{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N7WH75Z4A5WN6CBCBMJK26TNII","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":"6e72fda0fc4a48343e5d961148f43a6d76205158d53e78fc4de8d934f6f4e072","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-16T03:16:50Z","title_canon_sha256":"a48508ab65b5ad18b487f6185f18f2e18bc353c00ab2806ab8bc8828baadba51"},"schema_version":"1.0","source":{"id":"2605.16777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16777","created_at":"2026-05-20T00:03:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16777v1","created_at":"2026-05-20T00:03:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16777","created_at":"2026-05-20T00:03:21Z"},{"alias_kind":"pith_short_12","alias_value":"N7WH75Z4A5WN","created_at":"2026-05-20T00:03:21Z"},{"alias_kind":"pith_short_16","alias_value":"N7WH75Z4A5WN6CBC","created_at":"2026-05-20T00:03:21Z"},{"alias_kind":"pith_short_8","alias_value":"N7WH75Z4","created_at":"2026-05-20T00:03:21Z"}],"graph_snapshots":[{"event_id":"sha256:74e0ce31e8f70cdeb4f0ddd00994c0decc2f27d4aa176eb9c3d08765427594f1","target":"graph","created_at":"2026-05-20T00:03:21Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Simulations show AoI-MDP outperforms the standard MDP, demonstrating superior performance, feasibility, and generalization in underwater tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That adding age of information to the state and a wait action will produce better policies without introducing instability or requiring extensive new hyper-parameter tuning in the reinforcement learning process."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AoI-MDP integrates age of information into MDP state, action, and reward to optimize decision-making under observation delays for underwater autonomous vehicles."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Incorporating age of information into the state space and adding a wait action lets reinforcement learning produce better policies for underwater vehicles facing observation delays."}],"snapshot_sha256":"d8c18e4e2555920c764095222fddd4e2c36fd05ca2302f0a852f174281b9e6e7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:19.692358Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:40:53.426719Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.305472Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.440470Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16777/integrity.json","findings":[],"snapshot_sha256":"906e2927cd99a9c2102d3fb4590e1f73c983d7c1d96d59a388369d577a773b4e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ocean exploration places high demands on autonomous underwater vehicles, especially when there's observation delay. We propose age of information optimized Markov decision process (AoI-MDP) to enhance underwater tasks by modeling observation delay as signal delay and including it in the state space. AoI-MDP also introduces wait time in the action space and integrates AoI with reward functions, optimizing information freshness and decision-making using reinforcement learning. Simulations show AoI-MDP outperforms the standard MDP, demonstrating superior performance, feasibility, and generalizati","authors_text":"Guanwen Xie, Jingzehua Xu, Shuai Zhang, Xinqi Wang, Yimian Ding, Yiyuan Yang","cross_cats":["cs.SY"],"headline":"Incorporating age of information into the state space and adding a wait action lets reinforcement learning produce better policies for underwater vehicles facing observation delays.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-16T03:16:50Z","title":"AoI-MDP: An AoI Optimized Markov Decision Process (Student Abstract)"},"references":{"count":19,"internal_anchors":1,"resolved_work":19,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Vol and Energy-Aware AUV-Assisted Data Collection for Internet of Underwater Things , year=","work_id":"0e9f9b37-be43-45ce-8ce1-ad96cbb60c2b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Noncooperative Mobile Target Tracking Using Multiple AUVs in Anchor-Free Environments , year=","work_id":"0e379384-e9c2-4423-be6c-3ff21929b174","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Environment and Energy-Aware AUV-Assisted Data Collection for the Internet of Underwater Things , year=","work_id":"7709ad76-03a2-4bce-a03a-127abe2f6077","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Wei, Wei and Wang, Jingjing and Du, Jun and Fang, Zhengru and Ren, Yong and Chen, C. L. Philip , journal=. Differential Game-Based Deep Reinforcement Learning in Underwater Target Hunting Task , year=","work_id":"9ccdfe31-7027-4bdb-ab62-c163dd674da5","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Reinforcement Learning and Particle Swarm Optimization Supporting Real-Time Rescue Assignments for Multiple Autonomous Underwater Vehicles , year=","work_id":"d55f0825-a67d-401c-bec6-44763a2516e6","year":null}],"snapshot_sha256":"9b8b8c5b8802126a61be3904fb9f2b8db36f7f2cbcdd8b36c422eebe77e90f3d"},"source":{"id":"2605.16777","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:28:14.765743Z","id":"043061db-a3d2-4dc1-809d-c2b82d14cf7d","model_set":{"reader":"grok-4.3"},"one_line_summary":"AoI-MDP integrates age of information into MDP state, action, and reward to optimize decision-making under observation delays for underwater autonomous vehicles.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Incorporating age of information into the state space and adding a wait action lets reinforcement learning produce better policies for underwater vehicles facing observation delays.","strongest_claim":"Simulations show AoI-MDP outperforms the standard MDP, demonstrating superior performance, feasibility, and generalization in underwater tasks.","weakest_assumption":"That adding age of information to the state and a wait action will produce better policies without introducing instability or requiring extensive new hyper-parameter tuning in the reinforcement learning process."}},"verdict_id":"043061db-a3d2-4dc1-809d-c2b82d14cf7d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ca1266ecc283c87b65a30851b7b934849d59f31a7067afbcf5d9f13e85a472fb","target":"record","created_at":"2026-05-20T00:03:21Z","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":"6e72fda0fc4a48343e5d961148f43a6d76205158d53e78fc4de8d934f6f4e072","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-16T03:16:50Z","title_canon_sha256":"a48508ab65b5ad18b487f6185f18f2e18bc353c00ab2806ab8bc8828baadba51"},"schema_version":"1.0","source":{"id":"2605.16777","kind":"arxiv","version":1}},"canonical_sha256":"6fec7ff73c076cdf08220b12ad7a6d422e223a9f5a6b2644206b99abefde12df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fec7ff73c076cdf08220b12ad7a6d422e223a9f5a6b2644206b99abefde12df","first_computed_at":"2026-05-20T00:03:21.482424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:21.482424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twquYaoBkH46Xxe7oROABzvSvLg4FSFdGYtXNmzpeIjm4bEZRKKrzpNdKmu6ZS/RkYUlp3nxoW7sz6rVfCaZBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:21.483241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca1266ecc283c87b65a30851b7b934849d59f31a7067afbcf5d9f13e85a472fb","sha256:74e0ce31e8f70cdeb4f0ddd00994c0decc2f27d4aa176eb9c3d08765427594f1"],"state_sha256":"0e293c0c7c40e5ffad3a822bb033a00197ab1bfc7bc325188f9d9fe541cda44a"}