{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EVTEGSMKJH2HQVMQMANMBDOCAJ","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":"4c86b72ab38ec0bdd197855e1504640d5b49ab482c627e5ca5e2226c443d224e","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-24T17:46:47Z","title_canon_sha256":"951009dbd008f83d5d312444ba523761886afd62b1ce4ae5e9caa75d6f20245e"},"schema_version":"1.0","source":{"id":"2210.13431","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13431","created_at":"2026-07-05T05:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13431v4","created_at":"2026-07-05T05:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13431","created_at":"2026-07-05T05:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"EVTEGSMKJH2H","created_at":"2026-07-05T05:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"EVTEGSMKJH2HQVMQ","created_at":"2026-07-05T05:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"EVTEGSMK","created_at":"2026-07-05T05:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:497b4c16d79ba585ae6266e3dbc37e70836dcfbd4df72287bd595e91ff103df8","target":"graph","created_at":"2026-07-05T05:54:32Z","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/2210.13431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models lack visual grounding, making it difficult to connect language instructions with visual observations. On the other hand, methods that use pre-trained multimodal models typically come with divided language and visual representations, requiring designing specialized network architecture to fuse them together. We propose a simple yet effective model for robots","authors_text":"Hao Liu, Kimin Lee, Lisa Lee, Pieter Abbeel","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-24T17:46:47Z","title":"Instruction-Following Agents with Multimodal Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13431","kind":"arxiv","version":4},"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":"sha256:8b82bf14cf9e7d5ebc8f1f7d1f2297d20daa839816caa9c9fc0dfa0bfad7ad7f","target":"record","created_at":"2026-07-05T05:54:32Z","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":"4c86b72ab38ec0bdd197855e1504640d5b49ab482c627e5ca5e2226c443d224e","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-24T17:46:47Z","title_canon_sha256":"951009dbd008f83d5d312444ba523761886afd62b1ce4ae5e9caa75d6f20245e"},"schema_version":"1.0","source":{"id":"2210.13431","kind":"arxiv","version":4}},"canonical_sha256":"256643498a49f4785590601ac08dc2026e534c361d7c8cf963e74cb37922b03e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"256643498a49f4785590601ac08dc2026e534c361d7c8cf963e74cb37922b03e","first_computed_at":"2026-07-05T05:54:32.326989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:32.326989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cUPkHSjQXKztjTC2lQPmEje8xpmvvNohMQMlwwVbj5ZQYfJKmydWU8Q0JJbN5RtxvB8UPV/A0IswEPBxi51XDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:32.327490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13431","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b82bf14cf9e7d5ebc8f1f7d1f2297d20daa839816caa9c9fc0dfa0bfad7ad7f","sha256:497b4c16d79ba585ae6266e3dbc37e70836dcfbd4df72287bd595e91ff103df8"],"state_sha256":"b2c5884bedbcf29756e08c279cc23bd60efa5760920a74693b871de3f2d37d1d"}