{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:Z3EAZ6XNI35KJQSJUVKJNMMLXM","short_pith_number":"pith:Z3EAZ6XN","canonical_record":{"source":{"id":"1612.08810","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-28T06:47:15Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"ea549f2bf3720c586dfa483dcf6d129abf0d1a16fa98300ab54000ce9f216112","abstract_canon_sha256":"d94cb45bb0b0e4454a57217c194edb3c3b4764773527af429aa4f9785bf0458c"},"schema_version":"1.0"},"canonical_sha256":"cec80cfaed46faa4c249a55496b18bbb3825506833eb681585bf61948727ef5d","source":{"kind":"arxiv","id":"1612.08810","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08810","created_at":"2026-05-18T00:39:56Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08810v3","created_at":"2026-05-18T00:39:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08810","created_at":"2026-05-18T00:39:56Z"},{"alias_kind":"pith_short_12","alias_value":"Z3EAZ6XNI35K","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Z3EAZ6XNI35KJQSJ","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Z3EAZ6XN","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:Z3EAZ6XNI35KJQSJUVKJNMMLXM","target":"record","payload":{"canonical_record":{"source":{"id":"1612.08810","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-28T06:47:15Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"ea549f2bf3720c586dfa483dcf6d129abf0d1a16fa98300ab54000ce9f216112","abstract_canon_sha256":"d94cb45bb0b0e4454a57217c194edb3c3b4764773527af429aa4f9785bf0458c"},"schema_version":"1.0"},"canonical_sha256":"cec80cfaed46faa4c249a55496b18bbb3825506833eb681585bf61948727ef5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:56.779604Z","signature_b64":"2Uzn0D68CugFa2Uy3bUHdd26qsgx9kfUAqPPlrCZXGV9YrmfVKc6ZISPIpy11ROHVah9q2iVO2UPpoo0cKwdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cec80cfaed46faa4c249a55496b18bbb3825506833eb681585bf61948727ef5d","last_reissued_at":"2026-05-18T00:39:56.779213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:56.779213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.08810","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YUPBg7quS2ksVB0ihnSPxP8a/zcVeAw2sbVtkn7BIrNbtS5JAF69LjdxuYaflbcr7XjLeQpcl6DbQf1YaNcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:06:20.929691Z"},"content_sha256":"e8d4d0ff19ca7d304341a82cdc18ffb03189ef774cc5b8200032182cbe113bdd","schema_version":"1.0","event_id":"sha256:e8d4d0ff19ca7d304341a82cdc18ffb03189ef774cc5b8200032182cbe113bdd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:Z3EAZ6XNI35KJQSJUVKJNMMLXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Predictron: End-To-End Learning and Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Andre Barreto, Arthur Guez, David Reichert, David Silver, Gabriel Dulac-Arnold, Hado van Hasselt, Matteo Hessel, Neil Rabinowitz, Thomas Degris, Tim Harley, Tom Schaul","submitted_at":"2016-12-28T06:47:15Z","abstract_excerpt":"One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. The predictron consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple \"imagined\" planning steps. Each forward pass of the predictron accumulates internal rewards and values over multiple planning depths. The predictron is trained end-to-end so as to make these accumulated values accurately approximate the true value function. We applied the predictron to procedur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08810","kind":"arxiv","version":3},"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":"2026-05-18T00:39:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8ld+A5fCiFeKPLo//UmGWBR4p6HJZQCE/42dqbivfXM1Ux/a2XB3J5DpMb++qdZyWLefiCGVLYNFkxlF16SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:06:20.930041Z"},"content_sha256":"1c326ae155b210374a7d11d3c68590df42b851279516dbae3964798a4cb56e57","schema_version":"1.0","event_id":"sha256:1c326ae155b210374a7d11d3c68590df42b851279516dbae3964798a4cb56e57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3EAZ6XNI35KJQSJUVKJNMMLXM/bundle.json","state_url":"https://pith.science/pith/Z3EAZ6XNI35KJQSJUVKJNMMLXