{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GCZQ2EMF3SEM5EUQQLNBX72W3U","short_pith_number":"pith:GCZQ2EMF","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"},"canonical_sha256":"30b30d1185dc88ce929082da1bff56dd3fa7a2a044604771742efb8c839ae1dc","source":{"kind":"arxiv","id":"2007.00611","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GCZQ2EMF3SEM5EUQQLNBX72W3U","target":"record","payload":{"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"},"canonical_sha256":"30b30d1185dc88ce929082da1bff56dd3fa7a2a044604771742efb8c839ae1dc","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"},"source_kind":"arxiv","source_id":"2007.00611","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:36:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tyJGcO55FnfAmTm8UL+PcrSyYZm5tdFp9bOYPiOv1YKMXaXb1bVbze8P1k/yltHS/PLSf19ugeBol7piKvFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:24:41.738415Z"},"content_sha256":"4f0ad1ef1b44e545c4717fbd97f5bfc77dcd864e0ad9ccacc0fed7515bc7dc9b","schema_version":"1.0","event_id":"sha256:4f0ad1ef1b44e545c4717fbd97f5bfc77dcd864e0ad9ccacc0fed7515bc7dc9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GCZQ2EMF3SEM5EUQQLNBX72W3U","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:36:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4He8Bk2MYNlNiGxu2CG+ZXCsFF9Cyf3pUoi5HpNA2PinK8y/7x69vg+/+g6de6RG5hueiuGicDYzae2OhkXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:24:41.739015Z"},"content_sha256":"321239da4b5c8761f303d74bb94b74e6df2229c1f3c947b80d7770f05d037466","schema_version":"1.0","event_id":"sha256:321239da4b5c8761f303d74bb94b74e6df2229c1f3c947b80d7770f05d037466"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/bundle.json","state_url":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/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":"2026-08-07T00:24:41Z","links":{"resolver":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U","bundle":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/bundle.json","state":"https://pith.science/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCZQ2EMF3SEM5EUQQLNBX72W3U/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5A4lpe/QMDF2RIRAGhhtTU75Q8VZ1KJKaYa7UFGiYhw3IQozRS35jivBpSO/FmEZqujNB0y4jyaSvj7eA2nmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:24:41.744107Z","bundle_sha256":"caf9b2b0ad7874d24c4dfcc01cf27a0f48b71e6721883afca24321fe1098a1b4"}}