{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MDWQUDGP5OQZQBJLNT2KEWIDVF","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":"8040d0e4544b2eff39cf47f13940157f07fd114fea74fb7d7a99a78403a9897d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-21T16:00:39Z","title_canon_sha256":"7c9c4f5e5ec7aead38aefd63683acc037504586eadb5f0eff6209fedf87537e0"},"schema_version":"1.0","source":{"id":"2211.11603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11603","created_at":"2026-07-05T05:17:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11603v1","created_at":"2026-07-05T05:17:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11603","created_at":"2026-07-05T05:17:55Z"},{"alias_kind":"pith_short_12","alias_value":"MDWQUDGP5OQZ","created_at":"2026-07-05T05:17:55Z"},{"alias_kind":"pith_short_16","alias_value":"MDWQUDGP5OQZQBJL","created_at":"2026-07-05T05:17:55Z"},{"alias_kind":"pith_short_8","alias_value":"MDWQUDGP","created_at":"2026-07-05T05:17:55Z"}],"graph_snapshots":[{"event_id":"sha256:9bdc73b43b7ae0ddd0311bd6b90b2ce83a5cdb3fc39948c212f97de0d9774d16","target":"graph","created_at":"2026-07-05T05:17:55Z","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/2211.11603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world applications, collecting large and high-quality datasets may be too costly or impractical. Offline reinforcement learning (RL) aims to infer an optimal decision-making policy from a fixed set of data. Getting the most information from historical data is then vital for good performance once the policy is deployed. We propose a model-based data augmentation strategy, Trajectory Stitching (TS), to improve the quality of sub-optimal historical trajectories. TS introduces unseen actions joining previously disconnected states: using a probabilistic notion of state reachability, it","authors_text":"Charles A. Hepburn, Giovanni Montana","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-21T16:00:39Z","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11603","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":"sha256:048896fc033ac37f7af8c91bb6024ff1f737ba44e36c1c0b8911c31ff02bfee5","target":"record","created_at":"2026-07-05T05:17:55Z","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":"8040d0e4544b2eff39cf47f13940157f07fd114fea74fb7d7a99a78403a9897d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-21T16:00:39Z","title_canon_sha256":"7c9c4f5e5ec7aead38aefd63683acc037504586eadb5f0eff6209fedf87537e0"},"schema_version":"1.0","source":{"id":"2211.11603","kind":"arxiv","version":1}},"canonical_sha256":"60ed0a0ccfeba198052b6cf4a25903a97b3fb30135469be0b6f7c4cc44e25c2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60ed0a0ccfeba198052b6cf4a25903a97b3fb30135469be0b6f7c4cc44e25c2d","first_computed_at":"2026-07-05T05:17:55.874348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:55.874348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0PQD21iU4NyyASH5VuTlMMs0DDnwVcealA1Y75w1VOKWbLzYjnYZ2nXgG6lLk81DXvRagPDt9ooJ1oiSpHdfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:55.874846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:048896fc033ac37f7af8c91bb6024ff1f737ba44e36c1c0b8911c31ff02bfee5","sha256:9bdc73b43b7ae0ddd0311bd6b90b2ce83a5cdb3fc39948c212f97de0d9774d16"],"state_sha256":"8a82b255c1681003396c196dac37fbedd7a1fed154434bb0c59b4d4672fd4b2d"}