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3EAZ6XNI35KJQSJUVKJNMMLXM/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":"2026-06-01T10:06:20Z","links":{"resolver":"https://pith.science/pith/Z3EAZ6XNI35KJQSJUVKJNMMLXM","bundle":"https://pith.science/pith/Z3EAZ6XNI35KJQSJUVKJNMMLXM/bundle.json","state":"https://pith.science/pith/Z3EAZ6XNI35KJQSJUVKJNMMLXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3EAZ6XNI35KJQSJUVKJNMMLXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:Z3EAZ6XNI35KJQSJUVKJNMMLXM","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":"d94cb45bb0b0e4454a57217c194edb3c3b4764773527af429aa4f9785bf0458c","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-28T06:47:15Z","title_canon_sha256":"ea549f2bf3720c586dfa483dcf6d129abf0d1a16fa98300ab54000ce9f216112"},"schema_version":"1.0","source":{"id":"1612.08810","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08810","created_at":"2026-05-18T00:39:56Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08810v3","created_at":"2026-05-18T00:39:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08810","created_at":"2026-05-18T00:39:56Z"},{"alias_kind":"pith_short_12","alias_value":"Z3EAZ6XNI35K","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Z3EAZ6XNI35KJQSJ","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Z3EAZ6XN","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:1c326ae155b210374a7d11d3c68590df42b851279516dbae3964798a4cb56e57","target":"graph","created_at":"2026-05-18T00:39:56Z","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":"One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. The predictron consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple \"imagined\" planning steps. Each forward pass of the predictron accumulates internal rewards and values over multiple planning depths. The predictron is trained end-to-end so as to make these accumulated values accurately approximate the true value function. We applied the predictron to procedur","authors_text":"Andre Barreto, Arthur Guez, David Reichert, David Silver, Gabriel Dulac-Arnold, Hado van Hasselt, Matteo Hessel, Neil Rabinowitz, Thomas Degris, Tim Harley, Tom Schaul","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-28T06:47:15Z","title":"The Predictron: End-To-End Learning and Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08810","kind":"arxiv","version":3},"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:e8d4d0ff19ca7d304341a82cdc18ffb03189ef774cc5b8200032182cbe113bdd","target":"record","created_at":"2026-05-18T00:39:56Z","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":"d94cb45bb0b0e4454a57217c194edb3c3b4764773527af429aa4f9785bf0458c","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-28T06:47:15Z","title_canon_sha256":"ea549f2bf3720c586dfa483dcf6d129abf0d1a16fa98300ab54000ce9f216112"},"schema_version":"1.0","source":{"id":"1612.08810","kind":"arxiv","version":3}},"canonical_sha256":"cec80cfaed46faa4c249a55496b18bbb3825506833eb681585bf61948727ef5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cec80cfaed46faa4c249a55496b18bbb3825506833eb681585bf61948727ef5d","first_computed_at":"2026-05-18T00:39:56.779213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:56.779213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Uzn0D68CugFa2Uy3bUHdd26qsgx9kfUAqPPlrCZXGV9YrmfVKc6ZISPIpy11ROHVah9q2iVO2UPpoo0cKwdCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:56.779604Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.08810","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8d4d0ff19ca7d304341a82cdc18ffb03189ef774cc5b8200032182cbe113bdd","sha256:1c326ae155b210374a7d11d3c68590df42b851279516dbae3964798a4cb56e57"],"state_sha256":"34f323a019bc31a6a83d74f76750c40b453b3b9e43fb2fc848fb7f3e79852e78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSQNyHhTs0Cp7XafFZYjPImeJeFY7l7dBnlLxGxhKAEyHJFqe4U1aRoXA8dqhjF3eq/MFA7nT/6uxbszw2siCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T10:06:20.931984Z","bundle_sha256":"32f13eecf8a65d1d97f5f02e619bd5ba7cf5769d6029d924cb3d70e9d414842a"}}