{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:ZJAQCX2N5RKQ626OKXSZNHMKJ3","short_pith_number":"pith:ZJAQCX2N","canonical_record":{"source":{"id":"1011.0041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-10-30T03:09:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ce4ab7e6b197e61a409aca0ef4c9c8c6c956f2dd4138f22a76e5c58e6cce6efa","abstract_canon_sha256":"f1c960c5a1c157b66067c22daf57b52ce2009cf89c29464586a3e5f696cceb67"},"schema_version":"1.0"},"canonical_sha256":"ca41015f4dec550f6bce55e5969d8a4ed4b292561515a92e45548b8c458e3ebb","source":{"kind":"arxiv","id":"1011.0041","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1011.0041","created_at":"2026-05-18T02:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"1011.0041v2","created_at":"2026-05-18T02:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.0041","created_at":"2026-05-18T02:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZJAQCX2N5RKQ","created_at":"2026-05-18T12:26:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZJAQCX2N5RKQ626O","created_at":"2026-05-18T12:26:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZJAQCX2N","created_at":"2026-05-18T12:26:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:ZJAQCX2N5RKQ626OKXSZNHMKJ3","target":"record","payload":{"canonical_record":{"source":{"id":"1011.0041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-10-30T03:09:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ce4ab7e6b197e61a409aca0ef4c9c8c6c956f2dd4138f22a76e5c58e6cce6efa","abstract_canon_sha256":"f1c960c5a1c157b66067c22daf57b52ce2009cf89c29464586a3e5f696cceb67"},"schema_version":"1.0"},"canonical_sha256":"ca41015f4dec550f6bce55e5969d8a4ed4b292561515a92e45548b8c458e3ebb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:23:38.099351Z","signature_b64":"5z88lg8T6GEuieG1RTD+aLJ6dAVOXKENPsTT2ultj7JXVZhR/xK7tSj80kPVjMvnl8hi3ziUGTXDn/2kwJ/0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca41015f4dec550f6bce55e5969d8a4ed4b292561515a92e45548b8c458e3ebb","last_reissued_at":"2026-05-18T02:23:38.098694Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:23:38.098694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1011.0041","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":"2026-05-18T02:23:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RvrBefkQC4INHGXUZrl/mCpc7VJqiq7hMLxsbFRAvb52kMEbC1NGdektkMhV9VtH+llqxG6vL/xLdcXSwu46CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:30:38.054011Z"},"content_sha256":"cf7a54badf907e5f2777ada3c8341ad9c0c9e2268126df6e5536e8ea6833b563","schema_version":"1.0","event_id":"sha256:cf7a54badf907e5f2777ada3c8341ad9c0c9e2268126df6e5536e8ea6833b563"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:ZJAQCX2N5RKQ626OKXSZNHMKJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictive State Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Geoffrey J. Gordon","submitted_at":"2010-10-30T03:09:11Z","abstract_excerpt":"We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications, reinforcement learning (RL) is complicated by the fact that state is either high-dimensional or partially observable. Therefore, RL methods are designed to work with features of state rather than state itself, and the success or failure of learning is often determined by the suitability of the selected features. By comparison, subspace identification (SSID) methods are designed to select a feature set which preserves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.0041","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":"2026-05-18T02:23:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XxWdrv6OFINFVW71AtzOQXVRpkyJHASw/AiyciBFrhd76KO/vt4f8T4LokZPU2JKXT8GCvBylYxohYA/zQrwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:30:38.054376Z"},"content_sha256":"53d04c760d7a9cae198d328c4b55c1ebb2e7badf8f5f9e172a7484d211b68e06","schema_version":"1.0","event_id":"sha256:53d04c760d7a9cae198d328c4b55c1ebb2e7badf8f5f9e172a7484d211b68e06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJAQCX2N5RKQ626OKXSZNHMKJ3/bundle.json","state_url":"https://pith.science/pith