{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:P6KTRYMWJ5PDF4VEKIC7OIAYC3","short_pith_number":"pith:P6KTRYMW","canonical_record":{"source":{"id":"1206.6262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-27T13:27:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b61b15a49b065bbae9e944d76b00e56d5af44e579f75ac17a0d4fe499a556fd","abstract_canon_sha256":"2891a50f0a87b8e9e7194a038006ab6f201b559278bdecdccb0bfefbff1a7486"},"schema_version":"1.0"},"canonical_sha256":"7f9538e1964f5e32f2a45205f7201816e2363a6a4e0f268f55e64f85da32b4e5","source":{"kind":"arxiv","id":"1206.6262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.6262","created_at":"2026-05-18T03:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"1206.6262v1","created_at":"2026-05-18T03:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6262","created_at":"2026-05-18T03:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"P6KTRYMWJ5PD","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"P6KTRYMWJ5PDF4VE","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"P6KTRYMW","created_at":"2026-05-18T12:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:P6KTRYMWJ5PDF4VEKIC7OIAYC3","target":"record","payload":{"canonical_record":{"source":{"id":"1206.6262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-27T13:27:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b61b15a49b065bbae9e944d76b00e56d5af44e579f75ac17a0d4fe499a556fd","abstract_canon_sha256":"2891a50f0a87b8e9e7194a038006ab6f201b559278bdecdccb0bfefbff1a7486"},"schema_version":"1.0"},"canonical_sha256":"7f9538e1964f5e32f2a45205f7201816e2363a6a4e0f268f55e64f85da32b4e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:27.196336Z","signature_b64":"rohGuNonAexS9gejpkKZ8s/naxI7l66hqRiXtdcJ824cSht3Kh5vEYyIAdPRs08GeQ/F98NY0dGImgd5KT3GAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f9538e1964f5e32f2a45205f7201816e2363a6a4e0f268f55e64f85da32b4e5","last_reissued_at":"2026-05-18T03:52:27.195769Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:27.195769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.6262","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":"2026-05-18T03:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBeqmqtYZ9N/ojj55Xm42vFMtBEPEGfgyU09I4vaRwthSORLJtXE4qZvkS/4iDhLpZJa7QadRotG9l3/taIzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:13:34.854982Z"},"content_sha256":"17495351d79b74c4ad8446754bcd41e81b4a0a9a9e12e100df47410f2b08e8f1","schema_version":"1.0","event_id":"sha256:17495351d79b74c4ad8446754bcd41e81b4a0a9a9e12e100df47410f2b08e8f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:P6KTRYMWJ5PDF4VEKIC7OIAYC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Life-long Off-policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam White, Joseph Modayil, Richard S. Sutton","submitted_at":"2012-06-27T13:27:56Z","abstract_excerpt":"We pursue a life-long learning approach to artificial intelligence that makes extensive use of reinforcement learning algorithms. We build on our prior work with general value functions (GVFs) and the Horde architecture. GVFs have been shown able to represent a wide variety of facts about the world's dynamics that may be useful to a long-lived agent (Sutton et al. 2011). We have also previously shown scaling - that thousands of on-policy GVFs can be learned accurately in real-time on a mobile robot (Modayil, White & Sutton 2011). That work was limited in that it learned about only one policy a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6262","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":"2026-05-18T03:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"syGFULA4lLy4Fyfl/DiHdrCENm/8fXXgJOUoQzIQ7ZeHpfiUFUYjesM7+40kJ8I886Xq85sdadeLxEwJ/e/DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:13:34.855681Z"},"content_sha256":"83c6d0a4fbbcb818950d9cabdf0098a00abdcaeef4908fc580a326dd068c1b14","schema_version":"1.0","event_id":"sha256:83c6d0a4fbbcb818950d9cabdf0098a00abdcaeef4908fc580a326dd068c1b14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6KTRYMWJ5PDF4VEKIC7OIAYC3/bundle.json","state_url":"https://pith.science