{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IMTWFGXJJ4GJ6NLFK7GQGIPEXV","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":"1dfd21d5ba9a41a8034c60b2fe33bae875dd2b3a16d9ab64b0f44971e93b8bae","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-12T11:06:07Z","title_canon_sha256":"242e4185b88497eb5adcb9204c6d0848016aaa9247f92a5b5104382250fc1e46"},"schema_version":"1.0","source":{"id":"2401.00006","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00006","created_at":"2026-07-05T07:41:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00006v3","created_at":"2026-07-05T07:41:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00006","created_at":"2026-07-05T07:41:46Z"},{"alias_kind":"pith_short_12","alias_value":"IMTWFGXJJ4GJ","created_at":"2026-07-05T07:41:46Z"},{"alias_kind":"pith_short_16","alias_value":"IMTWFGXJJ4GJ6NLF","created_at":"2026-07-05T07:41:46Z"},{"alias_kind":"pith_short_8","alias_value":"IMTWFGXJ","created_at":"2026-07-05T07:41:46Z"}],"graph_snapshots":[{"event_id":"sha256:43c1b374ce5024ef29c34d8766054628007b0d69e1276c1dd092d149579672c4","target":"graph","created_at":"2026-07-05T07:41:46Z","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/2401.00006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks. However, existing research faces challenges in meeting the requirement of open-endedness. They typically either train LLM/RL models to adapt to a fixed counterpart, limiting exploration of novel skills and hindering the efficacy of human-AI interaction. To this end, we present OpenPAL, a co-training framework comprising two stages: (1) fine-tuning a pre-trai","authors_text":"Fuxian Huang, Jie Wang, Jing Hou, Ming Zhou, Qi Zhang, Shaopeng Zhai, Tianyi Zhang, Yu Liu, Yu Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-12T11:06:07Z","title":"Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00006","kind":"arxiv","version":3},"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:a6734b63848ead7daab6a08166a3f1aa89049bf2101ea892af8977f156ad93b3","target":"record","created_at":"2026-07-05T07:41:46Z","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":"1dfd21d5ba9a41a8034c60b2fe33bae875dd2b3a16d9ab64b0f44971e93b8bae","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-12T11:06:07Z","title_canon_sha256":"242e4185b88497eb5adcb9204c6d0848016aaa9247f92a5b5104382250fc1e46"},"schema_version":"1.0","source":{"id":"2401.00006","kind":"arxiv","version":3}},"canonical_sha256":"4327629ae94f0c9f356557cd0321e4bd576a53803ae01eb235d5fab5ef7e1d22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4327629ae94f0c9f356557cd0321e4bd576a53803ae01eb235d5fab5ef7e1d22","first_computed_at":"2026-07-05T07:41:46.530174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:46.530174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SAFqxt1TmcsVUWnTu1H00nu7Pqe5jXqYYFMQxp1lhletd3fBxK10bK7rYuyRL/I4b9A7x0d+Y8jkVZHlgduPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:46.530572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00006","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6734b63848ead7daab6a08166a3f1aa89049bf2101ea892af8977f156ad93b3","sha256:43c1b374ce5024ef29c34d8766054628007b0d69e1276c1dd092d149579672c4"],"state_sha256":"01b8f3149846536b29f4dc9816e169199fa50a868f55ef7f748f8941e04c0f69"}