation","attest_author":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4/action/author_attestation","sign_citation":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4/action/citation_signature","submit_replication":"https://pith.science/pith/CUHW2KBBGF7KEPB4MTGT7WPZY4/action/replication_record"}},"created_at":"2026-08-03T01:12:46.645385+00:00","updated_at":"2026-08-03T01:12:46.645385+00:00"}