{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3PM3EOL4ZK4O7MWR6CBYSJ4EJF","short_pith_number":"pith:3PM3EOL4","canonical_record":{"source":{"id":"2110.04935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T00:16:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16293308c288719eb92992ca93e707d3be68d446d7e7662d87fed72b23c63e41","abstract_canon_sha256":"d5dd4aa538ed69a3fc021c5c494348732e93af12b25dd194589bd0ac6c9749f2"},"schema_version":"1.0"},"canonical_sha256":"dbd9b2397ccab8efb2d1f08389278449755c03da5eaf736ca648ad661bea75e1","source":{"kind":"arxiv","id":"2110.04935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04935","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04935v1","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04935","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"3PM3EOL4ZK4O","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"3PM3EOL4ZK4O7MWR","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"3PM3EOL4","created_at":"2026-07-05T03:21:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3PM3EOL4ZK4O7MWR6CBYSJ4EJF","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T00:16:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16293308c288719eb92992ca93e707d3be68d446d7e7662d87fed72b23c63e41","abstract_canon_sha256":"d5dd4aa538ed69a3fc021c5c494348732e93af12b25dd194589bd0ac6c9749f2"},"schema_version":"1.0"},"canonical_sha256":"dbd9b2397ccab8efb2d1f08389278449755c03da5eaf736ca648ad661bea75e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:23.000784Z","signature_b64":"3JzYkbznp5MoRd9DXz3k4rhiiOvBRe5CmDgmJUyPDRq9dHzgSot5UpBH0KlP6Jo+xkDX1HdRexDugboif4XoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbd9b2397ccab8efb2d1f08389278449755c03da5eaf736ca648ad661bea75e1","last_reissued_at":"2026-07-05T03:21:23.000337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:23.000337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04935","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":"2026-07-05T03:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asL9qV4V3EL4IUwNflwt3zGWtGIXlAd42vfz7TsgPPXkLVWXWIMvVl0h50MKPCzYSercccwic94Qy5HtA3+PCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:46:20.425028Z"},"content_sha256":"c631b6e73add6cd3b6a1b7460a54585f4e0eba2188e10b9e7490d55e70bea895","schema_version":"1.0","event_id":"sha256:c631b6e73add6cd3b6a1b7460a54585f4e0eba2188e10b9e7490d55e70bea895"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3PM3EOL4ZK4O7MWR6CBYSJ4EJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lukas Sch\\\"afer, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2021-10-11T00:16:43Z","abstract_excerpt":"Deep reinforcement learning (RL) agents that exist in high-dimensional state spaces, such as those composed of images, have interconnected learning burdens. Agents must learn an action-selection policy that completes their given task, which requires them to learn a representation of the state space that discerns between useful and useless information. The reward function is the only supervised feedback that RL agents receive, which causes a representation learning bottleneck that can manifest in poor sample efficiency. We present $k$-Step Latent (KSL), a new representation learning method that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04935","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/2110.04935/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":"2026-07-05T03:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+6/Iitg0s8Rg91CGq6o9VEqpwG2djWGPcnGoj69NEXaSV2VDCajH+ofqkwS3SetnSqmCpBzQLYAH9U4JktPRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:46:20.425555Z"},"content_sha256":"01a958b8882db5c0e8528999ac4ac5eaecd4009dca07387582c6520bff23e77f","schema_version":"1.0","event_id":"sha256:01a958b8882db5c0e8528999ac4ac5eaecd4009dca07387582c6520bff23e77f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3PM3EOL4ZK4O7MWR6CBYSJ4EJF/bundle.json","state_url":"https://pith.science/pith/3PM3EOL4ZK4O7MWR6CBYSJ4EJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3PM3EOL4ZK4O7MWR6CBYSJ4EJF/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":"2026-08-01T12:46:20Z","links":{"resolver":"https://pith.science/pith/3PM3EOL4ZK4O7MWR6CBYSJ4EJF","bundle":"https://pith.science/pith/3PM3EOL4ZK4O7MWR6CBYSJ4EJF/bundle.json","state":"https://pith.science/pith/3PM3EOL4ZK4O7MWR6CBYSJ4EJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3PM3EOL4ZK4O7MWR6CBYSJ4EJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3PM3EOL4ZK4O7MWR6CBYSJ4EJF","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":"d5dd4aa538ed69a3fc021c5c494348732e93af12b25dd194589bd0ac6c9749f2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T00:16:43Z","title_canon_sha256":"16293308c288719eb92992ca93e707d3be68d446d7e7662d87fed72b23c63e41"},"schema_version":"1.0","source":{"id":"2110.04935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04935","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04935v1","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04935","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"3PM3EOL4ZK4O","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"3PM3EOL4ZK4O7MWR","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"3PM3EOL4","created_at":"2026-07-05T03:21:23Z"}],"graph_snapshots":[{"event_id":"sha256:01a958b8882db5c0e8528999ac4ac5eaecd4009dca07387582c6520bff23e77f","target":"graph","created_at":"2026-07-05T03:21:23Z","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/2110.04935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) agents that exist in high-dimensional state spaces, such as those composed of images, have interconnected learning burdens. Agents must learn an action-selection policy that completes their given task, which requires them to learn a representation of the state space that discerns between useful and useless information. The reward function is the only supervised feedback that RL agents receive, which causes a representation learning bottleneck that can manifest in poor sample efficiency. We present $k$-Step Latent (KSL), a new representation learning method that","authors_text":"Lukas Sch\\\"afer, Stefano V. Albrecht, Trevor McInroe","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T00:16:43Z","title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04935","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:c631b6e73add6cd3b6a1b7460a54585f4e0eba2188e10b9e7490d55e70bea895","target":"record","created_at":"2026-07-05T03:21:23Z","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":"d5dd4aa538ed69a3fc021c5c494348732e93af12b25dd194589bd0ac6c9749f2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T00:16:43Z","title_canon_sha256":"16293308c288719eb92992ca93e707d3be68d446d7e7662d87fed72b23c63e41"},"schema_version":"1.0","source":{"id":"2110.04935","kind":"arxiv","version":1}},"canonical_sha256":"dbd9b2397ccab8efb2d1f08389278449755c03da5eaf736ca648ad661bea75e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbd9b2397ccab8efb2d1f08389278449755c03da5eaf736ca648ad661bea75e1","first_computed_at":"2026-07-05T03:21:23.000337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:23.000337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3JzYkbznp5MoRd9DXz3k4rhiiOvBRe5CmDgmJUyPDRq9dHzgSot5UpBH0KlP6Jo+xkDX1HdRexDugboif4XoBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:23.000784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c631b6e73add6cd3b6a1b7460a54585f4e0eba2188e10b9e7490d55e70bea895","sha256:01a958b8882db5c0e8528999ac4ac5eaecd4009dca07387582c6520bff23e77f"],"state_sha256":"b449d39f6cc04bb9abc562c21303a980863b4ae11d16f76511253814c12d1e60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zpiiF9G92EQYwRvVCZXAk3T1HYOhQrEedQMeCUW/f2B/Zkp2Wsb6wqS2VMwf4QtEm98AxqRrfjLFR5bX0x9ODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T12:46:20.431108Z","bundle_sha256":"0789212987a041508f2047d87b373b1fe81168fbee2c71a1b24307d96a43bd30"}}