{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5EJVQFNLR4OO2JPG5XP25IMKVH","short_pith_number":"pith:5EJVQFNL","canonical_record":{"source":{"id":"2405.05008","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T12:24:52Z","cross_cats_sorted":[],"title_canon_sha256":"d15092bf911e859981432c00b64f75e3cf85aa340f2b723a1500bb28ade72f76","abstract_canon_sha256":"6e331022ce4366692a131bf78a8a568cd8fd235ca9d34f4d7ae675465cc29a1d"},"schema_version":"1.0"},"canonical_sha256":"e9135815ab8f1ced25e6eddfaea18aa9fb52181b1131c659028fdd540de069ba","source":{"kind":"arxiv","id":"2405.05008","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05008","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05008v2","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05008","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"5EJVQFNLR4OO","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"5EJVQFNLR4OO2JPG","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"5EJVQFNL","created_at":"2026-07-05T09:24:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5EJVQFNLR4OO2JPG5XP25IMKVH","target":"record","payload":{"canonical_record":{"source":{"id":"2405.05008","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T12:24:52Z","cross_cats_sorted":[],"title_canon_sha256":"d15092bf911e859981432c00b64f75e3cf85aa340f2b723a1500bb28ade72f76","abstract_canon_sha256":"6e331022ce4366692a131bf78a8a568cd8fd235ca9d34f4d7ae675465cc29a1d"},"schema_version":"1.0"},"canonical_sha256":"e9135815ab8f1ced25e6eddfaea18aa9fb52181b1131c659028fdd540de069ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:57.976072Z","signature_b64":"LUOD80nseM2YLiYw0JynzPGd4//Hlu8V2YmI+8vVDuSmFseR8q7oVQR/J1yfDCyUZRdjWFW2uKvZQP1fRUHMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9135815ab8f1ced25e6eddfaea18aa9fb52181b1131c659028fdd540de069ba","last_reissued_at":"2026-07-05T09:24:57.975594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:57.975594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.05008","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2bHjk1Oz7j4lpzpVeAuum/Iyl0VoAxIr8fZcKGIg7ZAtFlV75c/bYrsoeNaNKUB4U2U2TwMAJLHRajWV634AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:40:19.271378Z"},"content_sha256":"f242fd90ba7d4d9fd78b80ce529e1044b357e09dfe61331817a34597ef479671","schema_version":"1.0","event_id":"sha256:f242fd90ba7d4d9fd78b80ce529e1044b357e09dfe61331817a34597ef479671"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5EJVQFNLR4OO2JPG5XP25IMKVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ADELIE: Aligning Large Language Models on Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Xu, Hao Peng, Juanzi Li, Lei Hou, Xiaozhi Wang, Yunjia Qi","submitted_at":"2024-05-08T12:24:52Z","abstract_excerpt":"Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment datasets typically do not include IE data. In this paper, we introduce ADELIE (Aligning large language moDELs on Information Extraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect and construct a high-quality alignment corpus IEInstruct for IE. Then we train ADELIE_SFT using instruction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05008","kind":"arxiv","version":2},"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/2405.05008/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":"2026-07-05T09:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5tZ1TrfRbHaZhrnTqNVIN6jlQTF6HIoOgLgjtGz0ZLpSgwH+taz1qrL1JyJx+fH7tBMCw6gJGmQqaf+YJIbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:40:19.271886Z"},"content_sha256":"e03854aa544ab2e9ae5cd2f384ad9a8d4a367be64f1c3fcd63bcb1da2e9c2d0a","schema_version":"1.0","event_id":"sha256:e03854aa544ab2e9ae5cd2f384ad9a8d4a367be64f1c3fcd63bcb1da2e9c2d0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5EJVQFNLR4OO2JPG5XP25IMKVH/bundle.json","state_url":"https://pith.science/pith/5EJVQFNLR4OO2JPG5XP25IMKVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5EJVQFNLR4OO2JPG5XP25IMKVH/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":"2026-08-10T13:40:19Z","links":{"resolver":"https://pith.science/pith/5EJVQFNLR4OO2JPG5XP25IMKVH","bundle":"https://pith.science/pith/5EJVQFNLR4OO2JPG5XP25IMKVH/bundle.json","state":"https://pith.science/pith/5EJVQFNLR4OO2JPG5XP25IMKVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5EJVQFNLR4OO2JPG5XP25IMKVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5EJVQFNLR4OO2JPG5XP25IMKVH","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":"6e331022ce4366692a131bf78a8a568cd8fd235ca9d34f4d7ae675465cc29a1d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T12:24:52Z","title_canon_sha256":"d15092bf911e859981432c00b64f75e3cf85aa340f2b723a1500bb28ade72f76"},"schema_version":"1.0","source":{"id":"2405.05008","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05008","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05008v2","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05008","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"5EJVQFNLR4OO","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"5EJVQFNLR4OO2JPG","created_at":"2026-07-05T09:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"5EJVQFNL","created_at":"2026-07-05T09:24:57Z"}],"graph_snapshots":[{"event_id":"sha256:e03854aa544ab2e9ae5cd2f384ad9a8d4a367be64f1c3fcd63bcb1da2e9c2d0a","target":"graph","created_at":"2026-07-05T09:24:57Z","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/2405.05008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment datasets typically do not include IE data. In this paper, we introduce ADELIE (Aligning large language moDELs on Information Extraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect and construct a high-quality alignment corpus IEInstruct for IE. Then we train ADELIE_SFT using instruction","authors_text":"Bin Xu, Hao Peng, Juanzi Li, Lei Hou, Xiaozhi Wang, Yunjia Qi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T12:24:52Z","title":"ADELIE: Aligning Large Language Models on Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05008","kind":"arxiv","version":2},"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:f242fd90ba7d4d9fd78b80ce529e1044b357e09dfe61331817a34597ef479671","target":"record","created_at":"2026-07-05T09:24:57Z","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":"6e331022ce4366692a131bf78a8a568cd8fd235ca9d34f4d7ae675465cc29a1d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T12:24:52Z","title_canon_sha256":"d15092bf911e859981432c00b64f75e3cf85aa340f2b723a1500bb28ade72f76"},"schema_version":"1.0","source":{"id":"2405.05008","kind":"arxiv","version":2}},"canonical_sha256":"e9135815ab8f1ced25e6eddfaea18aa9fb52181b1131c659028fdd540de069ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9135815ab8f1ced25e6eddfaea18aa9fb52181b1131c659028fdd540de069ba","first_computed_at":"2026-07-05T09:24:57.975594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:57.975594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LUOD80nseM2YLiYw0JynzPGd4//Hlu8V2YmI+8vVDuSmFseR8q7oVQR/J1yfDCyUZRdjWFW2uKvZQP1fRUHMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:57.976072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05008","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f242fd90ba7d4d9fd78b80ce529e1044b357e09dfe61331817a34597ef479671","sha256:e03854aa544ab2e9ae5cd2f384ad9a8d4a367be64f1c3fcd63bcb1da2e9c2d0a"],"state_sha256":"b536a6562a30779f594b0fb6762718eec5877540d356047b00adeef6421a07be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJ3cwpiZehQOsKXuWmCxE+9zCn1ndWJ7kDOfRERTTaPVKAqmN7i0cfSqPWbGY6xS+SknQsksim7w415v50iXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:40:19.277455Z","bundle_sha256":"aac0d7e58cfa09d01fa66d45ca0307a34e86e525882aed9f3d6425eb68e135ce"}}