{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XT2A3DFCCSWMOBUF2NO4KSZFXP","short_pith_number":"pith:XT2A3DFC","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"},"canonical_sha256":"bcf40d8ca214acc70685d35dc54b25bbd55b276cef1166fecdf1b7b65e8a4f76","source":{"kind":"arxiv","id":"2308.03107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03107","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03107v1","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03107","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"pith_short_12","alias_value":"XT2A3DFCCSWM","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"pith_short_16","alias_value":"XT2A3DFCCSWMOBUF","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"pith_short_8","alias_value":"XT2A3DFC","created_at":"2026-07-05T06:38:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XT2A3DFCCSWMOBUF2NO4KSZFXP","target":"record","payload":{"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"},"canonical_sha256":"bcf40d8ca214acc70685d35dc54b25bbd55b276cef1166fecdf1b7b65e8a4f76","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"},"source_kind":"arxiv","source_id":"2308.03107","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":"2026-07-05T06:38:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PvQIdWMi3oh+5E2okpjKPQDt/6877M3c7WUL5FfZ4pfhrRhD7fjNEAarjUtdpXZQTfsXzOLiGzYFGO9wbNngDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:04.609798Z"},"content_sha256":"7dae31660cfc87059f745a6f5deefba66d94b8db26db815619d33704c31749ad","schema_version":"1.0","event_id":"sha256:7dae31660cfc87059f745a6f5deefba66d94b8db26db815619d33704c31749ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XT2A3DFCCSWMOBUF2NO4KSZFXP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:38:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHM2jA+brDyA51T85fYsRMwwX/rcjxhUdvniW7cdMyHQrrNcHDpBZC9zr2udW7a7hInDmCcLifnyc/UDRF6LCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:04.610179Z"},"content_sha256":"60db8f5d8922ab69c5555738c51a416b197e13a8a359122d7e707ca616cf560c","schema_version":"1.0","event_id":"sha256:60db8f5d8922ab69c5555738c51a416b197e13a8a359122d7e707ca616cf560c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/bundle.json","state_url":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/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":"2026-07-06T19:21:04Z","links":{"resolver":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP","bundle":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/bundle.json","state":"https://pith.science/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XT2A3DFCCSWMOBUF2NO4KSZFXP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XT2A3DFCCSWMOBUF2NO4KSZFXP","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":"8623b5acc7209257dc9b962a4697faea9dca17759b8f3f866c7dc9ba07313672","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-06T13:18:38Z","title_canon_sha256":"2bae22b807f345d26208cf151f3a84f93d2dcfd22f6e6a5756c2ff574d440e09"},"schema_version":"1.0","source":{"id":"2308.03107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03107","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03107v1","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03107","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"pith_short_12","alias_value":"XT2A3DFCCSWM","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"pith_short_16","alias_value":"XT2A3DFCCSWMOBUF","created_at":"2026-07-05T06:38:11Z"},{"alias_kind":"pith_short_8","alias_value":"XT2A3DFC","created_at":"2026-07-05T06:38:11Z"}],"graph_snapshots":[{"event_id":"sha256:60db8f5d8922ab69c5555738c51a416b197e13a8a359122d7e707ca616cf560c","target":"graph","created_at":"2026-07-05T06:38:11Z","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/2308.03107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kang Liu, Po Yang, Ruoling Peng, Shunbao Li, Zhipeng Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-06T13:18:38Z","title":"Embedding-based Retrieval with LLM for Effective Agriculture Information Extracting from Unstructured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03107","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":"sha256:7dae31660cfc87059f745a6f5deefba66d94b8db26db815619d33704c31749ad","target":"record","created_at":"2026-07-05T06:38:11Z","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":"8623b5acc7209257dc9b962a4697faea9dca17759b8f3f866c7dc9ba07313672","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-06T13:18:38Z","title_canon_sha256":"2bae22b807f345d26208cf151f3a84f93d2dcfd22f6e6a5756c2ff574d440e09"},"schema_version":"1.0","source":{"id":"2308.03107","kind":"arxiv","version":1}},"canonical_sha256":"bcf40d8ca214acc70685d35dc54b25bbd55b276cef1166fecdf1b7b65e8a4f76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcf40d8ca214acc70685d35dc54b25bbd55b276cef1166fecdf1b7b65e8a4f76","first_computed_at":"2026-07-05T06:38:11.955329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:38:11.955329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"daJIeYcVM2kXJQtWEDCoDB9IKD3r5aFf2Cnn5h4W3AkHF7qNlUOjiFKYaKiBJe+hPpFfE4OiBsY+fgnh4QoUAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:38:11.955826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.03107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dae31660cfc87059f745a6f5deefba66d94b8db26db815619d33704c31749ad","sha256:60db8f5d8922ab69c5555738c51a416b197e13a8a359122d7e707ca616cf560c"],"state_sha256":"09e29357c6cd94e2f993ceffd695e60c4780ae94e4288161c5b426f9faeca3d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hdaZ3Utc/RmGFnQ74t4/loigMv9gT/wX338hi6gfCiLn46ol5aMWKu5XQQG7F6sQXnlTba2QwVIRdPvLhDtBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:21:04.612097Z","bundle_sha256":"9da4a67ac156625b7af4792d0370acb1f94994e91db5a0079fd9027a7ace8883"}}