{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IBKMOZZHMMD6T3WSLKNNTSRHUY","short_pith_number":"pith:IBKMOZZH","canonical_record":{"source":{"id":"2307.05979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T07:51:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e453d6ce5adc132d98927cfddd437c8ca2d4947640f87871c545c1929b128ade","abstract_canon_sha256":"c8192b7501f9c5363565b35c0904a5b69ddef2e994999a5b69ca7f145ead6be1"},"schema_version":"1.0"},"canonical_sha256":"4054c767276307e9eed25a9ad9ca27a6056ffd0b0ce17ed8b9fd6a43e40b34ce","source":{"kind":"arxiv","id":"2307.05979","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05979","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05979v1","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05979","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"IBKMOZZHMMD6","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"IBKMOZZHMMD6T3WS","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"IBKMOZZH","created_at":"2026-07-05T06:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IBKMOZZHMMD6T3WSLKNNTSRHUY","target":"record","payload":{"canonical_record":{"source":{"id":"2307.05979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T07:51:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e453d6ce5adc132d98927cfddd437c8ca2d4947640f87871c545c1929b128ade","abstract_canon_sha256":"c8192b7501f9c5363565b35c0904a5b69ddef2e994999a5b69ca7f145ead6be1"},"schema_version":"1.0"},"canonical_sha256":"4054c767276307e9eed25a9ad9ca27a6056ffd0b0ce17ed8b9fd6a43e40b34ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:15.009087Z","signature_b64":"X9taKWrn4wHDYM6GX9LcgesOHR9B5sfM8WikW3oFaVYanYVQA1ZYxa2a2i6rLlsTBgj5YfYH7xgqozUG9hZFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4054c767276307e9eed25a9ad9ca27a6056ffd0b0ce17ed8b9fd6a43e40b34ce","last_reissued_at":"2026-07-05T06:30:15.008578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:15.008578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.05979","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":"2026-07-05T06:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ofqe5ihmfLH1g8f5vrSyBtcE6pa1Fw18o8icH7AXGAFbpv2jpQfD+AmxS2KoFjgHpB0wAP97PiBixMMQMpc7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:54.604925Z"},"content_sha256":"0971bc0ca26ce3fc23a7bcc7944a0aa35b504e3b1400ffcbd9bacb42ca0e4f73","schema_version":"1.0","event_id":"sha256:0971bc0ca26ce3fc23a7bcc7944a0aa35b504e3b1400ffcbd9bacb42ca0e4f73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IBKMOZZHMMD6T3WSLKNNTSRHUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers in Reinforcement Learning: A Survey","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aamer Abdul Rahman, Pierre-Luc St-Charles, Pranav Agarwal, Samira Ebrahimi Kahou, Simon J.D. Prince","submitted_at":"2023-07-12T07:51:12Z","abstract_excerpt":"Transformers have significantly impacted domains like natural language processing, computer vision, and robotics, where they improve performance compared to other neural networks. This survey explores how transformers are used in reinforcement learning (RL), where they are seen as a promising solution for addressing challenges such as unstable training, credit assignment, lack of interpretability, and partial observability. We begin by providing a brief domain overview of RL, followed by a discussion on the challenges of classical RL algorithms. Next, we delve into the properties of the transf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05979","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/2307.05979/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":"2026-07-05T06:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7EVV/pHbI2yskRm9odRq4llydjpiO3r18ZIBtJe8jpEBcvUSVJbxHukY2bwPJnTO2KxlkQo9wSR1iVQSi8FDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:54.605516Z"},"content_sha256":"53e84dbbc0603b59d3cb23dc85a3eecbd130ec7db809729dbfd0affe6283117b","schema_version":"1.0","event_id":"sha256:53e84dbbc0603b59d3cb23dc85a3eecbd130ec7db809729dbfd0affe6283117b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBKMOZZHMMD6T3WSLKNNTSRHUY/bundle.json","state_url":"https