{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BB6YAIRNV7TEOSVZAORFFULTGQ","short_pith_number":"pith:BB6YAIRN","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"},"canonical_sha256":"087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41","source":{"kind":"arxiv","id":"2605.13740","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13740","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13740v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13740","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"BB6YAIRNV7TE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BB6YAIRNV7TEOSVZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BB6YAIRN","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BB6YAIRNV7TEOSVZAORFFULTGQ","target":"record","payload":{"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"},"canonical_sha256":"087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41","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"},"source_kind":"arxiv","source_id":"2605.13740","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9y8lNewQCyLheSs0MZKFJh1FPgC4XJ9UM50WB7gAn0EyJna37E77pBiZw4xMMS3c57QUYCPTsvak5Om6XQ9rBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:52:53.895992Z"},"content_sha256":"e5c567a95eb3a13e5b4041361106d5f28f6fb022ebcbd21476232edcb9ba9ef6","schema_version":"1.0","event_id":"sha256:e5c567a95eb3a13e5b4041361106d5f28f6fb022ebcbd21476232edcb9ba9ef6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BB6YAIRNV7TEOSVZAORFFULTGQ","target":"graph","payload":{"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"},"verdict_id":"c747305a-4889-429f-bd26-553d0d25ac2b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDP+cudIoqbuY8M81F6hzdWzSzfcRzS/YEXAXiUhtZeuqEbWsH5sO7Zq+TJvl2aczuj627AI+xRiPXdeYX1SAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:52:53.897005Z"},"content_sha256":"884bfac4ec8309369feb200ac35ea79e41a31a3cd9d381fc65b0e08059544d8b","schema_version":"1.0","event_id":"sha256:884bfac4ec8309369feb200ac35ea79e41a31a3cd9d381fc65b0e08059544d8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/bundle.json","state_url":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T16:52:53Z","links":{"resolver":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ","bundle":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/bundle.json","state":"https://pith.science/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BB6YAIRNV7TEOSVZAORFFULTGQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BB6YAIRNV7TEOSVZAORFFULTGQ","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":"78e6322cca9170d5f72fbcd8225e80abe9f22040ec3b5cb2e64e0faaaf2a8616","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:18:15Z","title_canon_sha256":"ad83f015af5c17608de2bbe5b5343528b73018893b8c25ece0eb63c19beacdf2"},"schema_version":"1.0","source":{"id":"2605.13740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13740","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13740v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13740","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"BB6YAIRNV7TE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BB6YAIRNV7TEOSVZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BB6YAIRN","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:884bfac4ec8309369feb200ac35ea79e41a31a3cd9d381fc65b0e08059544d8b","target":"graph","created_at":"2026-05-18T02:44:16Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access."}],"snapshot_sha256":"f7d2bf228ed43e4d54dc6b648eabacb78819e9d1a405ffa4cbcc52c5761e1263"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b20fe43997b716a34595e08c4412383ecde1f2be9d36ccb4b8dcd8d8c709d629"},"paper":{"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","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","cross_cats":[],"headline":"An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:18:15Z","title":"Learning POMDP World Models from Observations with Language-Model Priors"},"references":{"count":60,"internal_anchors":4,"resolved_work":60,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Sutton and Andrew G","work_id":"5b66f797-bcf6-443f-a9c8-7e12732ddd11","year":2018},{"cited_arxiv_id":"1803.10122","doi":"","is_internal_anchor":true,"ref_index":2,"title":"World Models","work_id":"07227eee-8445-4c98-bce4-c6a6fd5ed907","year":2018},{"cited_arxiv_id":"2509.24527","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Training Agents Inside of Scalable World Models","work_id":"f0464a07-aaee-486f-a0b1-a4bce0bbc3e4","year":2025},{"cited_arxiv_id":"","doi":"10.1016/0022-247x(65)90154-x","is_internal_anchor":false,"ref_index":4,"title":"Aggregate: count rows whereCOUNTRY= Algeria. [target: Country]","work_id":"c1830d65-2327-4588-a847-abaa0f7884b2","year":1965},{"cited_arxiv_id":"","doi":"10.1016/s0004-3702(98)00023-x","is_internal_anchor":false,"ref_index":5,"title":"Planning and acting in partially observable stochastic domains","work_id":"b3ea0098-466e-4f58-abfe-1641bbce18de","year":1998}],"snapshot_sha256":"ba4aafca1db6ebe3431c0447bb9f8836a30c5547a0fdd0ec374f793813989a1c"},"source":{"id":"2605.13740","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:51:44.251932Z","id":"c747305a-4889-429f-bd26-553d0d25ac2b","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"An LLM proposes and refines POMDP models from observation-action trajectories alone to match methods with hidden-state access.","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.","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."}},"verdict_id":"c747305a-4889-429f-bd26-553d0d25ac2b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e5c567a95eb3a13e5b4041361106d5f28f6fb022ebcbd21476232edcb9ba9ef6","target":"record","created_at":"2026-05-18T02:44:16Z","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":"78e6322cca9170d5f72fbcd8225e80abe9f22040ec3b5cb2e64e0faaaf2a8616","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:18:15Z","title_canon_sha256":"ad83f015af5c17608de2bbe5b5343528b73018893b8c25ece0eb63c19beacdf2"},"schema_version":"1.0","source":{"id":"2605.13740","kind":"arxiv","version":1}},"canonical_sha256":"087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"087d80222dafe6474ab903a252d173342ad1d90424e97af023b8800184755b41","first_computed_at":"2026-05-18T02:44:16.468229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:16.468229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZeSlZakXElPZjaecwu9wrncupy9Lgawn7qDOrHmBvDt0A/0bHxqaPA88jbAm/QoSNnA/85+QyGPlFfkQ3ErECQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:16.468768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5c567a95eb3a13e5b4041361106d5f28f6fb022ebcbd21476232edcb9ba9ef6","sha256:884bfac4ec8309369feb200ac35ea79e41a31a3cd9d381fc65b0e08059544d8b"],"state_sha256":"cdf4e75fac7d8859ceb5a130a391f52ffb6779e016c41cc6ad5ec368581d9166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i2Ah3g/hMgcT74/zwFoy69BFLjcyziVnyO1sHTY2LJI3qJAKsUBRbHrwZvvDUvNKyHYLVhmsLBZ7T4WWDkmgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:52:53.901603Z","bundle_sha256":"ad47331a3ad974b65d56d6873ef763aaf60edafecd518132186c26eb086fd833"}}