{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZFI6AB22TY562WC5CTJ6NJGSQT","short_pith_number":"pith:ZFI6AB22","schema_version":"1.0","canonical_sha256":"c951e0075a9e3bed585d14d3e6a4d284d229b0781accee63e753d10529269c12","source":{"kind":"arxiv","id":"2303.05063","version":4},"attestation_state":"computed","paper":{"title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heng Tao Shen, Hui Liu, Jiabang He, Lei Wang, Ning Liu, Xing Xu, Yi Hu","submitted_at":"2023-03-09T06:24:50Z","abstract_excerpt":"Large language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples. Despite their successes in NLP tasks, no investigation has been conducted to assess the ability of LLMs to perform document information extraction (DIE) using in-context learning. Applying LLMs to DIE poses two challenges: the modality and task gap. To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to"},"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":"2303.05063","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-09T06:24:50Z","cross_cats_sorted":[],"title_canon_sha256":"89f29044a700354f465a0f35fa34e787868c200d03b9159f64d90037440d6aa2","abstract_canon_sha256":"ef702682d86fbc94f001cc3c7d1ba878e23ca4905b540c5285cae1ad8ea77cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:59.343894Z","signature_b64":"oW2MDwIJ442byrgrZGowIuWa1vNtdy7gDF3DUu/M9ZOo/xLgxTGwZzjlKIBuN3vTDRcZFQmAMFu2ubVXZRg6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c951e0075a9e3bed585d14d3e6a4d284d229b0781accee63e753d10529269c12","last_reissued_at":"2026-07-05T06:42:59.343451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:59.343451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heng Tao Shen, Hui Liu, Jiabang He, Lei Wang, Ning Liu, Xing Xu, Yi Hu","submitted_at":"2023-03-09T06:24:50Z","abstract_excerpt":"Large language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples. Despite their successes in NLP tasks, no investigation has been conducted to assess the ability of LLMs to perform document information extraction (DIE) using in-context learning. Applying LLMs to DIE poses two challenges: the modality and task gap. To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05063","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/2303.05063/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":"2303.05063","created_at":"2026-07-05T06:42:59.343521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05063v4","created_at":"2026-07-05T06:42:59.343521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05063","created_at":"2026-07-05T06:42:59.343521+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFI6AB22TY56","created_at":"2026-07-05T06:42:59.343521+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFI6AB22TY562WC5","created_at":"2026-07-05T06:42:59.343521+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFI6AB22","created_at":"2026-07-05T06:42:59.343521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.07895","citing_title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT","json":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT.json","graph_json":"https://pith.science/api/pith-number/ZFI6AB22TY562WC5CTJ6NJGSQT/graph.json","events_json":"https://pith.science/api/pith-number/ZFI6AB22TY562WC5CTJ6NJGSQT/events.json","paper":"https://pith.science/paper/ZFI6AB22"},"agent_actions":{"view_html":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT","download_json":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT.json","view_paper":"https://pith.science/paper/ZFI6AB22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05063&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFI6AB22TY562WC5CTJ6NJGSQT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFI6AB22TY562WC5CTJ6NJGSQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT/action/storage_attestation","attest_author":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT/action/author_attestation","sign_citation":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT/action/citation_signature","submit_replication":"https://pith.science/pith/ZFI6AB22TY562WC5CTJ6NJGSQT/action/replication_record"}},"created_at":"2026-07-05T06:42:59.343521+00:00","updated_at":"2026-07-05T06:42:59.343521+00:00"}