/ZJAQCX2N5RKQ626OKXSZNHMKJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJAQCX2N5RKQ626OKXSZNHMKJ3/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":"2026-06-01T05:30:38Z","links":{"resolver":"https://pith.science/pith/ZJAQCX2N5RKQ626OKXSZNHMKJ3","bundle":"https://pith.science/pith/ZJAQCX2N5RKQ626OKXSZNHMKJ3/bundle.json","state":"https://pith.science/pith/ZJAQCX2N5RKQ626OKXSZNHMKJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJAQCX2N5RKQ626OKXSZNHMKJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:ZJAQCX2N5RKQ626OKXSZNHMKJ3","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":"f1c960c5a1c157b66067c22daf57b52ce2009cf89c29464586a3e5f696cceb67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-10-30T03:09:11Z","title_canon_sha256":"ce4ab7e6b197e61a409aca0ef4c9c8c6c956f2dd4138f22a76e5c58e6cce6efa"},"schema_version":"1.0","source":{"id":"1011.0041","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1011.0041","created_at":"2026-05-18T02:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"1011.0041v2","created_at":"2026-05-18T02:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.0041","created_at":"2026-05-18T02:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZJAQCX2N5RKQ","created_at":"2026-05-18T12:26:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZJAQCX2N5RKQ626O","created_at":"2026-05-18T12:26:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZJAQCX2N","created_at":"2026-05-18T12:26:17Z"}],"graph_snapshots":[{"event_id":"sha256:53d04c760d7a9cae198d328c4b55c1ebb2e7badf8f5f9e172a7484d211b68e06","target":"graph","created_at":"2026-05-18T02:23:38Z","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 propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications, reinforcement learning (RL) is complicated by the fact that state is either high-dimensional or partially observable. Therefore, RL methods are designed to work with features of state rather than state itself, and the success or failure of learning is often determined by the suitability of the selected features. By comparison, subspace identification (SSID) methods are designed to select a feature set which preserves","authors_text":"Byron Boots, Geoffrey J. Gordon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-10-30T03:09:11Z","title":"Predictive State Temporal Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.0041","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:cf7a54badf907e5f2777ada3c8341ad9c0c9e2268126df6e5536e8ea6833b563","target":"record","created_at":"2026-05-18T02:23:38Z","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":"f1c960c5a1c157b66067c22daf57b52ce2009cf89c29464586a3e5f696cceb67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-10-30T03:09:11Z","title_canon_sha256":"ce4ab7e6b197e61a409aca0ef4c9c8c6c956f2dd4138f22a76e5c58e6cce6efa"},"schema_version":"1.0","source":{"id":"1011.0041","kind":"arxiv","version":2}},"canonical_sha256":"ca41015f4dec550f6bce55e5969d8a4ed4b292561515a92e45548b8c458e3ebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca41015f4dec550f6bce55e5969d8a4ed4b292561515a92e45548b8c458e3ebb","first_computed_at":"2026-05-18T02:23:38.098694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:23:38.098694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5z88lg8T6GEuieG1RTD+aLJ6dAVOXKENPsTT2ultj7JXVZhR/xK7tSj80kPVjMvnl8hi3ziUGTXDn/2kwJ/0Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:23:38.099351Z","signed_message":"canonical_sha256_bytes"},"source_id":"1011.0041","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf7a54badf907e5f2777ada3c8341ad9c0c9e2268126df6e5536e8ea6833b563","sha256:53d04c760d7a9cae198d328c4b55c1ebb2e7badf8f5f9e172a7484d211b68e06"],"state_sha256":"da1b709dbb5470b70866e5ab97cfb739768fc266d4cf947812562f0468c743ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ejg1YeMt5U9rrgju6tiAPp2dIeNyfhVGEpJ9ZzjtdNZcbIV7T7pzgygBlameTSfpyjQzbWv5Py8IF3E/3GB3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:30:38.056574Z","bundle_sha256":"473af99bc42ca398412933f9fa550cd482b454fb6ee207daa20b6411328ed051"}}