{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BP5CKIYNCLWKMOIHSGLRIQG35R","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":"21084af3584cd31e7f813b9e9044d4d25f059c0603d2d2e66c80cf88a7942446","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T10:36:13Z","title_canon_sha256":"ef26d21e62999c15db3f882651c74de902cf830d45b8fe8cec4940ef3a5fce9e"},"schema_version":"1.0","source":{"id":"2605.20996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20996","created_at":"2026-05-21T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20996v1","created_at":"2026-05-21T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20996","created_at":"2026-05-21T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"BP5CKIYNCLWK","created_at":"2026-05-21T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"BP5CKIYNCLWKMOIH","created_at":"2026-05-21T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"BP5CKIYN","created_at":"2026-05-21T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:ce6fe4b7f659fb4689ca410480ced589db0918b5ed76891f8e265710efc5b3c1","target":"graph","created_at":"2026-05-21T01:05:31Z","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/2605.20996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most value-based and actor--critic reinforcement learning methods rely on Bellman-style recursions, yet these recursions collapse under non-exponential discounting common in human preferences and survival processes. We show the breakdown is structural: exponential discounting sits at a fragile intersection of multiplicativity and time homogeneity, and violating either property breaks standard dynamic programming. To overcome this, we propose Pontryagin-Guided Direct Policy Optimization (PG-DPO), a variational framework that abandons recursion and couples the Pontryagin Maximum Principle with M","authors_text":"Hojin Ko, Jeonggyu Huh","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T10:36:13Z","title":"Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20996","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:eb6d1efdbbcd7524cac537c508fabfccdb403b1ebaada1509c3a8c9f8600e007","target":"record","created_at":"2026-05-21T01:05:31Z","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":"21084af3584cd31e7f813b9e9044d4d25f059c0603d2d2e66c80cf88a7942446","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T10:36:13Z","title_canon_sha256":"ef26d21e62999c15db3f882651c74de902cf830d45b8fe8cec4940ef3a5fce9e"},"schema_version":"1.0","source":{"id":"2605.20996","kind":"arxiv","version":1}},"canonical_sha256":"0bfa25230d12eca6390791971440dbec60872a1a577b76d2431d0283d1a57efb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bfa25230d12eca6390791971440dbec60872a1a577b76d2431d0283d1a57efb","first_computed_at":"2026-05-21T01:05:31.632680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:31.632680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KPFRZ4D+kczbW5w1UrZEg5/MiItk58qQgL5Qh6WraQbLIfnBrOi71Gstad7aeBYgzvG9er149wwBgImytas3Cg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:31.633439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb6d1efdbbcd7524cac537c508fabfccdb403b1ebaada1509c3a8c9f8600e007","sha256:ce6fe4b7f659fb4689ca410480ced589db0918b5ed76891f8e265710efc5b3c1"],"state_sha256":"efa1e88127d2fccefed5f7a68714110d9a2f413175b5f73d0d392db5c5b44cf4"}