{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FGBYWXQ77X4JUIOP5Q5SFI2ESR","short_pith_number":"pith:FGBYWXQ7","canonical_record":{"source":{"id":"1705.03967","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:43:11Z","cross_cats_sorted":[],"title_canon_sha256":"873bc6b5fb8317455b6d9a3f4a8861204e2243974095c4570a667b2677520d50","abstract_canon_sha256":"bf0c24d7f77123966646ad5220c2bbeffe9c9b9988e38bcbd515f8fbcb0434ae"},"schema_version":"1.0"},"canonical_sha256":"29838b5e1ffdf89a21cfec3b22a344944c5e292fc178c7528d3e3d37015b8236","source":{"kind":"arxiv","id":"1705.03967","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03967","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03967v1","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03967","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"FGBYWXQ77X4J","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FGBYWXQ77X4JUIOP","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FGBYWXQ7","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FGBYWXQ77X4JUIOP5Q5SFI2ESR","target":"record","payload":{"canonical_record":{"source":{"id":"1705.03967","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:43:11Z","cross_cats_sorted":[],"title_canon_sha256":"873bc6b5fb8317455b6d9a3f4a8861204e2243974095c4570a667b2677520d50","abstract_canon_sha256":"bf0c24d7f77123966646ad5220c2bbeffe9c9b9988e38bcbd515f8fbcb0434ae"},"schema_version":"1.0"},"canonical_sha256":"29838b5e1ffdf89a21cfec3b22a344944c5e292fc178c7528d3e3d37015b8236","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:41.747392Z","signature_b64":"N0D7tBhejENLEi2js1ljxzSBh60ZjHZrrTU5M2eCyUstVVTPstM41Zt6maWbYy3K4NKnlzB/++gBcwCtUPhUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29838b5e1ffdf89a21cfec3b22a344944c5e292fc178c7528d3e3d37015b8236","last_reissued_at":"2026-05-18T00:44:41.746956Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:41.746956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.03967","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":"2026-05-18T00:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zUFa7haqzkkpy9yvt8XQXLXJTp6SMeNdQzA6kNB3dJeoLkIXpiYjwk7ws86GqQzAdlJmbcQm2k1/Mw2hGzQjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:55:48.619101Z"},"content_sha256":"cbcc5d865c6026738bb158d4f90ff88ce5d1f30295e61030c543326fab25e194","schema_version":"1.0","event_id":"sha256:cbcc5d865c6026738bb158d4f90ff88ce5d1f30295e61030c543326fab25e194"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FGBYWXQ77X4JUIOP5Q5SFI2ESR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GQ($\\lambda$) Quick Reference and Implementation Guide","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam White, Richard S. Sutton","submitted_at":"2017-05-10T22:43:11Z","abstract_excerpt":"This document should serve as a quick reference for and guide to the implementation of linear GQ($\\lambda$), a gradient-based off-policy temporal-difference learning algorithm. Explanation of the intuition and theory behind the algorithm are provided elsewhere (e.g., Maei & Sutton 2010, Maei 2011). If you questions or concerns about the content in this document or the attached java code please email Adam White (adam.white@ualberta.ca).\n  The code is provided as part of the source files in the arXiv submission."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03967","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":"2026-05-18T00:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ITXuIXWOpw7Lpwn+IoAPZDFWG+foKpYRr6hYJlPox8JlM6Fe6vwq77m4hyqJlvMQ/BgmNmV71tBqXW8rYlWhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:55:48.619761Z"},"content_sha256":"b6a685cb1f6b6e1219c430e4742225bae25d9d39df4fcad8defd6907897cc199","schema_version":"1.0","event_id":"sha256:b6a685cb1f6b6e1219c430e4742225bae25d9d39df4fcad8defd6907897cc199"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGBYWXQ77X4JUIOP5Q5SFI2ESR/bundle.json","state_url":"https://pith.science/pith/FGBYWXQ77X4JUIOP5Q5SFI2ESR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGBYWXQ77X4JUIOP5Q5SFI2ESR/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":"2026-05-31T21:55:48Z","links":{"resolver":"https://pith.science/pith/FGBYWXQ77X4JUIOP5Q5SFI2ESR","bundle":"https://pith.science/pith/FGBYWXQ77X4JUIOP5Q5SFI2ESR/bundle.json","state":"https://pith.science/pith/FGBYWXQ77X4JUIOP5Q5SFI2ESR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGBYWXQ77X4JUIOP5Q5SFI2ESR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FGBYWXQ77X4JUIOP5Q5SFI2ESR","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":"bf0c24d7f77123966646ad5220c2bbeffe9c9b9988e38bcbd515f8fbcb0434ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:43:11Z","title_canon_sha256":"873bc6b5fb8317455b6d9a3f4a8861204e2243974095c4570a667b2677520d50"},"schema_version":"1.0","source":{"id":"1705.03967","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03967","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03967v1","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03967","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"FGBYWXQ77X4J","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FGBYWXQ77X4JUIOP","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FGBYWXQ7","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:b6a685cb1f6b6e1219c430e4742225bae25d9d39df4fcad8defd6907897cc199","target":"graph","created_at":"2026-05-18T00:44:41Z","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 document should serve as a quick reference for and guide to the implementation of linear GQ($\\lambda$), a gradient-based off-policy temporal-difference learning algorithm. Explanation of the intuition and theory behind the algorithm are provided elsewhere (e.g., Maei & Sutton 2010, Maei 2011). If you questions or concerns about the content in this document or the attached java code please email Adam White (adam.white@ualberta.ca).\n  The code is provided as part of the source files in the arXiv submission.","authors_text":"Adam White, Richard S. Sutton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:43:11Z","title":"GQ($\\lambda$) Quick Reference and Implementation Guide"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03967","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:cbcc5d865c6026738bb158d4f90ff88ce5d1f30295e61030c543326fab25e194","target":"record","created_at":"2026-05-18T00:44:41Z","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":"bf0c24d7f77123966646ad5220c2bbeffe9c9b9988e38bcbd515f8fbcb0434ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-10T22:43:11Z","title_canon_sha256":"873bc6b5fb8317455b6d9a3f4a8861204e2243974095c4570a667b2677520d50"},"schema_version":"1.0","source":{"id":"1705.03967","kind":"arxiv","version":1}},"canonical_sha256":"29838b5e1ffdf89a21cfec3b22a344944c5e292fc178c7528d3e3d37015b8236","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29838b5e1ffdf89a21cfec3b22a344944c5e292fc178c7528d3e3d37015b8236","first_computed_at":"2026-05-18T00:44:41.746956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:41.746956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N0D7tBhejENLEi2js1ljxzSBh60ZjHZrrTU5M2eCyUstVVTPstM41Zt6maWbYy3K4NKnlzB/++gBcwCtUPhUDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:41.747392Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.03967","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbcc5d865c6026738bb158d4f90ff88ce5d1f30295e61030c543326fab25e194","sha256:b6a685cb1f6b6e1219c430e4742225bae25d9d39df4fcad8defd6907897cc199"],"state_sha256":"7cb850a1ff5384e518d522878ffca63b9c494d319427123797bb853d19293e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bKDqGSCtncdtUFHNBiyMtR1ahrj05gWOvzrf257WHkn9wgGxo6TkGKrbB+kELrp3JqAO+XP5YEBZizp8I7xCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T21:55:48.623793Z","bundle_sha256":"6b566848ab02ae8b7c66726f7e60f27c554f349f601e50f3f8c4ea2a2c13a37b"}}