{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CUINF4QSFCKVQE2Z4M3VWDZC3Z","short_pith_number":"pith:CUINF4QS","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"},"canonical_sha256":"1510d2f2122895581359e3375b0f22de6f3c044b22ddd56d2e8a45336982d8d0","source":{"kind":"arxiv","id":"2507.05997","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05997","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05997v1","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05997","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"CUINF4QSFCKV","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"pith_short_16","alias_value":"CUINF4QSFCKVQE2Z","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"pith_short_8","alias_value":"CUINF4QS","created_at":"2026-07-05T11:33:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CUINF4QSFCKVQE2Z4M3VWDZC3Z","target":"record","payload":{"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"},"canonical_sha256":"1510d2f2122895581359e3375b0f22de6f3c044b22ddd56d2e8a45336982d8d0","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"},"source_kind":"arxiv","source_id":"2507.05997","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":"2026-07-05T11:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cOeClUV6o5kKJQfkuNKhz3+zTUSA4lccIbIIMT0JA07mndlKKZ78vzbqu8jv//6pUfs1XxlUJsJrhKwz89OxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:13:35.456639Z"},"content_sha256":"a0547632ae1ab5ddf6d6eb87c1baa14b29688850289d27defaaa5b66a51dfb73","schema_version":"1.0","event_id":"sha256:a0547632ae1ab5ddf6d6eb87c1baa14b29688850289d27defaaa5b66a51dfb73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CUINF4QSFCKVQE2Z4M3VWDZC3Z","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+2LLO4Oag8KaWrc/J28dlafPn11iPte0WMUp1SBav9jdxzL+7dfF+DeNrEie7W1oJNP+T7IQuDpjX4Bg5bLqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:13:35.457121Z"},"content_sha256":"e6ffde85e0ddf130252c5b10efaae323145fc095b95b702afa5918fccda5a4d1","schema_version":"1.0","event_id":"sha256:e6ffde85e0ddf130252c5b10efaae323145fc095b95b702afa5918fccda5a4d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/bundle.json","state_url":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/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":"2026-08-05T07:13:35Z","links":{"resolver":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z","bundle":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/bundle.json","state":"https://pith.science/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUINF4QSFCKVQE2Z4M3VWDZC3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CUINF4QSFCKVQE2Z4M3VWDZC3Z","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":"ed9c68d1035c55aec652b914228f1d81e65625433ce5faf922aa2e7e8c5d0de7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T13:55:25Z","title_canon_sha256":"c76158543515db26000c67bbd257f962a567f229e22932bbfa17bbb08ecebb66"},"schema_version":"1.0","source":{"id":"2507.05997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05997","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05997v1","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05997","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"CUINF4QSFCKV","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"pith_short_16","alias_value":"CUINF4QSFCKVQE2Z","created_at":"2026-07-05T11:33:39Z"},{"alias_kind":"pith_short_8","alias_value":"CUINF4QS","created_at":"2026-07-05T11:33:39Z"}],"graph_snapshots":[{"event_id":"sha256:e6ffde85e0ddf130252c5b10efaae323145fc095b95b702afa5918fccda5a4d1","target":"graph","created_at":"2026-07-05T11:33:39Z","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/2507.05997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ashish Kangen, Michael F\\\"arber, Nicholas Popovi\\v{c}, Tim Schopf","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T13:55:25Z","title":"DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05997","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:a0547632ae1ab5ddf6d6eb87c1baa14b29688850289d27defaaa5b66a51dfb73","target":"record","created_at":"2026-07-05T11:33:39Z","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":"ed9c68d1035c55aec652b914228f1d81e65625433ce5faf922aa2e7e8c5d0de7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T13:55:25Z","title_canon_sha256":"c76158543515db26000c67bbd257f962a567f229e22932bbfa17bbb08ecebb66"},"schema_version":"1.0","source":{"id":"2507.05997","kind":"arxiv","version":1}},"canonical_sha256":"1510d2f2122895581359e3375b0f22de6f3c044b22ddd56d2e8a45336982d8d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1510d2f2122895581359e3375b0f22de6f3c044b22ddd56d2e8a45336982d8d0","first_computed_at":"2026-07-05T11:33:39.712684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:39.712684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wUrSawLONN6+dFPjI+mLbUCre7M3YiYH+t+ZARadPqWc48RK1cHd7A3RPC2jqjgNJsQFMpSLKnyFIlud7cKtBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:39.713068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0547632ae1ab5ddf6d6eb87c1baa14b29688850289d27defaaa5b66a51dfb73","sha256:e6ffde85e0ddf130252c5b10efaae323145fc095b95b702afa5918fccda5a4d1"],"state_sha256":"1ed68763eceb37affa735e9fd1c7f9a8bd3d78ff4ba34a85b0313f646fe6ebe9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WhdyMASsR4k8cAuqlLiTsl95+h7tBaHtBHIv2YUevCglk8g7mh5r1s4/1Y030GGTd4NYHSimbk2JvJ5gIFIWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:13:35.460835Z","bundle_sha256":"e19a024d9c66de97dec6708e5a285541441305ceed2313859f9543673e14b263"}}