{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6Q7M7D7ETKKFPNRTSFRQILKV2I","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":"c18cbd2ebd3b6723242161d8a818a63ed5c02729bf31abe33ea728a67d7456f2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T20:15:14Z","title_canon_sha256":"10f7f935802c8e44cd94de0976aa998f9763916146c1d6f95fc741fddfaf151b"},"schema_version":"1.0","source":{"id":"2606.04188","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04188","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04188v1","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04188","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"6Q7M7D7ETKKF","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"6Q7M7D7ETKKFPNRT","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"6Q7M7D7E","created_at":"2026-06-04T01:08:19Z"}],"graph_snapshots":[{"event_id":"sha256:958824fedfdd0770f9becb3e4a1db1059fbadbd8db2b360e4be6152c208dcc18","target":"graph","created_at":"2026-06-04T01:08:19Z","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/2606.04188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide value fields that capture global goal reachability, but they do not directly specify which action should be preferred at a given state. We propose Dual Advantage Fields, a policy-extraction method that turns a bilinear dual value model into a local advantage signal. Under bilinear dual parameterization, the goal embedding is the gradient of the value field with respect to the state representation. DAF learns an action-effect model tha","authors_text":"Alexander Nikulin, Alexey Zemtsov, Arip Asadulaev, Dmitry V. Dylov, Fakhri Karray, Martin Tak\\'a\\v{c}, Maxim Bobrin, Vladislav Kurenkov","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T20:15:14Z","title":"Dual Advantage Fields"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04188","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":"sha256:9b5d4f3fdbf02b2fe865c5b80483e0ff8ac9dbb3c5215dd996b224befec839a5","target":"record","created_at":"2026-06-04T01:08:19Z","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":"c18cbd2ebd3b6723242161d8a818a63ed5c02729bf31abe33ea728a67d7456f2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T20:15:14Z","title_canon_sha256":"10f7f935802c8e44cd94de0976aa998f9763916146c1d6f95fc741fddfaf151b"},"schema_version":"1.0","source":{"id":"2606.04188","kind":"arxiv","version":1}},"canonical_sha256":"f43ecf8fe49a9457b6339163042d55d2071f3a9a60b25b821c8a839e4e20c744","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f43ecf8fe49a9457b6339163042d55d2071f3a9a60b25b821c8a839e4e20c744","first_computed_at":"2026-06-04T01:08:19.610232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:19.610232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zoa8v3sElyQ2806tcRCS7YvndZPK2n+MPpk9ZXQQJfq9FGwv8sHOXletTtiwsvMfVsw6ru2RRu8b3OfdQiTEAQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:19.611053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04188","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b5d4f3fdbf02b2fe865c5b80483e0ff8ac9dbb3c5215dd996b224befec839a5","sha256:958824fedfdd0770f9becb3e4a1db1059fbadbd8db2b360e4be6152c208dcc18"],"state_sha256":"ddc03be5685d54f3e338735b4be669cc2b0a936e24e87ab2b0c4b2bdfb9ff539"}