{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GHU7M5AFAOOS75OO4HK2U2NCZP","short_pith_number":"pith:GHU7M5AF","schema_version":"1.0","canonical_sha256":"31e9f67405039d2ff5cee1d5aa69a2cbd5963dddff839453f4bca9e14d877734","source":{"kind":"arxiv","id":"2401.08898","version":3},"attestation_state":"computed","paper":{"title":"Bridging State and History Representations: Understanding Self-Predictive RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Mahajan, Benjamin Eysenbach, Clement Gehring, Erfan Seyedsalehi, Michel Ma, Pierre-Luc Bacon, Tianwei Ni","submitted_at":"2024-01-17T00:47:43Z","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"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.08898","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T00:47:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be2a486be4efb0f347f2a71527d19943b17f37aa5e50b4549fb69088323d7654","abstract_canon_sha256":"96fabb3466a3d856b8e3c94f209dc0059599797ff17625b9e09a9f078b1900ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:22.122260Z","signature_b64":"T+1M/FRxRuzVjkMmUQiwetCsWtNjhOZO3rfLea1/gDN7QxQl7zuikWnGr63SHl9HV9zZf0j3bJhgx1zPE2SxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e9f67405039d2ff5cee1d5aa69a2cbd5963dddff839453f4bca9e14d877734","last_reissued_at":"2026-07-05T08:10:22.121778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:22.121778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging State and History Representations: Understanding Self-Predictive RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Mahajan, Benjamin Eysenbach, Clement Gehring, Erfan Seyedsalehi, Michel Ma, Pierre-Luc Bacon, Tianwei Ni","submitted_at":"2024-01-17T00:47:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08898","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/2401.08898/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.08898","created_at":"2026-07-05T08:10:22.121837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08898v3","created_at":"2026-07-05T08:10:22.121837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08898","created_at":"2026-07-05T08:10:22.121837+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHU7M5AFAOOS","created_at":"2026-07-05T08:10:22.121837+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHU7M5AFAOOS75OO","created_at":"2026-07-05T08:10:22.121837+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHU7M5AF","created_at":"2026-07-05T08:10:22.121837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.08902","citing_title":"Intention-Conditioned Flow Occupancy Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2506.10137","citing_title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06382","citing_title":"Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07083","citing_title":"Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03023","citing_title":"Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07057","citing_title":"Integrating Causal DAGs in Deep RL: Activating Minimal Markovian States with Multi-Order Exposure","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP","json":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP.json","graph_json":"https://pith.science/api/pith-number/GHU7M5AFAOOS75OO4HK2U2NCZP/graph.json","events_json":"https://pith.science/api/pith-number/GHU7M5AFAOOS75OO4HK2U2NCZP/events.json","paper":"https://pith.science/paper/GHU7M5AF"},"agent_actions":{"view_html":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP","download_json":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP.json","view_paper":"https://pith.science/paper/GHU7M5AF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08898&json=true","fetch_graph":"https://pith.science/api/pith-number/GHU7M5AFAOOS75OO4HK2U2NCZP/graph.json","fetch_events":"https://pith.science/api/pith-number/GHU7M5AFAOOS75OO4HK2U2NCZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP/action/storage_attestation","attest_author":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP/action/author_attestation","sign_citation":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP/action/citation_signature","submit_replication":"https://pith.science/pith/GHU7M5AFAOOS75OO4HK2U2NCZP/action/replication_record"}},"created_at":"2026-07-05T08:10:22.121837+00:00","updated_at":"2026-07-05T08:10:22.121837+00:00"}