{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VB3C75ZRWWPF776EUPT2IHRQG6","short_pith_number":"pith:VB3C75ZR","schema_version":"1.0","canonical_sha256":"a8762ff731b59e5fffc4a3e7a41e30378917a3638959755b996cf0a4eba216d8","source":{"kind":"arxiv","id":"2605.14440","version":1},"attestation_state":"computed","paper":{"title":"Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sampling as a membership oracle and model-checking as an equivalence oracle synthesize finite-state POMDP controllers with formal guarantees when the induced policy is regular.","cross_cats":["cs.FL","cs.LO"],"primary_cat":"cs.AI","authors_text":"Anirban Majumdar, Debraj Chakraborty, Jean-Fran\\c{c}ois Raskin, Prince Mathew, Sayan Mukherjee","submitted_at":"2026-05-14T06:37:31Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) are the standard framework for decision-making under uncertainty. While sampling-based methods scale well, they lack formal correctness guarantees, making them unsuitable for safety-critical applications. Conversely, formal synthesis techniques provide correctness-by-construction but often struggle with scalability, as general POMDP synthesis is undecidable. To bridge this gap, we propose a synthesis framework that integrates sampling, automata learning, and model-checking. Inspired by Angluin's $L^*$ algorithm, our approach utilizes samp"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:37:31Z","cross_cats_sorted":["cs.FL","cs.LO"],"title_canon_sha256":"caebc09d2818172a29b2b94a5bf45ff54341e5c77eecdd371cb3695ce75109c5","abstract_canon_sha256":"4904d2348426bb471b27a44f42023f7699ddd88cd612761991556bf618cf87be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.032205Z","signature_b64":"Tn8dkcsZ5LyB/1xIimEklL/VL7AvrKEIXjGY8c5w2kRZXPz5A+T6QpzlTNJqB8Q4m7y06WgA91MSizLUeZ67Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8762ff731b59e5fffc4a3e7a41e30378917a3638959755b996cf0a4eba216d8","last_reissued_at":"2026-05-17T23:39:07.031543Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.031543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sampling as a membership oracle and model-checking as an equivalence oracle synthesize finite-state POMDP controllers with formal guarantees when the induced policy is regular.","cross_cats":["cs.FL","cs.LO"],"primary_cat":"cs.AI","authors_text":"Anirban Majumdar, Debraj Chakraborty, Jean-Fran\\c{c}ois Raskin, Prince Mathew, Sayan Mukherjee","submitted_at":"2026-05-14T06:37:31Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) are the standard framework for decision-making under uncertainty. While sampling-based methods scale well, they lack formal correctness guarantees, making them unsuitable for safety-critical applications. Conversely, formal synthesis techniques provide correctness-by-construction but often struggle with scalability, as general POMDP synthesis is undecidable. To bridge this gap, we propose a synthesis framework that integrates sampling, automata learning, and model-checking. Inspired by Angluin's $L^*$ algorithm, our approach utilizes samp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We establish a relative completeness result for this framework. Experimental results from our prototypical implementation demonstrate that this method successfully solves threshold-safety problems that remain challenging for existing formal synthesis tools.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The framework provides formal guarantees provided the sampling-induced policy is regular; the approach assumes sampling functions as a reliable membership oracle and model-checking as a reliable equivalence oracle without detailing how noise or approximation in sampling is handled.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A new synthesis framework for POMDPs learns finite-state controllers via sampling and model-checking oracles, achieving relative completeness when the policy is regular and solving threshold-safety problems beyond existing formal tools.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sampling as a membership oracle and model-checking as an equivalence oracle synthesize finite-state POMDP controllers with formal guarantees when the induced policy is regular.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8946c918371df7ad5d26dfd6400795cf2414e7c9eef0661ec75bf8b579ef9941"},"source":{"id":"2605.14440","kind":"arxiv","version":1},"verdict":{"id":"6dc38e11-3840-4b02-a046-234609994078","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:51:26.470039Z","strongest_claim":"We establish a relative completeness result for this framework. Experimental results from our prototypical implementation demonstrate that this method successfully solves threshold-safety problems that remain challenging for existing formal synthesis tools.","one_line_summary":"A new synthesis framework for POMDPs learns finite-state controllers via sampling and model-checking oracles, achieving relative completeness when the policy is regular and solving threshold-safety problems beyond existing formal tools.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The framework provides formal guarantees provided the sampling-induced policy is regular; the approach assumes sampling functions as a reliable membership oracle and model-checking as a reliable equivalence oracle without detailing how noise or approximation in sampling is handled.","pith_extraction_headline":"Sampling as a membership oracle and model-checking as an equivalence oracle synthesize finite-state POMDP controllers with formal guarantees when the induced policy is regular."},"references":{"count":46,"sample":[{"doi":"","year":2022,"title":"In: Principles of Systems Design: Essays Dedicated to Thomas A","work_id":"129b3120-622c-4d1e-b322-962179e8b33f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"In: International Con- ference on Computer Aided Verification","work_id":"ae6e13fd-6ccc-43d1-9344-e3c57b862651","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"In: International Conference on Computer Aided Verification","work_id":"73389a62-716f-49a1-81b3-19c9f0e3ed97","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1987,"title":"Angluin, D.: Learning regular sets from queries and counterexamples. Inf. Comput. 75(2), 87–106 (1987)","work_id":"9074eabc-a777-4ac1-b878-8784d5dd7c8a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"MIT press (2008)","work_id":"ad903039-7863-4cda-a816-8cffb167bd50","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":46,"snapshot_sha256":"dced0dc1fb3b9af95fadafea341254ab42d7696484ea69276a585fee495a284e","internal_anchors":1},"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":"2605.14440","created_at":"2026-05-17T23:39:07.031655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14440v1","created_at":"2026-05-17T23:39:07.031655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14440","created_at":"2026-05-17T23:39:07.031655+00:00"},{"alias_kind":"pith_short_12","alias_value":"VB3C75ZRWWPF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VB3C75ZRWWPF776E","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VB3C75ZR","created_at":"2026-05-18T12:33:37.589309+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/VB3C75ZRWWPF776EUPT2IHRQG6","json":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6.json","graph_json":"https://pith.science/api/pith-number/VB3C75ZRWWPF776EUPT2IHRQG6/graph.json","events_json":"https://pith.science/api/pith-number/VB3C75ZRWWPF776EUPT2IHRQG6/events.json","paper":"https://pith.science/paper/VB3C75ZR"},"agent_actions":{"view_html":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6","download_json":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6.json","view_paper":"https://pith.science/paper/VB3C75ZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14440&json=true","fetch_graph":"https://pith.science/api/pith-number/VB3C75ZRWWPF776EUPT2IHRQG6/graph.json","fetch_events":"https://pith.science/api/pith-number/VB3C75ZRWWPF776EUPT2IHRQG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6/action/storage_attestation","attest_author":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6/action/author_attestation","sign_citation":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6/action/citation_signature","submit_replication":"https://pith.science/pith/VB3C75ZRWWPF776EUPT2IHRQG6/action/replication_record"}},"created_at":"2026-05-17T23:39:07.031655+00:00","updated_at":"2026-05-17T23:39:07.031655+00:00"}