{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WIVAEN5Y6IBMUJEOX65EUBHJQI","short_pith_number":"pith:WIVAEN5Y","canonical_record":{"source":{"id":"2606.04029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T19:40:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fbebc24d520f7537b911f70d9a1a3f3c1f26ce1d34db0466e424bac4d20e1a6","abstract_canon_sha256":"8479d106a21173480c73d202d868cd112feb26b6171d7edb6b302324610ca1c0"},"schema_version":"1.0"},"canonical_sha256":"b22a0237b8f202ca248ebfba4a04e98234465a979b2c289e990633d161134957","source":{"kind":"arxiv","id":"2606.04029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04029","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04029v1","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04029","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"WIVAEN5Y6IBM","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_16","alias_value":"WIVAEN5Y6IBMUJEO","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_8","alias_value":"WIVAEN5Y","created_at":"2026-06-04T00:06:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WIVAEN5Y6IBMUJEOX65EUBHJQI","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T19:40:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fbebc24d520f7537b911f70d9a1a3f3c1f26ce1d34db0466e424bac4d20e1a6","abstract_canon_sha256":"8479d106a21173480c73d202d868cd112feb26b6171d7edb6b302324610ca1c0"},"schema_version":"1.0"},"canonical_sha256":"b22a0237b8f202ca248ebfba4a04e98234465a979b2c289e990633d161134957","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T00:06:44.853105Z","signature_b64":"TYJARMh3OSZcYwFCu7akOw+W33bgS0XMSOe+j7df430uwfMVY4kCgM7rttzD3uNoX5fHNQdp9TPJCM935bTmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b22a0237b8f202ca248ebfba4a04e98234465a979b2c289e990633d161134957","last_reissued_at":"2026-06-04T00:06:44.852638Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T00:06:44.852638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04029","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T00:06:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/1P7eA29xovRrebBb3PcbRqLGXL3C+wKgNjrXVtjtxfhR/dz3vqCEty6iP0Ynk0l5WoVhhz2CA7ILmHyzSjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:04:25.675355Z"},"content_sha256":"12a53bafa652fe55bf78877a3bf7b2eb3d4f36d30bd96e3b854446c6254689dc","schema_version":"1.0","event_id":"sha256:12a53bafa652fe55bf78877a3bf7b2eb3d4f36d30bd96e3b854446c6254689dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WIVAEN5Y6IBMUJEOX65EUBHJQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Position: Deployed Reinforcement Learning should be Continual","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Golnaz Mesbahi, Kevin Roice, Parnian Behdin","submitted_at":"2026-06-01T19:40:10Z","abstract_excerpt":"Reinforcement Learning (RL) has received increasing attention and adoption in real-world use cases. Most of these systems follow a train-then-fix paradigm, where trained agents do not learn while interacting with the world until performance degrades and retraining becomes necessary. In this position paper, we argue that deploying an agent that is incapable of optimality, but receives an evaluative reward signal, is inherently a continual RL problem. We identify four sources of non-stationarity after deployment that necessitate never-ending learning, and highlight why the best deployed agents n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04029","kind":"arxiv","version":1},"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/2606.04029/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":"2026-06-04T00:06:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xzAV+Nqig/K4V7GCAjTx7xB/mLd0ODPfHIfcwEhmZ2Pzn8toZu9WsSBF/Q0p2nOYB689FoWpPoxogMuo4hWJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:04:25.675849Z"},"content_sha256":"11a36f0403c94673d5dd7e0e07fae73b2be2308ded2c29fd8adb362a0576f86a","schema_version":"1.0","event_id":"sha256:11a36f0403c94673d5dd7e0e07fae73b2be2308ded2c29fd8adb362a0576f86a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WIVAEN5Y6IBMUJEOX65EUBHJQI/bundle.json","state_url":"