{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NZ6WGPCPNIN26PXAW7WDHXJSQ4","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":"790a10d85bed776cf1f1f4a3212f0ab9b1590fd86a8aae58acd7249f5d48f1f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-25T17:45:31Z","title_canon_sha256":"92a9394d97721a45503c885a565aa2aa7339c261722d702cbf83dedf591e5be8"},"schema_version":"1.0","source":{"id":"2309.14320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.14320","created_at":"2026-07-05T06:54:09Z"},{"alias_kind":"arxiv_version","alias_value":"2309.14320v1","created_at":"2026-07-05T06:54:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14320","created_at":"2026-07-05T06:54:09Z"},{"alias_kind":"pith_short_12","alias_value":"NZ6WGPCPNIN2","created_at":"2026-07-05T06:54:09Z"},{"alias_kind":"pith_short_16","alias_value":"NZ6WGPCPNIN26PXA","created_at":"2026-07-05T06:54:09Z"},{"alias_kind":"pith_short_8","alias_value":"NZ6WGPCP","created_at":"2026-07-05T06:54:09Z"}],"graph_snapshots":[{"event_id":"sha256:31ff6e7e25d75f3365b6b8c7781e9fca2a73ea71d280033ee6c9e8eef5b12681","target":"graph","created_at":"2026-07-05T06:54:09Z","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/2309.14320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans use different modalities, such as speech, text, images, videos, etc., to communicate their intent and goals with teammates. For robots to become better assistants, we aim to endow them with the ability to follow instructions and understand tasks specified by their human partners. Most robotic policy learning methods have focused on one single modality of task specification while ignoring the rich cross-modal information. We present MUTEX, a unified approach to policy learning from multimodal task specifications. It trains a transformer-based architecture to facilitate cross-modal reason","authors_text":"Roberto Mart\\'in-Mart\\'in, Rutav Shah, Yuke Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-25T17:45:31Z","title":"MUTEX: Learning Unified Policies from Multimodal Task Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14320","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:e10ef511863a39035631243e52976a431e74a93f773075d3377b344e0c720790","target":"record","created_at":"2026-07-05T06:54:09Z","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":"790a10d85bed776cf1f1f4a3212f0ab9b1590fd86a8aae58acd7249f5d48f1f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-25T17:45:31Z","title_canon_sha256":"92a9394d97721a45503c885a565aa2aa7339c261722d702cbf83dedf591e5be8"},"schema_version":"1.0","source":{"id":"2309.14320","kind":"arxiv","version":1}},"canonical_sha256":"6e7d633c4f6a1baf3ee0b7ec33dd328712e2acf8b39ee410fb8e21e040069e07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e7d633c4f6a1baf3ee0b7ec33dd328712e2acf8b39ee410fb8e21e040069e07","first_computed_at":"2026-07-05T06:54:09.562813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:09.562813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z89LG8Hq0yr2RqX35HLiZ6SqB9AsGF8nVHCAnV9bbsZpBcqwrgylaWyfv4qldnZwfiS3+s9ymOrTvHhemm9TAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:09.563290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.14320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e10ef511863a39035631243e52976a431e74a93f773075d3377b344e0c720790","sha256:31ff6e7e25d75f3365b6b8c7781e9fca2a73ea71d280033ee6c9e8eef5b12681"],"state_sha256":"aebe825382a34b8be147fbdbcfa7f5de5178a5c31dd9f749d86c3e579f9e03e6"}