{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FHZQFG5XIT2N24E5IGCJ6UU4QO","short_pith_number":"pith:FHZQFG5X","canonical_record":{"source":{"id":"2111.12600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-24T16:19:59Z","cross_cats_sorted":[],"title_canon_sha256":"470b4e4cbc67224db832da7cf9ea7e05728a4d6c15039676f535ac652bc31706","abstract_canon_sha256":"12b0dfab94fff4ef3fd8dda9a465381ea0af7dc32baa384105940e03cb5828dd"},"schema_version":"1.0"},"canonical_sha256":"29f3029bb744f4dd709d41849f529c83a9d5dbcfa756390f648e612d3cd84243","source":{"kind":"arxiv","id":"2111.12600","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12600","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12600v2","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12600","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"pith_short_12","alias_value":"FHZQFG5XIT2N","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"pith_short_16","alias_value":"FHZQFG5XIT2N24E5","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"pith_short_8","alias_value":"FHZQFG5X","created_at":"2026-07-05T05:00:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FHZQFG5XIT2N24E5IGCJ6UU4QO","target":"record","payload":{"canonical_record":{"source":{"id":"2111.12600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-24T16:19:59Z","cross_cats_sorted":[],"title_canon_sha256":"470b4e4cbc67224db832da7cf9ea7e05728a4d6c15039676f535ac652bc31706","abstract_canon_sha256":"12b0dfab94fff4ef3fd8dda9a465381ea0af7dc32baa384105940e03cb5828dd"},"schema_version":"1.0"},"canonical_sha256":"29f3029bb744f4dd709d41849f529c83a9d5dbcfa756390f648e612d3cd84243","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:14.592663Z","signature_b64":"48dqB7jok2p+fp8WtH3ilH9TsvwA+Euxqlz9eZPwRDw0hLMzXw9KOJ+NLkQtmMV7CHLRqCr5Knw2lcoddMSaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29f3029bb744f4dd709d41849f529c83a9d5dbcfa756390f648e612d3cd84243","last_reissued_at":"2026-07-05T05:00:14.592238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:14.592238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.12600","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:00:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZxH6wnoCCHtNk+CEMZ4733ThDSCPXDPSSZs6FqBYkiY2voJwkDY/NtYycDLt6N5mYCjGaEtmjnq1XXl8k3jWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:23:48.803477Z"},"content_sha256":"f68efea995919487a2570aefb2000dfc1b5558ddd913b4493a2f77e2dbdbae64","schema_version":"1.0","event_id":"sha256:f68efea995919487a2570aefb2000dfc1b5558ddd913b4493a2f77e2dbdbae64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FHZQFG5XIT2N24E5IGCJ6UU4QO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning State Representations via Retracing in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changmin Yu, Dong Li, Jianye Hao, Jun Wang, Neil Burgess","submitted_at":"2021-11-24T16:19:59Z","abstract_excerpt":"We propose learning via retracing, a novel self-supervised approach for learning the state representation (and the associated dynamics model) for reinforcement learning tasks. In addition to the predictive (reconstruction) supervision in the forward direction, we propose to include \"retraced\" transitions for representation / model learning, by enforcing the cycle-consistency constraint between the original and retraced states, hence improve upon the sample efficiency of learning. Moreover, learning via retracing explicitly propagates information about future transitions backward for inferring "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12600","kind":"arxiv","version":2},"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/2111.12600/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":"2026-07-05T05:00:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7YJfHh+eX0ZAfYAGO7YCwHZH83i0ozyDoqAe89HZi0GGPudWeRl1oqtHaRZ8ttZ2UDWFc6UiaibF1E03WSbqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:23:48.804233Z"},"content_sha256":"045ec966251b951928e029d8f3144ec9fc248e289077abca986419624b3b4864","schema_version":"1.0","event_id":"sha256:045ec966251b951928e029d8f3144ec9fc248e289077abca986419624b3b4864"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHZQFG5XIT2N24E5IGCJ6UU4QO/bundle.json","state_url":"https://pith.science