{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2009:IBP4FX37OFAAELPPQHSOFBKMT2","short_pith_number":"pith:IBP4FX37","canonical_record":{"source":{"id":"0909.0801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2009-09-04T03:13:58Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"9987872be737c968bec776c89e6360e74802edfe2bb57ac09d100f24321bad85","abstract_canon_sha256":"1eeb706bc4a513df64e8b51033f1966cf3d97fb13fb92a866942ee9e4cf39ab5"},"schema_version":"1.0"},"canonical_sha256":"405fc2df7f7140022def81e4e2854c9e8cbdcedeffcc196b0181baab6049c969","source":{"kind":"arxiv","id":"0909.0801","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0909.0801","created_at":"2026-05-18T04:32:34Z"},{"alias_kind":"arxiv_version","alias_value":"0909.0801v2","created_at":"2026-05-18T04:32:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0909.0801","created_at":"2026-05-18T04:32:34Z"},{"alias_kind":"pith_short_12","alias_value":"IBP4FX37OFAA","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"IBP4FX37OFAAELPP","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"IBP4FX37","created_at":"2026-05-18T12:26:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2009:IBP4FX37OFAAELPPQHSOFBKMT2","target":"record","payload":{"canonical_record":{"source":{"id":"0909.0801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2009-09-04T03:13:58Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"9987872be737c968bec776c89e6360e74802edfe2bb57ac09d100f24321bad85","abstract_canon_sha256":"1eeb706bc4a513df64e8b51033f1966cf3d97fb13fb92a866942ee9e4cf39ab5"},"schema_version":"1.0"},"canonical_sha256":"405fc2df7f7140022def81e4e2854c9e8cbdcedeffcc196b0181baab6049c969","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:32:34.127693Z","signature_b64":"dxkoI0bWR+LF1xK3e1zd80frDwDMz8xE821F4GmqB1Kt3zGc5fwZrfw8SaQqKypaAtDW2o5rHE0jdzrR+RCICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405fc2df7f7140022def81e4e2854c9e8cbdcedeffcc196b0181baab6049c969","last_reissued_at":"2026-05-18T04:32:34.127244Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:32:34.127244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"0909.0801","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:32:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2QqrQbnJgGp2aRx8ggCOfN9w76usbGPtf2DwTI1ygc6I7JSOI6dGtQoHNUG7lpPGwrWL3OWJqAsie8BCt8oDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:51:03.959470Z"},"content_sha256":"2356dff67d6009fcefcc36d49cf34e422dd5f1dca9d3fc0371a6e953ec1fbe30","schema_version":"1.0","event_id":"sha256:2356dff67d6009fcefcc36d49cf34e422dd5f1dca9d3fc0371a6e953ec1fbe30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2009:IBP4FX37OFAAELPPQHSOFBKMT2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Monte Carlo AIXI Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"cs.AI","authors_text":"David Silver, Joel Veness, Kee Siong Ng, Marcus Hutter, William Uther","submitted_at":"2009-09-04T03:13:58Z","abstract_excerpt":"This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. Our approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents. Previously, it has been unclear whether the theory of AIXI could motivate the design of practical algorithms. We answer this hitherto open question in the affirmative, by providing the first computationally feasible approximation to the AIXI agent. To develop our approximation, we introduce a new Monte-Carlo Tree Search algorithm along with an agent-specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0909.0801","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:32:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kr/S2Wks00M8ODsti+T8HJsRBe8pZyomLyd23pGyT9onD4B638JaaRePYsR0FJhK94Uj3VALhWZ6NUDHuX2fAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:51:03.960207Z"},"content_sha256":"1efa8c87f7bf89fe14468ade538452bc4d318e2b1239303472fce6e63c305a44","schema_version":"1.0","event_id":"sha256:1efa8c87f7bf89fe14468ade538452bc4d318e2b1239303472fce6e63c305a44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBP4FX37OFAAELPPQHSOFBKMT2/bundle.json","state_url":"https://pith.science/pith/IBP4FX37OFAAELPPQHSOFBKMT