{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3KHNNSQVSC25SEXPZVRN2P3IIK","short_pith_number":"pith:3KHNNSQV","canonical_record":{"source":{"id":"2411.11327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T06:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"b703ba420172582f9086c17ba0b8e0243a1edfba3a13b98c3a76fb61b955c845","abstract_canon_sha256":"07f46fff93dd7ab03f48c02034c15b8f474c01a387e3f3d24587c2596a14efc1"},"schema_version":"1.0"},"canonical_sha256":"da8ed6ca1590b5d912efcd62dd3f6842a07ec301ac2f67581fad490fa219d34d","source":{"kind":"arxiv","id":"2411.11327","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11327","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11327v1","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11327","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"3KHNNSQVSC25","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"3KHNNSQVSC25SEXP","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"3KHNNSQV","created_at":"2026-07-05T09:36:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3KHNNSQVSC25SEXPZVRN2P3IIK","target":"record","payload":{"canonical_record":{"source":{"id":"2411.11327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T06:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"b703ba420172582f9086c17ba0b8e0243a1edfba3a13b98c3a76fb61b955c845","abstract_canon_sha256":"07f46fff93dd7ab03f48c02034c15b8f474c01a387e3f3d24587c2596a14efc1"},"schema_version":"1.0"},"canonical_sha256":"da8ed6ca1590b5d912efcd62dd3f6842a07ec301ac2f67581fad490fa219d34d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:54.673760Z","signature_b64":"dOdSpTmaLBFfzboDoTKV8UNHVlbhmWPyCy/fLYBeI/BTNfW9bLmFhsEjvVdOdJeT06U7VsFJyHTmSIgkGd5qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da8ed6ca1590b5d912efcd62dd3f6842a07ec301ac2f67581fad490fa219d34d","last_reissued_at":"2026-07-05T09:36:54.673292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:54.673292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.11327","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":"2026-07-05T09:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"35vhBpBefHZEjx9uukZs5d4Q+9268qL4DYVsWWzI9mGFxLfgz2tE8T5Vei30zty2DGuH26uS6su2gMZthTiWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:18:37.124799Z"},"content_sha256":"3af8be135d05f800bbc64fbb4ade6cffadc4bff2970665665163593f8fce4b95","schema_version":"1.0","event_id":"sha256:3af8be135d05f800bbc64fbb4ade6cffadc4bff2970665665163593f8fce4b95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3KHNNSQVSC25SEXPZVRN2P3IIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lipeng Wan, Long Qian, Xingyu Chen, Xuguang Lan, Zeyang Liu, Zhihong Liu","submitted_at":"2024-11-18T06:44:14Z","abstract_excerpt":"Decision Transformer (DT) can learn effective policy from offline datasets by converting the offline reinforcement learning (RL) into a supervised sequence modeling task, where the trajectory elements are generated auto-regressively conditioned on the return-to-go (RTG).However, the sequence modeling learning approach tends to learn policies that converge on the sub-optimal trajectories within the dataset, for lack of bridging data to move to better trajectories, even if the condition is set to the highest RTG.To address this issue, we introduce Diffusion-Based Trajectory Branch Generation (BG"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11327","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/2411.11327/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":"2026-07-05T09:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZTmzC6lCF2RhUjhY7f9alZmM2fpHpgXOoV3XT60bp7PteA8+YJ5OVi6kuATXR/PuzTraM7LGhG2LkYKXhmVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:18:37.125167Z"},"content_sha256":"fa24c2e9c04e7322345de418be867287f687f1ac8f02aa7a99bffa2fb94d0d62","schema_version":"1.0","event_id":"sha256:fa24c2e9c04e7322345de418be867287f687f1ac8f02aa7a99bffa2fb94d0d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3KHNNSQVSC25SEXPZVRN2P3IIK/bundle.json","state_url":"https://pith.science/pith/3KHNNSQVSC25SEXPZVRN2P3IIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3KHNNSQVSC25SEXPZVRN2P3IIK/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":"2026-07-06T23:18:37Z","links":{"resolver":"https://pith.science/pith/3KHNNSQVSC25SEXPZVRN2P3IIK","bundle":"https://pith.science/pith/3KHNNSQVSC25SEXPZVRN2P3IIK/bundle.json","state":"https://pith.science/pith/3KHNNSQVSC25SEXPZVRN2P3IIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3KHNNSQVSC25SEXPZVRN2P3IIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3KHNNSQVSC25SEXPZVRN2P3IIK","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":"07f46fff93dd7ab03f48c02034c15b8f474c01a387e3f3d24587c2596a14efc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T06:44:14Z","title_canon_sha256":"b703ba420172582f9086c17ba0b8e0243a1edfba3a13b98c3a76fb61b955c845"},"schema_version":"1.0","source":{"id":"2411.11327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11327","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11327v1","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11327","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"3KHNNSQVSC25","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"3KHNNSQVSC25SEXP","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"3KHNNSQV","created_at":"2026-07-05T09:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:fa24c2e9c04e7322345de418be867287f687f1ac8f02aa7a99bffa2fb94d0d62","target":"graph","created_at":"2026-07-05T09:36:54Z","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/2411.11327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decision Transformer (DT) can learn effective policy from offline datasets by converting the offline reinforcement learning (RL) into a supervised sequence modeling task, where the trajectory elements are generated auto-regressively conditioned on the return-to-go (RTG).However, the sequence modeling learning approach tends to learn policies that converge on the sub-optimal trajectories within the dataset, for lack of bridging data to move to better trajectories, even if the condition is set to the highest RTG.To address this issue, we introduce Diffusion-Based Trajectory Branch Generation (BG","authors_text":"Lipeng Wan, Long Qian, Xingyu Chen, Xuguang Lan, Zeyang Liu, Zhihong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T06:44:14Z","title":"Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11327","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":"sha256:3af8be135d05f800bbc64fbb4ade6cffadc4bff2970665665163593f8fce4b95","target":"record","created_at":"2026-07-05T09:36:54Z","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":"07f46fff93dd7ab03f48c02034c15b8f474c01a387e3f3d24587c2596a14efc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T06:44:14Z","title_canon_sha256":"b703ba420172582f9086c17ba0b8e0243a1edfba3a13b98c3a76fb61b955c845"},"schema_version":"1.0","source":{"id":"2411.11327","kind":"arxiv","version":1}},"canonical_sha256":"da8ed6ca1590b5d912efcd62dd3f6842a07ec301ac2f67581fad490fa219d34d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da8ed6ca1590b5d912efcd62dd3f6842a07ec301ac2f67581fad490fa219d34d","first_computed_at":"2026-07-05T09:36:54.673292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:54.673292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOdSpTmaLBFfzboDoTKV8UNHVlbhmWPyCy/fLYBeI/BTNfW9bLmFhsEjvVdOdJeT06U7VsFJyHTmSIgkGd5qBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:54.673760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3af8be135d05f800bbc64fbb4ade6cffadc4bff2970665665163593f8fce4b95","sha256:fa24c2e9c04e7322345de418be867287f687f1ac8f02aa7a99bffa2fb94d0d62"],"state_sha256":"cb9722f517125217dcc961aac9f7f6a5dd404f91b2a07221e69a62e7adee15e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qJQFGk5FaiD+fZkkRquCUnZC6SV7VVlFFXl2q1QB6Twjid0PqisaB+CHOFZaxpQE5MO9bUnG3a0CH+d5gBfXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:18:37.127344Z","bundle_sha256":"bb96f9831a5c0f3c40bf063b3f6d742d70c18a649ea692a94b84bb33ae64eff0"}}