{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D5Q4GNXMPEDRVH3S5W62KXUYHF","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":"9a55b6767d8d3e0d464d256fa0546138f6ccfc22043fdec906bcb61b666ecb4b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T15:39:54Z","title_canon_sha256":"26be96fcb8444e363154269e781c4eff166563287b26b1099a9f613dc26d9d16"},"schema_version":"1.0","source":{"id":"2405.05852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05852","created_at":"2026-07-05T08:17:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05852v1","created_at":"2026-07-05T08:17:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05852","created_at":"2026-07-05T08:17:26Z"},{"alias_kind":"pith_short_12","alias_value":"D5Q4GNXMPEDR","created_at":"2026-07-05T08:17:26Z"},{"alias_kind":"pith_short_16","alias_value":"D5Q4GNXMPEDRVH3S","created_at":"2026-07-05T08:17:26Z"},{"alias_kind":"pith_short_8","alias_value":"D5Q4GNXM","created_at":"2026-07-05T08:17:26Z"}],"graph_snapshots":[{"event_id":"sha256:ddcccfbac47a73817cb14b81b08d0921ec28635ddcf48c2ac20b70a8fa8e1367","target":"graph","created_at":"2026-07-05T08:17:26Z","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/2405.05852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied AI agents require a fine-grained understanding of the physical world mediated through visual and language inputs. Such capabilities are difficult to learn solely from task-specific data. This has led to the emergence of pre-trained vision-language models as a tool for transferring representations learned from internet-scale data to downstream tasks and new domains. However, commonly used contrastively trained representations such as in CLIP have been shown to fail at enabling embodied agents to gain a sufficiently fine-grained scene understanding -- a capability vital for control. To ","authors_text":"Cong Lu, Dhruv Batra, Gunshi Gupta, Karmesh Yadav, Tim G. J. Rudner, Yarin Gal, Zsolt Kira","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T15:39:54Z","title":"Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05852","kind":"arxiv","version":1},"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:ef67fe4d00b067e918359ada278760753ac82218060647bccb237df61e9fbcf9","target":"record","created_at":"2026-07-05T08:17:26Z","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":"9a55b6767d8d3e0d464d256fa0546138f6ccfc22043fdec906bcb61b666ecb4b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T15:39:54Z","title_canon_sha256":"26be96fcb8444e363154269e781c4eff166563287b26b1099a9f613dc26d9d16"},"schema_version":"1.0","source":{"id":"2405.05852","kind":"arxiv","version":1}},"canonical_sha256":"1f61c336ec79071a9f72edbda55e98397de85f8f0c2517b5b2a01a14979c5b75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f61c336ec79071a9f72edbda55e98397de85f8f0c2517b5b2a01a14979c5b75","first_computed_at":"2026-07-05T08:17:26.122486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:26.122486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"whAY4wjY2WTqUehAWm6R/B7Sajf8Q51N6rEwslgnP4TmGw/aIbYjSfmUSrOMjmV4oD3xxlVwWAxoy6VHzHRuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:26.122939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef67fe4d00b067e918359ada278760753ac82218060647bccb237df61e9fbcf9","sha256:ddcccfbac47a73817cb14b81b08d0921ec28635ddcf48c2ac20b70a8fa8e1367"],"state_sha256":"48545655750eca1b10d6e574fbd2c785ba4fce68d6ac93d4d11d5534250e13e2"}