{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7VUTX3ODBTZO2PBYCJAKJBOBLK","short_pith_number":"pith:7VUTX3OD","canonical_record":{"source":{"id":"2507.09523","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T07:34:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"873e800c1b46143331b7e27244a7fb673b76c5877296d765d38ca99a774732c7","abstract_canon_sha256":"a3823bb974e36ca8244a430c1710b1a57c81db23e1270f19cc45f9e3922f1ea0"},"schema_version":"1.0"},"canonical_sha256":"fd693bedc30cf2ed3c381240a485c15a87ab0c799d28fb79ebca87456e8f157c","source":{"kind":"arxiv","id":"2507.09523","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09523","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09523v2","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09523","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"7VUTX3ODBTZO","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"7VUTX3ODBTZO2PBY","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"7VUTX3OD","created_at":"2026-07-05T12:04:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7VUTX3ODBTZO2PBYCJAKJBOBLK","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09523","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T07:34:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"873e800c1b46143331b7e27244a7fb673b76c5877296d765d38ca99a774732c7","abstract_canon_sha256":"a3823bb974e36ca8244a430c1710b1a57c81db23e1270f19cc45f9e3922f1ea0"},"schema_version":"1.0"},"canonical_sha256":"fd693bedc30cf2ed3c381240a485c15a87ab0c799d28fb79ebca87456e8f157c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:38.531751Z","signature_b64":"/c1tIj0uFupk+SBAspbl0VOM0RaIGvCBVaz+0Wv63U7c0LFFmeY4b04ZBgUKF5Sq/vChNlOSW5xzTWt/0rtADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd693bedc30cf2ed3c381240a485c15a87ab0c799d28fb79ebca87456e8f157c","last_reissued_at":"2026-07-05T12:04:38.531217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:38.531217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09523","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":"2026-07-05T12:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x4HMPvTi1AV2m/znSFpr+S91szfRrbMbozxSo48F3Nn+oyVVrrcvOf5o7Uq9hC5bMHifGzNnjwzLgvEXUf+VBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:37:03.157047Z"},"content_sha256":"bbc27cffb01b49a1364bbfbb37824573deba630f66eaac75e74f8ce64ac1b6bd","schema_version":"1.0","event_id":"sha256:bbc27cffb01b49a1364bbfbb37824573deba630f66eaac75e74f8ce64ac1b6bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7VUTX3ODBTZO2PBYCJAKJBOBLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Analysis of Action-Value Temporal-Difference Methods That Learn State Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brett Daley, Marlos C. Machado, Martha White, Prabhat Nagarajan","submitted_at":"2025-07-13T07:34:33Z","abstract_excerpt":"The hallmark feature of temporal-difference (TD) learning is bootstrapping: using value predictions to generate new value predictions. The vast majority of TD methods for control learn a policy by bootstrapping from a single action-value function (e.g., Q-learning and Sarsa). Significantly less attention has been given to methods that bootstrap from two asymmetric value functions: i.e., methods that learn state values as an intermediate step in learning action values. Existing algorithms in this vein can be categorized as either QV-learning or AV-learning. Though these algorithms have been inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09523","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.09523/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T12:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VgxSoOOA5WNw08IGPYcAo+kr9ZMop5RruOWhuH4R1376434bfSb2jfXHYQPJ0+QRia5e2lLmnyzWNO092yloCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:37:03.158282Z"},"content_sha256":"dba0c0b8f7843b4df75ac38b3be189ee2f60bfe7b07a55e6a2929434948295e5","schema_version":"1.0","event_id":"sha256:dba0c0b8f7843b4df75ac38b3be189ee2f60bfe7b07a55e6a2929434948295e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VUTX3ODBTZO2PBYCJAKJBOBLK/bundle.json","state_url":"https://pith.science/pith/7VUTX3ODBTZO2PBYCJAKJBOBLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VUTX3ODBTZO2PBYCJAKJBOBLK/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":"2026-08-06T23:37:03Z","links":{"resolver":"https://pith.science/pith/7VUTX3ODBTZO2PBYCJAKJBOBLK","bundle":"https://pith.science/pith/7VUTX3ODBTZO2PBYCJAKJBOBLK/bundle.json","state":"https://pith.science/pith/7VUTX3ODBTZO2PBYCJAKJBOBLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VUTX3ODBTZO2PBYCJAKJBOBLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7VUTX3ODBTZO2PBYCJAKJBOBLK","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":"a3823bb974e36ca8244a430c1710b1a57c81db23e1270f19cc45f9e3922f1ea0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T07:34:33Z","title_canon_sha256":"873e800c1b46143331b7e27244a7fb673b76c5877296d765d38ca99a774732c7"},"schema_version":"1.0","source":{"id":"2507.09523","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09523","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09523v2","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09523","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"7VUTX3ODBTZO","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"7VUTX3ODBTZO2PBY","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"7VUTX3OD","created_at":"2026-07-05T12:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:dba0c0b8f7843b4df75ac38b3be189ee2f60bfe7b07a55e6a2929434948295e5","target":"graph","created_at":"2026-07-05T12:04:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.09523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The hallmark feature of temporal-difference (TD) learning is bootstrapping: using value predictions to generate new value predictions. The vast majority of TD methods for control learn a policy by bootstrapping from a single action-value function (e.g., Q-learning and Sarsa). Significantly less attention has been given to methods that bootstrap from two asymmetric value functions: i.e., methods that learn state values as an intermediate step in learning action values. Existing algorithms in this vein can be categorized as either QV-learning or AV-learning. Though these algorithms have been inv","authors_text":"Brett Daley, Marlos C. Machado, Martha White, Prabhat Nagarajan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T07:34:33Z","title":"An Analysis of Action-Value Temporal-Difference Methods That Learn State Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09523","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:bbc27cffb01b49a1364bbfbb37824573deba630f66eaac75e74f8ce64ac1b6bd","target":"record","created_at":"2026-07-05T12:04:38Z","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":"a3823bb974e36ca8244a430c1710b1a57c81db23e1270f19cc45f9e3922f1ea0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T07:34:33Z","title_canon_sha256":"873e800c1b46143331b7e27244a7fb673b76c5877296d765d38ca99a774732c7"},"schema_version":"1.0","source":{"id":"2507.09523","kind":"arxiv","version":2}},"canonical_sha256":"fd693bedc30cf2ed3c381240a485c15a87ab0c799d28fb79ebca87456e8f157c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd693bedc30cf2ed3c381240a485c15a87ab0c799d28fb79ebca87456e8f157c","first_computed_at":"2026-07-05T12:04:38.531217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:38.531217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/c1tIj0uFupk+SBAspbl0VOM0RaIGvCBVaz+0Wv63U7c0LFFmeY4b04ZBgUKF5Sq/vChNlOSW5xzTWt/0rtADg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:38.531751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09523","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbc27cffb01b49a1364bbfbb37824573deba630f66eaac75e74f8ce64ac1b6bd","sha256:dba0c0b8f7843b4df75ac38b3be189ee2f60bfe7b07a55e6a2929434948295e5"],"state_sha256":"158e894c16033b93d953308ab08dbb105c2fa1d4aa74a25c592693cc0ad923b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQh4bQS9ZBCNS86QyITUmsvYDKa+Gd1tmPGGnDIv/aHr24Tw5cJeor3VpjmP7oYvBWITJLePaIYa3GkiTKOzAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:37:03.165017Z","bundle_sha256":"e7a033e47780869de2fe4ee271f6748dc7d35e7f294af63eee6784d382c9af7a"}}