{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AGAXZFJBSPASDMK5SSCH6B3UAY","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":"850cf280744dd998f826c3cddd595de5da8c2e8ce0cefb1155e5461c1483048a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-29T09:29:18Z","title_canon_sha256":"0d5101b3ab6e0ac2251b175056111fec6080f205e1753755770f9ff2a6e64164"},"schema_version":"1.0","source":{"id":"2009.13891","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13891","created_at":"2026-07-05T01:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13891v3","created_at":"2026-07-05T01:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13891","created_at":"2026-07-05T01:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"AGAXZFJBSPAS","created_at":"2026-07-05T01:59:33Z"},{"alias_kind":"pith_short_16","alias_value":"AGAXZFJBSPASDMK5","created_at":"2026-07-05T01:59:33Z"},{"alias_kind":"pith_short_8","alias_value":"AGAXZFJB","created_at":"2026-07-05T01:59:33Z"}],"graph_snapshots":[{"event_id":"sha256:f055a771679705e84aacf9bffe18b3e9cd575032a49b6776493c2ac1646ee8e2","target":"graph","created_at":"2026-07-05T01:59:33Z","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/2009.13891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a few adaptation steps. We argue that improving the quality of context involves answering two questions: 1. How to train a compact and sufficient encoder that can embed the task-specific information contained in prior trajectories? 2. How to collect informative trajectories of which the corresponding context reflects the specification of tasks? To this end, we ","authors_text":"Chen Chen, Dong Li, Haotian Fu, Hongyao Tang, Jianye Hao, Wulong Liu, Xidong Feng","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-29T09:29:18Z","title":"Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13891","kind":"arxiv","version":3},"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:d71e762fa1e74f0c95da56f8ba126369765ec205c02a32b84a2aae85f6fcc102","target":"record","created_at":"2026-07-05T01:59:33Z","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":"850cf280744dd998f826c3cddd595de5da8c2e8ce0cefb1155e5461c1483048a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-29T09:29:18Z","title_canon_sha256":"0d5101b3ab6e0ac2251b175056111fec6080f205e1753755770f9ff2a6e64164"},"schema_version":"1.0","source":{"id":"2009.13891","kind":"arxiv","version":3}},"canonical_sha256":"01817c952193c121b15d94847f077406066209136e4889861ba8f97e6b0532d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01817c952193c121b15d94847f077406066209136e4889861ba8f97e6b0532d5","first_computed_at":"2026-07-05T01:59:33.032427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:33.032427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9b9pUxKSQ7/4j30UQ0lnQmvFCsLhlOaGxFXDRw2555uh/zidvGBg2jtl7KT3fdjKOOUKs/GcL+AgN1rN43m0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:33.032851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.13891","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d71e762fa1e74f0c95da56f8ba126369765ec205c02a32b84a2aae85f6fcc102","sha256:f055a771679705e84aacf9bffe18b3e9cd575032a49b6776493c2ac1646ee8e2"],"state_sha256":"0664002d6375266a625ca97c38519c304f6ef5e12361baacb5950b273e3e0b29"}