{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMA3C3YONEXU2ECQ2WHMLFJOW5","short_pith_number":"pith:JMA3C3YO","schema_version":"1.0","canonical_sha256":"4b01b16f0e692f4d1050d58ec5952eb7592e83ca780affef4f92d134aa1d18d8","source":{"kind":"arxiv","id":"2407.13006","version":1},"attestation_state":"computed","paper":{"title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuangchuang Sun, Minjae Cho","submitted_at":"2024-07-17T20:57:05Z","abstract_excerpt":"Reinforcement Learning (RL) has made notable success in decision-making fields like autonomous driving and robotic manipulation. Yet, its reliance on real-time feedback poses challenges in costly or hazardous settings. Furthermore, RL's training approach, centered on \"on-policy\" sampling, doesn't fully capitalize on data. Hence, Offline RL has emerged as a compelling alternative, particularly in conducting additional experiments is impractical, and abundant datasets are available. However, the challenge of distributional shift (extrapolation), indicating the disparity between data distribution"},"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":"2407.13006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T20:57:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be185150a8afb56a5f1f3c367cb3d9b92a7240d83890159238ff9b3ae730d97b","abstract_canon_sha256":"e9a09162a18e7db6b5a9f297c845fb96575074337fd12c7438d3ad095e083da9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:31.818733Z","signature_b64":"+N5qHX0CkE3Fdplh9VW6laxz/NeqjJ0n/DOk/Zt2Ax4orDtnDzffVhjH0a+qO2uBwZ3S3Z/KASoOXK+gBB7zAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b01b16f0e692f4d1050d58ec5952eb7592e83ca780affef4f92d134aa1d18d8","last_reissued_at":"2026-07-05T08:45:31.818269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:31.818269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuangchuang Sun, Minjae Cho","submitted_at":"2024-07-17T20:57:05Z","abstract_excerpt":"Reinforcement Learning (RL) has made notable success in decision-making fields like autonomous driving and robotic manipulation. Yet, its reliance on real-time feedback poses challenges in costly or hazardous settings. Furthermore, RL's training approach, centered on \"on-policy\" sampling, doesn't fully capitalize on data. Hence, Offline RL has emerged as a compelling alternative, particularly in conducting additional experiments is impractical, and abundant datasets are available. However, the challenge of distributional shift (extrapolation), indicating the disparity between data distribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13006","kind":"arxiv","version":1},"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/2407.13006/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":"2407.13006","created_at":"2026-07-05T08:45:31.818343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13006v1","created_at":"2026-07-05T08:45:31.818343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13006","created_at":"2026-07-05T08:45:31.818343+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMA3C3YONEXU","created_at":"2026-07-05T08:45:31.818343+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMA3C3YONEXU2ECQ","created_at":"2026-07-05T08:45:31.818343+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMA3C3YO","created_at":"2026-07-05T08:45:31.818343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5","json":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5.json","graph_json":"https://pith.science/api/pith-number/JMA3C3YONEXU2ECQ2WHMLFJOW5/graph.json","events_json":"https://pith.science/api/pith-number/JMA3C3YONEXU2ECQ2WHMLFJOW5/events.json","paper":"https://pith.science/paper/JMA3C3YO"},"agent_actions":{"view_html":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5","download_json":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5.json","view_paper":"https://pith.science/paper/JMA3C3YO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13006&json=true","fetch_graph":"https://pith.science/api/pith-number/JMA3C3YONEXU2ECQ2WHMLFJOW5/graph.json","fetch_events":"https://pith.science/api/pith-number/JMA3C3YONEXU2ECQ2WHMLFJOW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5/action/storage_attestation","attest_author":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5/action/author_attestation","sign_citation":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5/action/citation_signature","submit_replication":"https://pith.science/pith/JMA3C3YONEXU2ECQ2WHMLFJOW5/action/replication_record"}},"created_at":"2026-07-05T08:45:31.818343+00:00","updated_at":"2026-07-05T08:45:31.818343+00:00"}