{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BB6YAIRNV7TEOSVZAORFFULTGQ","short_pith_number":"pith:BB6YAIRN","schema_version":"1.0","canonical_sha256":"087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41","source":{"kind":"arxiv","id":"2605.13740","version":1},"attestation_state":"computed","paper":{"title":"Learning POMDP World Models from Observations with Language-Model Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alfonso Amayuelas, Bernhard Sch\\\"olkopf, David Hyland, Frederik Panse, Lancelot Da Costa, Mathis Fajeau, Mridul Sharma, Philipp Hennig, Tim Z. Xiao, Valentin Six","submitted_at":"2026-05-13T16:18:15Z","abstract_excerpt":"Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model of how that environment works. Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for such internal world models, but learning them from observation-action trajectories alone is challenging and typically requires extensive environment interaction. We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge, and introduce \\emph{Pinductor} (POMDP-inductor): an LLM propos"},"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":true},"canonical_record":{"source":{"id":"2605.13740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:18:15Z","cross_cats_sorted":[],"title_canon_sha256":"ad83f015af5c17608de2bbe5b5343528b73018893b8c25ece0eb63c19beacdf2","abstract_canon_sha256":"78e6322cca9170d5f72fbcd8225e80abe9f22040ec3b5cb2e64e0faaaf2a8616"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.468768Z","signature_b64":"ZeSlZakXElPZjaecwu9wrncupy9Lgawn7qDOrHmBvDt0A/0bHxqaPA88jbAm/QoSNnA/85+QyGPlFfkQ3ErECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41","last_reissued_at":"2026-05-18T02:44:16.468229Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.468229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning POMDP World Models from Observations with Language-Model Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alfonso Amayuelas, Bernhard Sch\\\"olkopf, David Hyland, Frederik Panse, Lancelot Da Costa, Mathis Fajeau, Mridul Sharma, Philipp Hennig, Tim Z. Xiao, Valentin Six","submitted_at":"2026-05-13T16:18:15Z","abstract_excerpt":"Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model of how that environment works. Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for such internal world models, but learning them from observation-action trajectories alone is challenging and typically requires extensive environment interaction. We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge, and introduce \\emph{Pinductor} (POMDP-inductor): an LLM propos"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Despite using strictly less information, Pinductor matches the performance and sample efficiency of LLM-based POMDP learning methods that assume privileged access to the hidden state, while significantly surpassing the sample efficiency of tabular POMDP baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an LLM can reliably propose and iteratively refine POMDP transition and observation models whose belief-based likelihood on limited trajectories corresponds to the true underlying dynamics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pinductor leverages language-model priors to learn POMDP world models from limited trajectories, matching privileged-access methods in performance and exceeding tabular baselines in sample efficiency.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f7d2bf228ed43e4d54dc6b648eabacb78819e9d1a405ffa4cbcc52c5761e1263"},"source":{"id":"2605.13740","kind":"arxiv","version":1},"verdict":{"id":"c747305a-4889-429f-bd26-553d0d25ac2b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:51:44.251932Z","strongest_claim":"Despite using strictly less information, Pinductor matches the performance and sample efficiency of LLM-based POMDP learning methods that assume privileged access to the hidden state, while significantly surpassing the sample efficiency of tabular POMDP baselines.","one_line_summary":"Pinductor leverages language-model priors to learn POMDP world models from limited trajectories, matching privileged-access methods in performance and exceeding tabular baselines in sample efficiency.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an LLM can reliably propose and iteratively refine POMDP transition and observation models whose belief-based likelihood on limited trajectories corresponds to the true underlying dynamics.","pith_extraction_headline":"An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access."},"references":{"count":60,"sample":[{"doi":"","year":2018,"title":"Sutton and Andrew G","work_id":"5b66f797-bcf6-443f-a9c8-7e12732ddd11","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"World Models","work_id":"07227eee-8445-4c98-bce4-c6a6fd5ed907","ref_index":2,"cited_arxiv_id":"1803.10122","is_internal_anchor":true},{"doi":"","year":2025,"title":"Training Agents Inside of Scalable World Models","work_id":"f0464a07-aaee-486f-a0b1-a4bce0bbc3e4","ref_index":3,"cited_arxiv_id":"2509.24527","is_internal_anchor":true},{"doi":"10.1016/0022-247x(65)90154-x","year":1965,"title":"Aggregate: count rows whereCOUNTRY= Algeria. [target: Country]","work_id":"c1830d65-2327-4588-a847-abaa0f7884b2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/s0004-3702(98)00023-x","year":1998,"title":"Planning and acting in partially observable stochastic domains","work_id":"b3ea0098-466e-4f58-abfe-1641bbce18de","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"ba4aafca1db6ebe3431c0447bb9f8836a30c5547a0fdd0ec374f793813989a1c","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b20fe43997b716a34595e08c4412383ecde1f2be9d36ccb4b8dcd8d8c709d629"},"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":"2605.13740","created_at":"2026-05-18T02:44:16.468323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13740v1","created_at":"2026-05-18T02:44:16.468323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13740","created_at":"2026-05-18T02:44:16.468323+00:00"},{"alias_kind":"pith_short_12","alias_value":"BB6YAIRNV7TE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BB6YAIRNV7TEOSVZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BB6YAIRN","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":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ","json":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ.json","graph_json":"https://pith.science/api/pith-number/BB6YAIRNV7TEOSVZAORFFULTGQ/graph.json","events_json":"https://pith.science/api/pith-number/BB6YAIRNV7TEOSVZAORFFULTGQ/events.json","paper":"https://pith.science/paper/BB6YAIRN"},"agent_actions":{"view_html":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ","download_json":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ.json","view_paper":"https://pith.science/paper/BB6YAIRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13740&json=true","fetch_graph":"https://pith.science/api/pith-number/BB6YAIRNV7TEOSVZAORFFULTGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BB6YAIRNV7TEOSVZAORFFULTGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/action/storage_attestation","attest_author":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/action/author_attestation","sign_citation":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/action/citation_signature","submit_replication":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/action/replication_record"}},"created_at":"2026-05-18T02:44:16.468323+00:00","updated_at":"2026-05-18T02:44:16.468323+00:00"}