{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RYO4WEN2TERQIFE3QUEVV45XD6","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":"7b647bf069cb17a3bc5683514ac4aee0fc724cb677c79af60d6f5dd434c216dd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-29T03:15:59Z","title_canon_sha256":"69a347c0f3e2ada342015382a27bc35a98179cd983ed65ddb37c8bb733c83a18"},"schema_version":"1.0","source":{"id":"2212.14164","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14164","created_at":"2026-07-05T05:34:51Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14164v2","created_at":"2026-07-05T05:34:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14164","created_at":"2026-07-05T05:34:51Z"},{"alias_kind":"pith_short_12","alias_value":"RYO4WEN2TERQ","created_at":"2026-07-05T05:34:51Z"},{"alias_kind":"pith_short_16","alias_value":"RYO4WEN2TERQIFE3","created_at":"2026-07-05T05:34:51Z"},{"alias_kind":"pith_short_8","alias_value":"RYO4WEN2","created_at":"2026-07-05T05:34:51Z"}],"graph_snapshots":[{"event_id":"sha256:efcb5872fa640918f55dbd32c7e13450c4233c47eec0fc31b7ce1557ff7cc790","target":"graph","created_at":"2026-07-05T05:34:51Z","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/2212.14164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement learning (RL) and the transformer-based models have manifested their potential in representative RL benchmarks. In this paper, we collect and dissect recent advances on transforming RL by transformer (transformer-based RL or TRL), in order to explore its development trajectory and future trend. We group existing developments in two categories: architecture enhan","authors_text":"Dacheng Tao, Li Shen, Shengchao Hu, Ya Zhang, Yixin Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-29T03:15:59Z","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14164","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":"sha256:542ca5eaf473152fe3e75d8fc50827b3335714eac33b3bab2bdd582d9ed669bf","target":"record","created_at":"2026-07-05T05:34:51Z","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":"7b647bf069cb17a3bc5683514ac4aee0fc724cb677c79af60d6f5dd434c216dd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-29T03:15:59Z","title_canon_sha256":"69a347c0f3e2ada342015382a27bc35a98179cd983ed65ddb37c8bb733c83a18"},"schema_version":"1.0","source":{"id":"2212.14164","kind":"arxiv","version":2}},"canonical_sha256":"8e1dcb11ba992304149b85095af3b71f898a1b5dd8929e44804aac1d140014ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e1dcb11ba992304149b85095af3b71f898a1b5dd8929e44804aac1d140014ac","first_computed_at":"2026-07-05T05:34:51.073079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:34:51.073079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/J45QGEyioU92MQK4SP7BOZeVAb4uweQK1bZFtbytnfvUPnv4lytcmKb97jyeZq8S4cdRlEb6XhBqg1WhTMkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:34:51.073577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.14164","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:542ca5eaf473152fe3e75d8fc50827b3335714eac33b3bab2bdd582d9ed669bf","sha256:efcb5872fa640918f55dbd32c7e13450c4233c47eec0fc31b7ce1557ff7cc790"],"state_sha256":"65d35eafbe468c43a6487614e492231ba496fa8e2475db9e90012799dee0db34"}