{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3EMYEZ7L7EXN7LI4Y23BPIJZAC","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":"60699dd9284e694ae171e9074df2280a815244b0ef6c3ad31ad3e2ee9ab707ae","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-19T17:39:20Z","title_canon_sha256":"0e2ec558740eeaf5bfd11b469039142f2edd758459e2d6f4193aac503477f1c4"},"schema_version":"1.0","source":{"id":"2309.10790","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10790","created_at":"2026-07-05T07:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10790v2","created_at":"2026-07-05T07:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10790","created_at":"2026-07-05T07:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"3EMYEZ7L7EXN","created_at":"2026-07-05T07:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"3EMYEZ7L7EXN7LI4","created_at":"2026-07-05T07:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"3EMYEZ7L","created_at":"2026-07-05T07:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:f8a4f82d96a7f2de1fba906bc65808ee5b6ade02a8b2d75bd140222727e765d0","target":"graph","created_at":"2026-07-05T07:04:50Z","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/2309.10790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing an agent capable of adapting to unseen environments remains a difficult challenge in imitation learning. This work presents Adaptive Return-conditioned Policy (ARP), an efficient framework designed to enhance the agent's generalization ability using natural language task descriptions and pre-trained multimodal encoders. Our key idea is to calculate a similarity between visual observations and natural language instructions in the pre-trained multimodal embedding space (such as CLIP) and use it as a reward signal. We then train a return-conditioned policy using expert demonstrations l","authors_text":"Changyeon Kim, Hao Liu, Honglak Lee, Jinwoo Shin, Kimin Lee, Lisa Lee, Younggyo Seo","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-19T17:39:20Z","title":"Guide Your Agent with Adaptive Multimodal Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10790","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":"sha256:2ca3dfa667186413bf1c9641c24cf4f3382cfb370b898d9930cad18458c01903","target":"record","created_at":"2026-07-05T07:04:50Z","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":"60699dd9284e694ae171e9074df2280a815244b0ef6c3ad31ad3e2ee9ab707ae","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-19T17:39:20Z","title_canon_sha256":"0e2ec558740eeaf5bfd11b469039142f2edd758459e2d6f4193aac503477f1c4"},"schema_version":"1.0","source":{"id":"2309.10790","kind":"arxiv","version":2}},"canonical_sha256":"d9198267ebf92edfad1cc6b617a13900b488d211d5eca67763a2ca0c9e9d511c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9198267ebf92edfad1cc6b617a13900b488d211d5eca67763a2ca0c9e9d511c","first_computed_at":"2026-07-05T07:04:50.766581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:50.766581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jyb4PWLbxbqUMsx8lmWAaCd+fFvhcrdj8n2twkV/l7QWsb1ArS92z6xoFhnRHbPh3tLtaVGS7W3HfZOJgxdMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:50.767078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10790","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ca3dfa667186413bf1c9641c24cf4f3382cfb370b898d9930cad18458c01903","sha256:f8a4f82d96a7f2de1fba906bc65808ee5b6ade02a8b2d75bd140222727e765d0"],"state_sha256":"b1d75388feeba7d7faa113caa37ad178ab447f1e1c34b562916ab0dce0dea5f9"}