{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AJBQR2QJALQE3XPIIERBTGSAYM","short_pith_number":"pith:AJBQR2QJ","canonical_record":{"source":{"id":"2303.03747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T09:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a1db06dec82fe18e4e2bdab920a659d3c979e3065571d73b6fb9c0539830bf4","abstract_canon_sha256":"f7a3762b67d8d8471ee1d323b3655d08409eb3e7ce885feb02be84d816518e0a"},"schema_version":"1.0"},"canonical_sha256":"024308ea0902e04ddde84122199a40c324ef1371c7240663fbb5baa1e8d6784b","source":{"kind":"arxiv","id":"2303.03747","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03747","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03747v1","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03747","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"AJBQR2QJALQE","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"pith_short_16","alias_value":"AJBQR2QJALQE3XPI","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"pith_short_8","alias_value":"AJBQR2QJ","created_at":"2026-07-05T05:48:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AJBQR2QJALQE3XPIIERBTGSAYM","target":"record","payload":{"canonical_record":{"source":{"id":"2303.03747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T09:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a1db06dec82fe18e4e2bdab920a659d3c979e3065571d73b6fb9c0539830bf4","abstract_canon_sha256":"f7a3762b67d8d8471ee1d323b3655d08409eb3e7ce885feb02be84d816518e0a"},"schema_version":"1.0"},"canonical_sha256":"024308ea0902e04ddde84122199a40c324ef1371c7240663fbb5baa1e8d6784b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:58.689580Z","signature_b64":"Tw2+a9zTEbQouiS2HEsAB/xcSTLwLb8MDJTPNJ+8oucZvO3fft5mHO3hePcAxCSuKVM6JJKxPK920RFZEKtnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"024308ea0902e04ddde84122199a40c324ef1371c7240663fbb5baa1e8d6784b","last_reissued_at":"2026-07-05T05:48:58.689080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:58.689080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.03747","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":"2026-07-05T05:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"igiZsg1+erWppr0cz1Y1ME5hd+NAfCPK4728wQdXBK/v3J70LBEB13DEv5m8DKbOYO6VBlA5bCrQJOhzajvFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:40:36.276143Z"},"content_sha256":"3b341845be80196b703dc6934e18d702a74d7c4f8bd5cbee6c610b3b7d778347","schema_version":"1.0","event_id":"sha256:3b341845be80196b703dc6934e18d702a74d7c4f8bd5cbee6c610b3b7d778347"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AJBQR2QJALQE3XPIIERBTGSAYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph Decision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Li Shen, Shengchao Hu, Ya Zhang","submitted_at":"2023-03-07T09:10:34Z","abstract_excerpt":"Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment. Recently, offline RL has been viewed as a sequence modeling problem, where an agent generates a sequence of subsequent actions based on a set of static transition experiences. However, existing approaches that use transformers to attend to all tokens naively can overlook the dependencies between different tokens and limit long-term dependency learning. In this paper, we propose the Graph Decision Transformer (GDT), a novel offline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03747","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/2303.03747/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":"2026-07-05T05:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P5hlSH0qxi84Ut3BDL9yHJJNdTUx9jmfxl8s9DrmiqohD8g1Toi+szxFT7VVc9Vaepu4C02f5DWCLenW4an/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:40:36.276651Z"},"content_sha256":"9949b6d166272a6977d8f195a71b884d03fca26385f0036342f209407cb260e2","schema_version":"1.0","event_id":"sha256:9949b6d166272a6977d8f195a71b884d03fca26385f0036342f209407cb260e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/bundle.json","state_url":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJBQR2QJALQE3XPIIERBTGSAYM/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":"2026-08-08T17:40:36Z","links":{"resolver":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM","bundle":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/bundle.json","state":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJBQR2QJALQE3XPIIERBTGSAYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AJBQR2QJALQE3XPIIERBTGSAYM","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":"f7a3762b67d8d8471ee1d323b3655d08409eb3e7ce885feb02be84d816518e0a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T09:10:34Z","title_canon_sha256":"7a1db06dec82fe18e4e2bdab920a659d3c979e3065571d73b6fb9c0539830bf4"},"schema_version":"1.0","source":{"id":"2303.03747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03747","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03747v1","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03747","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"AJBQR2QJALQE","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"pith_short_16","alias_value":"AJBQR2QJALQE3XPI","created_at":"2026-07-05T05:48:58Z"},{"alias_kind":"pith_short_8","alias_value":"AJBQR2QJ","created_at":"2026-07-05T05:48:58Z"}],"graph_snapshots":[{"event_id":"sha256:9949b6d166272a6977d8f195a71b884d03fca26385f0036342f209407cb260e2","target":"graph","created_at":"2026-07-05T05:48:58Z","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/2303.03747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment. Recently, offline RL has been viewed as a sequence modeling problem, where an agent generates a sequence of subsequent actions based on a set of static transition experiences. However, existing approaches that use transformers to attend to all tokens naively can overlook the dependencies between different tokens and limit long-term dependency learning. In this paper, we propose the Graph Decision Transformer (GDT), a novel offline","authors_text":"Dacheng Tao, Li Shen, Shengchao Hu, Ya Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T09:10:34Z","title":"Graph Decision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03747","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":"sha256:3b341845be80196b703dc6934e18d702a74d7c4f8bd5cbee6c610b3b7d778347","target":"record","created_at":"2026-07-05T05:48:58Z","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":"f7a3762b67d8d8471ee1d323b3655d08409eb3e7ce885feb02be84d816518e0a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T09:10:34Z","title_canon_sha256":"7a1db06dec82fe18e4e2bdab920a659d3c979e3065571d73b6fb9c0539830bf4"},"schema_version":"1.0","source":{"id":"2303.03747","kind":"arxiv","version":1}},"canonical_sha256":"024308ea0902e04ddde84122199a40c324ef1371c7240663fbb5baa1e8d6784b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"024308ea0902e04ddde84122199a40c324ef1371c7240663fbb5baa1e8d6784b","first_computed_at":"2026-07-05T05:48:58.689080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:58.689080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tw2+a9zTEbQouiS2HEsAB/xcSTLwLb8MDJTPNJ+8oucZvO3fft5mHO3hePcAxCSuKVM6JJKxPK920RFZEKtnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:58.689580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.03747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b341845be80196b703dc6934e18d702a74d7c4f8bd5cbee6c610b3b7d778347","sha256:9949b6d166272a6977d8f195a71b884d03fca26385f0036342f209407cb260e2"],"state_sha256":"4c155bc298aa28045dea566e3c7a790815b54322986a405972bcd8f0953fda94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2KCy50jXzzYc22SKSv2xEywsl1h0++Xt0oApD1CYKXNZ0LSmYs5OlezK2fGfxPgwTK62y5hAvf/WC/niNvzFCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:40:36.280466Z","bundle_sha256":"4a4005db65a10f413c410e8bd71f68649386edcd8c90072e4a806e3e8a0c10b9"}}