{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XT2A3DFCCSWMOBUF2NO4KSZFXP","short_pith_number":"pith:XT2A3DFC","schema_version":"1.0","canonical_sha256":"bcf40d8ca214acc70685d35dc54b25bbd55b276cef1166fecdf1b7b65e8a4f76","source":{"kind":"arxiv","id":"2308.03107","version":1},"attestation_state":"computed","paper":{"title":"Embedding-based Retrieval with LLM for Effective Agriculture Information Extracting from Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kang Liu, Po Yang, Ruoling Peng, Shunbao Li, Zhipeng Yuan","submitted_at":"2023-08-06T13:18:38Z","abstract_excerpt":"Pest identification is a crucial aspect of pest control in agriculture. However, most farmers are not capable of accurately identifying pests in the field, and there is a limited number of structured data sources available for rapid querying. In this work, we explored using domain-agnostic general pre-trained large language model(LLM) to extract structured data from agricultural documents with minimal or no human intervention. We propose a methodology that involves text retrieval and filtering using embedding-based retrieval, followed by LLM question-answering to automatically extract entities"},"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":"2308.03107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-06T13:18:38Z","cross_cats_sorted":[],"title_canon_sha256":"2bae22b807f345d26208cf151f3a84f93d2dcfd22f6e6a5756c2ff574d440e09","abstract_canon_sha256":"8623b5acc7209257dc9b962a4697faea9dca17759b8f3f866c7dc9ba07313672"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:11.955826Z","signature_b64":"daJIeYcVM2kXJQtWEDCoDB9IKD3r5aFf2Cnn5h4W3AkHF7qNlUOjiFKYaKiBJe+hPpFfE4OiBsY+fgnh4QoUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcf40d8ca214acc70685d35dc54b25bbd55b276cef1166fecdf1b7b65e8a4f76","last_reissued_at":"2026-07-05T06:38:11.955329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:11.955329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedding-based Retrieval with LLM for Effective Agriculture Information Extracting from Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kang Liu, Po Yang, Ruoling Peng, Shunbao Li, Zhipeng Yuan","submitted_at":"2023-08-06T13:18:38Z","abstract_excerpt":"Pest identification is a crucial aspect of pest control in agriculture. However, most farmers are not capable of accurately identifying pests in the field, and there is a limited number of structured data sources available for rapid querying. In this work, we explored using domain-agnostic general pre-trained large language model(LLM) to extract structured data from agricultural documents with minimal or no human intervention. We propose a methodology that involves text retrieval and filtering using embedding-based retrieval, followed by LLM question-answering to automatically extract entities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03107","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/2308.03107/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":"2308.03107","created_at":"2026-07-05T06:38:11.955393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.03107v1","created_at":"2026-07-05T06:38:11.955393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03107","created_at":"2026-07-05T06:38:11.955393+00:00"},{"alias_kind":"pith_short_12","alias_value":"XT2A3DFCCSWM","created_at":"2026-07-05T06:38:11.955393+00:00"},{"alias_kind":"pith_short_16","alias_value":"XT2A3DFCCSWMOBUF","created_at":"2026-07-05T06:38:11.955393+00:00"},{"alias_kind":"pith_short_8","alias_value":"XT2A3DFC","created_at":"2026-07-05T06:38:11.955393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16353","citing_title":"AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP","json":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP.json","graph_json":"https://pith.science/api/pith-number/XT2A3DFCCSWMOBUF2NO4KSZFXP/graph.json","events_json":"https://pith.science/api/pith-number/XT2A3DFCCSWMOBUF2NO4KSZFXP/events.json","paper":"https://pith.science/paper/XT2A3DFC"},"agent_actions":{"view_html":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP","download_json":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP.json","view_paper":"https://pith.science/paper/XT2A3DFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.03107&json=true","fetch_graph":"https://pith.science/api/pith-number/XT2A3DFCCSWMOBUF2NO4KSZFXP/graph.json","fetch_events":"https://pith.science/api/pith-number/XT2A3DFCCSWMOBUF2NO4KSZFXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/action/storage_attestation","attest_author":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/action/author_attestation","sign_citation":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/action/citation_signature","submit_replication":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/action/replication_record"}},"created_at":"2026-07-05T06:38:11.955393+00:00","updated_at":"2026-07-05T06:38:11.955393+00:00"}