{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QGKIYCCQ6RWW6LFNTVBFLLZB2G","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":"88b2d2ac9f082f2e468bd6d2586ea8e96fd797dac343b501bfb052c9c3a99d40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:12:39Z","title_canon_sha256":"d7cabd4239a8691bd17baffc2681f45e3bce6a5732880d34bad62925a2b847c3"},"schema_version":"1.0","source":{"id":"2405.17098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17098","created_at":"2026-07-05T08:23:39Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17098v1","created_at":"2026-07-05T08:23:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17098","created_at":"2026-07-05T08:23:39Z"},{"alias_kind":"pith_short_12","alias_value":"QGKIYCCQ6RWW","created_at":"2026-07-05T08:23:39Z"},{"alias_kind":"pith_short_16","alias_value":"QGKIYCCQ6RWW6LFN","created_at":"2026-07-05T08:23:39Z"},{"alias_kind":"pith_short_8","alias_value":"QGKIYCCQ","created_at":"2026-07-05T08:23:39Z"}],"graph_snapshots":[{"event_id":"sha256:104fcda2833d18fd79c71040a57b1807a82a084e0f369294be8c482a1eeefcea","target":"graph","created_at":"2026-07-05T08:23:39Z","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/2405.17098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action distribution based on history trajectory and target returns for each state. However, these methods often struggle with stitching together optimal trajectories from sub-optimal ones due to the inconsistency between the sampled returns within individual trajectories and the optimal returns across multiple trajectories. Fortunately, Dynamic Programming (DP) methods offer a solution by leveraging a value function to approximate optim","authors_text":"Chaoqin Huang, Dacheng Tao, Li Shen, Shengchao Hu, Yanfeng Wang, Ya Zhang, Ziqing Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:12:39Z","title":"Q-value Regularized Transformer for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17098","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":"sha256:27a168e97408d4d0781419d89b18ecf846fd85a66a9afe3df3a8a6d360bd1d9f","target":"record","created_at":"2026-07-05T08:23:39Z","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":"88b2d2ac9f082f2e468bd6d2586ea8e96fd797dac343b501bfb052c9c3a99d40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:12:39Z","title_canon_sha256":"d7cabd4239a8691bd17baffc2681f45e3bce6a5732880d34bad62925a2b847c3"},"schema_version":"1.0","source":{"id":"2405.17098","kind":"arxiv","version":1}},"canonical_sha256":"81948c0850f46d6f2cad9d4255af21d1bffd3f601cb8410f5e45af7909835241","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81948c0850f46d6f2cad9d4255af21d1bffd3f601cb8410f5e45af7909835241","first_computed_at":"2026-07-05T08:23:39.856812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:39.856812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zG4jPyjAFQ8kogidXI6K81O0G9ftcG9YVbOcXcIstw+lASK0U2bT0lGey2JpFm5D7FS8nEk6d5ilmDHV4GYpDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:39.857304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27a168e97408d4d0781419d89b18ecf846fd85a66a9afe3df3a8a6d360bd1d9f","sha256:104fcda2833d18fd79c71040a57b1807a82a084e0f369294be8c482a1eeefcea"],"state_sha256":"1e93a8a59926a3afb59dfe6c9c3f017b1620ae5ba6a32d1b36b8aa6caad4fd8c"}