{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VEDGH5EB4XV7KNTV2WNRBFDIIH","short_pith_number":"pith:VEDGH5EB","schema_version":"1.0","canonical_sha256":"a90663f481e5ebf53675d59b10946841faa5d8e6d36c123c04578ff3fbdc3482","source":{"kind":"arxiv","id":"2406.15193","version":5},"attestation_state":"computed","paper":{"title":"Inference Time Alignment with Reward-Guided Tree Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ambuj Mehrish, Chia-Yu Hung, Navonil Majumder, Soujanya Poria","submitted_at":"2024-06-21T14:35:16Z","abstract_excerpt":"Inference-time computation methods enhance the performance of Large Language Models (LLMs) by leveraging additional computational resources to achieve superior results. Common techniques, such as Best-of-N sampling, Majority Voting, and variants of tree-search algorithms have proven to be effective in boosting the performance of LLMs. These approaches strategically trade increased computational resources for improved model responses. In this work, we proposed DARWIN, an inference-time alignment method that leverages the guidance of a reward model to achieve alignment through a reward-guided tr"},"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":"2406.15193","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T14:35:16Z","cross_cats_sorted":[],"title_canon_sha256":"0e9067743c818c485b29bc52a7be87a510e17e2f8191a96090de500373e4a044","abstract_canon_sha256":"067883bc6e8cd9320526916bb1da7fa2992d355fbbb0c8da60fb36f5e544e0a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:41.098092Z","signature_b64":"z2Yt6OMNBc95M/Iej1jvYLuBzcYU5qb83cbEguaqNqFCjgKaxbPBdbalLbcvzSXJlpWckAAZm2n2jb4BWV+IAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a90663f481e5ebf53675d59b10946841faa5d8e6d36c123c04578ff3fbdc3482","last_reissued_at":"2026-07-05T09:40:41.097604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:41.097604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference Time Alignment with Reward-Guided Tree Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ambuj Mehrish, Chia-Yu Hung, Navonil Majumder, Soujanya Poria","submitted_at":"2024-06-21T14:35:16Z","abstract_excerpt":"Inference-time computation methods enhance the performance of Large Language Models (LLMs) by leveraging additional computational resources to achieve superior results. Common techniques, such as Best-of-N sampling, Majority Voting, and variants of tree-search algorithms have proven to be effective in boosting the performance of LLMs. These approaches strategically trade increased computational resources for improved model responses. In this work, we proposed DARWIN, an inference-time alignment method that leverages the guidance of a reward model to achieve alignment through a reward-guided tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15193","kind":"arxiv","version":5},"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/2406.15193/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":"2406.15193","created_at":"2026-07-05T09:40:41.097663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15193v5","created_at":"2026-07-05T09:40:41.097663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15193","created_at":"2026-07-05T09:40:41.097663+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEDGH5EB4XV7","created_at":"2026-07-05T09:40:41.097663+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEDGH5EB4XV7KNTV","created_at":"2026-07-05T09:40:41.097663+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEDGH5EB","created_at":"2026-07-05T09:40:41.097663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09016","citing_title":"A Survey on Training-free Alignment of Large Language Models","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH","json":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH.json","graph_json":"https://pith.science/api/pith-number/VEDGH5EB4XV7KNTV2WNRBFDIIH/graph.json","events_json":"https://pith.science/api/pith-number/VEDGH5EB4XV7KNTV2WNRBFDIIH/events.json","paper":"https://pith.science/paper/VEDGH5EB"},"agent_actions":{"view_html":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH","download_json":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH.json","view_paper":"https://pith.science/paper/VEDGH5EB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15193&json=true","fetch_graph":"https://pith.science/api/pith-number/VEDGH5EB4XV7KNTV2WNRBFDIIH/graph.json","fetch_events":"https://pith.science/api/pith-number/VEDGH5EB4XV7KNTV2WNRBFDIIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH/action/storage_attestation","attest_author":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH/action/author_attestation","sign_citation":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH/action/citation_signature","submit_replication":"https://pith.science/pith/VEDGH5EB4XV7KNTV2WNRBFDIIH/action/replication_record"}},"created_at":"2026-07-05T09:40:41.097663+00:00","updated_at":"2026-07-05T09:40:41.097663+00:00"}