{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:O6EHJPL3S6EPQJ2C5Q52CM44CP","short_pith_number":"pith:O6EHJPL3","canonical_record":{"source":{"id":"1705.07615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2017-05-22T08:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"c1ea65f72f70fb193351d3c8421c4b5078e5748444c1937aa1471896c62aa664","abstract_canon_sha256":"2854fe485dbba834325e2de2a789d1f955ca74c770c797e218b6974bb52f5e93"},"schema_version":"1.0"},"canonical_sha256":"778874bd7b9788f82742ec3ba1339c13d71e5c9c18a6ab87b01a2b580f72e56b","source":{"kind":"arxiv","id":"1705.07615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07615","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07615v1","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07615","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"pith_short_12","alias_value":"O6EHJPL3S6EP","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"O6EHJPL3S6EPQJ2C","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"O6EHJPL3","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:O6EHJPL3S6EPQJ2C5Q52CM44CP","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2017-05-22T08:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"c1ea65f72f70fb193351d3c8421c4b5078e5748444c1937aa1471896c62aa664","abstract_canon_sha256":"2854fe485dbba834325e2de2a789d1f955ca74c770c797e218b6974bb52f5e93"},"schema_version":"1.0"},"canonical_sha256":"778874bd7b9788f82742ec3ba1339c13d71e5c9c18a6ab87b01a2b580f72e56b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:05.039407Z","signature_b64":"QcCJ3FC9eK7MvoESfGWpqU1DIsKru4+Y/RfBn8s9InEekODZfPM3iwfTJULgcOqxcZJLrbE4+vrY8q9sQk6WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"778874bd7b9788f82742ec3ba1339c13d71e5c9c18a6ab87b01a2b580f72e56b","last_reissued_at":"2026-05-18T00:44:05.038850Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:05.038850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07615","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXey5x/JpPU4IitsV6+EFd3pcqiCRZF8ztbgguTKAJwIumwRk2KMXObSECt82JUhUbQBJMx+0Ol9Z7LxHeOZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T17:56:25.823436Z"},"content_sha256":"469b426f33edd8b665981361e9d66db02488d321f73041833c4621a80dd5a1ca","schema_version":"1.0","event_id":"sha256:469b426f33edd8b665981361e9d66db02488d321f73041833c4621a80dd5a1ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:O6EHJPL3S6EPQJ2C5Q52CM44CP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AIXIjs: A Software Demo for General Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"John Aslanides","submitted_at":"2017-05-22T08:56:54Z","abstract_excerpt":"Reinforcement learning is a general and powerful framework with which to study and implement artificial intelligence. Recent advances in deep learning have enabled RL algorithms to achieve impressive performance in restricted domains such as playing Atari video games (Mnih et al., 2015) and, recently, the board game Go (Silver et al., 2016). However, we are still far from constructing a generally intelligent agent. Many of the obstacles and open questions are conceptual: What does it mean to be intelligent? How does one explore and learn optimally in general, unknown environments? What, in fac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07615","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":""},"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":"2026-05-18T00:44:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38U4yVPyiGOz6cxDLZhKdMJeFRRXEmsX6mJyNz0dkcU2Oyrh2Ta1qmjuPLobdgyplW8e3mPpuuYkL1bDfd7QAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T17:56:25.823892Z"},"content_sha256":"496d6c588ef32fbb4503bc23df224279f86c1420b136d94a4296b671b1aeab90","schema_version":"1.0","event_id":"sha256:496d6c588ef32fbb4503bc23df224279f86c1420b136d94a4296b671b1aeab90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/bundle.json","state_url":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/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":"2026-05-27T17:56:25Z","links":{"resolver":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP","bundle":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/bundle.json","state":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:O6EHJPL3S6EPQJ2C5Q52CM44CP","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":"2854fe485dbba834325e2de2a789d1f955ca74c770c797e218b6974bb52f5e93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2017-05-22T08:56:54Z","title_canon_sha256":"c1ea65f72f70fb193351d3c8421c4b5078e5748444c1937aa1471896c62aa664"},"schema_version":"1.0","source":{"id":"1705.07615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07615","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07615v1","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07615","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"pith_short_12","alias_value":"O6EHJPL3S6EP","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"O6EHJPL3S6EPQJ2C","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"O6EHJPL3","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:496d6c588ef32fbb4503bc23df224279f86c1420b136d94a4296b671b1aeab90","target":"graph","created_at":"2026-05-18T00:44:05Z","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":"Reinforcement learning is a general and powerful framework with which to study and implement artificial intelligence. Recent advances in deep learning have enabled RL algorithms to achieve impressive performance in restricted domains such as playing Atari video games (Mnih et al., 2015) and, recently, the board game Go (Silver et al., 2016). However, we are still far from constructing a generally intelligent agent. Many of the obstacles and open questions are conceptual: What does it mean to be intelligent? How does one explore and learn optimally in general, unknown environments? What, in fac","authors_text":"John Aslanides","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2017-05-22T08:56:54Z","title":"AIXIjs: A Software Demo for General Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07615","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":"sha256:469b426f33edd8b665981361e9d66db02488d321f73041833c4621a80dd5a1ca","target":"record","created_at":"2026-05-18T00:44:05Z","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":"2854fe485dbba834325e2de2a789d1f955ca74c770c797e218b6974bb52f5e93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2017-05-22T08:56:54Z","title_canon_sha256":"c1ea65f72f70fb193351d3c8421c4b5078e5748444c1937aa1471896c62aa664"},"schema_version":"1.0","source":{"id":"1705.07615","kind":"arxiv","version":1}},"canonical_sha256":"778874bd7b9788f82742ec3ba1339c13d71e5c9c18a6ab87b01a2b580f72e56b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"778874bd7b9788f82742ec3ba1339c13d71e5c9c18a6ab87b01a2b580f72e56b","first_computed_at":"2026-05-18T00:44:05.038850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:05.038850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QcCJ3FC9eK7MvoESfGWpqU1DIsKru4+Y/RfBn8s9InEekODZfPM3iwfTJULgcOqxcZJLrbE4+vrY8q9sQk6WAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:05.039407Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:469b426f33edd8b665981361e9d66db02488d321f73041833c4621a80dd5a1ca","sha256:496d6c588ef32fbb4503bc23df224279f86c1420b136d94a4296b671b1aeab90"],"state_sha256":"29bd9ff12a4454c7b828f815411d4477b05fdaffe85a9d9744de5f8466e0f1d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NoDwqyyCmESGGxwa0RlMC1M/tmyKuqOXEx4PPPYnSu0MIioNkM0H4E8NNRquPgSzD7jtjcP6dvaDqHF36o7lDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T17:56:25.826855Z","bundle_sha256":"71320be07d572f6b27d7a45dd30a25e102de9e77a6f7e483ca6f0411e88d6dc3"}}