/pith/P6KTRYMWJ5PDF4VEKIC7OIAYC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6KTRYMWJ5PDF4VEKIC7OIAYC3/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":"2026-05-25T19:13:34Z","links":{"resolver":"https://pith.science/pith/P6KTRYMWJ5PDF4VEKIC7OIAYC3","bundle":"https://pith.science/pith/P6KTRYMWJ5PDF4VEKIC7OIAYC3/bundle.json","state":"https://pith.science/pith/P6KTRYMWJ5PDF4VEKIC7OIAYC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6KTRYMWJ5PDF4VEKIC7OIAYC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:P6KTRYMWJ5PDF4VEKIC7OIAYC3","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":"2891a50f0a87b8e9e7194a038006ab6f201b559278bdecdccb0bfefbff1a7486","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-27T13:27:56Z","title_canon_sha256":"4b61b15a49b065bbae9e944d76b00e56d5af44e579f75ac17a0d4fe499a556fd"},"schema_version":"1.0","source":{"id":"1206.6262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.6262","created_at":"2026-05-18T03:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"1206.6262v1","created_at":"2026-05-18T03:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6262","created_at":"2026-05-18T03:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"P6KTRYMWJ5PD","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"P6KTRYMWJ5PDF4VE","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"P6KTRYMW","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:83c6d0a4fbbcb818950d9cabdf0098a00abdcaeef4908fc580a326dd068c1b14","target":"graph","created_at":"2026-05-18T03:52:27Z","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":"We pursue a life-long learning approach to artificial intelligence that makes extensive use of reinforcement learning algorithms. We build on our prior work with general value functions (GVFs) and the Horde architecture. GVFs have been shown able to represent a wide variety of facts about the world's dynamics that may be useful to a long-lived agent (Sutton et al. 2011). We have also previously shown scaling - that thousands of on-policy GVFs can be learned accurately in real-time on a mobile robot (Modayil, White & Sutton 2011). That work was limited in that it learned about only one policy a","authors_text":"Adam White, Joseph Modayil, Richard S. Sutton","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-27T13:27:56Z","title":"Scaling Life-long Off-policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6262","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":"sha256:17495351d79b74c4ad8446754bcd41e81b4a0a9a9e12e100df47410f2b08e8f1","target":"record","created_at":"2026-05-18T03:52:27Z","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":"2891a50f0a87b8e9e7194a038006ab6f201b559278bdecdccb0bfefbff1a7486","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-27T13:27:56Z","title_canon_sha256":"4b61b15a49b065bbae9e944d76b00e56d5af44e579f75ac17a0d4fe499a556fd"},"schema_version":"1.0","source":{"id":"1206.6262","kind":"arxiv","version":1}},"canonical_sha256":"7f9538e1964f5e32f2a45205f7201816e2363a6a4e0f268f55e64f85da32b4e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f9538e1964f5e32f2a45205f7201816e2363a6a4e0f268f55e64f85da32b4e5","first_computed_at":"2026-05-18T03:52:27.195769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:27.195769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rohGuNonAexS9gejpkKZ8s/naxI7l66hqRiXtdcJ824cSht3Kh5vEYyIAdPRs08GeQ/F98NY0dGImgd5KT3GAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:27.196336Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.6262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17495351d79b74c4ad8446754bcd41e81b4a0a9a9e12e100df47410f2b08e8f1","sha256:83c6d0a4fbbcb818950d9cabdf0098a00abdcaeef4908fc580a326dd068c1b14"],"state_sha256":"9f4ed94715d93021cb631ea4a6d26926c8efff34160ce728ee314a8ed53a40ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2h+aGpH1wIcNJpfORZvU0ovpIMH3bdIz1DBvyj4lyHILHiCUvzl0c1kgQh4g5D+xNFFUBVjNmTWn2Tj4c6VBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:13:34.859570Z","bundle_sha256":"0947ecea7a86b380c1d5adf1da254abd4371999309c49f379c9127f4668b6736"}}