{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PV7ZDPVRC6K3GG7TL7SRBPY4C6","short_pith_number":"pith:PV7ZDPVR","canonical_record":{"source":{"id":"2106.01345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T17:53:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d58b305c53587d7a9b6b1e2d8667ae06316c83902a379f04d430a4f54999fd3c","abstract_canon_sha256":"ebd4efdd11afc5ee56f305abfbfac56bdbde63bbd62f5b7039ff8e2b3470b4f7"},"schema_version":"1.0"},"canonical_sha256":"7d7f91beb11795b31bf35fe510bf1c1798956522c752091587724771682b3323","source":{"kind":"arxiv","id":"2106.01345","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01345","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01345v2","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01345","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"PV7ZDPVRC6K3","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"PV7ZDPVRC6K3GG7T","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"PV7ZDPVR","created_at":"2026-05-18T15:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PV7ZDPVRC6K3GG7TL7SRBPY4C6","target":"record","payload":{"canonical_record":{"source":{"id":"2106.01345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T17:53:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d58b305c53587d7a9b6b1e2d8667ae06316c83902a379f04d430a4f54999fd3c","abstract_canon_sha256":"ebd4efdd11afc5ee56f305abfbfac56bdbde63bbd62f5b7039ff8e2b3470b4f7"},"schema_version":"1.0"},"canonical_sha256":"7d7f91beb11795b31bf35fe510bf1c1798956522c752091587724771682b3323","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T15:05:26.331147Z","signature_b64":"SuKb+d0EFs3k+FC1YLCO3kdih6Z0LD4YETGvHY5+UVIo7XjvT1Q0y9EUwbJrjEJ3bEqJFrOaDi5jmENa/YkpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d7f91beb11795b31bf35fe510bf1c1798956522c752091587724771682b3323","last_reissued_at":"2026-05-18T15:05:26.328089Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T15:05:26.328089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.01345","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":"2026-05-18T15:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftvlo0heCeFnLRR4WZ42NlnIMdrbXjlUONT/bUVeiEMBqokhUXJMyNf8KUiVu3Tvds3FsFIl+dJ5Bcf6C6zGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:37:46.280882Z"},"content_sha256":"56a825b3c309854f869c7763804409ab88c5e2f31a0c8ba42e7e9c6d55f5dfb9","schema_version":"1.0","event_id":"sha256:56a825b3c309854f869c7763804409ab88c5e2f31a0c8ba42e7e9c6d55f5dfb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PV7ZDPVRC6K3GG7TL7SRBPY4C6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Grover, Aravind Rajeswaran, Aravind Srinivas, Igor Mordatch, Kevin Lu, Kimin Lee, Lili Chen, Michael Laskin, Pieter Abbeel","submitted_at":"2021-06-02T17:53:39Z","abstract_excerpt":"We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01345","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":""},"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":"2026-05-18T15:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0w0uOLnCz+L9jSgKuo9usLjTX0iCP/4l8TQV2xJqJnU0pSdgl6HGXgaUghsH7h3nlH8uLIApbGUDkQrkOLC7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:37:46.281541Z"},"content_sha256":"1284139a45d3fc8fde77b6e8ee21fb72b974ecf825942bd92eb049ba93af2e0d","schema_version":"1.0","event_id":"sha256:1284139a45d3fc8fde77b6e8ee21fb72b974ecf825942bd92eb049ba93af2e0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PV7ZDPVRC6K3GG7TL7SRBPY4C6/bundle.json","state_url":"https://pith.science/pith/PV7ZDPVRC6K3GG7TL7SRBPY4C6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PV7ZDPVRC6K3GG7TL7SRBPY4C6/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":"2026-05-21T13:37:46Z","links":{"resolver":"https://pith.science/pith/PV7ZDPVRC6K3GG7TL7SRBPY4C6","bundle":"https://pith.science/pith/PV7ZDPVRC6K3GG7TL7SRBPY4C6/bundle.json","state":"https://pith.science/pith/PV7ZDPVRC6K3GG7TL7SRBPY4C6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PV7ZDPVRC6K3GG7TL7SRBPY4C6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PV7ZDPVRC6K3GG7TL7SRBPY4C6","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":"ebd4efdd11afc5ee56f305abfbfac56bdbde63bbd62f5b7039ff8e2b3470b4f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T17:53:39Z","title_canon_sha256":"d58b305c53587d7a9b6b1e2d8667ae06316c83902a379f04d430a4f54999fd3c"},"schema_version":"1.0","source":{"id":"2106.01345","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01345","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01345v2","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01345","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"PV7ZDPVRC6K3","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"PV7ZDPVRC6K3GG7T","created_at":"2026-05-18T15:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"PV7ZDPVR","created_at":"2026-05-18T15:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:1284139a45d3fc8fde77b6e8ee21fb72b974ecf825942bd92eb049ba93af2e0d","target":"graph","created_at":"2026-05-18T15:05:26Z","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"},"paper":{"abstract_excerpt":"We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregr","authors_text":"Aditya Grover, Aravind Rajeswaran, Aravind Srinivas, Igor Mordatch, Kevin Lu, Kimin Lee, Lili Chen, Michael Laskin, Pieter Abbeel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T17:53:39Z","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01345","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":"sha256:56a825b3c309854f869c7763804409ab88c5e2f31a0c8ba42e7e9c6d55f5dfb9","target":"record","created_at":"2026-05-18T15:05:26Z","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":"ebd4efdd11afc5ee56f305abfbfac56bdbde63bbd62f5b7039ff8e2b3470b4f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T17:53:39Z","title_canon_sha256":"d58b305c53587d7a9b6b1e2d8667ae06316c83902a379f04d430a4f54999fd3c"},"schema_version":"1.0","source":{"id":"2106.01345","kind":"arxiv","version":2}},"canonical_sha256":"7d7f91beb11795b31bf35fe510bf1c1798956522c752091587724771682b3323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d7f91beb11795b31bf35fe510bf1c1798956522c752091587724771682b3323","first_computed_at":"2026-05-18T15:05:26.328089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T15:05:26.328089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SuKb+d0EFs3k+FC1YLCO3kdih6Z0LD4YETGvHY5+UVIo7XjvT1Q0y9EUwbJrjEJ3bEqJFrOaDi5jmENa/YkpAg==","signature_status":"signed_v1","signed_at":"2026-05-18T15:05:26.331147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.01345","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56a825b3c309854f869c7763804409ab88c5e2f31a0c8ba42e7e9c6d55f5dfb9","sha256:1284139a45d3fc8fde77b6e8ee21fb72b974ecf825942bd92eb049ba93af2e0d"],"state_sha256":"04ce6539b0c5517fded878a7a1046d21981e5982375ed37c13bfc6d747c891fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VMCq80zUbF9OLDC9deT1vIh1cMzjnUWzGpdT5pGF4nfLd0a4cpnWZNlKgvbhBbK848ekRtyLwcqt0ixRNORtCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T13:37:46.284851Z","bundle_sha256":"fb0e596f1f07b23d33e2ef9f66093f46dec3355565c02cdefeb7dde39842f8cf"}}