{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PXVL4MFHK7TCYVYMD3J6IIXPQ7","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":"7e6bdc22a394463e8481e11bf69236ea4e3a15351704b05880652c8496b27424","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-15T16:58:19Z","title_canon_sha256":"b779f5d0d48f5f4c5f74d51eb9ff75be3d6806c406f46a03088d524d6e5d9fb0"},"schema_version":"1.0","source":{"id":"2004.07200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.07200","created_at":"2026-07-05T06:01:32Z"},{"alias_kind":"arxiv_version","alias_value":"2004.07200v2","created_at":"2026-07-05T06:01:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.07200","created_at":"2026-07-05T06:01:32Z"},{"alias_kind":"pith_short_12","alias_value":"PXVL4MFHK7TC","created_at":"2026-07-05T06:01:32Z"},{"alias_kind":"pith_short_16","alias_value":"PXVL4MFHK7TCYVYM","created_at":"2026-07-05T06:01:32Z"},{"alias_kind":"pith_short_8","alias_value":"PXVL4MFH","created_at":"2026-07-05T06:01:32Z"}],"graph_snapshots":[{"event_id":"sha256:9f1db3bd78fb06b280acf40a94bbddae78347e696be9963bb4543230c00d19e6","target":"graph","created_at":"2026-07-05T06:01:32Z","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/2004.07200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent breakthroughs in reinforcement learning (RL) and imitation learning (IL), existing algorithms fail to generalize beyond the training environments. In reality, humans can adapt to new tasks quickly by leveraging prior knowledge about the world such as language descriptions. To facilitate the research on language-guided agents with domain adaption, we propose a novel zero-shot compositional policy learning task, where the environments are characterized as a composition of different attributes. Since there are no public environments supporting this study, we introduce a new researc","authors_text":"Jingkang Wang, Sivabalan Manivasagam, Tianshi Cao, Yining Zhang","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-15T16:58:19Z","title":"Zero-Shot Compositional Policy Learning via Language Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.07200","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":"sha256:23d2b6be129d47ff385bb92848df273e9370084a861728789a660760405f6449","target":"record","created_at":"2026-07-05T06:01:32Z","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":"7e6bdc22a394463e8481e11bf69236ea4e3a15351704b05880652c8496b27424","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-15T16:58:19Z","title_canon_sha256":"b779f5d0d48f5f4c5f74d51eb9ff75be3d6806c406f46a03088d524d6e5d9fb0"},"schema_version":"1.0","source":{"id":"2004.07200","kind":"arxiv","version":2}},"canonical_sha256":"7deabe30a757e62c570c1ed3e422ef87e8642c9969c6aff90486270b3b4bd252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7deabe30a757e62c570c1ed3e422ef87e8642c9969c6aff90486270b3b4bd252","first_computed_at":"2026-07-05T06:01:32.660370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:32.660370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7DV8mjIhz9irNQdx5GeGRli6qSkWpRuEjkL5Pnhi2eck8X1S0WIIVUI8C9Luepe3sXHQwKR/zrh8AO9J46q7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:32.660873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.07200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23d2b6be129d47ff385bb92848df273e9370084a861728789a660760405f6449","sha256:9f1db3bd78fb06b280acf40a94bbddae78347e696be9963bb4543230c00d19e6"],"state_sha256":"1cf3ae3fb4e33485e4e26cb79129ef87773a6323f177b9549ff8d43498fe53fd"}