{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WR7MFAAK2FBWJL4VHQ5TIXSU76","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":"c0066bb2d94f98e3d38eeaba12fd0153b3c57e2c7b0f2cd8dee10e8686f27e53","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T16:34:00Z","title_canon_sha256":"d7ffbe2cb42fc15d0ba578306ca9c18b5f99da9726aa85862563e6581d90ae0a"},"schema_version":"1.0","source":{"id":"2310.18247","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18247","created_at":"2026-07-05T08:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18247v3","created_at":"2026-07-05T08:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18247","created_at":"2026-07-05T08:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"WR7MFAAK2FBW","created_at":"2026-07-05T08:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"WR7MFAAK2FBWJL4V","created_at":"2026-07-05T08:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"WR7MFAAK","created_at":"2026-07-05T08:53:17Z"}],"graph_snapshots":[{"event_id":"sha256:21d18efd2c2287878d0f7a1b69c6ff7af7dee349935837b90844d819bc2df72b","target":"graph","created_at":"2026-07-05T08:53:17Z","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/2310.18247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning (RL), an RL agent learns to solve a task using only a fixed dataset of previously collected data. While offline RL has been successful in learning real-world robot control policies, it typically requires large amounts of expert-quality data to learn effective policies that generalize to out-of-distribution states. Unfortunately, such data is often difficult and expensive to acquire in real-world tasks. Several recent works have leveraged data augmentation (DA) to inexpensively generate additional data, but most DA works apply augmentations in a random fashion ","authors_text":"Adam Labiosa, John U. Balis, Josiah P. Hanna, Nicholas E. Corrado, Yuxiao Qu","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T16:34:00Z","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18247","kind":"arxiv","version":3},"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":"sha256:67215c65ab1914f0ecc54840832c68c30d1030993d9c554e92c437bb8707ec83","target":"record","created_at":"2026-07-05T08:53:17Z","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":"c0066bb2d94f98e3d38eeaba12fd0153b3c57e2c7b0f2cd8dee10e8686f27e53","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T16:34:00Z","title_canon_sha256":"d7ffbe2cb42fc15d0ba578306ca9c18b5f99da9726aa85862563e6581d90ae0a"},"schema_version":"1.0","source":{"id":"2310.18247","kind":"arxiv","version":3}},"canonical_sha256":"b47ec2800ad14364af953c3b345e54ff9253b3ae15f869d1284c355f8b66dc6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b47ec2800ad14364af953c3b345e54ff9253b3ae15f869d1284c355f8b66dc6f","first_computed_at":"2026-07-05T08:53:17.929649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:17.929649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jXAd3y0XaHkzrAMjiQ9kohlhPbZ8SmpQJjeiSCbpo2JW2zkPEJhEiqVgL4Gn/vSx6TQOT8GihBi6Ptf3GuF5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:17.930132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18247","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67215c65ab1914f0ecc54840832c68c30d1030993d9c554e92c437bb8707ec83","sha256:21d18efd2c2287878d0f7a1b69c6ff7af7dee349935837b90844d819bc2df72b"],"state_sha256":"a414dd02ad1da1134dd84c6f5bb613d6d2880d92a5c33aca4774173fd04a411f"}