://pith.science/pith/IBKMOZZHMMD6T3WSLKNNTSRHUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBKMOZZHMMD6T3WSLKNNTSRHUY/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":"2026-08-03T19:16:54Z","links":{"resolver":"https://pith.science/pith/IBKMOZZHMMD6T3WSLKNNTSRHUY","bundle":"https://pith.science/pith/IBKMOZZHMMD6T3WSLKNNTSRHUY/bundle.json","state":"https://pith.science/pith/IBKMOZZHMMD6T3WSLKNNTSRHUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBKMOZZHMMD6T3WSLKNNTSRHUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IBKMOZZHMMD6T3WSLKNNTSRHUY","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":"c8192b7501f9c5363565b35c0904a5b69ddef2e994999a5b69ca7f145ead6be1","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T07:51:12Z","title_canon_sha256":"e453d6ce5adc132d98927cfddd437c8ca2d4947640f87871c545c1929b128ade"},"schema_version":"1.0","source":{"id":"2307.05979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05979","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05979v1","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05979","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"IBKMOZZHMMD6","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"IBKMOZZHMMD6T3WS","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"IBKMOZZH","created_at":"2026-07-05T06:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:53e84dbbc0603b59d3cb23dc85a3eecbd130ec7db809729dbfd0affe6283117b","target":"graph","created_at":"2026-07-05T06:30:15Z","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/2307.05979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers have significantly impacted domains like natural language processing, computer vision, and robotics, where they improve performance compared to other neural networks. This survey explores how transformers are used in reinforcement learning (RL), where they are seen as a promising solution for addressing challenges such as unstable training, credit assignment, lack of interpretability, and partial observability. We begin by providing a brief domain overview of RL, followed by a discussion on the challenges of classical RL algorithms. Next, we delve into the properties of the transf","authors_text":"Aamer Abdul Rahman, Pierre-Luc St-Charles, Pranav Agarwal, Samira Ebrahimi Kahou, Simon J.D. Prince","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T07:51:12Z","title":"Transformers in Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05979","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":"sha256:0971bc0ca26ce3fc23a7bcc7944a0aa35b504e3b1400ffcbd9bacb42ca0e4f73","target":"record","created_at":"2026-07-05T06:30:15Z","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":"c8192b7501f9c5363565b35c0904a5b69ddef2e994999a5b69ca7f145ead6be1","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T07:51:12Z","title_canon_sha256":"e453d6ce5adc132d98927cfddd437c8ca2d4947640f87871c545c1929b128ade"},"schema_version":"1.0","source":{"id":"2307.05979","kind":"arxiv","version":1}},"canonical_sha256":"4054c767276307e9eed25a9ad9ca27a6056ffd0b0ce17ed8b9fd6a43e40b34ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4054c767276307e9eed25a9ad9ca27a6056ffd0b0ce17ed8b9fd6a43e40b34ce","first_computed_at":"2026-07-05T06:30:15.008578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:15.008578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X9taKWrn4wHDYM6GX9LcgesOHR9B5sfM8WikW3oFaVYanYVQA1ZYxa2a2i6rLlsTBgj5YfYH7xgqozUG9hZFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:15.009087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.05979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0971bc0ca26ce3fc23a7bcc7944a0aa35b504e3b1400ffcbd9bacb42ca0e4f73","sha256:53e84dbbc0603b59d3cb23dc85a3eecbd130ec7db809729dbfd0affe6283117b"],"state_sha256":"ad8e72bd11165e74ca2f67a7f9342a02e64b5290347649b944af49b9f91ad2f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JYhNLvYKT5wGaLXukEuzsHgh7qmXh401xhlOrS82a2Auz3cxd5ZBLD4IYNJIlS9H4cmAJ3Bv08vXhhRnheRzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:16:54.610217Z","bundle_sha256":"d2c27750e9b8ad3c098bcac8ea6d97f765495d327d4f56a237f4cfd172deb108"}}