{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A6PJFTMDLEZJCNAKJEVZDDE6BF","short_pith_number":"pith:A6PJFTMD","canonical_record":{"source":{"id":"2403.12309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T23:18:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"962e36f2f668b69f0652aab203855fa3d5c460788f5c19d571003927d3cb84cc","abstract_canon_sha256":"0ad3100b0e806f63ecf65af51e9fd0ddab289aa8627e26a74bf3f97c6504defa"},"schema_version":"1.0"},"canonical_sha256":"079e92cd83593291340a492b918c9e094731af7c98f83f1a52fd19c41e6ebb88","source":{"kind":"arxiv","id":"2403.12309","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12309","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12309v2","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12309","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"A6PJFTMDLEZJ","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_16","alias_value":"A6PJFTMDLEZJCNAK","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_8","alias_value":"A6PJFTMD","created_at":"2026-07-05T08:36:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A6PJFTMDLEZJCNAKJEVZDDE6BF","target":"record","payload":{"canonical_record":{"source":{"id":"2403.12309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T23:18:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"962e36f2f668b69f0652aab203855fa3d5c460788f5c19d571003927d3cb84cc","abstract_canon_sha256":"0ad3100b0e806f63ecf65af51e9fd0ddab289aa8627e26a74bf3f97c6504defa"},"schema_version":"1.0"},"canonical_sha256":"079e92cd83593291340a492b918c9e094731af7c98f83f1a52fd19c41e6ebb88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:46.655853Z","signature_b64":"9i1K4AFHS8jRaoKNNQhISjUVNy72+v1aQvnAmpD6v9Rz6u67PlRhNV0R8eNVPj9V2yhVr8Z0cKM4ywtsjxrKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"079e92cd83593291340a492b918c9e094731af7c98f83f1a52fd19c41e6ebb88","last_reissued_at":"2026-07-05T08:36:46.655268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:46.655268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.12309","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bq7h1nqKsgnp+8M45wf81vydvk2znl6fnFO4fREParqnSAxgfkzVbwyCOJ51x8E8gdDGF6EXjlilcsFGxllyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:30:42.322811Z"},"content_sha256":"5afef7688b6788a30e5f73b7455787e3ed7bdf69013203b50cf0035cbce02e0d","schema_version":"1.0","event_id":"sha256:5afef7688b6788a30e5f73b7455787e3ed7bdf69013203b50cf0035cbce02e0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A6PJFTMDLEZJCNAKJEVZDDE6BF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning from Delayed Observations via World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Armin Karamzade, Kyungmin Kim, Montek Kalsi, Roy Fox","submitted_at":"2024-03-18T23:18:27Z","abstract_excerpt":"In standard reinforcement learning settings, agents typically assume immediate feedback about the effects of their actions after taking them. However, in practice, this assumption may not hold true due to physical constraints and can significantly impact the performance of learning algorithms. In this paper, we address observation delays in partially observable environments. We propose leveraging world models, which have shown success in integrating past observations and learning dynamics, to handle observation delays. By reducing delayed POMDPs to delayed MDPs with world models, our methods c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12309","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/2403.12309/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":"2026-07-05T08:36:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OdYPXm39j7GXAqztierdUc99MZdWOk8S0fKddrB7g5Taxm84GaVEy83V7f1dUsAskJmEm1BUy3JJQ0sqmMCTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:30:42.323194Z"},"content_sha256":"108dd07a8a51ec392297d09acce25413b63a4e18039fe3bb9af8ba5c21492bf0","schema_version":"1.0","event_id":"sha256:108dd07a8a51ec392297d09acce25413b63a4e18039fe3bb9af8ba5c21492bf0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6PJFTMDLEZJCNAKJEVZDDE6BF/bundle.json","state_url":"https://pith.science/pith/A6PJFTMDLEZJCNAKJEVZDDE6BF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6PJFTMDLEZJCNAKJEVZDDE6BF/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":"2026-07-07T05:30:42Z","links":{"resolver":"https://pith.science/pith/A6PJFTMDLEZJCNAKJEVZDDE6BF","bundle":"https://pith.science/pith/A6PJFTMDLEZJCNAKJEVZDDE6BF/bundle.json","state":"https://pith.science/pith/A6PJFTMDLEZJCNAKJEVZDDE6BF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6PJFTMDLEZJCNAKJEVZDDE6BF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A6PJFTMDLEZJCNAKJEVZDDE6BF","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":"0ad3100b0e806f63ecf65af51e9fd0ddab289aa8627e26a74bf3f97c6504defa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T23:18:27Z","title_canon_sha256":"962e36f2f668b69f0652aab203855fa3d5c460788f5c19d571003927d3cb84cc"},"schema_version":"1.0","source":{"id":"2403.12309","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12309","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12309v2","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12309","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"A6PJFTMDLEZJ","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_16","alias_value":"A6PJFTMDLEZJCNAK","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_8","alias_value":"A6PJFTMD","created_at":"2026-07-05T08:36:46Z"}],"graph_snapshots":[{"event_id":"sha256:108dd07a8a51ec392297d09acce25413b63a4e18039fe3bb9af8ba5c21492bf0","target":"graph","created_at":"2026-07-05T08:36:46Z","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/2403.12309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In standard reinforcement learning settings, agents typically assume immediate feedback about the effects of their actions after taking them. However, in practice, this assumption may not hold true due to physical constraints and can significantly impact the performance of learning algorithms. In this paper, we address observation delays in partially observable environments. We propose leveraging world models, which have shown success in integrating past observations and learning dynamics, to handle observation delays. By reducing delayed POMDPs to delayed MDPs with world models, our methods c","authors_text":"Armin Karamzade, Kyungmin Kim, Montek Kalsi, Roy Fox","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T23:18:27Z","title":"Reinforcement Learning from Delayed Observations via World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12309","kind":"arxiv","version":2},"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":"sha256:5afef7688b6788a30e5f73b7455787e3ed7bdf69013203b50cf0035cbce02e0d","target":"record","created_at":"2026-07-05T08:36:46Z","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":"0ad3100b0e806f63ecf65af51e9fd0ddab289aa8627e26a74bf3f97c6504defa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T23:18:27Z","title_canon_sha256":"962e36f2f668b69f0652aab203855fa3d5c460788f5c19d571003927d3cb84cc"},"schema_version":"1.0","source":{"id":"2403.12309","kind":"arxiv","version":2}},"canonical_sha256":"079e92cd83593291340a492b918c9e094731af7c98f83f1a52fd19c41e6ebb88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"079e92cd83593291340a492b918c9e094731af7c98f83f1a52fd19c41e6ebb88","first_computed_at":"2026-07-05T08:36:46.655268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:46.655268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9i1K4AFHS8jRaoKNNQhISjUVNy72+v1aQvnAmpD6v9Rz6u67PlRhNV0R8eNVPj9V2yhVr8Z0cKM4ywtsjxrKBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:46.655853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12309","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5afef7688b6788a30e5f73b7455787e3ed7bdf69013203b50cf0035cbce02e0d","sha256:108dd07a8a51ec392297d09acce25413b63a4e18039fe3bb9af8ba5c21492bf0"],"state_sha256":"19085aabc1b1d029052d0695b3a33c38fc585409e277e62b7d3c9401f26b3612"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFiPLlEEdGcrKETnoP+O/MBGqHMZXTxcnpM9+0Wzn44EjCz6STRi+0uggq0Fbq/EVSEUFAU2oaARhTR366/rDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:30:42.325353Z","bundle_sha256":"ff9884960a5bfac1618def80ccad37afdae00da704a9cfe33cbf52f011f46400"}}