/pith/FHZQFG5XIT2N24E5IGCJ6UU4QO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHZQFG5XIT2N24E5IGCJ6UU4QO/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":"2026-08-05T17:23:48Z","links":{"resolver":"https://pith.science/pith/FHZQFG5XIT2N24E5IGCJ6UU4QO","bundle":"https://pith.science/pith/FHZQFG5XIT2N24E5IGCJ6UU4QO/bundle.json","state":"https://pith.science/pith/FHZQFG5XIT2N24E5IGCJ6UU4QO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHZQFG5XIT2N24E5IGCJ6UU4QO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FHZQFG5XIT2N24E5IGCJ6UU4QO","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":"12b0dfab94fff4ef3fd8dda9a465381ea0af7dc32baa384105940e03cb5828dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-24T16:19:59Z","title_canon_sha256":"470b4e4cbc67224db832da7cf9ea7e05728a4d6c15039676f535ac652bc31706"},"schema_version":"1.0","source":{"id":"2111.12600","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12600","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12600v2","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12600","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"pith_short_12","alias_value":"FHZQFG5XIT2N","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"pith_short_16","alias_value":"FHZQFG5XIT2N24E5","created_at":"2026-07-05T05:00:14Z"},{"alias_kind":"pith_short_8","alias_value":"FHZQFG5X","created_at":"2026-07-05T05:00:14Z"}],"graph_snapshots":[{"event_id":"sha256:045ec966251b951928e029d8f3144ec9fc248e289077abca986419624b3b4864","target":"graph","created_at":"2026-07-05T05:00:14Z","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/2111.12600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose learning via retracing, a novel self-supervised approach for learning the state representation (and the associated dynamics model) for reinforcement learning tasks. In addition to the predictive (reconstruction) supervision in the forward direction, we propose to include \"retraced\" transitions for representation / model learning, by enforcing the cycle-consistency constraint between the original and retraced states, hence improve upon the sample efficiency of learning. Moreover, learning via retracing explicitly propagates information about future transitions backward for inferring ","authors_text":"Changmin Yu, Dong Li, Jianye Hao, Jun Wang, Neil Burgess","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-24T16:19:59Z","title":"Learning State Representations via Retracing in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12600","kind":"arxiv","version":2},"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:f68efea995919487a2570aefb2000dfc1b5558ddd913b4493a2f77e2dbdbae64","target":"record","created_at":"2026-07-05T05:00:14Z","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":"12b0dfab94fff4ef3fd8dda9a465381ea0af7dc32baa384105940e03cb5828dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-24T16:19:59Z","title_canon_sha256":"470b4e4cbc67224db832da7cf9ea7e05728a4d6c15039676f535ac652bc31706"},"schema_version":"1.0","source":{"id":"2111.12600","kind":"arxiv","version":2}},"canonical_sha256":"29f3029bb744f4dd709d41849f529c83a9d5dbcfa756390f648e612d3cd84243","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29f3029bb744f4dd709d41849f529c83a9d5dbcfa756390f648e612d3cd84243","first_computed_at":"2026-07-05T05:00:14.592238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:00:14.592238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"48dqB7jok2p+fp8WtH3ilH9TsvwA+Euxqlz9eZPwRDw0hLMzXw9KOJ+NLkQtmMV7CHLRqCr5Knw2lcoddMSaAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:00:14.592663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12600","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f68efea995919487a2570aefb2000dfc1b5558ddd913b4493a2f77e2dbdbae64","sha256:045ec966251b951928e029d8f3144ec9fc248e289077abca986419624b3b4864"],"state_sha256":"252436df34bfbd2dfcd1ff7022a524865821030854db4006ec412c40d980e815"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nbpT43aiXI99Tpws+h6dXOrLaWRuIWVqx6O2YWA2hqcDM89Yz0VlXx5w3cgUuw2P5vf5f92dZANNX9PDP/jfDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:23:48.812678Z","bundle_sha256":"9e6db2e2b883d44c686eec8d54f32f538604b65867efb49c3fb7d3adb87a823d"}}