{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EVTEGSMKJH2HQVMQMANMBDOCAJ","short_pith_number":"pith:EVTEGSMK","schema_version":"1.0","canonical_sha256":"256643498a49f4785590601ac08dc2026e534c361d7c8cf963e74cb37922b03e","source":{"kind":"arxiv","id":"2210.13431","version":4},"attestation_state":"computed","paper":{"title":"Instruction-Following Agents with Multimodal Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Hao Liu, Kimin Lee, Lisa Lee, Pieter Abbeel","submitted_at":"2022-10-24T17:46:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.13431","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-24T17:46:47Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"951009dbd008f83d5d312444ba523761886afd62b1ce4ae5e9caa75d6f20245e","abstract_canon_sha256":"4c86b72ab38ec0bdd197855e1504640d5b49ab482c627e5ca5e2226c443d224e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:32.327490Z","signature_b64":"cUPkHSjQXKztjTC2lQPmEje8xpmvvNohMQMlwwVbj5ZQYfJKmydWU8Q0JJbN5RtxvB8UPV/A0IswEPBxi51XDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"256643498a49f4785590601ac08dc2026e534c361d7c8cf963e74cb37922b03e","last_reissued_at":"2026-07-05T05:54:32.326989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:32.326989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instruction-Following Agents with Multimodal Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Hao Liu, Kimin Lee, Lisa Lee, Pieter Abbeel","submitted_at":"2022-10-24T17:46:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13431","kind":"arxiv","version":4},"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/2210.13431/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.13431","created_at":"2026-07-05T05:54:32.327058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13431v4","created_at":"2026-07-05T05:54:32.327058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13431","created_at":"2026-07-05T05:54:32.327058+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVTEGSMKJH2H","created_at":"2026-07-05T05:54:32.327058+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVTEGSMKJH2HQVMQ","created_at":"2026-07-05T05:54:32.327058+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVTEGSMK","created_at":"2026-07-05T05:54:32.327058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01938","citing_title":"PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":225,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14325","citing_title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ","json":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ.json","graph_json":"https://pith.science/api/pith-number/EVTEGSMKJH2HQVMQMANMBDOCAJ/graph.json","events_json":"https://pith.science/api/pith-number/EVTEGSMKJH2HQVMQMANMBDOCAJ/events.json","paper":"https://pith.science/paper/EVTEGSMK"},"agent_actions":{"view_html":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ","download_json":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ.json","view_paper":"https://pith.science/paper/EVTEGSMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13431&json=true","fetch_graph":"https://pith.science/api/pith-number/EVTEGSMKJH2HQVMQMANMBDOCAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EVTEGSMKJH2HQVMQMANMBDOCAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ/action/storage_attestation","attest_author":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ/action/author_attestation","sign_citation":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ/action/citation_signature","submit_replication":"https://pith.science/pith/EVTEGSMKJH2HQVMQMANMBDOCAJ/action/replication_record"}},"created_at":"2026-07-05T05:54:32.327058+00:00","updated_at":"2026-07-05T05:54:32.327058+00:00"}