{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N7YB5IQPNYHRQIC262I7STH4M5","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":"b310f9993b8283f5c802a278ce8061934e2bcf1e957f9cae13ab165943f8df1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-10T03:55:17Z","title_canon_sha256":"82c6650e07e1983413951d089774449089fdad3d9eb86b11c409becfb9815b54"},"schema_version":"1.0","source":{"id":"2110.04698","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04698","created_at":"2026-07-05T07:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04698v2","created_at":"2026-07-05T07:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04698","created_at":"2026-07-05T07:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"N7YB5IQPNYHR","created_at":"2026-07-05T07:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"N7YB5IQPNYHRQIC2","created_at":"2026-07-05T07:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"N7YB5IQP","created_at":"2026-07-05T07:22:11Z"}],"graph_snapshots":[{"event_id":"sha256:2253a4df3afa7c36b5918b1622915017927c2bd0b6ea8a818c2493cc9d363e58","target":"graph","created_at":"2026-07-05T07:22:11Z","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/2110.04698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making strategies. Our work evaluates this method's ability to scale to vast datasets consisting almost entirely of sub-optimal noise. A thorough investigation on a custom benchmark helps identify several key challenges involved in learning from high-noise datasets. We re-purpose prioritized experience sampling to locate expert-level demonstrations among millions of low-pe","authors_text":"Jake Grigsby, Yanjun Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-10T03:55:17Z","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04698","kind":"arxiv","version":2},"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":"sha256:7177b1782ae5a9aaa8ecc03c4e49ce07059178b3e37ccd1b1b746f9720aed44a","target":"record","created_at":"2026-07-05T07:22:11Z","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":"b310f9993b8283f5c802a278ce8061934e2bcf1e957f9cae13ab165943f8df1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-10T03:55:17Z","title_canon_sha256":"82c6650e07e1983413951d089774449089fdad3d9eb86b11c409becfb9815b54"},"schema_version":"1.0","source":{"id":"2110.04698","kind":"arxiv","version":2}},"canonical_sha256":"6ff01ea20f6e0f18205af691f94cfc6759865c271d6ec5d7c8c7d05e39f36d79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ff01ea20f6e0f18205af691f94cfc6759865c271d6ec5d7c8c7d05e39f36d79","first_computed_at":"2026-07-05T07:22:11.660885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:11.660885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uTeYl9b6tZPwNLgLk6tk+3WxNlqhk1mjnMfO2sFoKspnC5+7KP+qW3jfZt8pFBubAcMhGKa8s1CIVm4OipFeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:11.661372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04698","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7177b1782ae5a9aaa8ecc03c4e49ce07059178b3e37ccd1b1b746f9720aed44a","sha256:2253a4df3afa7c36b5918b1622915017927c2bd0b6ea8a818c2493cc9d363e58"],"state_sha256":"12aabed2aaf2b6689250632244a2847fe576edc91c5ed0f9083a984d9b5020dd"}