{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CUINF4QSFCKVQE2Z4M3VWDZC3Z","short_pith_number":"pith:CUINF4QS","schema_version":"1.0","canonical_sha256":"1510d2f2122895581359e3375b0f22de6f3c044b22ddd56d2e8a45336982d8d0","source":{"kind":"arxiv","id":"2507.05997","version":1},"attestation_state":"computed","paper":{"title":"DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Kangen, Michael F\\\"arber, Nicholas Popovi\\v{c}, Tim Schopf","submitted_at":"2025-07-08T13:55:25Z","abstract_excerpt":"Large, high-quality annotated corpora remain scarce in document-level entity and relation extraction in zero-shot or few-shot settings. In this paper, we present a fully automatic, LLM-based pipeline for synthetic data generation and in-context learning for document-level entity and relation extraction. In contrast to existing approaches that rely on manually annotated demonstrations or direct zero-shot inference, our method combines synthetic data generation with retrieval-based in-context learning, using a reasoning-optimized language model. This allows us to build a high-quality demonstrati"},"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":"2507.05997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T13:55:25Z","cross_cats_sorted":[],"title_canon_sha256":"c76158543515db26000c67bbd257f962a567f229e22932bbfa17bbb08ecebb66","abstract_canon_sha256":"ed9c68d1035c55aec652b914228f1d81e65625433ce5faf922aa2e7e8c5d0de7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:39.713068Z","signature_b64":"wUrSawLONN6+dFPjI+mLbUCre7M3YiYH+t+ZARadPqWc48RK1cHd7A3RPC2jqjgNJsQFMpSLKnyFIlud7cKtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1510d2f2122895581359e3375b0f22de6f3c044b22ddd56d2e8a45336982d8d0","last_reissued_at":"2026-07-05T11:33:39.712684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:39.712684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Kangen, Michael F\\\"arber, Nicholas Popovi\\v{c}, Tim Schopf","submitted_at":"2025-07-08T13:55:25Z","abstract_excerpt":"Large, high-quality annotated corpora remain scarce in document-level entity and relation extraction in zero-shot or few-shot settings. In this paper, we present a fully automatic, LLM-based pipeline for synthetic data generation and in-context learning for document-level entity and relation extraction. In contrast to existing approaches that rely on manually annotated demonstrations or direct zero-shot inference, our method combines synthetic data generation with retrieval-based in-context learning, using a reasoning-optimized language model. This allows us to build a high-quality demonstrati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05997","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/2507.05997/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":"2507.05997","created_at":"2026-07-05T11:33:39.712740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05997v1","created_at":"2026-07-05T11:33:39.712740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05997","created_at":"2026-07-05T11:33:39.712740+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUINF4QSFCKV","created_at":"2026-07-05T11:33:39.712740+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUINF4QSFCKVQE2Z","created_at":"2026-07-05T11:33:39.712740+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUINF4QS","created_at":"2026-07-05T11:33:39.712740+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/CUINF4QSFCKVQE2Z4M3VWDZC3Z","json":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z.json","graph_json":"https://pith.science/api/pith-number/CUINF4QSFCKVQE2Z4M3VWDZC3Z/graph.json","events_json":"https://pith.science/api/pith-number/CUINF4QSFCKVQE2Z4M3VWDZC3Z/events.json","paper":"https://pith.science/paper/CUINF4QS"},"agent_actions":{"view_html":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z","download_json":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z.json","view_paper":"https://pith.science/paper/CUINF4QS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05997&json=true","fetch_graph":"https://pith.science/api/pith-number/CUINF4QSFCKVQE2Z4M3VWDZC3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/CUINF4QSFCKVQE2Z4M3VWDZC3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/action/storage_attestation","attest_author":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/action/author_attestation","sign_citation":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/action/citation_signature","submit_replication":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/action/replication_record"}},"created_at":"2026-07-05T11:33:39.712740+00:00","updated_at":"2026-07-05T11:33:39.712740+00:00"}