{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3P2QCJ35BJE7ZY2ORT45HQMRNQ","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":"05c3f43404924aa24553fd082bf3dfbccfbc53ee9ceb86af665ad759ea673f5f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T13:07:38Z","title_canon_sha256":"80167e944de462791daac7bf8b2a2d715439bf7304078ce92934bad3e3087a46"},"schema_version":"1.0","source":{"id":"2406.14282","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14282","created_at":"2026-07-05T09:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14282v3","created_at":"2026-07-05T09:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14282","created_at":"2026-07-05T09:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"3P2QCJ35BJE7","created_at":"2026-07-05T09:24:36Z"},{"alias_kind":"pith_short_16","alias_value":"3P2QCJ35BJE7ZY2O","created_at":"2026-07-05T09:24:36Z"},{"alias_kind":"pith_short_8","alias_value":"3P2QCJ35","created_at":"2026-07-05T09:24:36Z"}],"graph_snapshots":[{"event_id":"sha256:109c059443a8a7f9554115cccdbc904ba6bd13396ff5b8904b3154d8186fa189","target":"graph","created_at":"2026-07-05T09:24:36Z","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/2406.14282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improving the performance of large language models (LLMs) in complex question-answering (QA) scenarios has always been a research focal point. Recent studies have attempted to enhance LLMs' performance by combining step-wise planning with external retrieval. While effective for advanced models like GPT-3.5, smaller LLMs face challenges in decomposing complex questions, necessitating supervised fine-tuning. Previous work has relied on manual annotation and knowledge distillation from teacher LLMs, which are time-consuming and not accurate enough. In this paper, we introduce a novel framework fo","authors_text":"BinBin Hu, Dan Yang, Huajun Chen, Jeff Z. Pan, Jinjie Gu, Junjie Wang, Jun Zhou, Mingyang Chen, Peng Wei, Wen Zhang, Yue Shen, Zhiqiang Zhang, Ziqi Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T13:07:38Z","title":"Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14282","kind":"arxiv","version":3},"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":"sha256:0e56957087adb92feb715e9608b280f073aa5cd2d3ef3230e9ac852d25282085","target":"record","created_at":"2026-07-05T09:24:36Z","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":"05c3f43404924aa24553fd082bf3dfbccfbc53ee9ceb86af665ad759ea673f5f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T13:07:38Z","title_canon_sha256":"80167e944de462791daac7bf8b2a2d715439bf7304078ce92934bad3e3087a46"},"schema_version":"1.0","source":{"id":"2406.14282","kind":"arxiv","version":3}},"canonical_sha256":"dbf501277d0a49fce34e8cf9d3c1916c134ac3b16dd481bd667c0e927fea37fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbf501277d0a49fce34e8cf9d3c1916c134ac3b16dd481bd667c0e927fea37fd","first_computed_at":"2026-07-05T09:24:36.295582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:36.295582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IBMej58r43e/q/TuOwM/La6yCGFiV8w2OL8Twhwv8pZWYPso3DrQj8uX/QtUHTHRVEckLcWPlpkIWGFziHtADw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:36.296051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14282","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e56957087adb92feb715e9608b280f073aa5cd2d3ef3230e9ac852d25282085","sha256:109c059443a8a7f9554115cccdbc904ba6bd13396ff5b8904b3154d8186fa189"],"state_sha256":"5c1f9ca5ea0c869fc3c87a141c49765aeea1ad3c9375790857a6a480b9ffb9df"}