{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QXQFWOOEFBN3NRMJYDSWTPZVQB","short_pith_number":"pith:QXQFWOOE","canonical_record":{"source":{"id":"2010.01112","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T17:13:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e629afa9969532c5dd46bb2c291fbd604e8c5aaa7d04a4c5083ce6bc3f262ed7","abstract_canon_sha256":"41adea3850ccec6bed9fdea9da3457b2c86f63fb0b9f14269164e56fbb1ef340"},"schema_version":"1.0"},"canonical_sha256":"85e05b39c4285bb6c589c0e569bf35805fb928ef032eeb9fdba5042d6d8c1791","source":{"kind":"arxiv","id":"2010.01112","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.01112","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2010.01112v4","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01112","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"QXQFWOOEFBN3","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"QXQFWOOEFBN3NRMJ","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"QXQFWOOE","created_at":"2026-07-05T02:37:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QXQFWOOEFBN3NRMJYDSWTPZVQB","target":"record","payload":{"canonical_record":{"source":{"id":"2010.01112","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T17:13:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e629afa9969532c5dd46bb2c291fbd604e8c5aaa7d04a4c5083ce6bc3f262ed7","abstract_canon_sha256":"41adea3850ccec6bed9fdea9da3457b2c86f63fb0b9f14269164e56fbb1ef340"},"schema_version":"1.0"},"canonical_sha256":"85e05b39c4285bb6c589c0e569bf35805fb928ef032eeb9fdba5042d6d8c1791","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:56.285218Z","signature_b64":"OPfvSVWzd3ggyPJGBklK8RoxuNZzRJhqkBUl+pRz3c2RUDzMOXORNVDXjoVaE0w+2h8Lle0MoZ/z23SRaMcVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85e05b39c4285bb6c589c0e569bf35805fb928ef032eeb9fdba5042d6d8c1791","last_reissued_at":"2026-07-05T02:37:56.284750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:56.284750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.01112","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:37:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5O5YK6qiVllmskM+2foakFe8+NfYnybdsibGYQhf8NDK28E532mNeXm7escIxKN2qiQDN8LuDpO5d8d+hXBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:50:01.145110Z"},"content_sha256":"0de73e7ecebe7091d833aca4bade42b222264b51b76f92721f29cb8479c42e4f","schema_version":"1.0","event_id":"sha256:0de73e7ecebe7091d833aca4bade42b222264b51b76f92721f29cb8479c42e4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QXQFWOOEFBN3NRMJYDSWTPZVQB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dijun Luo, Lanqing Li, Rui Yang","submitted_at":"2020-10-02T17:13:39Z","abstract_excerpt":"We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in many real-world applications. This problem is still not fully understood, for which two major challenges need to be addressed. First, offline RL usually suffers from bootstrapping errors of out-of-distribution state-actions which leads to divergence of value functions. Second, meta-RL requires efficient and robust task inference learned jointly with control p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01112","kind":"arxiv","version":4},"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/2010.01112/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:37:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWyE/dNvFlLO8kP0lAci7J9Zw7xreQIQWXxHbnfNt5GoOmofNm3FABgp0udd+1Z+nLbo6ixvciOWED8G/opGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:50:01.145698Z"},"content_sha256":"a804f327b452401e92823201c31d7fc26621a1d12b89cee7cfaee5694ebd44c5","schema_version":"1.0","event_id":"sha256:a804f327b452401e92823201c31d7fc26621a1d12b89cee7cfaee5694ebd44c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/bundle.json","state_url":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T19:50:01Z","links":{"resolver":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB","bundle":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/bundle.json","state":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QXQFWOOEFBN3NRMJYDSWTPZVQB","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":"41adea3850ccec6bed9fdea9da3457b2c86f63fb0b9f14269164e56fbb1ef340","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T17:13:39Z","title_canon_sha256":"e629afa9969532c5dd46bb2c291fbd604e8c5aaa7d04a4c5083ce6bc3f262ed7"},"schema_version":"1.0","source":{"id":"2010.01112","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.01112","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2010.01112v4","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01112","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"QXQFWOOEFBN3","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"QXQFWOOEFBN3NRMJ","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"QXQFWOOE","created_at":"2026-07-05T02:37:56Z"}],"graph_snapshots":[{"event_id":"sha256:a804f327b452401e92823201c31d7fc26621a1d12b89cee7cfaee5694ebd44c5","target":"graph","created_at":"2026-07-05T02:37:56Z","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/2010.01112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in many real-world applications. This problem is still not fully understood, for which two major challenges need to be addressed. First, offline RL usually suffers from bootstrapping errors of out-of-distribution state-actions which leads to divergence of value functions. Second, meta-RL requires efficient and robust task inference learned jointly with control p","authors_text":"Dijun Luo, Lanqing Li, Rui Yang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T17:13:39Z","title":"FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01112","kind":"arxiv","version":4},"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":"sha256:0de73e7ecebe7091d833aca4bade42b222264b51b76f92721f29cb8479c42e4f","target":"record","created_at":"2026-07-05T02:37:56Z","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":"41adea3850ccec6bed9fdea9da3457b2c86f63fb0b9f14269164e56fbb1ef340","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T17:13:39Z","title_canon_sha256":"e629afa9969532c5dd46bb2c291fbd604e8c5aaa7d04a4c5083ce6bc3f262ed7"},"schema_version":"1.0","source":{"id":"2010.01112","kind":"arxiv","version":4}},"canonical_sha256":"85e05b39c4285bb6c589c0e569bf35805fb928ef032eeb9fdba5042d6d8c1791","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85e05b39c4285bb6c589c0e569bf35805fb928ef032eeb9fdba5042d6d8c1791","first_computed_at":"2026-07-05T02:37:56.284750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:56.284750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OPfvSVWzd3ggyPJGBklK8RoxuNZzRJhqkBUl+pRz3c2RUDzMOXORNVDXjoVaE0w+2h8Lle0MoZ/z23SRaMcVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:56.285218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.01112","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0de73e7ecebe7091d833aca4bade42b222264b51b76f92721f29cb8479c42e4f","sha256:a804f327b452401e92823201c31d7fc26621a1d12b89cee7cfaee5694ebd44c5"],"state_sha256":"f3e2d5201bd5f27d9a65e8f1b13a9d1278740629633f85cfe4e2de98784128dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"slLW3Ry1LR9Ddwwmj/Mk0GLF7nShc67KQT8FV3qVK5LQJR24YBbCLaTy+tggd3aNA0Km9crevQjkv3WJcpalBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:50:01.153897Z","bundle_sha256":"274e2b9bd5ad1cfa3c4724bf8f6131f2536c4f6ec3f0c90b268cc1977e911df6"}}