{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VW7KUS4PYFMY6XN2VEN5MNQVLY","short_pith_number":"pith:VW7KUS4P","schema_version":"1.0","canonical_sha256":"adbeaa4b8fc1598f5dbaa91bd636155e298893d58ba6b1e0487212f3be1fdb4d","source":{"kind":"arxiv","id":"2305.16945","version":3},"attestation_state":"computed","paper":{"title":"Levin Tree Search with Context Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Laurent Orseau, Levi H.S. Lelis, Marcus Hutter","submitted_at":"2023-05-26T14:00:12Z","abstract_excerpt":"Levin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansions before reaching a goal node, depending on the quality of the policy. This guarantee can be used as a loss function, which we call the LTS loss, to optimize neural networks representing the policy (LTS+NN). In this work we show that the neural network can be substituted with parameterized context models originating from the online compression literature (LTS+CM). We show that the LTS loss is convex under this new mo"},"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":"2305.16945","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T14:00:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"15930d150601da4a3341f3d1c7a2b4c80f013046313bbc95887ec631c6b82821","abstract_canon_sha256":"c873d7e1e02a9249ffbbc04bd864562a7eb674f2ee4a9a4c49564284e266a3df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:09.073279Z","signature_b64":"CcoUzS14Zo2QqHTY3XU6Y8JvFrEuPia32C7pMcd2UUbSK8KMEF31Ob0f4MsBEtWBuw02/8slUcBZsE4mLZaaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adbeaa4b8fc1598f5dbaa91bd636155e298893d58ba6b1e0487212f3be1fdb4d","last_reissued_at":"2026-07-05T09:34:09.072818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:09.072818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Levin Tree Search with Context Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Laurent Orseau, Levi H.S. Lelis, Marcus Hutter","submitted_at":"2023-05-26T14:00:12Z","abstract_excerpt":"Levin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansions before reaching a goal node, depending on the quality of the policy. This guarantee can be used as a loss function, which we call the LTS loss, to optimize neural networks representing the policy (LTS+NN). In this work we show that the neural network can be substituted with parameterized context models originating from the online compression literature (LTS+CM). We show that the LTS loss is convex under this new mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16945","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/2305.16945/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":"2305.16945","created_at":"2026-07-05T09:34:09.072877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16945v3","created_at":"2026-07-05T09:34:09.072877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16945","created_at":"2026-07-05T09:34:09.072877+00:00"},{"alias_kind":"pith_short_12","alias_value":"VW7KUS4PYFMY","created_at":"2026-07-05T09:34:09.072877+00:00"},{"alias_kind":"pith_short_16","alias_value":"VW7KUS4PYFMY6XN2","created_at":"2026-07-05T09:34:09.072877+00:00"},{"alias_kind":"pith_short_8","alias_value":"VW7KUS4P","created_at":"2026-07-05T09:34:09.072877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY","json":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY.json","graph_json":"https://pith.science/api/pith-number/VW7KUS4PYFMY6XN2VEN5MNQVLY/graph.json","events_json":"https://pith.science/api/pith-number/VW7KUS4PYFMY6XN2VEN5MNQVLY/events.json","paper":"https://pith.science/paper/VW7KUS4P"},"agent_actions":{"view_html":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY","download_json":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY.json","view_paper":"https://pith.science/paper/VW7KUS4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16945&json=true","fetch_graph":"https://pith.science/api/pith-number/VW7KUS4PYFMY6XN2VEN5MNQVLY/graph.json","fetch_events":"https://pith.science/api/pith-number/VW7KUS4PYFMY6XN2VEN5MNQVLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY/action/storage_attestation","attest_author":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY/action/author_attestation","sign_citation":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY/action/citation_signature","submit_replication":"https://pith.science/pith/VW7KUS4PYFMY6XN2VEN5MNQVLY/action/replication_record"}},"created_at":"2026-07-05T09:34:09.072877+00:00","updated_at":"2026-07-05T09:34:09.072877+00:00"}