{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3ZKRAS6AU3KYT7EWIVHVACDPRV","short_pith_number":"pith:3ZKRAS6A","schema_version":"1.0","canonical_sha256":"de55104bc0a6d589fc96454f50086f8d57cfab1288aea9f0ddb2c14a1bb3d56a","source":{"kind":"arxiv","id":"2305.14766","version":3},"attestation_state":"computed","paper":{"title":"Allies: Prompting Large Language Model with Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Hao Sun, Linjun Yang, Nan Duan, Xiao Liu, Yan Zhang, Yeyun Gong","submitted_at":"2023-05-24T06:16:44Z","abstract_excerpt":"With the advance of large language models (LLMs), the research field of LLM applications becomes more and more popular and the idea of constructing pipelines to accomplish complex tasks by stacking LLM API calls come true. However, this kind of methods face two limitations: narrow information coverage and low fault tolerance. In this work, we propose a novel method called ALLIES. Given an input query, ALLIES leverages LLMs to iteratively generate new queries related to the original query, enabling an iterative reasoning process. By iteratively refining and expanding the scope of the original q"},"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":"2305.14766","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T06:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"8cc6bdc584f2fbb5d40b7dade42a5fec6612c8c962c21167d8beb9a48bd47dc5","abstract_canon_sha256":"6b7ecdceb007104351ec8c2fb4a06726c9c1eb1c3066652ad65e1b627995ea6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:29.396985Z","signature_b64":"DT7EE/KGlUHiNetAKetnDEmeQhmRYAMkpgmPak0t0yHmHY1kwuVWLVZsT45i6EpNeFiS+cdOql+HmSLdKV6MAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de55104bc0a6d589fc96454f50086f8d57cfab1288aea9f0ddb2c14a1bb3d56a","last_reissued_at":"2026-07-05T07:02:29.396444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:29.396444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Allies: Prompting Large Language Model with Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Hao Sun, Linjun Yang, Nan Duan, Xiao Liu, Yan Zhang, Yeyun Gong","submitted_at":"2023-05-24T06:16:44Z","abstract_excerpt":"With the advance of large language models (LLMs), the research field of LLM applications becomes more and more popular and the idea of constructing pipelines to accomplish complex tasks by stacking LLM API calls come true. However, this kind of methods face two limitations: narrow information coverage and low fault tolerance. In this work, we propose a novel method called ALLIES. Given an input query, ALLIES leverages LLMs to iteratively generate new queries related to the original query, enabling an iterative reasoning process. By iteratively refining and expanding the scope of the original q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14766","kind":"arxiv","version":3},"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/2305.14766/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":"2305.14766","created_at":"2026-07-05T07:02:29.396514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14766v3","created_at":"2026-07-05T07:02:29.396514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14766","created_at":"2026-07-05T07:02:29.396514+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZKRAS6AU3KY","created_at":"2026-07-05T07:02:29.396514+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZKRAS6AU3KYT7EW","created_at":"2026-07-05T07:02:29.396514+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZKRAS6A","created_at":"2026-07-05T07:02:29.396514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17175","citing_title":"RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV","json":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV.json","graph_json":"https://pith.science/api/pith-number/3ZKRAS6AU3KYT7EWIVHVACDPRV/graph.json","events_json":"https://pith.science/api/pith-number/3ZKRAS6AU3KYT7EWIVHVACDPRV/events.json","paper":"https://pith.science/paper/3ZKRAS6A"},"agent_actions":{"view_html":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV","download_json":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV.json","view_paper":"https://pith.science/paper/3ZKRAS6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14766&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZKRAS6AU3KYT7EWIVHVACDPRV/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZKRAS6AU3KYT7EWIVHVACDPRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV/action/storage_attestation","attest_author":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV/action/author_attestation","sign_citation":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV/action/citation_signature","submit_replication":"https://pith.science/pith/3ZKRAS6AU3KYT7EWIVHVACDPRV/action/replication_record"}},"created_at":"2026-07-05T07:02:29.396514+00:00","updated_at":"2026-07-05T07:02:29.396514+00:00"}