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBP4FX37OFAAELPPQHSOFBKMT2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T18:51:03Z","links":{"resolver":"https://pith.science/pith/IBP4FX37OFAAELPPQHSOFBKMT2","bundle":"https://pith.science/pith/IBP4FX37OFAAELPPQHSOFBKMT2/bundle.json","state":"https://pith.science/pith/IBP4FX37OFAAELPPQHSOFBKMT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBP4FX37OFAAELPPQHSOFBKMT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2009:IBP4FX37OFAAELPPQHSOFBKMT2","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":"1eeb706bc4a513df64e8b51033f1966cf3d97fb13fb92a866942ee9e4cf39ab5","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2009-09-04T03:13:58Z","title_canon_sha256":"9987872be737c968bec776c89e6360e74802edfe2bb57ac09d100f24321bad85"},"schema_version":"1.0","source":{"id":"0909.0801","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0909.0801","created_at":"2026-05-18T04:32:34Z"},{"alias_kind":"arxiv_version","alias_value":"0909.0801v2","created_at":"2026-05-18T04:32:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0909.0801","created_at":"2026-05-18T04:32:34Z"},{"alias_kind":"pith_short_12","alias_value":"IBP4FX37OFAA","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"IBP4FX37OFAAELPP","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"IBP4FX37","created_at":"2026-05-18T12:26:00Z"}],"graph_snapshots":[{"event_id":"sha256:1efa8c87f7bf89fe14468ade538452bc4d318e2b1239303472fce6e63c305a44","target":"graph","created_at":"2026-05-18T04:32:34Z","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"},"paper":{"abstract_excerpt":"This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. Our approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents. Previously, it has been unclear whether the theory of AIXI could motivate the design of practical algorithms. We answer this hitherto open question in the affirmative, by providing the first computationally feasible approximation to the AIXI agent. To develop our approximation, we introduce a new Monte-Carlo Tree Search algorithm along with an agent-specific","authors_text":"David Silver, Joel Veness, Kee Siong Ng, Marcus Hutter, William Uther","cross_cats":["cs.IT","cs.LG","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2009-09-04T03:13:58Z","title":"A Monte Carlo AIXI Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0909.0801","kind":"arxiv","version":2},"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":"sha256:2356dff67d6009fcefcc36d49cf34e422dd5f1dca9d3fc0371a6e953ec1fbe30","target":"record","created_at":"2026-05-18T04:32:34Z","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":"1eeb706bc4a513df64e8b51033f1966cf3d97fb13fb92a866942ee9e4cf39ab5","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2009-09-04T03:13:58Z","title_canon_sha256":"9987872be737c968bec776c89e6360e74802edfe2bb57ac09d100f24321bad85"},"schema_version":"1.0","source":{"id":"0909.0801","kind":"arxiv","version":2}},"canonical_sha256":"405fc2df7f7140022def81e4e2854c9e8cbdcedeffcc196b0181baab6049c969","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"405fc2df7f7140022def81e4e2854c9e8cbdcedeffcc196b0181baab6049c969","first_computed_at":"2026-05-18T04:32:34.127244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:32:34.127244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dxkoI0bWR+LF1xK3e1zd80frDwDMz8xE821F4GmqB1Kt3zGc5fwZrfw8SaQqKypaAtDW2o5rHE0jdzrR+RCICw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:32:34.127693Z","signed_message":"canonical_sha256_bytes"},"source_id":"0909.0801","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2356dff67d6009fcefcc36d49cf34e422dd5f1dca9d3fc0371a6e953ec1fbe30","sha256:1efa8c87f7bf89fe14468ade538452bc4d318e2b1239303472fce6e63c305a44"],"state_sha256":"60bd98c7a7498d12b8422caeda5228f170b1627b88d505b9b6211d71e17b75ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EA05is+wrzyhjh8qDwhaXw4Vy443D44tlDyCmRCFXjHW67elp80bfUz9+ASqoqwdWoP/d8braAak7hrtK+aKCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T18:51:03.962913Z","bundle_sha256":"56cbed81dcf35697bdf0952d5d210f9ca0d5d4485046907db18cd809f8e17b9d"}}