{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U3GUAX22RJ5GAQN6IMVICQJLPS","short_pith_number":"pith:U3GUAX22","schema_version":"1.0","canonical_sha256":"a6cd405f5a8a7a6041be432a81412b7c8fe4c118e56e54915a72545239052b38","source":{"kind":"arxiv","id":"2305.11527","version":4},"attestation_state":"computed","paper":{"title":"InstructIE: A Bilingual Instruction-based Information Extraction Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hongbin Ye, Honghao Gui, Huajun Chen, Jeff Z. Pan, Jintian Zhang, Lei Liang, Mengshu Sun, Ningyu Zhang, Shuofei Qiao","submitted_at":"2023-05-19T08:51:11Z","abstract_excerpt":"Large language models can perform well on general natural language tasks, but their effectiveness is still suboptimal for information extraction (IE). Recent works indicate that the main reason lies in the lack of extensive data on IE instructions. Note that the existing datasets on IE instructions not only have limited coverage but also involve high construction costs. To address this issue, we introduce InstructIE, a bilingual instruction-based IE dataset, which covers 12 diverse domains. We propose KG2Instruction, a framework specifically for the automatic generation of such datasets. Addit"},"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":"2305.11527","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T08:51:11Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"f37100eaf43ed5c7442729acec36de0867a0b165a514c824fcc6ea809a5fcf08","abstract_canon_sha256":"b02e1dc30c82d37f2a81ea03ce0d37479f115272d283d2eda70c69a3a326e07a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:24.444376Z","signature_b64":"mL08Q8eNX7/mz7KKbreJScP6hrXxK4SmStKZgag+s8B2UHcVsH1zypVk617jDNFSZF592eHp22E0aUUTTuFmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6cd405f5a8a7a6041be432a81412b7c8fe4c118e56e54915a72545239052b38","last_reissued_at":"2026-07-05T08:49:24.443867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:24.443867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructIE: A Bilingual Instruction-based Information Extraction Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hongbin Ye, Honghao Gui, Huajun Chen, Jeff Z. Pan, Jintian Zhang, Lei Liang, Mengshu Sun, Ningyu Zhang, Shuofei Qiao","submitted_at":"2023-05-19T08:51:11Z","abstract_excerpt":"Large language models can perform well on general natural language tasks, but their effectiveness is still suboptimal for information extraction (IE). Recent works indicate that the main reason lies in the lack of extensive data on IE instructions. Note that the existing datasets on IE instructions not only have limited coverage but also involve high construction costs. To address this issue, we introduce InstructIE, a bilingual instruction-based IE dataset, which covers 12 diverse domains. We propose KG2Instruction, a framework specifically for the automatic generation of such datasets. Addit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11527","kind":"arxiv","version":4},"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/2305.11527/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":"2305.11527","created_at":"2026-07-05T08:49:24.443932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11527v4","created_at":"2026-07-05T08:49:24.443932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11527","created_at":"2026-07-05T08:49:24.443932+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3GUAX22RJ5G","created_at":"2026-07-05T08:49:24.443932+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3GUAX22RJ5GAQN6","created_at":"2026-07-05T08:49:24.443932+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3GUAX22","created_at":"2026-07-05T08:49:24.443932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS","json":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS.json","graph_json":"https://pith.science/api/pith-number/U3GUAX22RJ5GAQN6IMVICQJLPS/graph.json","events_json":"https://pith.science/api/pith-number/U3GUAX22RJ5GAQN6IMVICQJLPS/events.json","paper":"https://pith.science/paper/U3GUAX22"},"agent_actions":{"view_html":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS","download_json":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS.json","view_paper":"https://pith.science/paper/U3GUAX22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11527&json=true","fetch_graph":"https://pith.science/api/pith-number/U3GUAX22RJ5GAQN6IMVICQJLPS/graph.json","fetch_events":"https://pith.science/api/pith-number/U3GUAX22RJ5GAQN6IMVICQJLPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS/action/storage_attestation","attest_author":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS/action/author_attestation","sign_citation":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS/action/citation_signature","submit_replication":"https://pith.science/pith/U3GUAX22RJ5GAQN6IMVICQJLPS/action/replication_record"}},"created_at":"2026-07-05T08:49:24.443932+00:00","updated_at":"2026-07-05T08:49:24.443932+00:00"}