{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3EMYEZ7L7EXN7LI4Y23BPIJZAC","short_pith_number":"pith:3EMYEZ7L","canonical_record":{"source":{"id":"2309.10790","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-19T17:39:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"0e2ec558740eeaf5bfd11b469039142f2edd758459e2d6f4193aac503477f1c4","abstract_canon_sha256":"60699dd9284e694ae171e9074df2280a815244b0ef6c3ad31ad3e2ee9ab707ae"},"schema_version":"1.0"},"canonical_sha256":"d9198267ebf92edfad1cc6b617a13900b488d211d5eca67763a2ca0c9e9d511c","source":{"kind":"arxiv","id":"2309.10790","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3EMYEZ7L7EXN7LI4Y23BPIJZAC","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10790","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-19T17:39:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"0e2ec558740eeaf5bfd11b469039142f2edd758459e2d6f4193aac503477f1c4","abstract_canon_sha256":"60699dd9284e694ae171e9074df2280a815244b0ef6c3ad31ad3e2ee9ab707ae"},"schema_version":"1.0"},"canonical_sha256":"d9198267ebf92edfad1cc6b617a13900b488d211d5eca67763a2ca0c9e9d511c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:50.767078Z","signature_b64":"Jyb4PWLbxbqUMsx8lmWAaCd+fFvhcrdj8n2twkV/l7QWsb1ArS92z6xoFhnRHbPh3tLtaVGS7W3HfZOJgxdMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9198267ebf92edfad1cc6b617a13900b488d211d5eca67763a2ca0c9e9d511c","last_reissued_at":"2026-07-05T07:04:50.766581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:50.766581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10790","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+cR4YgY4UpGquegCkTq2lFLQwmbYdRtCK389CWg/VT4/RpndZ+PCIzoCGPCzhbWmgXe5EROYxUVUctGRJz3+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:44:57.728834Z"},"content_sha256":"2ca3dfa667186413bf1c9641c24cf4f3382cfb370b898d9930cad18458c01903","schema_version":"1.0","event_id":"sha256:2ca3dfa667186413bf1c9641c24cf4f3382cfb370b898d9930cad18458c01903"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3EMYEZ7L7EXN7LI4Y23BPIJZAC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guide Your Agent with Adaptive Multimodal Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changyeon Kim, Hao Liu, Honglak Lee, Jinwoo Shin, Kimin Lee, Lisa Lee, Younggyo Seo","submitted_at":"2023-09-19T17:39:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10790","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.10790/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRbCotl0X/6oTXqoWMNA9xj8WYuxbqXJjKThVZUGc6FBA1QeBYHFkfZ9p/h4Ai3LeDXZFWo8pis3WlE5v8BlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:44:57.729244Z"},"content_sha256":"f8a4f82d96a7f2de1fba906bc65808ee5b6ade02a8b2d75bd140222727e765d0","schema_version":"1.0","event_id":"sha256:f8a4f82d96a7f2de1fba906bc65808ee5b6ade02a8b2d75bd140222727e765d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EMYEZ7L7EXN7LI4Y23BPIJZAC/bundle.json","state_url":"https://pith.science/pith/3EMYEZ7L7EXN7LI4Y23BPIJZAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EMYEZ7L7EXN7LI4Y23BPIJZAC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T07:44:57Z","links":{"resolver":"https://pith.science/pith/3EMYEZ7L7EXN7LI4Y23BPIJZAC","bundle":"https://pith.science/pith/3EMYEZ7L7EXN7LI4Y23BPIJZAC/bundle.json","state":"https://pith.science/pith/3EMYEZ7L7EXN7LI4Y23BPIJZAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EMYEZ7L7EXN7LI4Y23BPIJZAC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wSeXnCCwc770p004iSyGispa/Idm0zP4TQH+fP/d0uaN7LGKsxYsPWD6UjbGjdzLc0Askm1w/15zUeeMzDmyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:44:57.758383Z","bundle_sha256":"ae92affe43f16cd542850d5121e8b5e3b59d7d4c98e185dd8bd30e06454736b0"}}