{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LXXJR2WDWJDCSK4ZUX4LMRWSEO","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":"5d62d5bb816f4b0beb3b79ac178dd5ee5b3de8ef17b11bdd68aaba7c2460ce15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T18:43:56Z","title_canon_sha256":"e1bbed1318078d3773b4c60b73df856ea763fe009014878997dd116b893a7715"},"schema_version":"1.0","source":{"id":"2412.06877","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06877","created_at":"2026-07-05T11:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06877v2","created_at":"2026-07-05T11:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06877","created_at":"2026-07-05T11:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"LXXJR2WDWJDC","created_at":"2026-07-05T11:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"LXXJR2WDWJDCSK4Z","created_at":"2026-07-05T11:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"LXXJR2WD","created_at":"2026-07-05T11:16:53Z"}],"graph_snapshots":[{"event_id":"sha256:bba14cea069089406277c2b6d4f125550220df336da229b5500ac1299d54a48a","target":"graph","created_at":"2026-07-05T11:16:53Z","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/2412.06877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing autonomous agents capable of performing complex, multi-step decision-making tasks specified in natural language remains a significant challenge, particularly in realistic settings where labeled data is scarce and real-time experimentation is impractical. Existing reinforcement learning (RL) approaches often struggle to generalize to unseen goals and states, limiting their applicability. In this paper, we introduce TEDUO, a novel training pipeline for offline language-conditioned policy learning in symbolic environments. Unlike conventional methods, TEDUO operates on readily availabl","authors_text":"Hao Sun, Katarzyna Kobalczyk, Mihaela van der Schaar, Thomas Pouplin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T18:43:56Z","title":"The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06877","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":"sha256:5472573ff1832e78c413eda78144fef1ce50f849522ce2c31fc2b725e08c112e","target":"record","created_at":"2026-07-05T11:16:53Z","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":"5d62d5bb816f4b0beb3b79ac178dd5ee5b3de8ef17b11bdd68aaba7c2460ce15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T18:43:56Z","title_canon_sha256":"e1bbed1318078d3773b4c60b73df856ea763fe009014878997dd116b893a7715"},"schema_version":"1.0","source":{"id":"2412.06877","kind":"arxiv","version":2}},"canonical_sha256":"5dee98eac3b246292b99a5f8b646d223adeabe549f748a41c748f2e8c82cc96e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dee98eac3b246292b99a5f8b646d223adeabe549f748a41c748f2e8c82cc96e","first_computed_at":"2026-07-05T11:16:53.043566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:53.043566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w4VzXPbKpEPaf4QL+sr/ZL0NWktU8Aq4SPsYrmaxzC8FLCwSNhfkmpd57YJo5zCBeD/wjQZDtg9qlhEQyCr2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:53.044065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06877","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5472573ff1832e78c413eda78144fef1ce50f849522ce2c31fc2b725e08c112e","sha256:bba14cea069089406277c2b6d4f125550220df336da229b5500ac1299d54a48a"],"state_sha256":"aaebc7a15fbee6895d529b233bde7497ca80abc8de56930be895a82e09f22282"}