{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YBUFCZHOPYZUCQBTDXEOPNSBCK","short_pith_number":"pith:YBUFCZHO","schema_version":"1.0","canonical_sha256":"c0685164ee7e334140331dc8e7b64112872c093c290f4e40f48cb7f4794bd944","source":{"kind":"arxiv","id":"2105.07351","version":3},"attestation_state":"computed","paper":{"title":"Model-Based Offline Planning with Trajectory Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Haoran Xu, Xiangyu Zhu, Xianyuan Zhan","submitted_at":"2021-05-16T05:00:54Z","abstract_excerpt":"The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without environment interaction. Unfortunately, existing offline RL methods still face many practical challenges in real-world system control tasks, such as computational restriction during agent training and the requirement of extra control flexibility. The model-based planning framework provides an attractive alternative. However, most model-based planning algorithms are not designed for offline settings. Simply combining "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2105.07351","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-05-16T05:00:54Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"a9af88abb38d47cd3c41519ad779843a6dc87602f05090c5558471b435671f3e","abstract_canon_sha256":"4dd6681340115eb706cbad13696daedff1d437e188b9cc717b9fde2f652e43c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:35.674535Z","signature_b64":"oBaBcDoKVRDiRDsfMJlfJG4V3TNcBzJtpCR9/+dHKKsiI+1wfibVWsbt+VFMsQT2qkLK6gOPbFVl/DeUot/rAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0685164ee7e334140331dc8e7b64112872c093c290f4e40f48cb7f4794bd944","last_reissued_at":"2026-07-05T04:16:35.673995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:35.673995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Offline Planning with Trajectory Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Haoran Xu, Xiangyu Zhu, Xianyuan Zhan","submitted_at":"2021-05-16T05:00:54Z","abstract_excerpt":"The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without environment interaction. Unfortunately, existing offline RL methods still face many practical challenges in real-world system control tasks, such as computational restriction during agent training and the requirement of extra control flexibility. The model-based planning framework provides an attractive alternative. However, most model-based planning algorithms are not designed for offline settings. Simply combining "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07351","kind":"arxiv","version":3},"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/2105.07351/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2105.07351","created_at":"2026-07-05T04:16:35.674066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07351v3","created_at":"2026-07-05T04:16:35.674066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07351","created_at":"2026-07-05T04:16:35.674066+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBUFCZHOPYZU","created_at":"2026-07-05T04:16:35.674066+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBUFCZHOPYZUCQBT","created_at":"2026-07-05T04:16:35.674066+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBUFCZHO","created_at":"2026-07-05T04:16:35.674066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04528","citing_title":"Receding-Horizon Control via Drifting Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK","json":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK.json","graph_json":"https://pith.science/api/pith-number/YBUFCZHOPYZUCQBTDXEOPNSBCK/graph.json","events_json":"https://pith.science/api/pith-number/YBUFCZHOPYZUCQBTDXEOPNSBCK/events.json","paper":"https://pith.science/paper/YBUFCZHO"},"agent_actions":{"view_html":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK","download_json":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK.json","view_paper":"https://pith.science/paper/YBUFCZHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07351&json=true","fetch_graph":"https://pith.science/api/pith-number/YBUFCZHOPYZUCQBTDXEOPNSBCK/graph.json","fetch_events":"https://pith.science/api/pith-number/YBUFCZHOPYZUCQBTDXEOPNSBCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK/action/storage_attestation","attest_author":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK/action/author_attestation","sign_citation":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK/action/citation_signature","submit_replication":"https://pith.science/pith/YBUFCZHOPYZUCQBTDXEOPNSBCK/action/replication_record"}},"created_at":"2026-07-05T04:16:35.674066+00:00","updated_at":"2026-07-05T04:16:35.674066+00:00"}