{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GCZQ2EMF3SEM5EUQQLNBX72W3U","short_pith_number":"pith:GCZQ2EMF","schema_version":"1.0","canonical_sha256":"30b30d1185dc88ce929082da1bff56dd3fa7a2a044604771742efb8c839ae1dc","source":{"kind":"arxiv","id":"2007.00611","version":4},"attestation_state":"computed","paper":{"title":"Gradient Temporal-Difference Learning with Regularized Corrections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam White, Andrew Patterson, Dhawal Gupta, Martha White, Shivam Garg, Sina Ghiassian","submitted_at":"2020-07-01T16:56:56Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.00611","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T16:56:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fb4dea2d0da2fd0611b77dfb0ba2a415c380901d2d819d31c6737289c353a3cf","abstract_canon_sha256":"ed2e99486222dce39b75907024f1a0d3770a918fc3c9948b2de6e9d1977b6f06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:18.241895Z","signature_b64":"iL+Gk9DKe9MMPZx4d6yMQGGCIV0ZF3DtHGGRik7+o/8+TBITRhsKWTNxR8G1ENqv8rw4GsNQR9T4ANCPljpfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b30d1185dc88ce929082da1bff56dd3fa7a2a044604771742efb8c839ae1dc","last_reissued_at":"2026-07-05T01:36:18.241549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:18.241549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Temporal-Difference Learning with Regularized Corrections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam White, Andrew Patterson, Dhawal Gupta, Martha White, Shivam Garg, Sina Ghiassian","submitted_at":"2020-07-01T16:56:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00611","kind":"arxiv","version":4},"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/2007.00611/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.00611","created_at":"2026-07-05T01:36:18.241604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.00611v4","created_at":"2026-07-05T01:36:18.241604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00611","created_at":"2026-07-05T01:36:18.241604+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCZQ2EMF3SEM","created_at":"2026-07-05T01:36:18.241604+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCZQ2EMF3SEM5EUQ","created_at":"2026-07-05T01:36:18.241604+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCZQ2EMF","created_at":"2026-07-05T01:36:18.241604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U","json":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U.json","graph_json":"https://pith.science/api/pith-number/GCZQ2EMF3SEM5EUQQLNBX72W3U/graph.json","events_json":"https://pith.science/api/pith-number/GCZQ2EMF3SEM5EUQQLNBX72W3U/events.json","paper":"https://pith.science/paper/GCZQ2EMF"},"agent_actions":{"view_html":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U","download_json":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U.json","view_paper":"https://pith.science/paper/GCZQ2EMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.00611&json=true","fetch_graph":"https://pith.science/api/pith-number/GCZQ2EMF3SEM5EUQQLNBX72W3U/graph.json","fetch_events":"https://pith.science/api/pith-number/GCZQ2EMF3SEM5EUQQLNBX72W3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/action/storage_attestation","attest_author":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/action/author_attestation","sign_citation":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/action/citation_signature","submit_replication":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/action/replication_record"}},"created_at":"2026-07-05T01:36:18.241604+00:00","updated_at":"2026-07-05T01:36:18.241604+00:00"}