{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G77Z6KQWERQRMRWTKCMV4NRSBY","short_pith_number":"pith:G77Z6KQW","schema_version":"1.0","canonical_sha256":"37ff9f2a1624611646d350995e36320e1652657e989be12110fdb37776a5be2a","source":{"kind":"arxiv","id":"2505.09518","version":3},"attestation_state":"computed","paper":{"title":"Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Maris F. L. Galesloot, Milan \\v{C}e\\v{s}ka, Nils Jansen, Roman Andriushchenko, Sebastian Junges","submitted_at":"2025-05-14T16:15:58Z","abstract_excerpt":"Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not be robust against perturbations in the environment. Hidden-model POMDPs (HM-POMDPs) capture sets of different environment models, that is, POMDPs with a shared action and observation space. The intuition is that the true model is hidden among a set of potential models, and it is unknown which model will be the environment at execution time. A policy is robust for a given HM-POMDP if it achieves sufficient performanc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.09518","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-14T16:15:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"594921b80ec0b4739d79281d5340d3ecd0c470e6b0c55b4ddb3cf13786d5cd4c","abstract_canon_sha256":"e70c45e1712b5cdd5e2b40e11d04f613506ad4a82a52bd5816c28aec285a0a9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:19.589994Z","signature_b64":"X0OClEymTR4G42oyFtWg3IWvMi+uoYG7Cobe+30jrvIVNk5T9gl1zkMYRMJ0S2J/ttcgXv+fvoU7NdP31k5jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37ff9f2a1624611646d350995e36320e1652657e989be12110fdb37776a5be2a","last_reissued_at":"2026-07-05T11:56:19.589483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:19.589483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Maris F. L. Galesloot, Milan \\v{C}e\\v{s}ka, Nils Jansen, Roman Andriushchenko, Sebastian Junges","submitted_at":"2025-05-14T16:15:58Z","abstract_excerpt":"Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not be robust against perturbations in the environment. Hidden-model POMDPs (HM-POMDPs) capture sets of different environment models, that is, POMDPs with a shared action and observation space. The intuition is that the true model is hidden among a set of potential models, and it is unknown which model will be the environment at execution time. A policy is robust for a given HM-POMDP if it achieves sufficient performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09518","kind":"arxiv","version":3},"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/2505.09518/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.09518","created_at":"2026-07-05T11:56:19.589540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09518v3","created_at":"2026-07-05T11:56:19.589540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09518","created_at":"2026-07-05T11:56:19.589540+00:00"},{"alias_kind":"pith_short_12","alias_value":"G77Z6KQWERQR","created_at":"2026-07-05T11:56:19.589540+00:00"},{"alias_kind":"pith_short_16","alias_value":"G77Z6KQWERQRMRWT","created_at":"2026-07-05T11:56:19.589540+00:00"},{"alias_kind":"pith_short_8","alias_value":"G77Z6KQW","created_at":"2026-07-05T11:56:19.589540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY","json":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY.json","graph_json":"https://pith.science/api/pith-number/G77Z6KQWERQRMRWTKCMV4NRSBY/graph.json","events_json":"https://pith.science/api/pith-number/G77Z6KQWERQRMRWTKCMV4NRSBY/events.json","paper":"https://pith.science/paper/G77Z6KQW"},"agent_actions":{"view_html":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY","download_json":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY.json","view_paper":"https://pith.science/paper/G77Z6KQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09518&json=true","fetch_graph":"https://pith.science/api/pith-number/G77Z6KQWERQRMRWTKCMV4NRSBY/graph.json","fetch_events":"https://pith.science/api/pith-number/G77Z6KQWERQRMRWTKCMV4NRSBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY/action/storage_attestation","attest_author":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY/action/author_attestation","sign_citation":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY/action/citation_signature","submit_replication":"https://pith.science/pith/G77Z6KQWERQRMRWTKCMV4NRSBY/action/replication_record"}},"created_at":"2026-07-05T11:56:19.589540+00:00","updated_at":"2026-07-05T11:56:19.589540+00:00"}