{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7TZPQVNQYXASPRTWMCQNWCCCG4","short_pith_number":"pith:7TZPQVNQ","schema_version":"1.0","canonical_sha256":"fcf2f855b0c5c127c67660a0db08423713aab3b3c3a37130413be3fdd3c88b77","source":{"kind":"arxiv","id":"2407.03951","version":3},"attestation_state":"computed","paper":{"title":"Uncertainty-Guided Likelihood Tree Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Ahmad Rashid, Cheng Zhang, Julia Grosse, Pascal Poupart, Philipp Hennig, Ruotian Wu","submitted_at":"2024-07-04T14:08:50Z","abstract_excerpt":"Tree search is a fundamental tool for planning, as many sequential decision-making problems can be framed as searching over tree-structured spaces. We propose an uncertainty-guided tree search algorithm for settings where the reward function is a log-likelihood function of the paths. Due to the combinatorial explosion of the tree size, the set of paths for which one can obtain rewards is sparse, particularly when the likelihood is obtained through expensive evaluations, such as by querying a large language model. We address this challenge by deriving an probabilistic search heuristic based on "},"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":"2407.03951","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T14:08:50Z","cross_cats_sorted":[],"title_canon_sha256":"cc62351774fd7ea49355c286ac5637b4bab27353dcb151868a00323202be78bf","abstract_canon_sha256":"4b2822dc3a477a807ea5f127d99fbc5ea60cfc23985a0f90eaf58c12423968e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:27.352004Z","signature_b64":"GRcJVei640/TlJBKuG4tvmDZMKPuGigUg8l2P1lW8qa0F0uHEXBKIP1t+C5knHzah0BUr5fQVZGI7yovffCHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf2f855b0c5c127c67660a0db08423713aab3b3c3a37130413be3fdd3c88b77","last_reissued_at":"2026-07-05T12:04:27.351487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:27.351487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Guided Likelihood Tree Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Ahmad Rashid, Cheng Zhang, Julia Grosse, Pascal Poupart, Philipp Hennig, Ruotian Wu","submitted_at":"2024-07-04T14:08:50Z","abstract_excerpt":"Tree search is a fundamental tool for planning, as many sequential decision-making problems can be framed as searching over tree-structured spaces. We propose an uncertainty-guided tree search algorithm for settings where the reward function is a log-likelihood function of the paths. Due to the combinatorial explosion of the tree size, the set of paths for which one can obtain rewards is sparse, particularly when the likelihood is obtained through expensive evaluations, such as by querying a large language model. We address this challenge by deriving an probabilistic search heuristic based on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03951","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/2407.03951/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":"2407.03951","created_at":"2026-07-05T12:04:27.351547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03951v3","created_at":"2026-07-05T12:04:27.351547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03951","created_at":"2026-07-05T12:04:27.351547+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TZPQVNQYXAS","created_at":"2026-07-05T12:04:27.351547+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TZPQVNQYXASPRTW","created_at":"2026-07-05T12:04:27.351547+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TZPQVNQ","created_at":"2026-07-05T12:04:27.351547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08221","citing_title":"De novo molecular generation with optical property preconditioning at the token level","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":222,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4","json":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4.json","graph_json":"https://pith.science/api/pith-number/7TZPQVNQYXASPRTWMCQNWCCCG4/graph.json","events_json":"https://pith.science/api/pith-number/7TZPQVNQYXASPRTWMCQNWCCCG4/events.json","paper":"https://pith.science/paper/7TZPQVNQ"},"agent_actions":{"view_html":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4","download_json":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4.json","view_paper":"https://pith.science/paper/7TZPQVNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03951&json=true","fetch_graph":"https://pith.science/api/pith-number/7TZPQVNQYXASPRTWMCQNWCCCG4/graph.json","fetch_events":"https://pith.science/api/pith-number/7TZPQVNQYXASPRTWMCQNWCCCG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4/action/storage_attestation","attest_author":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4/action/author_attestation","sign_citation":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4/action/citation_signature","submit_replication":"https://pith.science/pith/7TZPQVNQYXASPRTWMCQNWCCCG4/action/replication_record"}},"created_at":"2026-07-05T12:04:27.351547+00:00","updated_at":"2026-07-05T12:04:27.351547+00:00"}