{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4SLNCK7PXRZA7CGLHOILTZK3QV","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":"6d9b540f9f71b7d184f7ba96c3dd50c60c672555567700079dec0b540cfaec9e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T03:08:23Z","title_canon_sha256":"ec0519715e3dac289ca44879b66f1f18ccc0c83587a13df55dfa59674eafa8d5"},"schema_version":"1.0","source":{"id":"2112.00950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00950","created_at":"2026-07-05T03:37:01Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00950v1","created_at":"2026-07-05T03:37:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00950","created_at":"2026-07-05T03:37:01Z"},{"alias_kind":"pith_short_12","alias_value":"4SLNCK7PXRZA","created_at":"2026-07-05T03:37:01Z"},{"alias_kind":"pith_short_16","alias_value":"4SLNCK7PXRZA7CGL","created_at":"2026-07-05T03:37:01Z"},{"alias_kind":"pith_short_8","alias_value":"4SLNCK7P","created_at":"2026-07-05T03:37:01Z"}],"graph_snapshots":[{"event_id":"sha256:e1b035c6d530dfce89f59f7ebd5687663f0f600e3ec7025ab22b78ef5c61a5b9","target":"graph","created_at":"2026-07-05T03:37:01Z","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/2112.00950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce quantile filtered imitation learning (QFIL), a novel policy improvement operator designed for offline reinforcement learning. QFIL performs policy improvement by running imitation learning on a filtered version of the offline dataset. The filtering process removes $ s,a $ pairs whose estimated Q values fall below a given quantile of the pushforward distribution over values induced by sampling actions from the behavior policy. The definitions of both the pushforward Q distribution and resulting value function quantile are key contributions of our method. We prove that QFIL gives us","authors_text":"David Brandfonbrener, Joan Bruna, Rajesh Ranganath, William F. Whitney","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T03:08:23Z","title":"Quantile Filtered Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00950","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":"sha256:9b6766d8b0b32f68c76d7bdb1c127da76179be2ad661c8854fe2bb448fd96d39","target":"record","created_at":"2026-07-05T03:37:01Z","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":"6d9b540f9f71b7d184f7ba96c3dd50c60c672555567700079dec0b540cfaec9e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T03:08:23Z","title_canon_sha256":"ec0519715e3dac289ca44879b66f1f18ccc0c83587a13df55dfa59674eafa8d5"},"schema_version":"1.0","source":{"id":"2112.00950","kind":"arxiv","version":1}},"canonical_sha256":"e496d12befbc720f88cb3b90b9e55b85452f7a218c1f36c5937bfd9bbc254fe1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e496d12befbc720f88cb3b90b9e55b85452f7a218c1f36c5937bfd9bbc254fe1","first_computed_at":"2026-07-05T03:37:01.792230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:01.792230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2j10bmwGtBg+Ks9g/zGmeI7cVz9bUIfS4iH1d6WoU8BUonZgQo8+0ZTAgO0iDeGr+7RZoZvkU7y8Ak8o4GU8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:01.792689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.00950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b6766d8b0b32f68c76d7bdb1c127da76179be2ad661c8854fe2bb448fd96d39","sha256:e1b035c6d530dfce89f59f7ebd5687663f0f600e3ec7025ab22b78ef5c61a5b9"],"state_sha256":"b9a5cbb4a1049f17c200e0fffbd08528e6ab3c38ce9aff97b18602ad2a7b3ba1"}