{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FE4VYZDZKKS2HCEF4LHPZSUWH4","short_pith_number":"pith:FE4VYZDZ","schema_version":"1.0","canonical_sha256":"29395c647952a5a38885e2cefcca963f2495b41353cb9f641146b751c54ab8a6","source":{"kind":"arxiv","id":"2505.02216","version":2},"attestation_state":"computed","paper":{"title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aidan Curtis, Hao Tang, Joshua Tenenbaum, Kevin Ellis, Leslie Pack Kaelbling, Thiago Veloso, Tom\\'as Lozano-P\\'erez","submitted_at":"2025-05-04T18:59:07Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) model decision making under uncertainty. While there are many approaches to approximately solving POMDPs, we aim to address the problem of learning such models. In particular, we are interested in a subclass of POMDPs wherein the components of the model, including the observation function, reward function, transition function, and initial state distribution function, can be modeled as low-complexity probabilistic graphical models in the form of a short probabilistic program. Our strategy to learn these programs uses an LLM as a prior, gen"},"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":"2505.02216","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-04T18:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"07584f9d4a565ccf71597197083f3f73a883bb7e5dde84e47ad2c71526666a8f","abstract_canon_sha256":"1b44f47ce8b35b3e80a319e6538147d934d3ca0e68b8635783a517d0953f722c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:36.087366Z","signature_b64":"ERGNTOVnOn4IoPv1gDbrrPaYEGKOzMZ8BiHqw3nSvUFOMTuHHRo4kB4g8TOF7q5DhhWpkft5Bg6OPlAoBlA7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29395c647952a5a38885e2cefcca963f2495b41353cb9f641146b751c54ab8a6","last_reissued_at":"2026-07-05T11:01:36.086895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:36.086895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aidan Curtis, Hao Tang, Joshua Tenenbaum, Kevin Ellis, Leslie Pack Kaelbling, Thiago Veloso, Tom\\'as Lozano-P\\'erez","submitted_at":"2025-05-04T18:59:07Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) model decision making under uncertainty. While there are many approaches to approximately solving POMDPs, we aim to address the problem of learning such models. In particular, we are interested in a subclass of POMDPs wherein the components of the model, including the observation function, reward function, transition function, and initial state distribution function, can be modeled as low-complexity probabilistic graphical models in the form of a short probabilistic program. Our strategy to learn these programs uses an LLM as a prior, gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02216","kind":"arxiv","version":2},"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/2505.02216/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":"2505.02216","created_at":"2026-07-05T11:01:36.086955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02216v2","created_at":"2026-07-05T11:01:36.086955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02216","created_at":"2026-07-05T11:01:36.086955+00:00"},{"alias_kind":"pith_short_12","alias_value":"FE4VYZDZKKS2","created_at":"2026-07-05T11:01:36.086955+00:00"},{"alias_kind":"pith_short_16","alias_value":"FE4VYZDZKKS2HCEF","created_at":"2026-07-05T11:01:36.086955+00:00"},{"alias_kind":"pith_short_8","alias_value":"FE4VYZDZ","created_at":"2026-07-05T11:01:36.086955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.15830","citing_title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4","json":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4.json","graph_json":"https://pith.science/api/pith-number/FE4VYZDZKKS2HCEF4LHPZSUWH4/graph.json","events_json":"https://pith.science/api/pith-number/FE4VYZDZKKS2HCEF4LHPZSUWH4/events.json","paper":"https://pith.science/paper/FE4VYZDZ"},"agent_actions":{"view_html":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4","download_json":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4.json","view_paper":"https://pith.science/paper/FE4VYZDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02216&json=true","fetch_graph":"https://pith.science/api/pith-number/FE4VYZDZKKS2HCEF4LHPZSUWH4/graph.json","fetch_events":"https://pith.science/api/pith-number/FE4VYZDZKKS2HCEF4LHPZSUWH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4/action/storage_attestation","attest_author":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4/action/author_attestation","sign_citation":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4/action/citation_signature","submit_replication":"https://pith.science/pith/FE4VYZDZKKS2HCEF4LHPZSUWH4/action/replication_record"}},"created_at":"2026-07-05T11:01:36.086955+00:00","updated_at":"2026-07-05T11:01:36.086955+00:00"}