{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AS5OSWX6VG5TKYT7HLY26NQVLO","short_pith_number":"pith:AS5OSWX6","canonical_record":{"source":{"id":"2406.02035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:22:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3eeb1729a8ecb1f88893fffa4387555639991904e41c4eb67b386cf05891dd80","abstract_canon_sha256":"d162d7ce9ce423898cb97749d275af1ef4e4af5e456307e1f83281b150638493"},"schema_version":"1.0"},"canonical_sha256":"04bae95afea9bb35627f3af1af36155b97730ae7df92977287324dcea8034f60","source":{"kind":"arxiv","id":"2406.02035","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AS5OSWX6VG5TKYT7HLY26NQVLO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:22:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3eeb1729a8ecb1f88893fffa4387555639991904e41c4eb67b386cf05891dd80","abstract_canon_sha256":"d162d7ce9ce423898cb97749d275af1ef4e4af5e456307e1f83281b150638493"},"schema_version":"1.0"},"canonical_sha256":"04bae95afea9bb35627f3af1af36155b97730ae7df92977287324dcea8034f60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:13.564009Z","signature_b64":"sy69a9JRxzOrUfjfselyFavPf2Ts/cvMw14G4mjfUicZV7BYAngKzC5s9sN9e0kk8ulTl9pvrlhyc/yyesQtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04bae95afea9bb35627f3af1af36155b97730ae7df92977287324dcea8034f60","last_reissued_at":"2026-07-05T08:27:13.563431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:13.563431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02035","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0cqOCpohKvPSrxFMaU70QvX86LOMs3TVUO0xfkwJJzmuk0t6Y0swA0hOwwJ8ist9S10zjh7M7FIP2sYA5ovlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:24:21.818897Z"},"content_sha256":"065190e8c6e919ac24c972b9696e2df11400792c398516ffd581e4d7f979835c","schema_version":"1.0","event_id":"sha256:065190e8c6e919ac24c972b9696e2df11400792c398516ffd581e4d7f979835c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AS5OSWX6VG5TKYT7HLY26NQVLO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Guez, Bernardo Avila Pires, Clare Lyle, Diana Borsa, Khimya Khetarpal, Mark Rowland, Nicolas Heess, Will Dabney, Yunhao Tang, Zhaohan Daniel Guo","submitted_at":"2024-06-04T07:22:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02035","kind":"arxiv","version":1},"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/2406.02035/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":"2026-07-05T08:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JgoP6wwH6wQoX746XpSJ9NpDWu2avNzlxkDbAGb7v2BSlF5E9IX6mKt/fSmqstZxyA88w9UDIn5TO7QcQmvoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:24:21.819422Z"},"content_sha256":"b5cc4dd53e869e612d5325a0e8f2966a7540609030a9a4ad236cb124c01d631b","schema_version":"1.0","event_id":"sha256:b5cc4dd53e869e612d5325a0e8f2966a7540609030a9a4ad236cb124c01d631b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/bundle.json","state_url":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/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":"2026-08-08T11:24:21Z","links":{"resolver":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO","bundle":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/bundle.json","state":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WK+q6rpdhigRGSZIvByfKsuynDEb7iaUoGUoxDbG3Wdp+4Ybz6mTNKeV+j6t/WQEzRF8ZgCiqU8g0l0kU3vbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:24:21.826495Z","bundle_sha256":"09935842e00805c3c48995d4abf71bdb47014d556182a9dda04ba3740a9f245c"}}