{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6H3H7CQAUY6QFPKBVLFGOSYBDU","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":"b260001993c3d20e96fc819ac6190e00cacf37cba19e483c8f0eb9375491fbba","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T23:06:34Z","title_canon_sha256":"42acb39379196816aeb8c08960f30fb99c342a583c3dc1cc26691c75ef1995b8"},"schema_version":"1.0","source":{"id":"2501.12539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12539","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12539v1","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12539","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"6H3H7CQAUY6Q","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"6H3H7CQAUY6QFPKB","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"6H3H7CQA","created_at":"2026-07-05T10:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:398de223de97fb04968afbe40dbe3ed98916b5579cc362d7772f6769c35f6607","target":"graph","created_at":"2026-07-05T10:03:54Z","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/2501.12539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Combining reinforcement learning with language grounding is challenging as the agent needs to explore the environment while simultaneously learning multiple language-conditioned tasks. To address this, we introduce a novel method: the compositionally-enabled reinforcement learning language agent (CERLLA). Our method reduces the sample complexity of tasks specified with language by leveraging compositional policy representations and a semantic parser trained using reinforcement learning and in-context learning. We evaluate our approach in an environment requiring function approximation and demo","authors_text":"Benjamin Rosman, Geraud Nangue Tasse, Matthew Gombolay, Nakul Gopalan, Ray Mooney, Steven James, Vanya Cohen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T23:06:34Z","title":"Compositional Instruction Following with Language Models and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12539","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:a1516eea40d6632e257faef7cca43c3188cef952e529441354790b75d3674333","target":"record","created_at":"2026-07-05T10:03:54Z","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":"b260001993c3d20e96fc819ac6190e00cacf37cba19e483c8f0eb9375491fbba","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T23:06:34Z","title_canon_sha256":"42acb39379196816aeb8c08960f30fb99c342a583c3dc1cc26691c75ef1995b8"},"schema_version":"1.0","source":{"id":"2501.12539","kind":"arxiv","version":1}},"canonical_sha256":"f1f67f8a00a63d02bd41aaca674b011d14a9ef1635122b4801ba81e7cb37c4db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1f67f8a00a63d02bd41aaca674b011d14a9ef1635122b4801ba81e7cb37c4db","first_computed_at":"2026-07-05T10:03:54.628347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:54.628347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UKuKe688nBr0bdKRLONLygqiepfK/B1hKbo4Y9BjhWnqTzsc4MssN8W4nkRTudMyJOtOnHkpzdeba8imkujoCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:54.628950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1516eea40d6632e257faef7cca43c3188cef952e529441354790b75d3674333","sha256:398de223de97fb04968afbe40dbe3ed98916b5579cc362d7772f6769c35f6607"],"state_sha256":"02631d034506d2d8a650149f81140ffe00583da47cb15e2f93b3866ab9ae92db"}