{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4J4BC4YI5JTOBDVILKMUIWMRB7","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":"51eb33523c42a47029c007a1cbb05962f522e4988ac0b8bb4f29ce0522636ddd","cross_cats_sorted":["cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-09T18:40:24Z","title_canon_sha256":"228f9547e5c7f8e4a2d384112f70b77b7172106a070df5a9ce8d686ad56ee4b3"},"schema_version":"1.0","source":{"id":"2406.05881","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05881","created_at":"2026-07-05T11:59:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05881v6","created_at":"2026-07-05T11:59:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05881","created_at":"2026-07-05T11:59:52Z"},{"alias_kind":"pith_short_12","alias_value":"4J4BC4YI5JTO","created_at":"2026-07-05T11:59:52Z"},{"alias_kind":"pith_short_16","alias_value":"4J4BC4YI5JTOBDVI","created_at":"2026-07-05T11:59:52Z"},{"alias_kind":"pith_short_8","alias_value":"4J4BC4YI","created_at":"2026-07-05T11:59:52Z"}],"graph_snapshots":[{"event_id":"sha256:414f31b459e292a68daa2cf2f4ae3217d0a6d2fee9807478d4f04273cfbe8e73","target":"graph","created_at":"2026-07-05T11:59:52Z","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/2406.05881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation. However, translating natural language instructions into effective robotic control policies remains a significant challenge, especially for tasks requiring long-horizon planning and operating under sparse reward conditions. Hierarchical Reinforcement Learning (HRL) provides a natural framework to address this challenge in robotics; however, it typically suffers from non-stationarity caused by the changing behavior of the lower-level policy during training, destabilizing h","authors_text":"Pramit Bhattacharyya, Utsav Singh, Vinay P. Namboodiri","cross_cats":["cs.CL","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-09T18:40:24Z","title":"LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05881","kind":"arxiv","version":6},"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:c0af4dec8076e002e25ce1ff7623cef39d14a4edbced46ebf0114f2ca88772d7","target":"record","created_at":"2026-07-05T11:59:52Z","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":"51eb33523c42a47029c007a1cbb05962f522e4988ac0b8bb4f29ce0522636ddd","cross_cats_sorted":["cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-09T18:40:24Z","title_canon_sha256":"228f9547e5c7f8e4a2d384112f70b77b7172106a070df5a9ce8d686ad56ee4b3"},"schema_version":"1.0","source":{"id":"2406.05881","kind":"arxiv","version":6}},"canonical_sha256":"e278117308ea66e08ea85a994459910fd569c187ef170b9c3651dcc355d98a6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e278117308ea66e08ea85a994459910fd569c187ef170b9c3651dcc355d98a6b","first_computed_at":"2026-07-05T11:59:52.404499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:52.404499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KPPM3MEE8GxNS16n/Aia9Eu+QfgKTOLVsuhroS8dLbfWlrFCy/bPD5h7pizQXkn+w8d+ZBAriL+PWgS7rnoqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:52.404945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05881","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0af4dec8076e002e25ce1ff7623cef39d14a4edbced46ebf0114f2ca88772d7","sha256:414f31b459e292a68daa2cf2f4ae3217d0a6d2fee9807478d4f04273cfbe8e73"],"state_sha256":"581964a7f1d5ce8c38629b8d4678311f7224d3b924cb7606956476494fe3faf3"}