{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:32UKFNZM3OYPCNZRUIMBJ62XJL","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":"009ab9f6dbc206abc0dadade8d1a7948a38bf9d607e46115dda28e7690e83bdb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-29T18:21:05Z","title_canon_sha256":"09ba76dd0fd0c7e1bb178072fd3d072d4e4e1c0c64b191fb3c234b9cb2b853ab"},"schema_version":"1.0","source":{"id":"2301.12507","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12507","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12507v2","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12507","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"32UKFNZM3OYP","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"32UKFNZM3OYPCNZR","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"32UKFNZM","created_at":"2026-07-05T06:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:8c91b1b96580e8dd74dba3979501293786fb87107643d2a008061c18954cdec8","target":"graph","created_at":"2026-07-05T06:20:40Z","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/2301.12507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interaction data. To address this challenge, we propose using pretrained vision-language models (VLMs) to supervise embodied agents. We combine ideas from model distillation and hindsight experience replay (HER), using a VLM to retroactively generate language describing the agent's behavior. Simple prompting allows us to control the supervision signal, teaching an agent to interact wi","authors_text":"Arun Ahuja, Ishita Dasgupta, Kenneth Marino, Rob Fergus, Theodore Sumers","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-29T18:21:05Z","title":"Distilling Internet-Scale Vision-Language Models into Embodied Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12507","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":"sha256:30f25d83d124c7bcf19f515297441887ed429d9c81788d1694e1848a794b0076","target":"record","created_at":"2026-07-05T06:20:40Z","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":"009ab9f6dbc206abc0dadade8d1a7948a38bf9d607e46115dda28e7690e83bdb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-29T18:21:05Z","title_canon_sha256":"09ba76dd0fd0c7e1bb178072fd3d072d4e4e1c0c64b191fb3c234b9cb2b853ab"},"schema_version":"1.0","source":{"id":"2301.12507","kind":"arxiv","version":2}},"canonical_sha256":"dea8a2b72cdbb0f13731a21814fb574ae7c97f55b1592ecfcce43c7078a83afc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dea8a2b72cdbb0f13731a21814fb574ae7c97f55b1592ecfcce43c7078a83afc","first_computed_at":"2026-07-05T06:20:40.263079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:40.263079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z+bZJC5iIk8qx4drn1UDiyXzQXmhDUe96oIl7R9XPAoPikbvTsZqpL9PlqUW4SB8Hk2Uy49ocJ9Pae8eDaNzAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:40.263527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12507","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30f25d83d124c7bcf19f515297441887ed429d9c81788d1694e1848a794b0076","sha256:8c91b1b96580e8dd74dba3979501293786fb87107643d2a008061c18954cdec8"],"state_sha256":"56efc8730db48a654de48c398a45816ef086e0b01cc8bac5c713acac079e04af"}