{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V4HTRK3FDJ67H6RKQL5WYOLFRW","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":"3c52a168be7bd54b414f321141d2f416de9dbb5eda12e150e7b59b6cd95f1017","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T07:01:06Z","title_canon_sha256":"ef47c082f04e1e1d306685428e3e36556e4a5a49e9a1fac5f40accd24a5d0b20"},"schema_version":"1.0","source":{"id":"2303.05069","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.05069","created_at":"2026-07-05T05:49:36Z"},{"alias_kind":"arxiv_version","alias_value":"2303.05069v1","created_at":"2026-07-05T05:49:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05069","created_at":"2026-07-05T05:49:36Z"},{"alias_kind":"pith_short_12","alias_value":"V4HTRK3FDJ67","created_at":"2026-07-05T05:49:36Z"},{"alias_kind":"pith_short_16","alias_value":"V4HTRK3FDJ67H6RK","created_at":"2026-07-05T05:49:36Z"},{"alias_kind":"pith_short_8","alias_value":"V4HTRK3F","created_at":"2026-07-05T05:49:36Z"}],"graph_snapshots":[{"event_id":"sha256:44c8cde8a3838c3e08582daf9925d4c93211f42ee36858c4c8e853b4a32c6d19","target":"graph","created_at":"2026-07-05T05:49:36Z","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/2303.05069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across environments. Existing studies of language-conditioned RL methods often learn the joint representation as a simple latent layer for the given instances (episode-specific observation and text), which inevitably includes ","authors_text":"Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Yunji Chen, Zidong Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T07:01:06Z","title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05069","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:fd09849c724c4c4ad759bb3259697952739bd2fecbd738c5a454df59f6ecdf39","target":"record","created_at":"2026-07-05T05:49:36Z","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":"3c52a168be7bd54b414f321141d2f416de9dbb5eda12e150e7b59b6cd95f1017","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T07:01:06Z","title_canon_sha256":"ef47c082f04e1e1d306685428e3e36556e4a5a49e9a1fac5f40accd24a5d0b20"},"schema_version":"1.0","source":{"id":"2303.05069","kind":"arxiv","version":1}},"canonical_sha256":"af0f38ab651a7df3fa2a82fb6c39658da7d3a9761a9f817a18809a8d924b6ad6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af0f38ab651a7df3fa2a82fb6c39658da7d3a9761a9f817a18809a8d924b6ad6","first_computed_at":"2026-07-05T05:49:36.965484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:36.965484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kzn1dN4Y6/Nk36MvSgVtcbSjOnDFo/3rjU2MFF0DXq5PnCWwS9WTQxSJzKs5N93aqmcTz3mpExhzxuOcDGzjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:36.965823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.05069","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd09849c724c4c4ad759bb3259697952739bd2fecbd738c5a454df59f6ecdf39","sha256:44c8cde8a3838c3e08582daf9925d4c93211f42ee36858c4c8e853b4a32c6d19"],"state_sha256":"be20c5c71cc6a97c91758c13fe34dbbb38162fd011325c7b15dae9940f0f840b"}