{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JBJWL4RC6BRMMRF4O5INNPMBAB","short_pith_number":"pith:JBJWL4RC","schema_version":"1.0","canonical_sha256":"485365f222f062c644bc7750d6bd810064e3dfb8abd60d9c8f3e7a6b69b6dd78","source":{"kind":"arxiv","id":"2401.14953","version":1},"attestation_state":"computed","paper":{"title":"Learning Universal Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anian Ruoss, Christopher Mattern, Elliot Catt, Gr\\'egoire Del\\'etang, Joel Veness, Jordi Grau-Moya, Laurent Orseau, Li Kevin Wenliang, Marcus Hutter, Matthew Aitchison, Tim Genewein","submitted_at":"2024-01-26T15:37:16Z","abstract_excerpt":"Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile representations enabling general problem solving. But, what are the limits of meta-learning? In this work, we explore the potential of amortizing the most powerful universal predictor, namely Solomonoff Induction (SI), into neural networks via leveraging meta-learning to its limits. We use Universal Turing Machines (UTMs) to generate training data used to expose networks to a broad range of patterns. We provide theoretical "},"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":"2401.14953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T15:37:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f27d0ed508a14e2558f494866b5c47155f0abb90443a92ee04375793dd0eb83","abstract_canon_sha256":"a0560cbc28967e2c09332fe8f92ba9da86d3f8d1f83f6c51b7e87c888c8e2cd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:04.434717Z","signature_b64":"I3TeyqO8x78rfE/Agt0sd6ALAhv5CUTdRf21orYM3557OQbCwQkiMYrjMXKf+WsCiE77/o03yaiOMVI1CwFLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"485365f222f062c644bc7750d6bd810064e3dfb8abd60d9c8f3e7a6b69b6dd78","last_reissued_at":"2026-07-05T07:38:04.434294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:04.434294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Universal Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anian Ruoss, Christopher Mattern, Elliot Catt, Gr\\'egoire Del\\'etang, Joel Veness, Jordi Grau-Moya, Laurent Orseau, Li Kevin Wenliang, Marcus Hutter, Matthew Aitchison, Tim Genewein","submitted_at":"2024-01-26T15:37:16Z","abstract_excerpt":"Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile representations enabling general problem solving. But, what are the limits of meta-learning? In this work, we explore the potential of amortizing the most powerful universal predictor, namely Solomonoff Induction (SI), into neural networks via leveraging meta-learning to its limits. We use Universal Turing Machines (UTMs) to generate training data used to expose networks to a broad range of patterns. We provide theoretical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14953","kind":"arxiv","version":1},"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/2401.14953/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":"2401.14953","created_at":"2026-07-05T07:38:04.434358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14953v1","created_at":"2026-07-05T07:38:04.434358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14953","created_at":"2026-07-05T07:38:04.434358+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBJWL4RC6BRM","created_at":"2026-07-05T07:38:04.434358+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBJWL4RC6BRMMRF4","created_at":"2026-07-05T07:38:04.434358+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBJWL4RC","created_at":"2026-07-05T07:38:04.434358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10878","citing_title":"Neural Weight Norm = Kolmogorov Complexity","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05115","citing_title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","ref_index":247,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB","json":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB.json","graph_json":"https://pith.science/api/pith-number/JBJWL4RC6BRMMRF4O5INNPMBAB/graph.json","events_json":"https://pith.science/api/pith-number/JBJWL4RC6BRMMRF4O5INNPMBAB/events.json","paper":"https://pith.science/paper/JBJWL4RC"},"agent_actions":{"view_html":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB","download_json":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB.json","view_paper":"https://pith.science/paper/JBJWL4RC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14953&json=true","fetch_graph":"https://pith.science/api/pith-number/JBJWL4RC6BRMMRF4O5INNPMBAB/graph.json","fetch_events":"https://pith.science/api/pith-number/JBJWL4RC6BRMMRF4O5INNPMBAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB/action/storage_attestation","attest_author":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB/action/author_attestation","sign_citation":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB/action/citation_signature","submit_replication":"https://pith.science/pith/JBJWL4RC6BRMMRF4O5INNPMBAB/action/replication_record"}},"created_at":"2026-07-05T07:38:04.434358+00:00","updated_at":"2026-07-05T07:38:04.434358+00:00"}