{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CP2X56JCZS5Q3LSDJPWPNDCNK3","short_pith_number":"pith:CP2X56JC","canonical_record":{"source":{"id":"2306.11488","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:20:23Z","cross_cats_sorted":[],"title_canon_sha256":"aed0dab0ad15d9777b6e8f35306df7f964e065526ac80709f0b740e1ecc43a37","abstract_canon_sha256":"8703849628a8d4dab3cee0dd1649e006714f272c48bfb283dc320363d00f86ea"},"schema_version":"1.0"},"canonical_sha256":"13f57ef922ccbb0dae434becf68c4d56cc97208c86478a3f4fdc715d1834ad3c","source":{"kind":"arxiv","id":"2306.11488","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11488","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11488v3","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11488","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_12","alias_value":"CP2X56JCZS5Q","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_16","alias_value":"CP2X56JCZS5Q3LSD","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_8","alias_value":"CP2X56JC","created_at":"2026-07-05T11:16:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CP2X56JCZS5Q3LSDJPWPNDCNK3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11488","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:20:23Z","cross_cats_sorted":[],"title_canon_sha256":"aed0dab0ad15d9777b6e8f35306df7f964e065526ac80709f0b740e1ecc43a37","abstract_canon_sha256":"8703849628a8d4dab3cee0dd1649e006714f272c48bfb283dc320363d00f86ea"},"schema_version":"1.0"},"canonical_sha256":"13f57ef922ccbb0dae434becf68c4d56cc97208c86478a3f4fdc715d1834ad3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:47.528226Z","signature_b64":"a5TYS/ZrGIuBDoSpOc+t2ydKfPJ5fie1W+AkzpdKjnB+cJEZHztkuT37kdgZ0cSm94wqBIH/SFFdknAxIDRPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f57ef922ccbb0dae434becf68c4d56cc97208c86478a3f4fdc715d1834ad3c","last_reissued_at":"2026-07-05T11:16:47.527708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:47.527708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11488","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jlj16XHEf8kj1/6jnUDi/KMcB1+NTzf4Ftuswcr2nyV208adiHd9I+/sg4IwGxCFv9Q3hhF3lGnwV9Iqoz0/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:14:15.324265Z"},"content_sha256":"7fac95c68ef02be3ed3cf43d9dcb1ac25fa4b6ea885eafa2c83376e51c52608b","schema_version":"1.0","event_id":"sha256:7fac95c68ef02be3ed3cf43d9dcb1ac25fa4b6ea885eafa2c83376e51c52608b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CP2X56JCZS5Q3LSDJPWPNDCNK3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrien Bolland, Damien Ernst, Gaspard Lambrechts","submitted_at":"2023-06-20T12:20:23Z","abstract_excerpt":"In this work, we generalize the problem of learning through interaction in a POMDP by accounting for eventual additional information available at training time. First, we introduce the informed POMDP, a new learning paradigm offering a clear distinction between the information at training and the observation at execution. Next, we propose an objective that leverages this information for learning a sufficient statistic of the history for the optimal control. We then adapt this informed objective to learn a world model able to sample latent trajectories. Finally, we empirically show a learning s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11488","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/2306.11488/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9qtd2ldLJVGIt03q+QSDKepqDfHPmaOYu3OsU2eBP20W7mxM1/vxW0oJKk94tui6MWnmj3MheE/SLcknonlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:14:15.324805Z"},"content_sha256":"f7e3c93fc59a5e5bd28bb7f247d8b8c7cd1d419dedfef38450ee4fbf0adf1610","schema_version":"1.0","event_id":"sha256:f7e3c93fc59a5e5bd28bb7f247d8b8c7cd1d419dedfef38450ee4fbf0adf1610"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/bundle.json","state_url":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/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":"2026-08-09T18:14:15Z","links":{"resolver":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3","bundle":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/bundle.json","state":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CP2X56JCZS5Q3LSDJPWPNDCNK3","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":"8703849628a8d4dab3cee0dd1649e006714f272c48bfb283dc320363d00f86ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:20:23Z","title_canon_sha256":"aed0dab0ad15d9777b6e8f35306df7f964e065526ac80709f0b740e1ecc43a37"},"schema_version":"1.0","source":{"id":"2306.11488","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11488","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11488v3","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11488","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_12","alias_value":"CP2X56JCZS5Q","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_16","alias_value":"CP2X56JCZS5Q3LSD","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_8","alias_value":"CP2X56JC","created_at":"2026-07-05T11:16:47Z"}],"graph_snapshots":[{"event_id":"sha256:f7e3c93fc59a5e5bd28bb7f247d8b8c7cd1d419dedfef38450ee4fbf0adf1610","target":"graph","created_at":"2026-07-05T11:16:47Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.11488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we generalize the problem of learning through interaction in a POMDP by accounting for eventual additional information available at training time. First, we introduce the informed POMDP, a new learning paradigm offering a clear distinction between the information at training and the observation at execution. Next, we propose an objective that leverages this information for learning a sufficient statistic of the history for the optimal control. We then adapt this informed objective to learn a world model able to sample latent trajectories. Finally, we empirically show a learning s","authors_text":"Adrien Bolland, Damien Ernst, Gaspard Lambrechts","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:20:23Z","title":"Informed POMDP: Leveraging Additional Information in Model-Based RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11488","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7fac95c68ef02be3ed3cf43d9dcb1ac25fa4b6ea885eafa2c83376e51c52608b","target":"record","created_at":"2026-07-05T11:16:47Z","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":"8703849628a8d4dab3cee0dd1649e006714f272c48bfb283dc320363d00f86ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:20:23Z","title_canon_sha256":"aed0dab0ad15d9777b6e8f35306df7f964e065526ac80709f0b740e1ecc43a37"},"schema_version":"1.0","source":{"id":"2306.11488","kind":"arxiv","version":3}},"canonical_sha256":"13f57ef922ccbb0dae434becf68c4d56cc97208c86478a3f4fdc715d1834ad3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13f57ef922ccbb0dae434becf68c4d56cc97208c86478a3f4fdc715d1834ad3c","first_computed_at":"2026-07-05T11:16:47.527708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:47.527708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a5TYS/ZrGIuBDoSpOc+t2ydKfPJ5fie1W+AkzpdKjnB+cJEZHztkuT37kdgZ0cSm94wqBIH/SFFdknAxIDRPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:47.528226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11488","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fac95c68ef02be3ed3cf43d9dcb1ac25fa4b6ea885eafa2c83376e51c52608b","sha256:f7e3c93fc59a5e5bd28bb7f247d8b8c7cd1d419dedfef38450ee4fbf0adf1610"],"state_sha256":"903086b3d75ceb7523a8229224c8dfa86244690595e8f68e22e0720498db7adf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"221lycRwbEajmiN9NPYCtBZgWGklDo4RJa3YB62rc6CfJWYxpOQ3YOpapfD9tolOzgkp06fipukISknFE8WTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:14:15.329076Z","bundle_sha256":"baced96d9ff9a3d2fe4fd23d25ca701ff4b06d495e98985d301da2ca156b184b"}}