https://pith.science/pith/WIVAEN5Y6IBMUJEOX65EUBHJQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WIVAEN5Y6IBMUJEOX65EUBHJQI/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":"2026-07-03T17:04:25Z","links":{"resolver":"https://pith.science/pith/WIVAEN5Y6IBMUJEOX65EUBHJQI","bundle":"https://pith.science/pith/WIVAEN5Y6IBMUJEOX65EUBHJQI/bundle.json","state":"https://pith.science/pith/WIVAEN5Y6IBMUJEOX65EUBHJQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WIVAEN5Y6IBMUJEOX65EUBHJQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WIVAEN5Y6IBMUJEOX65EUBHJQI","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":"8479d106a21173480c73d202d868cd112feb26b6171d7edb6b302324610ca1c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T19:40:10Z","title_canon_sha256":"0fbebc24d520f7537b911f70d9a1a3f3c1f26ce1d34db0466e424bac4d20e1a6"},"schema_version":"1.0","source":{"id":"2606.04029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04029","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04029v1","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04029","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"WIVAEN5Y6IBM","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_16","alias_value":"WIVAEN5Y6IBMUJEO","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_8","alias_value":"WIVAEN5Y","created_at":"2026-06-04T00:06:44Z"}],"graph_snapshots":[{"event_id":"sha256:11a36f0403c94673d5dd7e0e07fae73b2be2308ded2c29fd8adb362a0576f86a","target":"graph","created_at":"2026-06-04T00:06:44Z","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/2606.04029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has received increasing attention and adoption in real-world use cases. Most of these systems follow a train-then-fix paradigm, where trained agents do not learn while interacting with the world until performance degrades and retraining becomes necessary. In this position paper, we argue that deploying an agent that is incapable of optimality, but receives an evaluative reward signal, is inherently a continual RL problem. We identify four sources of non-stationarity after deployment that necessitate never-ending learning, and highlight why the best deployed agents n","authors_text":"Golnaz Mesbahi, Kevin Roice, Parnian Behdin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T19:40:10Z","title":"Position: Deployed Reinforcement Learning should be Continual"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04029","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":"sha256:12a53bafa652fe55bf78877a3bf7b2eb3d4f36d30bd96e3b854446c6254689dc","target":"record","created_at":"2026-06-04T00:06:44Z","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":"8479d106a21173480c73d202d868cd112feb26b6171d7edb6b302324610ca1c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T19:40:10Z","title_canon_sha256":"0fbebc24d520f7537b911f70d9a1a3f3c1f26ce1d34db0466e424bac4d20e1a6"},"schema_version":"1.0","source":{"id":"2606.04029","kind":"arxiv","version":1}},"canonical_sha256":"b22a0237b8f202ca248ebfba4a04e98234465a979b2c289e990633d161134957","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b22a0237b8f202ca248ebfba4a04e98234465a979b2c289e990633d161134957","first_computed_at":"2026-06-04T00:06:44.852638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T00:06:44.852638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TYJARMh3OSZcYwFCu7akOw+W33bgS0XMSOe+j7df430uwfMVY4kCgM7rttzD3uNoX5fHNQdp9TPJCM935bTmDw==","signature_status":"signed_v1","signed_at":"2026-06-04T00:06:44.853105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12a53bafa652fe55bf78877a3bf7b2eb3d4f36d30bd96e3b854446c6254689dc","sha256:11a36f0403c94673d5dd7e0e07fae73b2be2308ded2c29fd8adb362a0576f86a"],"state_sha256":"193d3be16b68a51af8ba1760e12152e8622a8a4a20650fdd629951671f5d9bd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJAx4BWAymRurwWTQFX0yxNoNMfzeLfl47jAK14hMCW3wU7ol+jO+CvkbRnx/r1Gb0+m0GSpI0pUj5NWgty3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T17:04:25.678112Z","bundle_sha256":"021986449ff387e67675a616afcdb673b469d260a98489ac65efd48b5ba6b477"}}