{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AS5OSWX6VG5TKYT7HLY26NQVLO","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":"d162d7ce9ce423898cb97749d275af1ef4e4af5e456307e1f83281b150638493","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:22:12Z","title_canon_sha256":"3eeb1729a8ecb1f88893fffa4387555639991904e41c4eb67b386cf05891dd80"},"schema_version":"1.0","source":{"id":"2406.02035","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02035","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02035v1","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02035","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"AS5OSWX6VG5T","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"AS5OSWX6VG5TKYT7","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"AS5OSWX6","created_at":"2026-07-05T08:27:13Z"}],"graph_snapshots":[{"event_id":"sha256:b5cc4dd53e869e612d5325a0e8f2966a7540609030a9a4ad236cb124c01d631b","target":"graph","created_at":"2026-07-05T08:27:13Z","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/2406.02035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning a good representation is a crucial challenge for Reinforcement Learning (RL) agents. Self-predictive learning provides means to jointly learn a latent representation and dynamics model by bootstrapping from future latent representations (BYOL). Recent work has developed theoretical insights into these algorithms by studying a continuous-time ODE model for self-predictive representation learning under the simplifying assumption that the algorithm depends on a fixed policy (BYOL-$\\Pi$); this assumption is at odds with practical instantiations of such algorithms, which explicitly conditi","authors_text":"Arthur Guez, Bernardo Avila Pires, Clare Lyle, Diana Borsa, Khimya Khetarpal, Mark Rowland, Nicolas Heess, Will Dabney, Yunhao Tang, Zhaohan Daniel Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:22:12Z","title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02035","kind":"arxiv","version":1},"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":"sha256:065190e8c6e919ac24c972b9696e2df11400792c398516ffd581e4d7f979835c","target":"record","created_at":"2026-07-05T08:27:13Z","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":"d162d7ce9ce423898cb97749d275af1ef4e4af5e456307e1f83281b150638493","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:22:12Z","title_canon_sha256":"3eeb1729a8ecb1f88893fffa4387555639991904e41c4eb67b386cf05891dd80"},"schema_version":"1.0","source":{"id":"2406.02035","kind":"arxiv","version":1}},"canonical_sha256":"04bae95afea9bb35627f3af1af36155b97730ae7df92977287324dcea8034f60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04bae95afea9bb35627f3af1af36155b97730ae7df92977287324dcea8034f60","first_computed_at":"2026-07-05T08:27:13.563431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:13.563431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sy69a9JRxzOrUfjfselyFavPf2Ts/cvMw14G4mjfUicZV7BYAngKzC5s9sN9e0kk8ulTl9pvrlhyc/yyesQtDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:13.564009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02035","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:065190e8c6e919ac24c972b9696e2df11400792c398516ffd581e4d7f979835c","sha256:b5cc4dd53e869e612d5325a0e8f2966a7540609030a9a4ad236cb124c01d631b"],"state_sha256":"49751de71d2321a4cbf3461bf88f60d7f68427e24dd485b6764cc6c4851fbf36"}