{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HLHTXXLSGQ7YCEBPDYY64734GK","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":"87ce31fc69270cb6014c1fe4550a7f241b98c43c97882d0b400a7d142294161e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:20:15Z","title_canon_sha256":"99f1a6bb2501bcf17139cdc3d3b7255f215c014a8a45a87edd48b555ce21458d"},"schema_version":"1.0","source":{"id":"2312.10003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10003","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10003v1","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10003","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_12","alias_value":"HLHTXXLSGQ7Y","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_16","alias_value":"HLHTXXLSGQ7YCEBP","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_8","alias_value":"HLHTXXLS","created_at":"2026-07-05T07:24:43Z"}],"graph_snapshots":[{"event_id":"sha256:b36695a66043155dd4999b9c51d132c5543622d67efa8fcc3357901d67b2ca16","target":"graph","created_at":"2026-07-05T07:24:43Z","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/2312.10003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These systems, however, suffer from various failure cases, and we cannot directly train them end-to-end to fix such failures, as interaction with external knowledge is non-differentiable. To address these deficiencies, we define a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We further refine the agent through a ReST-like method","authors_text":"Daliang Li, Felix Yu, Kavya Kopparapu, Manzil Zaheer, Pranesh Srinivasan, Renat Aksitov, Ruiqi Guo, Sanjiv Kumar, Sheila Babayan, Sobhan Miryoosefi, Sushant Prakash, Zachary Fisher, Zonglin Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:20:15Z","title":"ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10003","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":"sha256:360be07bacd275942efff5b72fbdfb806ee00f12e83d08342191d142bacf5833","target":"record","created_at":"2026-07-05T07:24:43Z","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":"87ce31fc69270cb6014c1fe4550a7f241b98c43c97882d0b400a7d142294161e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:20:15Z","title_canon_sha256":"99f1a6bb2501bcf17139cdc3d3b7255f215c014a8a45a87edd48b555ce21458d"},"schema_version":"1.0","source":{"id":"2312.10003","kind":"arxiv","version":1}},"canonical_sha256":"3acf3bdd72343f81102f1e31ee7f7c3294318fdc35df90b5f5ae4685304589ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3acf3bdd72343f81102f1e31ee7f7c3294318fdc35df90b5f5ae4685304589ef","first_computed_at":"2026-07-05T07:24:43.547319Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:43.547319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rPf5khXxU/4apqPTXBo2YNpW8Vwno0potTuP7ya0fKFLVZsP2M+K6WSwJojO19Azmsdq046pnSGHs+wDC7FpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:43.547801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:360be07bacd275942efff5b72fbdfb806ee00f12e83d08342191d142bacf5833","sha256:b36695a66043155dd4999b9c51d132c5543622d67efa8fcc3357901d67b2ca16"],"state_sha256":"21461dd6605aa516559ae485331f22dbfccebed34f9c43bc03fc7c19c633dff5"}