{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GCZQ2EMF3SEM5EUQQLNBX72W3U","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":"ed2e99486222dce39b75907024f1a0d3770a918fc3c9948b2de6e9d1977b6f06","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T16:56:56Z","title_canon_sha256":"fb4dea2d0da2fd0611b77dfb0ba2a415c380901d2d819d31c6737289c353a3cf"},"schema_version":"1.0","source":{"id":"2007.00611","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00611","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00611v4","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00611","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"pith_short_12","alias_value":"GCZQ2EMF3SEM","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"pith_short_16","alias_value":"GCZQ2EMF3SEM5EUQ","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"pith_short_8","alias_value":"GCZQ2EMF","created_at":"2026-07-05T01:36:18Z"}],"graph_snapshots":[{"event_id":"sha256:321239da4b5c8761f303d74bb94b74e6df2229c1f3c947b80d7770f05d037466","target":"graph","created_at":"2026-07-05T01:36:18Z","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/2007.00611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is still common to use Q-learning and temporal difference (TD) learning-even though they have divergence issues and sound Gradient TD alternatives exist-because divergence seems rare and they typically perform well. However, recent work with large neural network learning systems reveals that instability is more common than previously thought. Practitioners face a difficult dilemma: choose an easy to use and performant TD method, or a more complex algorithm that is more sound but harder to tune and all but unexplored with non-linear function approximation or control. In this paper, we introd","authors_text":"Adam White, Andrew Patterson, Dhawal Gupta, Martha White, Shivam Garg, Sina Ghiassian","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T16:56:56Z","title":"Gradient Temporal-Difference Learning with Regularized Corrections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00611","kind":"arxiv","version":4},"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":"sha256:4f0ad1ef1b44e545c4717fbd97f5bfc77dcd864e0ad9ccacc0fed7515bc7dc9b","target":"record","created_at":"2026-07-05T01:36:18Z","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":"ed2e99486222dce39b75907024f1a0d3770a918fc3c9948b2de6e9d1977b6f06","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T16:56:56Z","title_canon_sha256":"fb4dea2d0da2fd0611b77dfb0ba2a415c380901d2d819d31c6737289c353a3cf"},"schema_version":"1.0","source":{"id":"2007.00611","kind":"arxiv","version":4}},"canonical_sha256":"30b30d1185dc88ce929082da1bff56dd3fa7a2a044604771742efb8c839ae1dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30b30d1185dc88ce929082da1bff56dd3fa7a2a044604771742efb8c839ae1dc","first_computed_at":"2026-07-05T01:36:18.241549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:18.241549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iL+Gk9DKe9MMPZx4d6yMQGGCIV0ZF3DtHGGRik7+o/8+TBITRhsKWTNxR8G1ENqv8rw4GsNQR9T4ANCPljpfCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:18.241895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.00611","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f0ad1ef1b44e545c4717fbd97f5bfc77dcd864e0ad9ccacc0fed7515bc7dc9b","sha256:321239da4b5c8761f303d74bb94b74e6df2229c1f3c947b80d7770f05d037466"],"state_sha256":"16ffd1744340f447831b1d0b9e541873cc8d3c6adb954c8e9ed7c2bbb80021e6"}