{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GHU7M5AFAOOS75OO4HK2U2NCZP","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":"96fabb3466a3d856b8e3c94f209dc0059599797ff17625b9e09a9f078b1900ae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T00:47:43Z","title_canon_sha256":"be2a486be4efb0f347f2a71527d19943b17f37aa5e50b4549fb69088323d7654"},"schema_version":"1.0","source":{"id":"2401.08898","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08898","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08898v3","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08898","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"GHU7M5AFAOOS","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"GHU7M5AFAOOS75OO","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"GHU7M5AF","created_at":"2026-07-05T08:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:02843fc6a8898238680dd3928c6b99db9f1f2434fe35feccdd310b0409f3c822","target":"graph","created_at":"2026-07-05T08:10:22Z","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/2401.08898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representations are at the core of all deep reinforcement learning (RL) methods for both Markov decision processes (MDPs) and partially observable Markov decision processes (POMDPs). Many representation learning methods and theoretical frameworks have been developed to understand what constitutes an effective representation. However, the relationships between these methods and the shared properties among them remain unclear. In this paper, we show that many of these seemingly distinct methods and frameworks for state and history abstractions are, in fact, based on a common idea of self-predict","authors_text":"Aditya Mahajan, Benjamin Eysenbach, Clement Gehring, Erfan Seyedsalehi, Michel Ma, Pierre-Luc Bacon, Tianwei Ni","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T00:47:43Z","title":"Bridging State and History Representations: Understanding Self-Predictive RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08898","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":"sha256:86618003f267e837fe094dfe9b9f88f81a30bded3e7bd1fcd1d9af795640298a","target":"record","created_at":"2026-07-05T08:10:22Z","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":"96fabb3466a3d856b8e3c94f209dc0059599797ff17625b9e09a9f078b1900ae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T00:47:43Z","title_canon_sha256":"be2a486be4efb0f347f2a71527d19943b17f37aa5e50b4549fb69088323d7654"},"schema_version":"1.0","source":{"id":"2401.08898","kind":"arxiv","version":3}},"canonical_sha256":"31e9f67405039d2ff5cee1d5aa69a2cbd5963dddff839453f4bca9e14d877734","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31e9f67405039d2ff5cee1d5aa69a2cbd5963dddff839453f4bca9e14d877734","first_computed_at":"2026-07-05T08:10:22.121778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:22.121778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T+1M/FRxRuzVjkMmUQiwetCsWtNjhOZO3rfLea1/gDN7QxQl7zuikWnGr63SHl9HV9zZf0j3bJhgx1zPE2SxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:22.122260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08898","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86618003f267e837fe094dfe9b9f88f81a30bded3e7bd1fcd1d9af795640298a","sha256:02843fc6a8898238680dd3928c6b99db9f1f2434fe35feccdd310b0409f3c822"],"state_sha256":"263b3499f9bd612c41bb1f5a0fda3e2217ff94f112c3f68bc4f732b6388d93e9"}