{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:32UKFNZM3OYPCNZRUIMBJ62XJL","short_pith_number":"pith:32UKFNZM","canonical_record":{"source":{"id":"2301.12507","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-29T18:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"09ba76dd0fd0c7e1bb178072fd3d072d4e4e1c0c64b191fb3c234b9cb2b853ab","abstract_canon_sha256":"009ab9f6dbc206abc0dadade8d1a7948a38bf9d607e46115dda28e7690e83bdb"},"schema_version":"1.0"},"canonical_sha256":"dea8a2b72cdbb0f13731a21814fb574ae7c97f55b1592ecfcce43c7078a83afc","source":{"kind":"arxiv","id":"2301.12507","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:32UKFNZM3OYPCNZRUIMBJ62XJL","target":"record","payload":{"canonical_record":{"source":{"id":"2301.12507","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-29T18:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"09ba76dd0fd0c7e1bb178072fd3d072d4e4e1c0c64b191fb3c234b9cb2b853ab","abstract_canon_sha256":"009ab9f6dbc206abc0dadade8d1a7948a38bf9d607e46115dda28e7690e83bdb"},"schema_version":"1.0"},"canonical_sha256":"dea8a2b72cdbb0f13731a21814fb574ae7c97f55b1592ecfcce43c7078a83afc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:40.263527Z","signature_b64":"z+bZJC5iIk8qx4drn1UDiyXzQXmhDUe96oIl7R9XPAoPikbvTsZqpL9PlqUW4SB8Hk2Uy49ocJ9Pae8eDaNzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea8a2b72cdbb0f13731a21814fb574ae7c97f55b1592ecfcce43c7078a83afc","last_reissued_at":"2026-07-05T06:20:40.263079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:40.263079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.12507","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":"2026-07-05T06:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bWg1Kx/CeL8K+aWsaQq2jCPuL2w6ihpAg6aKiza1oDLByqElnRUdCBtp8N7C946FJHGWQNTTP9gomF7PO/YJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:19:59.888067Z"},"content_sha256":"30f25d83d124c7bcf19f515297441887ed429d9c81788d1694e1848a794b0076","schema_version":"1.0","event_id":"sha256:30f25d83d124c7bcf19f515297441887ed429d9c81788d1694e1848a794b0076"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:32UKFNZM3OYPCNZRUIMBJ62XJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Internet-Scale Vision-Language Models into Embodied Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Arun Ahuja, Ishita Dasgupta, Kenneth Marino, Rob Fergus, Theodore Sumers","submitted_at":"2023-01-29T18:21:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12507","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/2301.12507/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":"2026-07-05T06:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AlCugIPLnX3Hsn7rqJi0hrEWHfzmLrMnsVbXh0FXSN3w16S38WpEP/SRFWL5INJPv5HHj9KJ7TksEVyZhU8iDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:19:59.888566Z"},"content_sha256":"8c91b1b96580e8dd74dba3979501293786fb87107643d2a008061c18954cdec8","schema_version":"1.0","event_id":"sha256:8c91b1b96580e8dd74dba3979501293786fb87107643d2a008061c18954cdec8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32UKFNZM3OYPCNZRUIMBJ62XJL/bundle.json","state_url":"https://pith.science/pith/32UKFNZM3OYPCNZRUIMBJ62XJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32UKFNZM3OYPCNZRUIMBJ62XJL/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":"2026-08-08T16:19:59Z","links":{"resolver":"https://pith.science/pith/32UKFNZM3OYPCNZRUIMBJ62XJL","bundle":"https://pith.science/pith/32UKFNZM3OYPCNZRUIMBJ62XJL/bundle.json","state":"https://pith.science/pith/32UKFNZM3OYPCNZRUIMBJ62XJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32UKFNZM3OYPCNZRUIMBJ62XJL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TK/qUfbJyqFg70zrBb3wZ3DY9nV3wtjzwg9r5DcQrqx957a5bJcAyVbPJygjOpoBYCg5EaSrhHtXf1ow+9DAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:19:59.892421Z","bundle_sha256":"27396d417cf9df819633e8fa138130be3ab6fcf8d32f05706a3733c7bc894197"}}