{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GCQDM5WNIMHJDDQDCCV5ESKUR3","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":"0341fbe98414d335b0167fb8b9f1bfbf102bc1c1cfa470768fef594f8420b897","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T08:08:18Z","title_canon_sha256":"aa6f6e04d83f0550a2fcce8abee224457917bac413aa3a564a9e0f05c6ba7048"},"schema_version":"1.0","source":{"id":"2507.15356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15356","created_at":"2026-07-05T11:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15356v1","created_at":"2026-07-05T11:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15356","created_at":"2026-07-05T11:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"GCQDM5WNIMHJ","created_at":"2026-07-05T11:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"GCQDM5WNIMHJDDQD","created_at":"2026-07-05T11:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"GCQDM5WN","created_at":"2026-07-05T11:40:23Z"}],"graph_snapshots":[{"event_id":"sha256:7dce9b886e006fd50cac8852a87626af790595051ffcf29df5d105072e46bf18","target":"graph","created_at":"2026-07-05T11:40:23Z","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/2507.15356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) enables agents to learn policies from fixed datasets, avoiding costly or unsafe environment interactions. However, its effectiveness is often limited by dataset sparsity and the lack of transition overlap between suboptimal and expert trajectories, which makes long-horizon planning particularly challenging. Prior solutions based on synthetic data augmentation or trajectory stitching often fail to generalize to novel states and rely on heuristic stitching points. To address these challenges, we propose Retrieval High-quAlity Demonstrations (RAD) for decision-","authors_text":"Lichang Song, Lu Guo, Qifan Liang, Ting Long, Weinan Zhang, Yi Chang, Yixiang Shan, Zhengbang Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T08:08:18Z","title":"RAD: Retrieval High-quality Demonstrations to Enhance Decision-making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15356","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":"sha256:0182c7e084b127c2c3fa02b4d0f8e9e1d79d259f21c99f2b8b16910ba9fad18a","target":"record","created_at":"2026-07-05T11:40:23Z","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":"0341fbe98414d335b0167fb8b9f1bfbf102bc1c1cfa470768fef594f8420b897","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T08:08:18Z","title_canon_sha256":"aa6f6e04d83f0550a2fcce8abee224457917bac413aa3a564a9e0f05c6ba7048"},"schema_version":"1.0","source":{"id":"2507.15356","kind":"arxiv","version":1}},"canonical_sha256":"30a03676cd430e918e0310abd249548ed78ac2343fb75c3db494f20f31c56dfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30a03676cd430e918e0310abd249548ed78ac2343fb75c3db494f20f31c56dfa","first_computed_at":"2026-07-05T11:40:23.262173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:23.262173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rQ67cDRt2A+Lz4lxgeYG1yqSgFxHBh+/4l6cxibD9Un2H+szuqnfvr+P7vHjXt3zC9V8HcMvf07Ml7LqV+f+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:23.262648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0182c7e084b127c2c3fa02b4d0f8e9e1d79d259f21c99f2b8b16910ba9fad18a","sha256:7dce9b886e006fd50cac8852a87626af790595051ffcf29df5d105072e46bf18"],"state_sha256":"15414b7a70766a495d87d7414c83101edc6d054d851f9f34365be4507e7723de"}