{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ALQWUDYCWUYXH73RGHRMDSNNTH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"647d4d47700f0739d048ffa22d200cf0fd38fd1075d2e9d8571d33a4c107aa79","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-21T18:05:21Z","title_canon_sha256":"9fafcb176a785e64dea7537a35a7774f0e6b313084b7fd156357d3ae60ba9de6"},"schema_version":"1.0","source":{"id":"2010.11223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11223","created_at":"2026-07-05T01:45:07Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11223v1","created_at":"2026-07-05T01:45:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11223","created_at":"2026-07-05T01:45:07Z"},{"alias_kind":"pith_short_12","alias_value":"ALQWUDYCWUYX","created_at":"2026-07-05T01:45:07Z"},{"alias_kind":"pith_short_16","alias_value":"ALQWUDYCWUYXH73R","created_at":"2026-07-05T01:45:07Z"},{"alias_kind":"pith_short_8","alias_value":"ALQWUDYC","created_at":"2026-07-05T01:45:07Z"}],"graph_snapshots":[{"event_id":"sha256:06d542b779c7c4b57c7b46e29bc6f5210fafd7c047d3574e6d4b1b6cc2958781","target":"graph","created_at":"2026-07-05T01:45:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.11223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol incentivises agents to behave Bayes-optimally. We empirically investigate this claim on a number of prediction and bandit tasks. Inspired by ideas from theoretical computer science, we show that meta-learned and Bayes-optimal agents not only behave alike, but they even share a similar computational structure, in the sense that one agent system can approximately ","authors_text":"Gr\\'egoire Del\\'etang, Miljan Martic, Pedro A. Ortega, Shane Legg, Tim Genewein, Tom McGrath, Vladimir Mikulik","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-21T18:05:21Z","title":"Meta-trained agents implement Bayes-optimal agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11223","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6cb9948baebe3ad3377b2d35d0db87fe6e2bcf6b182915078cb1707b05ed2581","target":"record","created_at":"2026-07-05T01:45:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"647d4d47700f0739d048ffa22d200cf0fd38fd1075d2e9d8571d33a4c107aa79","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-21T18:05:21Z","title_canon_sha256":"9fafcb176a785e64dea7537a35a7774f0e6b313084b7fd156357d3ae60ba9de6"},"schema_version":"1.0","source":{"id":"2010.11223","kind":"arxiv","version":1}},"canonical_sha256":"02e16a0f02b53173ff7131e2c1c9ad99cd873addb7c45e3fe153a21d61026416","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02e16a0f02b53173ff7131e2c1c9ad99cd873addb7c45e3fe153a21d61026416","first_computed_at":"2026-07-05T01:45:07.514165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:07.514165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"znPUScrYRzjd3g9tW3lEEfNQR9v09RQ7dAo7Ht4yyVCNMgUyQUYPAFg4NHH1oy6huulFGc90Qe8VDeZUb7y3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:07.514745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cb9948baebe3ad3377b2d35d0db87fe6e2bcf6b182915078cb1707b05ed2581","sha256:06d542b779c7c4b57c7b46e29bc6f5210fafd7c047d3574e6d4b1b6cc2958781"],"state_sha256":"71a1d553a8dbf638affc396be3e1e9a95735cefe0a1f24a501aefefaef5baabd"}